Merge branch 'main' into instance_schema

.cloud-build/cleanup/cleanup.py

@@ -5,8 +5,6 @@ from resource_cleanup_manager import (
     ModelResourceCleanupManager,
     EndpointResourceCleanupManager,
     ResourceCleanupManager,
-    MatchingEngineIndexEndpointResourceCleanupManager,
-    MatchingEngineIndexResourceCleanupManager,
 )
 
 rate_limit = RateLimit(max_count=25, per=60, greedy=False)
@@ -42,12 +40,10 @@ if is_dry_run:
     print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
-managers: List[ResourceCleanupManager] = [
+managers = [
     DatasetResourceCleanupManager(),
     EndpointResourceCleanupManager(),
     ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
-    MatchingEngineIndexEndpointResourceCleanupManager(),
-    MatchingEngineIndexResourceCleanupManager(),
 ]
 
 run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -109,11 +109,3 @@ class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
 
 class ModelResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Model
-
-
-class MatchingEngineIndexResourceCleanupManager(VertexAIResourceCleanupManager):
-    vertex_ai_resource = aiplatform.MatchingEngineIndex
-
-
-class MatchingEngineIndexEndpointResourceCleanupManager(VertexAIResourceCleanupManager):
-    vertex_ai_resource = aiplatform.MatchingEngineIndexEndpoint

.cloud-build/execute_changed_notebooks_helper.py

@@ -38,7 +38,7 @@ from utils import NotebookProcessors, util
 
 # A buffer so that workers finish before the orchestrating job
 WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
-PYTHON_VERSION = "3.9"  # Set default python version
+PYTHON_VERSION = "3.9" # Set default python version
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -102,7 +102,6 @@ def _process_notebook(
             "VPC_NETWORK": variable_vpc_network,
         },
     )
-    unique_strings_preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
 
     # Use no-execute preprocessor
     (
@@ -111,7 +110,6 @@ def _process_notebook(
     ) = remove_no_execute_cells_preprocessor.preprocess(nb)
 
     (nb, resources) = update_variables_preprocessor.preprocess(nb, resources)
-    (nb, resources) = unique_strings_preprocessor.preprocess(nb, resources)
 
     with open(notebook_path, mode="w", encoding="utf-8") as new_file:
         nbformat.write(nb, new_file)
@@ -129,15 +127,13 @@ def _get_notebook_python_version(notebook_path: str) -> str:
     src = file.read()
     nb_json = json.loads(src)
 
-    # Iterate over the cells in the ipynb
-    for cell in nb_json["cells"]:
-        if cell["cell_type"] == "markdown":
-            markdown = str.join("", cell["source"])
+    #Iterate over the cells in the ipynb
+    for cell in nb_json['cells']:
+        if cell['cell_type'] == 'markdown':
+            markdown = str.join('', cell['source'])
 
             # Look for the python version specification pattern
-            re_match = re.search(
-                "python version = (\d\.\d)", markdown, flags=re.IGNORECASE
-            )
+            re_match = re.search('python version = (\d\.\d)', markdown, flags=re.IGNORECASE)
             if re_match:
                 # get the version number
                 python_version = re_match.group(1)
@@ -205,9 +201,7 @@ def process_and_execute_notebook(
     operation = None
     try:
         # Get the python version for running the notebook if specified
-        notebook_exec_python_version = _get_notebook_python_version(
-            notebook_path=notebook
-        )
+        notebook_exec_python_version = _get_notebook_python_version(notebook_path=notebook)
         print(f"Running notebook with python {notebook_exec_python_version}")
 
         # Pre-process notebook by substituting variable names
@@ -236,7 +230,7 @@ def process_and_execute_notebook(
             private_pool_id=private_pool_id,
             private_pool_region=variable_region,
             timeout_in_seconds=timeout_in_seconds,
-            python_version=notebook_exec_python_version,
+            python_version=notebook_exec_python_version
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
@@ -449,7 +443,7 @@ def process_and_execute_notebooks(
                         result.log_url,
                         result.output_uri,
                         result.output_uri_web,
-                        result.logs_bucket,
+                        result.logs_bucket
                     ]
                     for result in results_sorted
                 ],
@@ -460,34 +454,34 @@ def process_and_execute_notebooks(
                     "log_url",
                     "output_uri",
                     "output_uri_web",
-                    "logs_bucket",
+                    "logs_bucket"
                 ],
             )
         )
 
         if len(notebooks) == 1:
-            print("=" * 100)
-            print("The notebook execution build log:\n")
-            print("=" * 100)
+          print("="*100)
+          print("The notebook execution build log:\n")
+          print("="*100)
 
-            build_id = results_sorted[0].build_id
-            logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
-            log_file_name = f"log-{build_id}.txt"
+          build_id = results_sorted[0].build_id
+          logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
+          log_file_name = f"log-{build_id}.txt"
 
-            log_contents = util.download_blob_into_memory(
-                bucket_name=logs_bucket_name,
-                blob_name=log_file_name,
-                download_as_text=True,
+          log_contents = util.download_blob_into_memory(
+            bucket_name=logs_bucket_name,
+            blob_name=log_file_name,
+            download_as_text=True
             )
 
-            # Remove extra steps from the log
-            match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
+          # Remove extra steps from the log
+          match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
 
-            if match is not None:
-                match_index = match.span()[0]
-                print(log_contents[match_index:])
-            else:
-                print(log_contents)
+          if match is not None:
+            match_index = match.span()[0]
+            print(log_contents[match_index:])
+          else:
+            print(log_contents)
 
         print("\n=== END RESULTS===\n")
 

.cloud-build/test_notebook_vm.txt

@@ -2,4 +2,5 @@ notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb
 notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb
 notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb
 notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
 .cloud-build/tests/python_version_test.ipynb

.cloud-build/utils/NotebookProcessors.py

@@ -14,8 +14,6 @@
 # limitations under the License.
 
 from typing import Dict
-import random
-import string
 
 from nbconvert.preprocessors import Preprocessor
 
@@ -65,36 +63,3 @@ class UpdateVariablesPreprocessor(Preprocessor):
             executable_cells.append(cell)
         notebook.cells = executable_cells
         return notebook, resources
-
-
-# Generate a uuid of a specifed length
-def generate_uuid(length: int = 8) -> str:
-    return "".join(random.choices(string.ascii_lowercase + string.digits, k=length))
-
-
-class UniqueStringsPreprocessor(Preprocessor):
-    # A preprocessor that replaces strings that end with "-unique" or "_unique" with a uuid.
-
-    @staticmethod
-    def update_unique_strings(content: str):
-        # Replace strings that end with "-unique" or "_unique" with a uuid.
-
-        unique_id = generate_uuid()
-        return (
-            content.replace('-unique"', f'-{unique_id}"')
-            .replace("-unique'", f'-{unique_id}"')
-            .replace('_unique"', f'_{unique_id}"')
-            .replace("_unique'", f'_{unique_id}"')
-        )
-
-    def preprocess(self, notebook, resources=None):
-        executable_cells = []
-        for cell in notebook.cells:
-            if cell.cell_type == "code":
-                cell.source = self.update_unique_strings(
-                    content=cell.source,
-                )
-
-            executable_cells.append(cell)
-        notebook.cells = executable_cells
-        return notebook, resources

.cloud-build/utils/UpdateNotebookVariables.py

@@ -40,3 +40,65 @@ def get_updated_value(content: str, variable_name: str, variable_value: str) ->
         content,
         flags=re.M,
     )
+
+
+def test_update_value():
+    new_content = get_updated_value(
+        content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert (
+        new_content
+        == 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
+    )
+
+
+def test_update_value_single_quotes():
+    new_content = get_updated_value(
+        content="PROJECT_ID = '[your-project-id]'",
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert new_content == "PROJECT_ID = 'sample-project'"
+
+
+def test_update_value_avoidance():
+    new_content = get_updated_value(
+        content="PROJECT_ID = shell_output[0] ",
+        variable_name="PROJECT_ID",
+        variable_value="sample-project",
+    )
+    assert new_content == "PROJECT_ID = shell_output[0] "
+
+
+def test_region():
+    new_content = get_updated_value(
+        content='REGION = "[your-region]"  # @param {type:"string"}',
+        variable_name="REGION",
+        variable_value="us-central1",
+    )
+    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
+
+
+def test_region_equal_equals_ignore():
+    # Tests that == is ignored
+    new_content = get_updated_value(
+        content='REGION == "[your-region]"  # @param {type:"string"}',
+        variable_name="REGION",
+        variable_value="us-central1",
+    )
+    assert new_content == 'REGION == "[your-region]"  # @param {type:"string"}'
+
+
+def test_service_account():
+    # Tests that == is ignored
+    new_content = get_updated_value(
+        content='SERVICE_ACCOUNT = "[your-service-account]"  # @param {type:"string"}',
+        variable_name="SERVICE_ACCOUNT",
+        variable_value="12345-compute@developer.gserviceaccount.com",
+    )
+    assert (
+        new_content
+        == 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com"  # @param {type:"string"}'
+    )

.cloud-build/utils/tests/test_preprocessors.py

@@ -1,14 +0,0 @@
-from utils import NotebookProcessors
-
-
-def test_update_value():
-    # Test that the content was updated
-    preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
-
-    content = 'PROJECT_ID = "your-project-id-unique"'
-
-    new_content = preprocessor.update_unique_strings(content)
-
-    assert new_content != content
-    assert new_content.startswith('PROJECT_ID = "your-project-id-')
-    assert new_content.endswith('"')

.cloud-build/utils/tests/test_update_notebook_variables.py

@@ -1,63 +0,0 @@
-from utils import UpdateNotebookVariables
-
-
-def test_update_value():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert (
-        new_content
-        == 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
-    )
-
-
-def test_update_value_single_quotes():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content="PROJECT_ID = '[your-project-id]'",
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert new_content == "PROJECT_ID = 'sample-project'"
-
-
-def test_update_value_avoidance():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content="PROJECT_ID = shell_output[0] ",
-        variable_name="PROJECT_ID",
-        variable_value="sample-project",
-    )
-    assert new_content == "PROJECT_ID = shell_output[0] "
-
-
-def test_region():
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='REGION = "[your-region]"  # @param {type:"string"}',
-        variable_name="REGION",
-        variable_value="us-central1",
-    )
-    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
-
-
-def test_region_equal_equals_ignore():
-    # Tests that == is ignored
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='REGION == "[your-region]"  # @param {type:"string"}',
-        variable_name="REGION",
-        variable_value="us-central1",
-    )
-    assert new_content == 'REGION == "[your-region]"  # @param {type:"string"}'
-
-
-def test_service_account():
-    # Tests that == is ignored
-    new_content = UpdateNotebookVariables.get_updated_value(
-        content='SERVICE_ACCOUNT = "[your-service-account]"  # @param {type:"string"}',
-        variable_name="SERVICE_ACCOUNT",
-        variable_value="12345-compute@developer.gserviceaccount.com",
-    )
-    assert (
-        new_content
-        == 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com"  # @param {type:"string"}'
-    )

.cloud-build/utils/util.py

@@ -61,7 +61,9 @@ def archive_code_and_upload(staging_bucket: str):
 
 
 def download_blob_into_memory(
-    bucket_name: str, blob_name: str, download_as_text: Optional[bool] = False
+  bucket_name: str,
+  blob_name: str,
+  download_as_text: Optional[bool]=False
 ) -> Union[bytes, str]:
     """
     Downloads a blob into memory as byte or as text if
@@ -77,10 +79,13 @@ def download_blob_into_memory(
 
     # Download the blob content
     if download_as_text:
-        contents = blob.download_as_text()
+      contents = blob.download_as_text()
     else:
-        contents = blob.download_as_bytes()
+      contents = blob.download_as_bytes()
 
-    print(f"Downloaded storage object {blob_name} from bucket {bucket_name}.")
+    print(
+        f"Downloaded storage object {blob_name} from bucket {bucket_name}."
+    )
 
     return contents
+

.github/workflows/linter/requirements.txt

@@ -2,9 +2,9 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==22.10.0
-pyupgrade==2.38.4
+black==22.6.0
+pyupgrade==2.34.0
 isort==5.10.1
 flake8==4.0.1
-nbqa==1.5.3
+nbqa==1.4.0
 

community-content/CODEOWNERS

@@ -6,5 +6,3 @@
 /sklearn_text_classification_from_script_using_vertex_sdk       @maxhardt
 /pluto_on_workbench @wkharold
 /cpr-examples @samthrasher
-/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines @Ark-kun
-/pipeline_components @Ark-kun

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_logistic_regression_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,83 +0,0 @@
-name: Train tabular classification logistic regression model using Scikit learn pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_classification_logistic_regression_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Binarize column using Pandas on CSV data:
-        componentRef:
-          digest: d699afd4d7cae862708717cc160f4394ed0c04e536e9515923ef1e8865f01d44
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          column_name: tips
-          predicate: '> 0'
-          new_column_name: class
-        annotations:
-          editor.position: '{"x":40,"y":380,"width":180,"height":54}'
-      Train logistic regression model using scikit learn from CSV:
-        componentRef:
-          digest: a864625a822e4b1c8ef6fe4ae1454fd90f15438f70a6712bb4c30e0dda4d35b7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Binarize column using Pandas on CSV data
-              type: CSV
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":40,"y":510,"width":180,"height":70}'
-      Upload Scikit learn pickle model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 81c91c8d7d21ec97e0872f669d68bd89edea87279d703685db54aa94743bebcd
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train logistic regression model using scikit learn from CSV
-              type: ScikitLearnPickleModel
-        annotations:
-          editor.position: '{"x":40,"y":660,"width":180,"height":70}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_logistic_regression_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.py

@@ -1,73 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_classification_logistic_regression_model_using_Scikit_learn_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    classification_label_column = "class"
-    all_columns = [label_column] + feature_columns
-
-    training_data = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    training_data = select_columns_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    # Cleaning the NaN values.
-    training_data = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        replacement_value="0",
-        #replacement_type_name="float",
-    ).outputs["transformed_table"]
-
-    classification_training_data = binarize_column_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_name=label_column,
-        predicate="> 0",
-        new_column_name=classification_label_column,
-    ).outputs["transformed_table"]
-
-    model = train_logistic_regression_model_using_scikit_learn_from_CSV_op(
-        dataset=classification_training_data,
-        label_column_name=classification_label_column,
-        # Optional:
-        #penalty="l2",
-        #solver="lbfgs",
-        #max_iterations=100,
-        #multi_class_mode="auto",
-        #random_seed=0,
-    ).outputs["model"]
-
-    vertex_model_name = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        sklearn_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func = train_tabular_classification_logistic_regression_model_using_Scikit_learn_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,114 +0,0 @@
-name: Train tabular classification model using PyTorch pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_classification_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":240,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":240,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":240,"y":250,"width":180,"height":54}'
-      Create fully connected pytorch network:
-        componentRef:
-          digest: d03d8248fd358a0275ec33568ee7dd7dce576cc112b09dfafe2651e4d97e04a9
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-          output_activation_name: sigmoid
-        annotations:
-          editor.position: '{"x":40,"y":360,"width":180,"height":54}'
-      Binarize column using Pandas on CSV data:
-        componentRef:
-          digest: d699afd4d7cae862708717cc160f4394ed0c04e536e9515923ef1e8865f01d44
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          column_name: tips
-          predicate: ' > 0'
-          new_column_name: class
-        annotations:
-          editor.position: '{"x":240,"y":360,"width":180,"height":54}'
-      Train pytorch model from csv:
-        componentRef:
-          digest: 40f3185eb61e9727f41a4e0c05dd3d3b44bd802aa0f378cfc31756560033949a
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected pytorch network
-              type: PyTorchScriptModule
-          training_data:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Binarize column using Pandas on CSV data
-              type: CSV
-          label_column_name: class
-          loss_function_name: binary_cross_entropy
-        annotations:
-          editor.position: '{"x":240,"y":490,"width":180,"height":40}'
-      Create PyTorch Model Archive with base handler:
-        componentRef:
-          digest: 8298b5ee1b0f0879f893add4cf352c8dec7cf9e21bb9db134c91a2d046cdb0ec
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml
-        arguments:
-          Model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train pytorch model from csv
-              type: PyTorchScriptModule
-          Model name: model
-          Model version: '1.0'
-        annotations:
-          editor.position: '{"x":240,"y":590,"width":180,"height":54}'
-      Upload PyTorch model archive to Google Cloud Vertex AI:
-        componentRef:
-          digest: 4450212fae7b9001482aca7eb78b28413c205506eccf08a04e7754a8dfa99004
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model_archive:
-            taskOutput:
-              outputName: Model archive
-              taskId: Create PyTorch Model Archive with base handler
-              type: PyTorchModelArchive
-        annotations:
-          editor.position: '{"x":240,"y":720,"width":180,"height":70}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.py

@@ -1,95 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_classification_model_using_PyTorch_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    classification_label_column = "class"
-    all_columns = [label_column] + feature_columns
-
-    training_data = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    training_data = select_columns_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    # Cleaning the NaN values.
-    training_data = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        replacement_value="0",
-        #replacement_type_name="float",
-    ).outputs["transformed_table"]
-
-    classification_training_data = binarize_column_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_name=label_column,
-        predicate=" > 0",
-        new_column_name=classification_label_column,
-    ).outputs["transformed_table"]
-
-    network = create_fully_connected_pytorch_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        output_activation_name="sigmoid",
-        # output_size=1,
-    ).outputs["model"]
-
-    model = train_pytorch_model_from_csv_op(
-        model=network,
-        training_data=classification_training_data,
-        label_column_name=classification_label_column,
-        loss_function_name="binary_cross_entropy",
-        # Optional:
-        #number_of_epochs=1,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #batch_log_interval=100,
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    model_archive = create_pytorch_model_archive_with_base_handler_op(
-        model=model,
-        # Optional:
-        # model_name="model",
-        # model_version="1.0",
-    ).outputs["Model archive"]
-
-    vertex_model_name = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op(
-        model_archive=model_archive,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func=train_tabular_classification_model_using_PyTorch_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,132 +0,0 @@
-name: Train tabular classification model using TensorFlow pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_classification_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Binarize column using Pandas on CSV data:
-        componentRef:
-          digest: d699afd4d7cae862708717cc160f4394ed0c04e536e9515923ef1e8865f01d44
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          column_name: tips
-          predicate: ' > 0'
-          new_column_name: class
-        annotations:
-          editor.position: '{"x":40,"y":370,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Binarize column using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":170,"y":500,"width":180,"height":40}'
-      Create fully connected tensorflow network:
-        componentRef:
-          digest: bfcafbc5ce711b1f69cabf1338212d10d50136a73db9f9f7c984de7b80b4bfb0
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-          output_activation_name: sigmoid
-        annotations:
-          editor.position: '{"x":370,"y":500,"width":180,"height":54}'
-      Train model using Keras on CSV:
-        componentRef:
-          digest: 42ae60c889034dbad74815653e95b4f7d576b5f47f803173e8679c7b54984609
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected tensorflow network
-              type: TensorflowSavedModel
-          label_column_name: class
-          loss_function_name: binary_crossentropy
-          number_of_epochs: '10'
-        annotations:
-          editor.position: '{"x":40,"y":620,"width":180,"height":54}'
-      Upload Tensorflow model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 2e45263ff640b1a688e359b6936e27a81b2407749a84f340af2aa5547e0cb92c
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-        annotations:
-          editor.position: '{"x":40,"y":750,"width":180,"height":54}'
-      Predict with TensorFlow model on CSV data:
-        componentRef:
-          digest: 921bb1563e93a78233b8acceab87055b9154ccf5595d056028cf0396ca224cd4
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":240,"y":750,"width":180,"height":54}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.py

@@ -1,106 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_classification_model_using_TensorFlow_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    classification_label_column = "class"
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    classification_dataset = binarize_column_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_name=label_column,
-        predicate=" > 0",
-        new_column_name=classification_label_column,
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=classification_dataset,
-        fraction_1=training_set_fraction,
-    )
-    classification_training_data = split_task.outputs["split_1"]
-    classification_testing_data = split_task.outputs["split_2"]
-
-    network = create_fully_connected_tensorflow_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        output_activation_name="sigmoid",
-        # output_size=1,
-    ).outputs["model"]
-
-    model = train_model_using_Keras_on_CSV_op(
-        training_data=classification_training_data,
-        model=network,
-        label_column_name=classification_label_column,
-        # Optional:
-        loss_function_name="binary_crossentropy",
-        number_of_epochs=10,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #metric_names=["mean_absolute_error"],
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    predictions = predict_with_TensorFlow_model_on_CSV_data_op(
-        dataset=classification_testing_data,
-        model=model,
-        # label_column_name needs to be set when doing prediction on a dataset that has labels
-        label_column_name=classification_label_column,
-        # Optional:
-        # batch_size=1000,
-    ).outputs["predictions"]
-
-    vertex_model_name = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func = train_tabular_classification_model_using_TensorFlow_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,115 +0,0 @@
-name: Train tabular classification model using XGBoost pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_classification_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Binarize column using Pandas on CSV data:
-        componentRef:
-          digest: d699afd4d7cae862708717cc160f4394ed0c04e536e9515923ef1e8865f01d44
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          column_name: tips
-          predicate: '> 0'
-          new_column_name: class
-        annotations:
-          editor.position: '{"x":40,"y":380,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Binarize column using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":170,"y":510,"width":180,"height":40}'
-      Train XGBoost model on CSV:
-        componentRef:
-          digest: 538c5a01eb38deaf532d619f0bbeaff4efc550fe1f0f776fc06791097b68ceac
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: class
-          objective: binary:logistic
-        annotations:
-          editor.position: '{"x":40,"y":630,"width":180,"height":40}'
-      Upload XGBoost model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 5a5a273c403670743820986c03a4175b7cb4595a556524fefcce403656286977
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-        annotations:
-          editor.position: '{"x":40,"y":750,"width":180,"height":54}'
-      Xgboost predict on CSV:
-        componentRef:
-          digest: 0876233a0c7306fefec188bd70f059b46d1fb5aa57be231799570e3bbbdd0d95
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml
-        arguments:
-          data:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":240,"y":750,"width":180,"height":40}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.py

@@ -1,94 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_classification_model_using_XGBoost_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    classification_label_column = "class"
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    classification_dataset = binarize_column_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_name=label_column,
-        predicate="> 0",
-        new_column_name=classification_label_column,
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=classification_dataset,
-        fraction_1=training_set_fraction,
-    )
-    classification_training_data = split_task.outputs["split_1"]
-    classification_testing_data = split_task.outputs["split_2"]
-
-    model = train_XGBoost_model_on_CSV_op(
-        training_data=classification_training_data,
-        label_column_name=classification_label_column,
-        objective="binary:logistic",
-        # Optional:
-        #starting_model=None,
-        #num_iterations=10,
-        #booster_params={},
-        #booster="gbtree",
-        #learning_rate=0.3,
-        #min_split_loss=0,
-        #max_depth=6,
-    ).outputs["model"]
-
-    # Predicting on the testing data
-    predictions = xgboost_predict_on_CSV_op(
-        data=classification_testing_data,
-        model=model,
-        # label_column needs to be set when doing prediction on a dataset that has labels
-        label_column_name=classification_label_column,
-    ).outputs["predictions"]
-
-    vertex_model_name = upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func = train_tabular_classification_model_using_XGBoost_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,257 +0,0 @@
-name: Train tabular classification model using all frameworks pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_classification_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":550,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":550,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":550,"y":250,"width":180,"height":54}'
-      Binarize column using Pandas on CSV data:
-        componentRef:
-          digest: d699afd4d7cae862708717cc160f4394ed0c04e536e9515923ef1e8865f01d44
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          column_name: tips
-          predicate: ' > 0'
-          new_column_name: class
-        annotations:
-          editor.position: '{"x":550,"y":380,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Binarize column using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":550,"y":490,"width":180,"height":40}'
-      Create fully connected pytorch network:
-        componentRef:
-          digest: d03d8248fd358a0275ec33568ee7dd7dce576cc112b09dfafe2651e4d97e04a9
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-          output_activation_name: sigmoid
-        annotations:
-          editor.position: '{"x":380,"y":620,"width":180,"height":54}'
-      Create fully connected tensorflow network:
-        componentRef:
-          digest: bfcafbc5ce711b1f69cabf1338212d10d50136a73db9f9f7c984de7b80b4bfb0
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-          output_activation_name: sigmoid
-        annotations:
-          editor.position: '{"x":40,"y":630,"width":180,"height":54}'
-      Train model using Keras on CSV:
-        componentRef:
-          digest: 42ae60c889034dbad74815653e95b4f7d576b5f47f803173e8679c7b54984609
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected tensorflow network
-              type: TensorflowSavedModel
-          label_column_name: class
-          loss_function_name: binary_crossentropy
-          number_of_epochs: '10'
-        annotations:
-          editor.position: '{"x":40,"y":750,"width":180,"height":54}'
-      Train pytorch model from csv:
-        componentRef:
-          digest: 40f3185eb61e9727f41a4e0c05dd3d3b44bd802aa0f378cfc31756560033949a
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected pytorch network
-              type: PyTorchScriptModule
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: class
-          loss_function_name: binary_cross_entropy
-        annotations:
-          editor.position: '{"x":380,"y":750,"width":180,"height":40}'
-      Train XGBoost model on CSV:
-        componentRef:
-          digest: 538c5a01eb38deaf532d619f0bbeaff4efc550fe1f0f776fc06791097b68ceac
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: class
-          objective: binary:logistic
-        annotations:
-          editor.position: '{"x":720,"y":750,"width":180,"height":40}'
-      Train logistic regression model using scikit learn from CSV:
-        componentRef:
-          digest: a864625a822e4b1c8ef6fe4ae1454fd90f15438f70a6712bb4c30e0dda4d35b7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":1030,"y":750,"width":180,"height":70}'
-      Predict with TensorFlow model on CSV data:
-        componentRef:
-          digest: 921bb1563e93a78233b8acceab87055b9154ccf5595d056028cf0396ca224cd4
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":160,"y":880,"width":180,"height":54}'
-      Create PyTorch Model Archive with base handler:
-        componentRef:
-          digest: 8298b5ee1b0f0879f893add4cf352c8dec7cf9e21bb9db134c91a2d046cdb0ec
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml
-        arguments:
-          Model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train pytorch model from csv
-              type: PyTorchScriptModule
-          Model name: model
-          Model version: '1.0'
-        annotations:
-          editor.position: '{"x":380,"y":880,"width":180,"height":54}'
-      Xgboost predict on CSV:
-        componentRef:
-          digest: 0876233a0c7306fefec188bd70f059b46d1fb5aa57be231799570e3bbbdd0d95
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml
-        arguments:
-          data:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-          label_column_name: class
-        annotations:
-          editor.position: '{"x":810,"y":880,"width":180,"height":40}'
-      Upload Scikit learn pickle model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 81c91c8d7d21ec97e0872f669d68bd89edea87279d703685db54aa94743bebcd
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train logistic regression model using scikit learn from CSV
-              type: ScikitLearnPickleModel
-        annotations:
-          editor.position: '{"x":1030,"y":880,"width":180,"height":70}'
-      Upload Tensorflow model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 2e45263ff640b1a688e359b6936e27a81b2407749a84f340af2aa5547e0cb92c
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-        annotations:
-          editor.position: '{"x":40,"y":1010,"width":180,"height":54}'
-      Upload PyTorch model archive to Google Cloud Vertex AI:
-        componentRef:
-          digest: 4450212fae7b9001482aca7eb78b28413c205506eccf08a04e7754a8dfa99004
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model_archive:
-            taskOutput:
-              outputName: Model archive
-              taskId: Create PyTorch Model Archive with base handler
-              type: PyTorchModelArchive
-        annotations:
-          editor.position: '{"x":380,"y":1010,"width":180,"height":70}'
-      Upload XGBoost model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 5a5a273c403670743820986c03a4175b7cb4595a556524fefcce403656286977
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-        annotations:
-          editor.position: '{"x":720,"y":1010,"width":180,"height":54}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_classification_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.py

@@ -1,224 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-binarize_column_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-
-# TensorFlow
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-
-# PyTorch
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-
-# XGBoost
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-
-# Scikit-learn
-#train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-train_logistic_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-
-# Vertex AI
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_classification_model_using_all_frameworks_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    classification_label_column = "class"
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    classification_dataset = binarize_column_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_name=label_column,
-        predicate=" > 0",
-        new_column_name=classification_label_column,
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=classification_dataset,
-        fraction_1=training_set_fraction,
-    )
-    classification_training_data = split_task.outputs["split_1"]
-    classification_testing_data = split_task.outputs["split_2"]
-
-    # TensorFlow
-    tensorflow_network = create_fully_connected_tensorflow_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        output_activation_name="sigmoid",
-        # output_size=1,
-    ).outputs["model"]
-
-    tensorflow_model = train_model_using_Keras_on_CSV_op(
-        training_data=classification_training_data,
-        model=tensorflow_network,
-        label_column_name=classification_label_column,
-        # Optional:
-        loss_function_name="binary_crossentropy",
-        number_of_epochs=10,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #metric_names=["mean_absolute_error"],
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    tensorflow_predictions = predict_with_TensorFlow_model_on_CSV_data_op(
-        dataset=classification_testing_data,
-        model=tensorflow_model,
-        # label_column_name needs to be set when doing prediction on a dataset that has labels
-        label_column_name=classification_label_column,
-        # Optional:
-        # batch_size=1000,
-    ).outputs["predictions"]
-
-    tensorflow_vertex_model_name = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op(
-        model=tensorflow_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        tensorflow_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=tensorflow_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # PyTorch
-    pytorch_network = create_fully_connected_pytorch_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        output_activation_name="sigmoid",
-        # output_size=1,
-    ).outputs["model"]
-
-    pytorch_model = train_pytorch_model_from_csv_op(
-        model=pytorch_network,
-        training_data=classification_training_data,
-        label_column_name=classification_label_column,
-        loss_function_name="binary_cross_entropy",
-        # Optional:
-        #number_of_epochs=1,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #batch_log_interval=100,
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    pytorch_model_archive = create_pytorch_model_archive_with_base_handler_op(
-        model=pytorch_model,
-        # Optional:
-        # model_name="model",
-        # model_version="1.0",
-    ).outputs["Model archive"]
-
-    pytorch_vertex_model_name = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op(
-        model_archive=pytorch_model_archive,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        pytorch_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=pytorch_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # XGBoost
-    xgboost_model = train_XGBoost_model_on_CSV_op(
-        training_data=classification_training_data,
-        label_column_name=classification_label_column,
-        objective="binary:logistic",
-        # Optional:
-        #starting_model=None,
-        #num_iterations=10,
-        #booster_params={},
-        #booster="gbtree",
-        #learning_rate=0.3,
-        #min_split_loss=0,
-        #max_depth=6,
-    ).outputs["model"]
-
-    # Predicting on the testing data
-    xgboost_predictions = xgboost_predict_on_CSV_op(
-        data=classification_testing_data,
-        model=xgboost_model,
-        # label_column needs to be set when doing prediction on a dataset that has labels
-        label_column_name=classification_label_column,
-    ).outputs["predictions"]
-
-    xgboost_vertex_model_name = upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op(
-        model=xgboost_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        xgboost_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=xgboost_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # Scikit-learn
-    sklearn_model = train_logistic_regression_model_using_scikit_learn_from_CSV_op(
-        dataset=classification_training_data,
-        label_column_name=classification_label_column,
-        # Optional:
-        #penalty="l2",
-        #solver="lbfgs",
-        #max_iterations=100,
-        #multi_class_mode="auto",
-        #random_seed=0,
-    ).outputs["model"]
-
-    sklearn_vertex_model_name = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op(
-        model=sklearn_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        sklearn_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=sklearn_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func=train_tabular_classification_model_using_all_frameworks_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_linear_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,68 +0,0 @@
-name: Train tabular regression linear model using Scikit learn pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_regression_linear_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Train linear regression model using scikit learn from CSV:
-        componentRef:
-          digest: c7fe7912ab0d1fb45d201d452e9ce6be5544e7d8c6d229db7a4b931ff58560f3
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":40,"y":360,"width":180,"height":54}'
-      Upload Scikit learn pickle model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 81c91c8d7d21ec97e0872f669d68bd89edea87279d703685db54aa94743bebcd
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train linear regression model using scikit learn from CSV
-              type: ScikitLearnPickleModel
-        annotations:
-          editor.position: '{"x":40,"y":490,"width":180,"height":70}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_linear_model_using_Scikit_learn_and_import_to_Vertex_AI/pipeline.py

@@ -1,57 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_regression_linear_model_using_Scikit_learn_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    all_columns = [label_column] + feature_columns
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    training_data = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    training_data = select_columns_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    # Cleaning the NaN values.
-    training_data = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        replacement_value="0",
-        #replacement_type_name="float",
-    ).outputs["transformed_table"]
-
-    model = train_linear_regression_model_using_scikit_learn_from_CSV_op(
-        dataset=training_data,
-        label_column_name=label_column,
-    ).outputs["model"]
-
-    vertex_model_name = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        sklearn_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func = train_tabular_regression_linear_model_using_Scikit_learn_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,97 +0,0 @@
-name: Train tabular regression model using PyTorch pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_regression_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":240,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":240,"y":130,"width":180,"height":54}'
-      Create fully connected pytorch network:
-        componentRef:
-          digest: d03d8248fd358a0275ec33568ee7dd7dce576cc112b09dfafe2651e4d97e04a9
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-        annotations:
-          editor.position: '{"x":40,"y":240,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":240,"y":240,"width":180,"height":54}'
-      Train pytorch model from csv:
-        componentRef:
-          digest: 40f3185eb61e9727f41a4e0c05dd3d3b44bd802aa0f378cfc31756560033949a
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected pytorch network
-              type: PyTorchScriptModule
-          training_data:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":240,"y":380,"width":180,"height":40}'
-      Create PyTorch Model Archive with base handler:
-        componentRef:
-          digest: 8298b5ee1b0f0879f893add4cf352c8dec7cf9e21bb9db134c91a2d046cdb0ec
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml
-        arguments:
-          Model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train pytorch model from csv
-              type: PyTorchScriptModule
-          Model name: model
-          Model version: '1.0'
-        annotations:
-          editor.position: '{"x":240,"y":500,"width":180,"height":54}'
-      Upload PyTorch model archive to Google Cloud Vertex AI:
-        componentRef:
-          digest: 4450212fae7b9001482aca7eb78b28413c205506eccf08a04e7754a8dfa99004
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model_archive:
-            taskOutput:
-              outputName: Model archive
-              taskId: Create PyTorch Model Archive with base handler
-              type: PyTorchModelArchive
-        annotations:
-          editor.position: '{"x":240,"y":630,"width":180,"height":70}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_PyTorch_and_import_to_Vertex_AI/pipeline.py

@@ -1,85 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_regression_model_using_PyTorch_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    all_columns = [label_column] + feature_columns
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    training_data = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    training_data = select_columns_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    # Cleaning the NaN values.
-    training_data = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=training_data,
-        replacement_value="0",
-        #replacement_type_name="float",
-    ).outputs["transformed_table"]
-
-    network = create_fully_connected_pytorch_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        # output_activation_name=None,
-        # output_size=1,
-    ).outputs["model"]
-
-    model = train_pytorch_model_from_csv_op(
-        model=network,
-        training_data=training_data,
-        label_column_name=label_column,
-        # Optional:
-        #loss_function_name="mse_loss",
-        #number_of_epochs=1,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #batch_log_interval=100,
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    model_archive = create_pytorch_model_archive_with_base_handler_op(
-        model=model,
-        # Optional:
-        # model_name="model",
-        # model_version="1.0",
-    ).outputs["Model archive"]
-
-    vertex_model_name = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op(
-        model_archive=model_archive,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func=train_tabular_regression_model_using_PyTorch_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,116 +0,0 @@
-name: Train tabular regression model using Tensorflow pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_regression_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":170,"y":380,"width":180,"height":40}'
-      Create fully connected tensorflow network:
-        componentRef:
-          digest: bfcafbc5ce711b1f69cabf1338212d10d50136a73db9f9f7c984de7b80b4bfb0
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-        annotations:
-          editor.position: '{"x":370,"y":380,"width":180,"height":54}'
-      Train model using Keras on CSV:
-        componentRef:
-          digest: 42ae60c889034dbad74815653e95b4f7d576b5f47f803173e8679c7b54984609
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected tensorflow network
-              type: TensorflowSavedModel
-          label_column_name: tips
-          number_of_epochs: '10'
-          metric_names: '["mean_absolute_error"]'
-        annotations:
-          editor.position: '{"x":40,"y":500,"width":180,"height":54}'
-      Upload Tensorflow model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 2e45263ff640b1a688e359b6936e27a81b2407749a84f340af2aa5547e0cb92c
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-        annotations:
-          editor.position: '{"x":40,"y":630,"width":180,"height":54}'
-      Predict with TensorFlow model on CSV data:
-        componentRef:
-          digest: 921bb1563e93a78233b8acceab87055b9154ccf5595d056028cf0396ca224cd4
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":240,"y":630,"width":180,"height":54}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_TensorFlow_and_import_to_Vertex_AI/pipeline.py

@@ -1,97 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_regression_model_using_Tensorflow_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=dataset,
-        fraction_1=training_set_fraction,
-    )
-    training_data = split_task.outputs["split_1"]
-    testing_data = split_task.outputs["split_2"]
-
-    network = create_fully_connected_tensorflow_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        # output_activation_name=None,
-        # output_size=1,
-    ).outputs["model"]
-
-    model = train_model_using_Keras_on_CSV_op(
-        training_data=training_data,
-        model=network,
-        label_column_name=label_column,
-        # Optional:
-        #loss_function_name="mean_squared_error",
-        number_of_epochs=10,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        metric_names=["mean_absolute_error"],
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    predictions = predict_with_TensorFlow_model_on_CSV_data_op(
-        dataset=testing_data,
-        model=model,
-        # label_column_name needs to be set when doing prediction on a dataset that has labels
-        label_column_name=label_column,
-        # Optional:
-        # batch_size=1000,
-    ).outputs["predictions"]
-
-    vertex_model_name = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func=train_tabular_regression_model_using_Tensorflow_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,99 +0,0 @@
-name: Train tabular regression model using XGBoost pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_regression_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":40,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":40,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":40,"y":250,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":170,"y":360,"width":180,"height":40}'
-      Train XGBoost model on CSV:
-        componentRef:
-          digest: 538c5a01eb38deaf532d619f0bbeaff4efc550fe1f0f776fc06791097b68ceac
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":40,"y":480,"width":180,"height":40}'
-      Upload XGBoost model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 5a5a273c403670743820986c03a4175b7cb4595a556524fefcce403656286977
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-        annotations:
-          editor.position: '{"x":40,"y":600,"width":180,"height":54}'
-      Xgboost predict on CSV:
-        componentRef:
-          digest: 0876233a0c7306fefec188bd70f059b46d1fb5aa57be231799570e3bbbdd0d95
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml
-        arguments:
-          data:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":240,"y":600,"width":180,"height":40}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_XGBoost_and_import_to_Vertex_AI/pipeline.py

@@ -1,85 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_regression_model_using_XGBoost_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=dataset,
-        fraction_1=training_set_fraction,
-    )
-    training_data = split_task.outputs["split_1"]
-    testing_data = split_task.outputs["split_2"]
-
-    model = train_XGBoost_model_on_CSV_op(
-        training_data=training_data,
-        label_column_name=label_column,
-        # Optional:
-        #starting_model=None,
-        #num_iterations=10,
-        #booster_params={},
-        #objective="reg:squarederror",
-        #booster="gbtree",
-        #learning_rate=0.3,
-        #min_split_loss=0,
-        #max_depth=6,
-    ).outputs["model"]
-
-    # Predicting on the testing data
-    predictions = xgboost_predict_on_CSV_op(
-        data=testing_data,
-        model=model,
-        # label_column needs to be set when doing prediction on a dataset that has labels
-        label_column_name=label_column,
-    ).outputs["predictions"]
-
-    vertex_model_name = upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op(
-        model=model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func = train_tabular_regression_model_using_XGBoost_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.component.yaml

@@ -1,238 +0,0 @@
-name: Train tabular regression model using all frameworks pipeline
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/samples/Google_Cloud_Vertex_AI/Train_tabular_regression_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.component.yaml
-    sdk: https://cloud-pipelines.net/pipeline-editor/
-implementation:
-  graph:
-    tasks:
-      Download from GCS:
-        componentRef:
-          digest: 4175c9ff143cb8cc75d05451c0a0ebdf5a0d6d020816e29f5e9cefbb7d56f241
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          GCS path: gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv
-        annotations:
-          editor.position: '{"x":550,"y":40,"width":180,"height":40}'
-      Select columns using Pandas on CSV data:
-        componentRef:
-          digest: 9b9500f461c1d04f1e48992de9138db14a6800f23649d73048673d5ea6dc56ad
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/components/pandas/Select_columns/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: Data
-              taskId: Download from GCS
-          column_names: '["tips", "trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]'
-        annotations:
-          editor.position: '{"x":550,"y":140,"width":180,"height":54}'
-      Fill all missing values using Pandas on CSV data:
-        componentRef:
-          digest: a1b0c29a4615f2e3652aa5d31b9255fa15700e146627c755f8fc172f82e71af7
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Select columns using Pandas on CSV data
-              type: CSV
-          replacement_value: '0'
-        annotations:
-          editor.position: '{"x":550,"y":250,"width":180,"height":54}'
-      Split rows into subsets:
-        componentRef:
-          digest: a609c3c9196484290f24a1174955f95b27f07a7b458aa5cb8cde28866cb2cb46
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml
-        arguments:
-          table:
-            taskOutput:
-              outputName: transformed_table
-              taskId: Fill all missing values using Pandas on CSV data
-              type: CSV
-          fraction_1: '0.8'
-        annotations:
-          editor.position: '{"x":550,"y":360,"width":180,"height":40}'
-      Create fully connected pytorch network:
-        componentRef:
-          digest: d03d8248fd358a0275ec33568ee7dd7dce576cc112b09dfafe2651e4d97e04a9
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-        annotations:
-          editor.position: '{"x":380,"y":490,"width":180,"height":54}'
-      Create fully connected tensorflow network:
-        componentRef:
-          digest: bfcafbc5ce711b1f69cabf1338212d10d50136a73db9f9f7c984de7b80b4bfb0
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml
-        arguments:
-          input_size: '7'
-          hidden_layer_sizes: '[10]'
-          activation_name: elu
-        annotations:
-          editor.position: '{"x":40,"y":500,"width":180,"height":54}'
-      Train model using Keras on CSV:
-        componentRef:
-          digest: 42ae60c889034dbad74815653e95b4f7d576b5f47f803173e8679c7b54984609
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected tensorflow network
-              type: TensorflowSavedModel
-          label_column_name: tips
-          number_of_epochs: '10'
-          metric_names: '["mean_absolute_error"]'
-        annotations:
-          editor.position: '{"x":40,"y":620,"width":180,"height":54}'
-      Train pytorch model from csv:
-        componentRef:
-          digest: 40f3185eb61e9727f41a4e0c05dd3d3b44bd802aa0f378cfc31756560033949a
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Create fully connected pytorch network
-              type: PyTorchScriptModule
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":380,"y":620,"width":180,"height":40}'
-      Train XGBoost model on CSV:
-        componentRef:
-          digest: 538c5a01eb38deaf532d619f0bbeaff4efc550fe1f0f776fc06791097b68ceac
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml
-        arguments:
-          training_data:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":720,"y":620,"width":180,"height":40}'
-      Train linear regression model using scikit learn from CSV:
-        componentRef:
-          digest: c7fe7912ab0d1fb45d201d452e9ce6be5544e7d8c6d229db7a4b931ff58560f3
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_1
-              taskId: Split rows into subsets
-              type: CSV
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":1030,"y":620,"width":180,"height":54}'
-      Predict with TensorFlow model on CSV data:
-        componentRef:
-          digest: 921bb1563e93a78233b8acceab87055b9154ccf5595d056028cf0396ca224cd4
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/components/tensorflow/Predict/on_CSV/component.yaml
-        arguments:
-          dataset:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":160,"y":750,"width":180,"height":54}'
-      Create PyTorch Model Archive with base handler:
-        componentRef:
-          digest: 8298b5ee1b0f0879f893add4cf352c8dec7cf9e21bb9db134c91a2d046cdb0ec
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml
-        arguments:
-          Model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train pytorch model from csv
-              type: PyTorchScriptModule
-          Model name: model
-          Model version: '1.0'
-        annotations:
-          editor.position: '{"x":380,"y":750,"width":180,"height":54}'
-      Xgboost predict on CSV:
-        componentRef:
-          digest: 0876233a0c7306fefec188bd70f059b46d1fb5aa57be231799570e3bbbdd0d95
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml
-        arguments:
-          data:
-            taskOutput:
-              outputName: split_2
-              taskId: Split rows into subsets
-              type: CSV
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-          label_column_name: tips
-        annotations:
-          editor.position: '{"x":810,"y":750,"width":180,"height":40}'
-      Upload Scikit learn pickle model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 81c91c8d7d21ec97e0872f669d68bd89edea87279d703685db54aa94743bebcd
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train linear regression model using scikit learn from CSV
-              type: ScikitLearnPickleModel
-        annotations:
-          editor.position: '{"x":1030,"y":750,"width":180,"height":70}'
-      Upload Tensorflow model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 2e45263ff640b1a688e359b6936e27a81b2407749a84f340af2aa5547e0cb92c
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: trained_model
-              taskId: Train model using Keras on CSV
-              type: TensorflowSavedModel
-        annotations:
-          editor.position: '{"x":40,"y":880,"width":180,"height":54}'
-      Upload PyTorch model archive to Google Cloud Vertex AI:
-        componentRef:
-          digest: 4450212fae7b9001482aca7eb78b28413c205506eccf08a04e7754a8dfa99004
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model_archive:
-            taskOutput:
-              outputName: Model archive
-              taskId: Create PyTorch Model Archive with base handler
-              type: PyTorchModelArchive
-        annotations:
-          editor.position: '{"x":380,"y":880,"width":180,"height":70}'
-      Upload XGBoost model to Google Cloud Vertex AI:
-        componentRef:
-          digest: 5a5a273c403670743820986c03a4175b7cb4595a556524fefcce403656286977
-          url: https://raw.githubusercontent.com/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml
-        arguments:
-          model:
-            taskOutput:
-              outputName: model
-              taskId: Train XGBoost model on CSV
-              type: XGBoostModel
-        annotations:
-          editor.position: '{"x":720,"y":880,"width":180,"height":54}'
-    outputValues: {}

community-content/Train_tabular_models_with_many_frameworks_and_import_to_Vertex_AI_using_Pipelines/Train_tabular_regression_model_using_all_frameworks_and_import_to_Vertex_AI/pipeline.py

@@ -1,208 +0,0 @@
-# python3 -m pip install "kfp<2.0.0" "google-cloud-aiplatform>=1.16.0" --upgrade --quiet
-from kfp import components
-
-# %% Loading components
-download_from_gcs_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/storage/download/component.yaml")
-select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml")
-fill_all_missing_values_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml")
-split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml")
-
-# TensorFlow
-create_fully_connected_tensorflow_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml")
-train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml")
-predict_with_TensorFlow_model_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml")
-upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml")
-
-# PyTorch
-create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml")
-train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml")
-create_pytorch_model_archive_with_base_handler_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml")
-upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml")
-
-# XGBoost
-train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Train/component.yaml")
-xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/XGBoost/Predict/component.yaml")
-upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml")
-
-# Scikit-learn
-train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/1f5cf6e06409b704064b2086c0a705e4e6b4fcde/community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml")
-upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml")
-
-# Vertex AI
-deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/399405402d95f4a011e2d2e967c96f8508ba5688/community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml")
-
-# %% Pipeline definition
-def train_tabular_regression_model_using_all_frameworks_pipeline():
-    dataset_gcs_uri = "gs://ml-pipeline-dataset/Chicago_taxi_trips/chicago_taxi_trips_2019-01-01_-_2019-02-01_limit=10000.csv"
-    feature_columns = ["trip_seconds", "trip_miles", "pickup_community_area", "dropoff_community_area", "fare", "tolls", "extras"]  # Excluded "trip_total"
-    label_column = "tips"
-    training_set_fraction = 0.8
-    # Deploying the model might incur additional costs over time
-    deploy_model = False
-
-    all_columns = [label_column] + feature_columns
-
-    dataset = download_from_gcs_op(
-        gcs_path=dataset_gcs_uri
-    ).outputs["Data"]
-
-    dataset = select_columns_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        column_names=all_columns,
-    ).outputs["transformed_table"]
-
-    dataset = fill_all_missing_values_using_Pandas_on_CSV_data_op(
-        table=dataset,
-        replacement_value="0",
-        # # Optional:
-        # column_names=None,  # =[...]
-    ).outputs["transformed_table"]
-
-    split_task = split_rows_into_subsets_op(
-        table=dataset,
-        fraction_1=training_set_fraction,
-    )
-    training_data = split_task.outputs["split_1"]
-    testing_data = split_task.outputs["split_2"]
-
-    # TensorFlow
-    tensorflow_network = create_fully_connected_tensorflow_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        # output_activation_name=None,
-        # output_size=1,
-    ).outputs["model"]
-
-    tensorflow_model = train_model_using_Keras_on_CSV_op(
-        training_data=training_data,
-        model=tensorflow_network,
-        label_column_name=label_column,
-        # Optional:
-        #loss_function_name="mean_squared_error",
-        number_of_epochs=10,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        metric_names=["mean_absolute_error"],
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    tensorflow_predictions = predict_with_TensorFlow_model_on_CSV_data_op(
-        dataset=testing_data,
-        model=tensorflow_model,
-        # label_column_name needs to be set when doing prediction on a dataset that has labels
-        label_column_name=label_column,
-        # Optional:
-        # batch_size=1000,
-    ).outputs["predictions"]
-
-    tensorflow_vertex_model_name = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI_op(
-        model=tensorflow_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        tensorflow_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=tensorflow_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # PyTorch
-    pytorch_network = create_fully_connected_pytorch_network_op(
-        input_size=len(feature_columns),
-        # Optional:
-        hidden_layer_sizes=[10],
-        activation_name="elu",
-        # output_activation_name=None,
-        # output_size=1,
-    ).outputs["model"]
-
-    pytorch_model = train_pytorch_model_from_csv_op(
-        model=pytorch_network,
-        training_data=training_data,
-        label_column_name=label_column,
-        # Optional:
-        #loss_function_name="mse_loss",
-        #number_of_epochs=1,
-        #learning_rate=0.1,
-        #optimizer_name="Adadelta",
-        #optimizer_parameters={},
-        #batch_size=32,
-        #batch_log_interval=100,
-        #random_seed=0,
-    ).outputs["trained_model"]
-
-    pytorch_model_archive = create_pytorch_model_archive_with_base_handler_op(
-        model=pytorch_model,
-        # Optional:
-        # model_name="model",
-        # model_version="1.0",
-    ).outputs["Model archive"]
-
-    pytorch_vertex_model_name = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI_op(
-        model_archive=pytorch_model_archive,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        pytorch_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=pytorch_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # XGBoost
-    xgboost_model = train_XGBoost_model_on_CSV_op(
-        training_data=training_data,
-        label_column_name=label_column,
-        # Optional:
-        #starting_model=None,
-        #num_iterations=10,
-        #booster_params={},
-        #objective="reg:squarederror",
-        #booster="gbtree",
-        #learning_rate=0.3,
-        #min_split_loss=0,
-        #max_depth=6,
-    ).outputs["model"]
-
-    # Predicting on the testing data
-    xgboost_predictions = xgboost_predict_on_CSV_op(
-        data=testing_data,
-        model=xgboost_model,
-        # label_column needs to be set when doing prediction on a dataset that has labels
-        label_column_name=label_column,
-    ).outputs["predictions"]
-
-    xgboost_vertex_model_name = upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op(
-        model=xgboost_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        xgboost_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=xgboost_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-    # Scikit-learn
-    sklearn_model = train_linear_regression_model_using_scikit_learn_from_CSV_op(
-        dataset=training_data,
-        label_column_name=label_column,
-    ).outputs["model"]
-
-    sklearn_vertex_model_name = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI_op(
-        model=sklearn_model,
-    ).outputs["model_name"]
-
-    # Deploying the model might incur additional costs over time
-    if deploy_model:
-        sklearn_vertex_endpoint_name = deploy_model_to_endpoint_op(
-            model_name=sklearn_vertex_model_name,
-        ).outputs["endpoint_name"]
-
-pipeline_func=train_tabular_regression_model_using_all_frameworks_pipeline
-
-# %% Pipeline submission
-if __name__ == '__main__':
-    from google.cloud import aiplatform
-    aiplatform.PipelineJob.from_pipeline_func(pipeline_func=pipeline_func).submit()

community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml

@@ -1,64 +0,0 @@
-name: Train linear regression model using scikit learn from CSV
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/ML_frameworks/Scikit_learn/Train_linear_regression_model/from_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: label_column_name, type: String}
-outputs:
-- {name: model, type: ScikitLearnPickleModel}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'scikit-learn==1.0.2' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'scikit-learn==1.0.2' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_linear_regression_model_using_scikit_learn_from_CSV(
-          dataset_path,
-          model_path,
-          label_column_name,
-      ):
-          import pandas
-          import pickle
-          from sklearn import linear_model
-
-          df = pandas.read_csv(dataset_path)
-          model = linear_model.LinearRegression()
-          model.fit(
-              X=df.drop(columns=label_column_name),
-              y=df[label_column_name],
-          )
-
-          with open(model_path, "wb") as f:
-              pickle.dump(model, f)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train linear regression model using scikit learn from CSV', description='')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_linear_regression_model_using_scikit_learn_from_CSV(**_parsed_args)
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml

@@ -1,163 +0,0 @@
-name: Train logistic regression model using scikit learn from CSV
-description: Train logistic regression model using Scikit-learn
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/ML_frameworks/Scikit_learn/Train_logistic_regression_model/from_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: label_column_name, type: String}
-- {name: penalty, type: String, default: l2, optional: true}
-- {name: solver, type: String, default: lbfgs, optional: true}
-- {name: max_iterations, type: Integer, default: '100', optional: true}
-- {name: multi_class_mode, type: String, default: auto, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: ScikitLearnPickleModel}
-- {name: model_parameters, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'scikit-learn==1.0.2' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'scikit-learn==1.0.2' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_logistic_regression_model_using_scikit_learn_from_CSV(
-          dataset_path,
-          model_path,
-          label_column_name,
-          penalty = "l2", # l1, l2, elasticnet, none
-          solver = "lbfgs", # newton-cg, lbfgs, liblinear, sag, saga
-          max_iterations = 100,
-          multi_class_mode = "auto", # auto, ovr, multinomial
-          random_seed = 0,
-      ):
-          """Train logistic regression model using Scikit-learn
-
-          See https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
-          """
-          import json
-          import pandas
-          import pickle
-          from sklearn import linear_model
-
-          df = pandas.read_csv(dataset_path)
-          model = linear_model.LogisticRegression(
-              penalty=penalty,
-              #dual=False,
-              #tol=1e-4,
-              #C=1.0,
-              #fit_intercept=True,
-              #intercept_scaling=1,
-              #class_weight=None,
-              random_state=random_seed,
-              solver=solver,
-              max_iter=max_iterations,
-              multi_class=multi_class_mode,
-              #l1_ratio=None,
-              verbose=1,
-          )
-
-          model_parameters = model.get_params()
-          model_parameters_json = json.dumps(model_parameters, indent=2)
-          print("Model parameters:")
-          print(model_parameters_json)
-          print()
-
-          model.fit(
-              X=df.drop(columns=label_column_name),
-              y=df[label_column_name],
-          )
-
-          with open(model_path, "wb") as f:
-              pickle.dump(model, f)
-
-          return (model_parameters_json,)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train logistic regression model using scikit learn from CSV', description='Train logistic regression model using Scikit-learn')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--penalty", dest="penalty", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--solver", dest="solver", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-iterations", dest="max_iterations", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--multi-class-mode", dest="multi_class_mode", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=1)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = train_logistic_regression_model_using_scikit_learn_from_CSV(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: penalty}
-        then:
-        - --penalty
-        - {inputValue: penalty}
-    - if:
-        cond: {isPresent: solver}
-        then:
-        - --solver
-        - {inputValue: solver}
-    - if:
-        cond: {isPresent: max_iterations}
-        then:
-        - --max-iterations
-        - {inputValue: max_iterations}
-    - if:
-        cond: {isPresent: multi_class_mode}
-        then:
-        - --multi-class-mode
-        - {inputValue: multi_class_mode}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}
-    - '----output-paths'
-    - {outputPath: model_parameters}

community-content/pipeline_components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml

@@ -1,41 +0,0 @@
-name: Create PyTorch Model Archive with base handler
-inputs:
-- {name: Model, type: PyTorchScriptModule}
-- {name: Model name, type: String, default: model}
-- {name: Model version, type: String, default: "1.0"}
-outputs:
-- {name: Model archive, type: PyTorchModelArchive}
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Create_PyTorch_Model_Archive/with_base_handler/component.yaml'
-implementation:
-  container:
-    image: pytorch/torchserve:0.6.0-cpu
-    command:
-    - bash
-    - -exc
-    - |
-      model_path=$0
-      model_name=$1
-      model_version=$2
-      output_model_archive_path=$3
-
-      mkdir -p "$(dirname "$output_model_archive_path")"
-
-      # TODO: Use the built-in base_handler once my fix is merged: https://github.com/pytorch/serve/pull/1682
-      echo '
-      from ts.torch_handler import base_handler
-      class BaseHandler(base_handler.BaseHandler):
-          pass
-      ' > base_handler.py  # torch-model-archiver needs the handler to have .py extension
-      torch-model-archiver --model-name "$model_name" --version "$model_version" --serialized-file "$model_path" --handler base_handler.py
-
-      # torch-model-archiver does not allow specifying the output path, but always writes to "${model_name}.<format>"
-      expected_model_archive_path="${model_name}.mar"
-      mv "$expected_model_archive_path" "$output_model_archive_path"
-
-    - {inputPath: Model}
-    - {inputValue: Model name}
-    - {inputValue: Model version}
-    - {outputPath: Model archive}

community-content/pipeline_components/PyTorch/Create_fully_connected_network/component.yaml

@@ -1,117 +0,0 @@
-name: Create fully connected pytorch network
-description: Creates fully-connected network in PyTorch ScriptModule format
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Create_fully_connected_network/component.yaml'}
-inputs:
-- {name: input_size, type: Integer}
-- {name: hidden_layer_sizes, type: JsonArray, default: '[]', optional: true}
-- {name: output_size, type: Integer, default: '1', optional: true}
-- {name: activation_name, type: String, default: relu, optional: true}
-- {name: output_activation_name, type: String, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: PyTorchScriptModule}
-implementation:
-  container:
-    image: pytorch/pytorch:1.7.1-cuda11.0-cudnn8-runtime
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def create_fully_connected_pytorch_network(
-          input_size,
-          model_path,
-          hidden_layer_sizes = [],
-          output_size = 1,
-          activation_name = 'relu',
-          output_activation_name = None,
-          random_seed = 0,
-      ):
-          '''Creates fully-connected network in PyTorch ScriptModule format'''
-          import torch
-          torch.manual_seed(random_seed)
-
-          activation = getattr(torch, activation_name, None) or getattr(torch.nn.functional, activation_name, None)
-          if not activation:
-              raise ValueError(f'Activation "{activation_name}" was not found.')
-
-          class ActivationLayer(torch.nn.Module):
-              def forward(self, input):
-                  return activation(input)
-
-          layers = []
-          prev_layer_size = input_size
-          for layer_size in hidden_layer_sizes:
-              layer = torch.nn.Linear(prev_layer_size, layer_size)
-              prev_layer_size = layer_size
-              layers.append(layer)
-              layers.append(ActivationLayer())
-
-          # Adding the output layer
-          layers.append(torch.nn.Linear(prev_layer_size, output_size))
-
-          # Adding the optional activation after the output layer
-          if output_activation_name:
-              output_activation = getattr(torch, output_activation_name, None) or getattr(torch.nn.functional, output_activation_name, None)
-              class OutputActivationLayer(torch.nn.Module):
-                  def forward(self, input):
-                      return output_activation(input)
-              layers.append(OutputActivationLayer())
-
-          network = torch.nn.Sequential(*layers)
-          script_module = torch.jit.script(network)
-          print(script_module)
-          script_module.save(model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Create fully connected pytorch network', description='Creates fully-connected network in PyTorch ScriptModule format')
-      _parser.add_argument("--input-size", dest="input_size", type=int, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--hidden-layer-sizes", dest="hidden_layer_sizes", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-size", dest="output_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--activation-name", dest="activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-activation-name", dest="output_activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = create_fully_connected_pytorch_network(**_parsed_args)
-    args:
-    - --input-size
-    - {inputValue: input_size}
-    - if:
-        cond: {isPresent: hidden_layer_sizes}
-        then:
-        - --hidden-layer-sizes
-        - {inputValue: hidden_layer_sizes}
-    - if:
-        cond: {isPresent: output_size}
-        then:
-        - --output-size
-        - {inputValue: output_size}
-    - if:
-        cond: {isPresent: activation_name}
-        then:
-        - --activation-name
-        - {inputValue: activation_name}
-    - if:
-        cond: {isPresent: output_activation_name}
-        then:
-        - --output-activation-name
-        - {inputValue: output_activation_name}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml

@@ -1,209 +0,0 @@
-name: Train pytorch model from csv
-description: Trains PyTorch model
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/PyTorch/Train_PyTorch_model/from_CSV/component.yaml'
-inputs:
-- {name: model, type: PyTorchScriptModule}
-- {name: training_data, type: CSV}
-- {name: label_column_name, type: String}
-- {name: loss_function_name, type: String, default: mse_loss, optional: true}
-- {name: number_of_epochs, type: Integer, default: '1', optional: true}
-- {name: learning_rate, type: Float, default: '0.1', optional: true}
-- {name: optimizer_name, type: String, default: Adadelta, optional: true}
-- {name: optimizer_parameters, type: JsonObject, optional: true}
-- {name: batch_size, type: Integer, default: '32', optional: true}
-- {name: batch_log_interval, type: Integer, default: '100', optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: trained_model, type: PyTorchScriptModule}
-implementation:
-  container:
-    image: pytorch/pytorch:1.7.1-cuda11.0-cudnn8-runtime
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_pytorch_model_from_csv(
-          model_path,
-          training_data_path,
-          trained_model_path,
-          label_column_name,
-          loss_function_name = 'mse_loss',
-          number_of_epochs = 1,
-          learning_rate = 0.1,
-          optimizer_name = 'Adadelta',
-          optimizer_parameters = None,
-          batch_size = 32,
-          batch_log_interval = 100,
-          random_seed = 0,
-      ):
-          '''Trains PyTorch model'''
-          import pandas
-          import torch
-
-          torch.manual_seed(random_seed)
-
-          use_cuda = torch.cuda.is_available()
-          device = torch.device("cuda" if use_cuda else "cpu")
-
-          model = torch.jit.load(model_path)
-          model.to(device)
-          model.train()
-
-          optimizer_class = getattr(torch.optim, optimizer_name, None)
-          if not optimizer_class:
-              raise ValueError(f'Optimizer "{optimizer_name}" was not found.')
-
-          optimizer_parameters = optimizer_parameters or {}
-          optimizer_parameters['lr'] = learning_rate
-          optimizer = optimizer_class(model.parameters(), **optimizer_parameters)
-
-          loss_function = getattr(torch, loss_function_name, None) or getattr(torch.nn, loss_function_name, None) or getattr(torch.nn.functional, loss_function_name, None)
-          if not loss_function:
-              raise ValueError(f'Loss function "{loss_function_name}" was not found.')
-
-          class CsvDataset(torch.utils.data.Dataset):
-
-              def __init__(self, file_path, label_column_name, drop_nan_columns_or_rows = 'columns'):
-                  dataframe = pandas.read_csv(file_path).convert_dtypes()
-                  # Preventing error: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found object
-                  if drop_nan_columns_or_rows == 'columns':
-                      non_nan_data = dataframe.dropna(axis='columns')
-                      removed_columns = set(dataframe.columns) - set(non_nan_data.columns)
-                      if removed_columns:
-                          print('Skipping columns with NaNs: ' + str(removed_columns))
-                      dataframe = non_nan_data
-                  if drop_nan_columns_or_rows == 'rows':
-                      non_nan_data = dataframe.dropna(axis='index')
-                      number_of_removed_rows = len(dataframe) - len(non_nan_data)
-                      if number_of_removed_rows:
-                          print(f'Skipped {number_of_removed_rows} rows with NaNs.')
-                      dataframe = non_nan_data
-                  numerical_data = dataframe.select_dtypes(include='number')
-                  non_numerical_data = dataframe.select_dtypes(exclude='number')
-                  if not non_numerical_data.empty:
-                      print('Skipping non-number columns:')
-                      print(non_numerical_data.dtypes)
-                  self._dataframe = dataframe
-                  self.labels = numerical_data[[label_column_name]]
-                  self.features = numerical_data.drop(columns=[label_column_name])
-
-              def __len__(self):
-                  return len(self._dataframe)
-
-              def __getitem__(self, index):
-                  return [self.features.loc[index].to_numpy(dtype='float32'), self.labels.loc[index].to_numpy(dtype='float32')]
-
-          dataset = CsvDataset(
-              file_path=training_data_path,
-              label_column_name=label_column_name,
-          )
-          train_loader = torch.utils.data.DataLoader(
-              dataset=dataset,
-              batch_size=batch_size,
-              shuffle=True,
-          )
-
-          last_full_batch_loss = None
-          for epoch in range(1, number_of_epochs + 1):
-              for batch_idx, (data, target) in enumerate(train_loader):
-                  data, target = data.to(device), target.to(device)
-                  optimizer.zero_grad()
-                  output = model(data)
-                  loss = loss_function(output, target)
-                  loss.backward()
-                  optimizer.step()
-                  if len(data) == batch_size:
-                      last_full_batch_loss = loss.item()
-                  if batch_idx % batch_log_interval == 0:
-                      print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
-                          epoch, batch_idx * len(data), len(train_loader.dataset),
-                          100. * batch_idx / len(train_loader), loss.item()))
-              print(f'Training epoch {epoch} completed. Last full batch loss: {last_full_batch_loss:.6f}')
-
-          # print(optimizer.state_dict())
-          model.save(trained_model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train pytorch model from csv', description='Trains PyTorch model')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--loss-function-name", dest="loss_function_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--number-of-epochs", dest="number_of_epochs", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-name", dest="optimizer_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-parameters", dest="optimizer_parameters", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-log-interval", dest="batch_log_interval", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--trained-model", dest="trained_model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_pytorch_model_from_csv(**_parsed_args)
-    args:
-    - --model
-    - {inputPath: model}
-    - --training-data
-    - {inputPath: training_data}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: loss_function_name}
-        then:
-        - --loss-function-name
-        - {inputValue: loss_function_name}
-    - if:
-        cond: {isPresent: number_of_epochs}
-        then:
-        - --number-of-epochs
-        - {inputValue: number_of_epochs}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: optimizer_name}
-        then:
-        - --optimizer-name
-        - {inputValue: optimizer_name}
-    - if:
-        cond: {isPresent: optimizer_parameters}
-        then:
-        - --optimizer-parameters
-        - {inputValue: optimizer_parameters}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - if:
-        cond: {isPresent: batch_log_interval}
-        then:
-        - --batch-log-interval
-        - {inputValue: batch_log_interval}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --trained-model
-    - {outputPath: trained_model}

community-content/pipeline_components/XGBoost/Predict/component.yaml

@@ -1,110 +0,0 @@
-name: Xgboost predict on CSV
-description: Makes predictions using a trained XGBoost model.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/XGBoost/Predict/component.yaml'}
-inputs:
-- {name: data, type: CSV, description: Feature data in Apache Parquet format.}
-- {name: model, type: XGBoostModel, description: Trained model in binary XGBoost format.}
-- {name: label_column_name, type: String, description: Optional. Name of the column
-    containing the label data that is excluded during the prediction., optional: true}
-outputs:
-- {name: predictions, description: Model predictions.}
-implementation:
-  container:
-    image: python:3.10
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'xgboost==1.6.1' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'xgboost==1.6.1' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def xgboost_predict_on_CSV(
-          data_path,
-          model_path,
-          predictions_path,
-          label_column_name = None,
-      ):
-          """Makes predictions using a trained XGBoost model.
-
-          Args:
-              data_path: Feature data in Apache Parquet format.
-              model_path: Trained model in binary XGBoost format.
-              predictions_path: Model predictions.
-              label_column_name: Optional. Name of the column containing the label data that is excluded during the prediction.
-
-          Annotations:
-              author: Alexey Volkov <alexey.volkov@ark-kun.com>
-          """
-          from pathlib import Path
-
-          import numpy
-          import pandas
-          import xgboost
-
-          df = pandas.read_csv(
-              data_path,
-          ).convert_dtypes()
-          print("Evaluation data information:")
-          df.info(verbose=True)
-          # Converting column types that XGBoost does not support
-          for column_name, dtype in df.dtypes.items():
-              if dtype in ["string", "object"]:
-                  print(f"Treating the {dtype.name} column '{column_name}' as categorical.")
-                  df[column_name] = df[column_name].astype("category")
-                  print(f"Inferred {len(df[column_name].cat.categories)} categories for the '{column_name}' column.")
-              # Working around the XGBoost issue with nullable floats: https://github.com/dmlc/xgboost/issues/8213
-              if pandas.api.types.is_float_dtype(dtype):
-                  # Converting from "Float64" to "float64"
-                  df[column_name] = df[column_name].astype(dtype.name.lower())
-          print("Final evaluation data information:")
-          df.info(verbose=True)
-
-          if label_column_name is not None:
-              df = df.drop(columns=[label_column_name])
-
-          testing_data = xgboost.DMatrix(
-              data=df,
-              enable_categorical=True,
-          )
-
-          model = xgboost.Booster(model_file=model_path)
-
-          predictions = model.predict(testing_data)
-
-          Path(predictions_path).parent.mkdir(parents=True, exist_ok=True)
-          numpy.savetxt(predictions_path, predictions)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Xgboost predict on CSV', description='Makes predictions using a trained XGBoost model.')
-      _parser.add_argument("--data", dest="data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--predictions", dest="predictions_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = xgboost_predict_on_CSV(**_parsed_args)
-    args:
-    - --data
-    - {inputPath: data}
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: label_column_name}
-        then:
-        - --label-column-name
-        - {inputValue: label_column_name}
-    - --predictions
-    - {outputPath: predictions}

community-content/pipeline_components/XGBoost/Train/component.yaml

@@ -1,241 +0,0 @@
-name: Train XGBoost model on CSV
-description: Trains an XGBoost model.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/XGBoost/Train/component.yaml'}
-inputs:
-- {name: training_data, type: CSV, description: Training data in CSV format.}
-- {name: label_column_name, type: String, description: Name of the column containing
-    the label data.}
-- {name: starting_model, type: XGBoostModel, description: Existing trained model to
-    start from (in the binary XGBoost format)., optional: true}
-- {name: num_iterations, type: Integer, description: Number of boosting iterations.,
-  default: '10', optional: true}
-- name: objective
-  type: String
-  description: |-
-    The learning task and the corresponding learning objective.
-    See https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
-    The most common values are:
-    "reg:squarederror" - Regression with squared loss (default).
-    "reg:logistic" - Logistic regression.
-    "binary:logistic" - Logistic regression for binary classification, output probability.
-    "binary:logitraw" - Logistic regression for binary classification, output score before logistic transformation
-    "rank:pairwise" - Use LambdaMART to perform pairwise ranking where the pairwise loss is minimized
-    "rank:ndcg" - Use LambdaMART to perform list-wise ranking where Normalized Discounted Cumulative Gain (NDCG) is maximized
-  default: reg:squarederror
-  optional: true
-- {name: booster, type: String, description: 'The booster to use. Can be `gbtree`,
-    `gblinear` or `dart`; `gbtree` and `dart` use tree based models while `gblinear`
-    uses linear functions.', default: gbtree, optional: true}
-- {name: learning_rate, type: Float, description: 'Step size shrinkage used in update
-    to prevents overfitting. Range: [0,1].', default: '0.3', optional: true}
-- name: min_split_loss
-  type: Float
-  description: |-
-    Minimum loss reduction required to make a further partition on a leaf node of the tree.
-    The larger `min_split_loss` is, the more conservative the algorithm will be. Range: [0,Inf].
-  default: '0'
-  optional: true
-- name: max_depth
-  type: Integer
-  description: |-
-    Maximum depth of a tree. Increasing this value will make the model more complex and more likely to overfit.
-    0 indicates no limit on depth. Range: [0,Inf].
-  default: '6'
-  optional: true
-- {name: booster_params, type: JsonObject, description: 'Parameters for the booster.
-    See https://xgboost.readthedocs.io/en/latest/parameter.html', optional: true}
-outputs:
-- {name: model, type: XGBoostModel, description: Trained model in the binary XGBoost
-    format.}
-- {name: model_config, type: XGBoostModelConfig, description: The internal parameter
-    configuration of Booster as a JSON string.}
-implementation:
-  container:
-    image: python:3.10
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'xgboost==1.6.1' 'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'xgboost==1.6.1' 'pandas==1.4.3'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_XGBoost_model_on_CSV(
-          training_data_path,
-          model_path,
-          model_config_path,
-          label_column_name,
-          starting_model_path = None,
-          num_iterations = 10,
-          # Booster parameters
-          objective = "reg:squarederror",
-          booster = "gbtree",
-          learning_rate = 0.3,
-          min_split_loss = 0,
-          max_depth = 6,
-          booster_params = None,
-      ):
-          """Trains an XGBoost model.
-
-          Args:
-              training_data_path: Training data in CSV format.
-              model_path: Trained model in the binary XGBoost format.
-              model_config_path: The internal parameter configuration of Booster as a JSON string.
-              starting_model_path: Existing trained model to start from (in the binary XGBoost format).
-              label_column_name: Name of the column containing the label data.
-              num_iterations: Number of boosting iterations.
-              booster_params: Parameters for the booster. See https://xgboost.readthedocs.io/en/latest/parameter.html
-              objective: The learning task and the corresponding learning objective.
-                  See https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
-                  The most common values are:
-                  "reg:squarederror" - Regression with squared loss (default).
-                  "reg:logistic" - Logistic regression.
-                  "binary:logistic" - Logistic regression for binary classification, output probability.
-                  "binary:logitraw" - Logistic regression for binary classification, output score before logistic transformation
-                  "rank:pairwise" - Use LambdaMART to perform pairwise ranking where the pairwise loss is minimized
-                  "rank:ndcg" - Use LambdaMART to perform list-wise ranking where Normalized Discounted Cumulative Gain (NDCG) is maximized
-              booster: The booster to use. Can be `gbtree`, `gblinear` or `dart`; `gbtree` and `dart` use tree based models while `gblinear` uses linear functions.
-              learning_rate: Step size shrinkage used in update to prevents overfitting. Range: [0,1].
-              min_split_loss: Minimum loss reduction required to make a further partition on a leaf node of the tree.
-                  The larger `min_split_loss` is, the more conservative the algorithm will be. Range: [0,Inf].
-              max_depth: Maximum depth of a tree. Increasing this value will make the model more complex and more likely to overfit.
-                  0 indicates no limit on depth. Range: [0,Inf].
-
-          Annotations:
-              author: Alexey Volkov <alexey.volkov@ark-kun.com>
-          """
-          import pandas
-          import xgboost
-
-          df = pandas.read_csv(
-              training_data_path,
-          ).convert_dtypes()
-          print("Training data information:")
-          df.info(verbose=True)
-          # Converting column types that XGBoost does not support
-          for column_name, dtype in df.dtypes.items():
-              if dtype in ["string", "object"]:
-                  print(f"Treating the {dtype.name} column '{column_name}' as categorical.")
-                  df[column_name] = df[column_name].astype("category")
-                  print(f"Inferred {len(df[column_name].cat.categories)} categories for the '{column_name}' column.")
-              # Working around the XGBoost issue with nullable floats: https://github.com/dmlc/xgboost/issues/8213
-              if pandas.api.types.is_float_dtype(dtype):
-                  # Converting from "Float64" to "float64"
-                  df[column_name] = df[column_name].astype(dtype.name.lower())
-          print()
-          print("Final training data information:")
-          df.info(verbose=True)
-
-          training_data = xgboost.DMatrix(
-              data=df.drop(columns=[label_column_name]),
-              label=df[[label_column_name]],
-              enable_categorical=True,
-          )
-
-          booster_params = booster_params or {}
-          booster_params.setdefault("objective", objective)
-          booster_params.setdefault("booster", booster)
-          booster_params.setdefault("learning_rate", learning_rate)
-          booster_params.setdefault("min_split_loss", min_split_loss)
-          booster_params.setdefault("max_depth", max_depth)
-
-          starting_model = None
-          if starting_model_path:
-              starting_model = xgboost.Booster(model_file=starting_model_path)
-
-          print()
-          print("Training the model:")
-          model = xgboost.train(
-              params=booster_params,
-              dtrain=training_data,
-              num_boost_round=num_iterations,
-              xgb_model=starting_model,
-              evals=[(training_data, "training_data")],
-          )
-
-          # Saving the model in binary format
-          model.save_model(model_path)
-
-          model_config_str = model.save_config()
-          with open(model_config_path, "w") as model_config_file:
-              model_config_file.write(model_config_str)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train XGBoost model on CSV', description='Trains an XGBoost model.')
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--starting-model", dest="starting_model_path", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--num-iterations", dest="num_iterations", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--objective", dest="objective", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--booster", dest="booster", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--min-split-loss", dest="min_split_loss", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-depth", dest="max_depth", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--booster-params", dest="booster_params", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model-config", dest="model_config_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_XGBoost_model_on_CSV(**_parsed_args)
-    args:
-    - --training-data
-    - {inputPath: training_data}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: starting_model}
-        then:
-        - --starting-model
-        - {inputPath: starting_model}
-    - if:
-        cond: {isPresent: num_iterations}
-        then:
-        - --num-iterations
-        - {inputValue: num_iterations}
-    - if:
-        cond: {isPresent: objective}
-        then:
-        - --objective
-        - {inputValue: objective}
-    - if:
-        cond: {isPresent: booster}
-        then:
-        - --booster
-        - {inputValue: booster}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: min_split_loss}
-        then:
-        - --min-split-loss
-        - {inputValue: min_split_loss}
-    - if:
-        cond: {isPresent: max_depth}
-        then:
-        - --max-depth
-        - {inputValue: max_depth}
-    - if:
-        cond: {isPresent: booster_params}
-        then:
-        - --booster-params
-        - {inputValue: booster_params}
-    - --model
-    - {outputPath: model}
-    - --model-config
-    - {outputPath: model_config}

community-content/pipeline_components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml

@@ -1,204 +0,0 @@
-name: Split rows into subsets
-description: Splits the data table according to the split fractions.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/dataset_manipulation/Split_rows_into_subsets/in_CSV/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: fraction_1, type: Float, description: 'The proportion of the lines to put
-    into the 1st split. Range: [0, 1]'}
-- name: fraction_2
-  type: Float
-  description: |-
-    The proportion of the lines to put into the 2nd split. Range: [0, 1]
-    If fraction_2 is not specified, then fraction_2 = 1 - fraction_1.
-    The remaining lines go to the 3rd split (if any).
-  optional: true
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: split_1, type: CSV}
-- {name: split_2, type: CSV}
-- {name: split_3, type: CSV}
-- {name: split_1_count, type: Integer}
-- {name: split_2_count, type: Integer}
-- {name: split_3_count, type: Integer}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def split_rows_into_subsets(
-          table_path,
-          split_1_path,
-          split_2_path,
-          split_3_path,
-          fraction_1,
-          fraction_2 = None,
-          random_seed = 0,
-      ):
-          """Splits the data table according to the split fractions.
-
-          Args:
-              fraction_1: The proportion of the lines to put into the 1st split. Range: [0, 1]
-              fraction_2: The proportion of the lines to put into the 2nd split. Range: [0, 1]
-                  If fraction_2 is not specified, then fraction_2 = 1 - fraction_1.
-                  The remaining lines go to the 3rd split (if any).
-          """
-          import random
-
-          random.seed(random_seed)
-
-          SHUFFLE_BUFFER_SIZE = 10000
-
-          num_splits = 3
-
-          if fraction_1 < 0 or fraction_1 > 1:
-              raise ValueError("fraction_1 must be in between 0 and 1.")
-
-          if fraction_2 is None:
-              fraction_2 = 1 - fraction_1
-          if fraction_2 < 0 or fraction_2 > 1:
-              raise ValueError("fraction_2 must be in between 0 and 1.")
-
-          fraction_3 = 1 - fraction_1 - fraction_2
-
-          fractions = [
-              fraction_1,
-              fraction_2,
-              fraction_3,
-          ]
-
-          assert sum(fractions) == 1
-
-          written_line_counts = [0] * num_splits
-
-          output_files = [
-              open(split_1_path, "wb"),
-              open(split_2_path, "wb"),
-              open(split_3_path, "wb"),
-          ]
-
-          with open(table_path, "rb") as input_file:
-              # Writing the headers
-              header_line = input_file.readline()
-              for output_file in output_files:
-                  output_file.write(header_line)
-
-              while True:
-                  line_buffer = []
-                  for i in range(SHUFFLE_BUFFER_SIZE):
-                      line = input_file.readline()
-                      if not line:
-                          break
-                      line_buffer.append(line)
-
-                  # We need to exactly partition the lines between the output files
-                  # To overcome possible systematic bias, we could calculate the total numbers
-                  # of lines written to each file and take that into account.
-                  num_read_lines = len(line_buffer)
-                  number_of_lines_for_files = [0] * num_splits
-                  # List that will have the index of the destination file for each line
-                  file_index_for_line = []
-                  remaining_lines = num_read_lines
-                  remaining_fraction = 1
-                  for i in range(num_splits):
-                      number_of_lines_for_file = (
-                          round(remaining_lines * (fractions[i] / remaining_fraction))
-                          if remaining_fraction > 0
-                          else 0
-                      )
-                      number_of_lines_for_files[i] = number_of_lines_for_file
-                      remaining_lines -= number_of_lines_for_file
-                      remaining_fraction -= fractions[i]
-                      file_index_for_line.extend([i] * number_of_lines_for_file)
-
-                  assert remaining_lines == 0, f"{remaining_lines}"
-                  assert len(file_index_for_line) == num_read_lines
-
-                  random.shuffle(file_index_for_line)
-
-                  for i in range(num_read_lines):
-                      output_files[file_index_for_line[i]].write(line_buffer[i])
-                      written_line_counts[file_index_for_line[i]] += 1
-
-                  # Exit if the file ended before we were able to fully fill the buffer
-                  if len(line_buffer) != SHUFFLE_BUFFER_SIZE:
-                      break
-
-          for output_file in output_files:
-              output_file.close()
-
-          return written_line_counts
-
-      def _serialize_int(int_value: int) -> str:
-          if isinstance(int_value, str):
-              return int_value
-          if not isinstance(int_value, int):
-              raise TypeError('Value "{}" has type "{}" instead of int.'.format(str(int_value), str(type(int_value))))
-          return str(int_value)
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Split rows into subsets', description='Splits the data table according to the split fractions.')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--fraction-1", dest="fraction_1", type=float, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--fraction-2", dest="fraction_2", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-1", dest="split_1_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-2", dest="split_2_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--split-3", dest="split_3_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=3)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = split_rows_into_subsets(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_int,
-          _serialize_int,
-          _serialize_int,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --table
-    - {inputPath: table}
-    - --fraction-1
-    - {inputValue: fraction_1}
-    - if:
-        cond: {isPresent: fraction_2}
-        then:
-        - --fraction-2
-        - {inputValue: fraction_2}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --split-1
-    - {outputPath: split_1}
-    - --split-2
-    - {outputPath: split_2}
-    - --split-3
-    - {outputPath: split_3}
-    - '----output-paths'
-    - {outputPath: split_1_count}
-    - {outputPath: split_2_count}
-    - {outputPath: split_3_count}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/component.yaml

@@ -1,241 +0,0 @@
-name: Deploy model to endpoint for Google Cloud Vertex AI Model
-description: Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model_name, type: String, description: Full resource name of a Google Cloud
-    Vertex AI Model}
-- name: endpoint_name
-  type: String
-  description: |-
-    Optional. Full name of Google Cloud Vertex Endpoint. A new
-    endpoint is created if the name is not passed.
-  optional: true
-- name: machine_type
-  type: String
-  description: |-
-    The type of the machine. See the [list of machine types
-    supported for prediction
-    ](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types).
-    Defaults to "n1-standard-2"
-  default: n1-standard-2
-  optional: true
-- name: min_replica_count
-  type: Integer
-  description: |-
-    Optional. The minimum number of machine replicas this deployed
-    model will be always deployed on. If traffic against it increases,
-    it may dynamically be deployed onto more replicas, and as traffic
-    decreases, some of these extra replicas may be freed.
-  default: '1'
-  optional: true
-- name: max_replica_count
-  type: Integer
-  description: |-
-    Optional. The maximum number of replicas this deployed model may
-    be deployed on when the traffic against it increases. If requested
-    value is too large, the deployment will error, but if deployment
-    succeeds then the ability to scale the model to that many replicas
-    is guaranteed (barring service outages). If traffic against the
-    deployed model increases beyond what its replicas at maximum may
-    handle, a portion of the traffic will be dropped. If this value
-    is not provided, the smaller value of min_replica_count or 1 will
-    be used.
-  default: '1'
-  optional: true
-- name: accelerator_type
-  type: String
-  description: |-
-    Optional. Hardware accelerator type. Must also set accelerator_count if used.
-    One of ACCELERATOR_TYPE_UNSPECIFIED, NVIDIA_TESLA_K80, NVIDIA_TESLA_P100,
-    NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4
-  optional: true
-- {name: accelerator_count, type: Integer, description: Optional. The number of accelerators
-    to attach to a worker replica., optional: true}
-outputs:
-- {name: endpoint_name, type: String}
-- {name: endpoint_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.7.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.7.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def deploy_model_to_endpoint_for_Google_Cloud_Vertex_AI_Model(
-          model_name,
-          endpoint_name = None,
-          machine_type = "n1-standard-2",
-          min_replica_count = 1,
-          max_replica_count = 1,
-          accelerator_type = None,
-          accelerator_count = None,
-          #
-          # Uncomment when anyone requests these:
-          # deployed_model_display_name: str = None,
-          # traffic_percentage: int = 0,
-          # traffic_split: dict = None,
-          # service_account: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-          #
-          # encryption_spec_key_name: str = None,
-      ):
-          """Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.
-
-          Args:
-              model_name: Full resource name of a Google Cloud Vertex AI Model
-              endpoint_name: Optional. Full name of Google Cloud Vertex Endpoint. A new
-                  endpoint is created if the name is not passed.
-              machine_type: The type of the machine. See the [list of machine types
-                  supported for prediction
-                  ](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types).
-                  Defaults to "n1-standard-2"
-              min_replica_count (int):
-                  Optional. The minimum number of machine replicas this deployed
-                  model will be always deployed on. If traffic against it increases,
-                  it may dynamically be deployed onto more replicas, and as traffic
-                  decreases, some of these extra replicas may be freed.
-              max_replica_count (int):
-                  Optional. The maximum number of replicas this deployed model may
-                  be deployed on when the traffic against it increases. If requested
-                  value is too large, the deployment will error, but if deployment
-                  succeeds then the ability to scale the model to that many replicas
-                  is guaranteed (barring service outages). If traffic against the
-                  deployed model increases beyond what its replicas at maximum may
-                  handle, a portion of the traffic will be dropped. If this value
-                  is not provided, the smaller value of min_replica_count or 1 will
-                  be used.
-              accelerator_type (str):
-                  Optional. Hardware accelerator type. Must also set accelerator_count if used.
-                  One of ACCELERATOR_TYPE_UNSPECIFIED, NVIDIA_TESLA_K80, NVIDIA_TESLA_P100,
-                  NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4
-              accelerator_count (int):
-                  Optional. The number of accelerators to attach to a worker replica.
-          """
-          import json
-          from google.cloud import aiplatform
-
-          model = aiplatform.Model(model_name=model_name)
-
-          if endpoint_name:
-              endpoint = aiplatform.Endpoint(endpoint_name=endpoint_name)
-          else:
-              endpoint_display_name = model.display_name[:118] + "_endpoint"
-              endpoint = aiplatform.Endpoint.create(
-                  display_name=endpoint_display_name,
-                  project=model.project,
-                  location=model.location,
-                  # encryption_spec_key_name=encryption_spec_key_name,
-                  labels={"component-source": "github-com-ark-kun-pipeline-components"},
-              )
-
-          endpoint = model.deploy(
-              endpoint=endpoint,
-              # deployed_model_display_name=deployed_model_display_name,
-              machine_type=machine_type,
-              min_replica_count=min_replica_count,
-              max_replica_count=max_replica_count,
-              accelerator_type=accelerator_type,
-              accelerator_count=accelerator_count,
-              # service_account=service_account,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-              # encryption_spec_key_name=encryption_spec_key_name,
-          )
-
-          endpoint_json = json.dumps(endpoint.to_dict(), indent=2)
-          print(endpoint_json)
-          return (endpoint.resource_name, endpoint_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Deploy model to endpoint for Google Cloud Vertex AI Model', description='Deploys Google Cloud Vertex AI Model to a Google Cloud Vertex AI Endpoint.')
-      _parser.add_argument("--model-name", dest="model_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--endpoint-name", dest="endpoint_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--machine-type", dest="machine_type", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--min-replica-count", dest="min_replica_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--max-replica-count", dest="max_replica_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--accelerator-type", dest="accelerator_type", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--accelerator-count", dest="accelerator_count", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = deploy_model_to_endpoint_for_Google_Cloud_Vertex_AI_Model(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model-name
-    - {inputValue: model_name}
-    - if:
-        cond: {isPresent: endpoint_name}
-        then:
-        - --endpoint-name
-        - {inputValue: endpoint_name}
-    - if:
-        cond: {isPresent: machine_type}
-        then:
-        - --machine-type
-        - {inputValue: machine_type}
-    - if:
-        cond: {isPresent: min_replica_count}
-        then:
-        - --min-replica-count
-        - {inputValue: min_replica_count}
-    - if:
-        cond: {isPresent: max_replica_count}
-        then:
-        - --max-replica-count
-        - {inputValue: max_replica_count}
-    - if:
-        cond: {isPresent: accelerator_type}
-        then:
-        - --accelerator-type
-        - {inputValue: accelerator_type}
-    - if:
-        cond: {isPresent: accelerator_count}
-        then:
-        - --accelerator-count
-        - {inputValue: accelerator_count}
-    - '----output-paths'
-    - {outputPath: endpoint_name}
-    - {outputPath: endpoint_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/component.yaml

@@ -1,297 +0,0 @@
-name: Upload PyTorch model archive to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model_archive, type: PyTorchModelArchive}
-- {name: torchserve_version, type: String, default: 0.6.0, optional: true}
-- name: use_gpu
-  type: Boolean
-  default: "False"
-  optional: true
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.13.1' 'google-cloud-build==3.8.3' || PIP_DISABLE_PIP_VERSION_CHECK=1
-      python3 -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.13.1'
-      'google-cloud-build==3.8.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI(
-          model_archive_path,
-          torchserve_version = "0.6.0",
-          use_gpu = False,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          container_image_tag = torchserve_version + "-" + ("gpu" if use_gpu else "cpu")
-          container_image_uri = f"pytorch/torchserve:{container_image_tag}"
-
-          # Vertex Endpoints refuse to support non-Google container registries.
-          # We have to work around this to reduce user frustration
-          # TODO: Remove this code when Vertex Endpoints service starts supporting other container registries.
-          def copy_container_image(
-              src_container_image_uri,
-              dst_container_image_uri,
-              project_id,
-          ):
-              from google.cloud.devtools import cloudbuild
-              from google import protobuf
-              build_client = cloudbuild.CloudBuildClient()
-              build_config = cloudbuild.Build(
-                  images=[dst_container_image_uri],
-                  steps=[
-                      cloudbuild.BuildStep(
-                          name="gcr.io/cloud-builders/docker",
-                          entrypoint="bash",
-                          args=[
-                              "-exc",
-                              'docker pull --quiet "$0" && docker tag "$0" "$1"',
-                              src_container_image_uri,
-                              dst_container_image_uri,
-                          ],
-                      ),
-                  ],
-                  timeout=protobuf.duration_pb2.Duration(
-                      seconds=1800,
-                  ),
-              )
-              build_operation = build_client.create_build(
-                  project_id=project_id,
-                  build=build_config,
-              )
-              try:
-                  result = build_operation.result()
-              except:
-                  print(f"Logs are available at [{build_operation.metadata.build.log_url}].")
-                  raise
-              return result
-
-          project_id = aiplatform.initializer.global_config.project
-          mirrored_container_uri = f"gcr.io/{project_id}/container_mirror/{container_image_uri}"
-          # FIX: Only mirror when image does not exist
-          # docker does is unable to get the registry data from inside container (it cannot connecto to docker socket):
-          # docker.errors.DockerException: Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory'))
-          # import docker
-          # try:
-          #     docker_client = docker.from_env()
-          #     docker_client.images.get_registry_data(mirrored_container_uri)
-          # except docker.errors.NotFound:
-          if True:
-              print(f"Mirroring {container_image_uri} to {mirrored_container_uri}")
-              copy_container_image(
-                  src_container_image_uri=container_image_uri,
-                  dst_container_image_uri=mirrored_container_uri,
-                  project_id=project_id,
-              )
-          container_image_uri = mirrored_container_uri
-          # End of container image mirroring code
-
-          model_archive_file_name = os.path.basename(model_archive_path)
-          model_archive_dir = os.path.dirname(model_archive_path)
-
-          model = aiplatform.Model.upload(
-              # FIX: Use public image or mirror the official image
-              #serving_container_image_uri="gcr.io/avolkov-31337/mirror/pytorch/torchserve",
-              serving_container_image_uri=container_image_uri,
-              artifact_uri=model_archive_dir,
-              serving_container_command=[
-                  "bash",
-                  "-exc",
-                  '''
-      model_archive_uri="$0"
-      #model_archive_local_path=$(mktemp --suffix ".mar")
-      # For some reason the model must already be inside the model-store directory.
-      model_archive_local_path=./model-store/model.mar
-
-      # Downloading the model archive from GCS
-      # TODO: Fix gsutil bugs (requires project ID, has auth issues) and use gsutil instead.
-      # gsutil cp "$model_archive_uri" "$model_archive_local_path"
-      pip install google-cloud-storage
-      python -c '
-      import sys
-      from google.cloud import storage
-
-      model_archive_uri = sys.argv[1]
-      model_archive_local_path = sys.argv[2]
-
-      storage_client = storage.Client()
-      blob = storage.Blob.from_string(uri=model_archive_uri, client=storage_client)
-      blob.download_to_filename(filename=model_archive_local_path)
-      ' "$model_archive_uri" "$model_archive_local_path"
-
-      #Note: config.properties is owned by root. Our user is not root.
-      echo "
-      service_envelope=json
-      # Needed for external access
-      inference_address=http://0.0.0.0:8080
-      management_address=http://0.0.0.0:8081
-      " > config2.properties
-      torchserve --start --foreground --no-config-snapshots --models main-model="$model_archive_local_path" --model-store ./model-store/ --ts-config config2.properties
-                  ''',
-                  "$(AIP_STORAGE_URI)/" + model_archive_file_name,
-              ],
-              serving_container_predict_route="/predictions/main-model",
-              #serving_container_predict_route="/v1/models/main-model:predict",
-              serving_container_health_route="/ping",
-              serving_container_ports=[8080],
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload PyTorch model archive to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model-archive", dest="model_archive_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--torchserve-version", dest="torchserve_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--use-gpu", dest="use_gpu", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_PyTorch_model_archive_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model-archive
-    - {inputPath: model_archive}
-    - if:
-        cond: {isPresent: torchserve_version}
-        then:
-        - --torchserve-version
-        - {inputValue: torchserve_version}
-    - if:
-        cond: {isPresent: use_gpu}
-        then:
-        - --use-gpu
-        - {inputValue: use_gpu}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/component.yaml

@@ -1,181 +0,0 @@
-name: Upload Scikit learn pickle model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: ScikitLearnPickleModel}
-- {name: sklearn_version, type: String, optional: true}
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          sklearn_version = None,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          import shutil
-          import tempfile
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          # The serving container decides the model type based on the model file extension.
-          # So we need to rename the mode file (e.g. /tmp/inputs/model/data) to *.pkl
-          _, renamed_model_path = tempfile.mkstemp(suffix=".pkl")
-          shutil.copyfile(src=model_path, dst=renamed_model_path)
-
-          model = aiplatform.Model.upload_scikit_learn_model_file(
-              model_file_path=renamed_model_path,
-              sklearn_version=sklearn_version,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload Scikit learn pickle model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--sklearn-version", dest="sklearn_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_Scikit_learn_pickle_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: sklearn_version}
-        then:
-        - --sklearn-version
-        - {inputValue: sklearn_version}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/component.yaml

@@ -1,190 +0,0 @@
-name: Upload Tensorflow model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/KFPv2_hell/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: TensorflowSavedModel}
-- {name: tensorflow_version, type: String, optional: true}
-- name: use_gpu
-  type: Boolean
-  default: "False"
-  optional: true
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_Tensorflow_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          tensorflow_version = None,
-          use_gpu = False,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          model = aiplatform.Model.upload_tensorflow_saved_model(
-              saved_model_dir=model_path,
-              tensorflow_version=tensorflow_version,
-              use_gpu=use_gpu,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload Tensorflow model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--tensorflow-version", dest="tensorflow_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--use-gpu", dest="use_gpu", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_Tensorflow_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: tensorflow_version}
-        then:
-        - --tensorflow-version
-        - {inputValue: tensorflow_version}
-    - if:
-        cond: {isPresent: use_gpu}
-        then:
-        - --use-gpu
-        - {inputValue: use_gpu}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/component.yaml

@@ -1,181 +0,0 @@
-name: Upload XGBoost model to Google Cloud Vertex AI
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/google-cloud/Vertex_AI/Models/Upload_XGBoost_model/workaround_for_buggy_KFPv2_compiler/component.yaml'}
-inputs:
-- {name: model, type: XGBoostModel}
-- {name: xgboost_version, type: String, optional: true}
-- {name: display_name, type: String, optional: true}
-- {name: description, type: String, optional: true}
-- {name: project, type: String, optional: true}
-- {name: location, type: String, optional: true}
-- {name: labels, type: JsonObject, optional: true}
-- {name: staging_bucket, type: String, optional: true}
-outputs:
-- {name: model_name, type: String}
-- {name: model_dict, type: JsonObject}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-aiplatform==1.16.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'google-cloud-aiplatform==1.16.0'
-      --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def upload_XGBoost_model_to_Google_Cloud_Vertex_AI(
-          model_path,
-          xgboost_version = None,
-
-          display_name = None,
-          description = None,
-
-          # Uncomment when anyone requests these:
-          # instance_schema_uri: str = None,
-          # parameters_schema_uri: str = None,
-          # prediction_schema_uri: str = None,
-          # explanation_metadata: "google.cloud.aiplatform_v1.types.explanation_metadata.ExplanationMetadata" = None,
-          # explanation_parameters: "google.cloud.aiplatform_v1.types.explanation.ExplanationParameters" = None,
-
-          project = None,
-          location = None,
-          labels = None,
-          # encryption_spec_key_name: str = None,
-          staging_bucket = None,
-      ):
-          import json
-          import os
-          import shutil
-          import tempfile
-          from google.cloud import aiplatform
-
-          if not location:
-              location = os.environ.get("CLOUD_ML_REGION")
-
-          if not labels:
-              labels = {}
-          labels["component-source"] = "github-com-ark-kun-pipeline-components"
-
-          # The serving container decides the model type based on the model file extension.
-          # So we need to rename the mode file (e.g. /tmp/inputs/model/data) to *.pkl
-          _, renamed_model_path = tempfile.mkstemp(suffix=".pkl")
-          shutil.copyfile(src=model_path, dst=renamed_model_path)
-
-          model = aiplatform.Model.upload_xgboost_model_file(
-              model_file_path=renamed_model_path,
-              xgboost_version=xgboost_version,
-
-              display_name=display_name,
-              description=description,
-
-              # instance_schema_uri=instance_schema_uri,
-              # parameters_schema_uri=parameters_schema_uri,
-              # prediction_schema_uri=prediction_schema_uri,
-              # explanation_metadata=explanation_metadata,
-              # explanation_parameters=explanation_parameters,
-
-              project=project,
-              location=location,
-              labels=labels,
-              # encryption_spec_key_name=encryption_spec_key_name,
-              staging_bucket=staging_bucket,
-          )
-          model_json = json.dumps(model.to_dict(), indent=2)
-          print(model_json)
-          return (model.resource_name, model_json)
-
-      def _serialize_json(obj) -> str:
-          if isinstance(obj, str):
-              return obj
-          import json
-          def default_serializer(obj):
-              if hasattr(obj, 'to_struct'):
-                  return obj.to_struct()
-              else:
-                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
-          return json.dumps(obj, default=default_serializer, sort_keys=True)
-
-      def _serialize_str(str_value: str) -> str:
-          if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
-          return str_value
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Upload XGBoost model to Google Cloud Vertex AI', description='')
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--xgboost-version", dest="xgboost_version", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--display-name", dest="display_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--description", dest="description", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--project", dest="project", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--location", dest="location", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--labels", dest="labels", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--staging-bucket", dest="staging_bucket", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=2)
-      _parsed_args = vars(_parser.parse_args())
-      _output_files = _parsed_args.pop("_output_paths", [])
-
-      _outputs = upload_XGBoost_model_to_Google_Cloud_Vertex_AI(**_parsed_args)
-
-      _output_serializers = [
-          _serialize_str,
-          _serialize_json,
-
-      ]
-
-      import os
-      for idx, output_file in enumerate(_output_files):
-          try:
-              os.makedirs(os.path.dirname(output_file))
-          except OSError:
-              pass
-          with open(output_file, 'w') as f:
-              f.write(_output_serializers[idx](_outputs[idx]))
-    args:
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: xgboost_version}
-        then:
-        - --xgboost-version
-        - {inputValue: xgboost_version}
-    - if:
-        cond: {isPresent: display_name}
-        then:
-        - --display-name
-        - {inputValue: display_name}
-    - if:
-        cond: {isPresent: description}
-        then:
-        - --description
-        - {inputValue: description}
-    - if:
-        cond: {isPresent: project}
-        then:
-        - --project
-        - {inputValue: project}
-    - if:
-        cond: {isPresent: location}
-        then:
-        - --location
-        - {inputValue: location}
-    - if:
-        cond: {isPresent: labels}
-        then:
-        - --labels
-        - {inputValue: labels}
-    - if:
-        cond: {isPresent: staging_bucket}
-        then:
-        - --staging-bucket
-        - {inputValue: staging_bucket}
-    - '----output-paths'
-    - {outputPath: model_name}
-    - {outputPath: model_dict}

community-content/pipeline_components/google-cloud/storage/download/component.yaml

@@ -1,35 +0,0 @@
-name: Download from GCS
-inputs:
-- {name: GCS path, type: String}
-outputs:
-- {name: Data}
-metadata:
-  annotations:
-    author: Alexey Volkov <alexey.volkov@ark-kun.com>
-    canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml'
-implementation:
-    container:
-        image: google/cloud-sdk
-        command:
-        - bash # Pattern comparison only works in Bash
-        - -ex
-        - -c
-        - |
-            if [ -n "${GOOGLE_APPLICATION_CREDENTIALS}" ]; then
-                gcloud auth activate-service-account --key-file="${GOOGLE_APPLICATION_CREDENTIALS}"
-            fi
-
-            uri="$0"
-            output_path="$1"
-
-            # Checking whether the URI points to a single blob, a directory or a URI pattern
-            # URI points to a blob when that URI does not end with slash and listing that URI only yields the same URI
-            if [[ "$uri" != */ ]] && (gsutil ls "$uri" | grep --fixed-strings --line-regexp "$uri"); then
-                mkdir -p "$(dirname "$output_path")"
-                gsutil -m cp -r "$uri" "$output_path"
-            else
-                mkdir -p "$output_path" # When source path is a directory, gsutil requires the destination to also be a directory
-                gsutil -m rsync -r "$uri" "$output_path" # gsutil cp has different path handling than Linux cp. It always puts the source directory (name) inside the destination directory. gsutil rsync does not have that problem.
-            fi
-        - inputValue: GCS path
-        - outputPath: Data

community-content/pipeline_components/pandas/Binarize_column/in_CSV_format/component.yaml

@@ -1,113 +0,0 @@
-name: Binarize column using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Binarize_column/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: column_name, type: String}
-- {name: predicate, type: String, default: '> 0', optional: true}
-- {name: new_column_name, type: String, optional: true}
-- name: keep_original_column
-  type: Boolean
-  default: "False"
-  optional: true
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.3' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.3' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def binarize_column_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          column_name,
-          predicate = "> 0",
-          new_column_name = None,
-          keep_original_column = False,
-      ):
-          import pandas
-
-          df = pandas.read_csv(table_path).convert_dtypes()
-          original_series = df[column_name]
-
-          # Dynamically executing the predicate code
-          # Variable namespace for code execution
-          namespace = dict(x=original_series)
-          # I though that there should be no space before `predicate` so that "dot" predicate methods like ".between(min, max)" work.
-          # However Python allows spaces before dot: `df .isna()`.
-          # So having a space is not a problem
-          transform_code = f"""new_series_boolean = x {predicate}"""
-          # Note: exec() takes no keyword arguments
-          # exec(__source=transform_code, __globals=namespace)
-          exec(transform_code, namespace)
-          new_series_boolean = namespace["new_series_boolean"]
-
-          # There are multiple ways to convert boolean column to integer.
-          # .apply(int) might be faster. https://stackoverflow.com/a/49804868/1497385
-          # TODO: Do a proper benchmark.
-          new_series = new_series_boolean.apply(int)
-          # new_series = new_series_boolean.astype(int)
-          # new_series = new_series_boolean.replace({False: 0, True: 1})
-
-          if new_column_name:
-              df.insert(loc=0, column=new_column_name, value=new_series)
-              if not keep_original_column:
-                  df = df.drop(columns=[column_name])
-          else:
-              df[column_name] = new_series
-
-          df.to_csv(transformed_table_path, index=False)
-
-      def _deserialize_bool(s) -> bool:
-          from distutils.util import strtobool
-          return strtobool(s) == 1
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Binarize column using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-name", dest="column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--predicate", dest="predicate", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--new-column-name", dest="new_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--keep-original-column", dest="keep_original_column", type=_deserialize_bool, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = binarize_column_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - --column-name
-    - {inputValue: column_name}
-    - if:
-        cond: {isPresent: predicate}
-        then:
-        - --predicate
-        - {inputValue: predicate}
-    - if:
-        cond: {isPresent: new_column_name}
-        then:
-        - --new-column-name
-        - {inputValue: new_column_name}
-    - if:
-        cond: {isPresent: keep_original_column}
-        then:
-        - --keep-original-column
-        - {inputValue: keep_original_column}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml

@@ -1,75 +0,0 @@
-name: Fill all missing values using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Fill_all_missing_values/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: replacement_value, type: String, default: '0', optional: true}
-- {name: column_names, type: JsonArray, optional: true}
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.1' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.1' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def fill_all_missing_values_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          replacement_value = "0",
-          column_names = None,
-      ):
-          import pandas
-
-          df = pandas.read_csv(
-              table_path,
-              dtype="string",
-          )
-
-          for column_name in column_names or df.columns:
-              df[column_name] = df[column_name].fillna(value=replacement_value)
-
-          df.to_csv(
-              transformed_table_path, index=False,
-          )
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Fill all missing values using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--replacement-value", dest="replacement_value", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-names", dest="column_names", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = fill_all_missing_values_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - if:
-        cond: {isPresent: replacement_value}
-        then:
-        - --replacement-value
-        - {inputValue: replacement_value}
-    - if:
-        cond: {isPresent: column_names}
-        then:
-        - --column-names
-        - {inputValue: column_names}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/pandas/Select_columns/in_CSV_format/component.yaml

@@ -1,59 +0,0 @@
-name: Select columns using Pandas on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/pandas/Select_columns/in_CSV_format/component.yaml'}
-inputs:
-- {name: table, type: CSV}
-- {name: column_names, type: JsonArray}
-outputs:
-- {name: transformed_table, type: CSV}
-implementation:
-  container:
-    image: python:3.9
-    command:
-    - sh
-    - -c
-    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'pandas==1.4.2' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
-      --no-warn-script-location 'pandas==1.4.2' --user) && "$0" "$@"
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def select_columns_using_Pandas_on_CSV_data(
-          table_path,
-          transformed_table_path,
-          column_names,
-      ):
-          import pandas
-
-          df = pandas.read_csv(
-              table_path,
-              dtype="string",
-          )
-          df = df[column_names]
-          df.to_csv(transformed_table_path, index=False)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Select columns using Pandas on CSV data', description='')
-      _parser.add_argument("--table", dest="table_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--column-names", dest="column_names", type=json.loads, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--transformed-table", dest="transformed_table_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = select_columns_using_Pandas_on_CSV_data(**_parsed_args)
-    args:
-    - --table
-    - {inputPath: table}
-    - --column-names
-    - {inputValue: column_names}
-    - --transformed-table
-    - {outputPath: transformed_table}

community-content/pipeline_components/tensorflow/Create_fully_connected_network/component.yaml

@@ -1,102 +0,0 @@
-name: Create fully connected tensorflow network
-description: Creates fully-connected network in Tensorflow SavedModel format
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Create_fully_connected_network/component.yaml'}
-inputs:
-- {name: input_size, type: Integer}
-- {name: hidden_layer_sizes, type: JsonArray, default: '[]', optional: true}
-- {name: output_size, type: Integer, default: '1', optional: true}
-- {name: activation_name, type: String, default: relu, optional: true}
-- {name: output_activation_name, type: String, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: model, type: TensorflowSavedModel}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.7.0
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def create_fully_connected_tensorflow_network(
-          input_size,
-          model_path,
-          hidden_layer_sizes = [],
-          output_size = 1,
-          activation_name = "relu",
-          output_activation_name = None,
-          random_seed = 0,
-      ):
-          """Creates fully-connected network in Tensorflow SavedModel format"""
-          import tensorflow as tf
-          tf.random.set_seed(seed=random_seed)
-
-          model = tf.keras.models.Sequential()
-          model.add(tf.keras.Input(shape=(input_size,)))
-          for layer_size in hidden_layer_sizes:
-              model.add(tf.keras.layers.Dense(units=layer_size, activation=activation_name))
-          # The last layer is left without activation
-          model.add(tf.keras.layers.Dense(units=output_size, activation=output_activation_name))
-
-          print(model.summary())
-
-          # Using tf.keras.models.save_model instead of tf.saved_model.save to prevent downstream error:
-          #tf.saved_model.save(model, model_path)
-          # ValueError: Unable to create a Keras model from this SavedModel.
-          # This SavedModel was created with `tf.saved_model.save`, and lacks the Keras metadata.
-          # Please save your Keras model by calling `model.save`or `tf.keras.models.save_model`.
-          # See https://github.com/keras-team/keras/issues/16451
-          tf.keras.models.save_model(model, model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Create fully connected tensorflow network', description='Creates fully-connected network in Tensorflow SavedModel format')
-      _parser.add_argument("--input-size", dest="input_size", type=int, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--hidden-layer-sizes", dest="hidden_layer_sizes", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-size", dest="output_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--activation-name", dest="activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--output-activation-name", dest="output_activation_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = create_fully_connected_tensorflow_network(**_parsed_args)
-    args:
-    - --input-size
-    - {inputValue: input_size}
-    - if:
-        cond: {isPresent: hidden_layer_sizes}
-        then:
-        - --hidden-layer-sizes
-        - {inputValue: hidden_layer_sizes}
-    - if:
-        cond: {isPresent: output_size}
-        then:
-        - --output-size
-        - {inputValue: output_size}
-    - if:
-        cond: {isPresent: activation_name}
-        then:
-        - --activation-name
-        - {inputValue: activation_name}
-    - if:
-        cond: {isPresent: output_activation_name}
-        then:
-        - --output-activation-name
-        - {inputValue: output_activation_name}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --model
-    - {outputPath: model}

community-content/pipeline_components/tensorflow/Predict/on_CSV/component.yaml

@@ -1,100 +0,0 @@
-name: Predict with TensorFlow model on CSV data
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Predict/on_CSV/component.yaml'}
-inputs:
-- {name: dataset, type: CSV}
-- {name: model, type: TensorflowSavedModel}
-- {name: label_column_name, type: String, optional: true}
-- {name: batch_size, type: Integer, default: '1000', optional: true}
-outputs:
-- {name: predictions}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.9.1
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def predict_with_TensorFlow_model_on_CSV_data(
-          dataset_path,
-          model_path,
-          predictions_path,
-          label_column_name = None,
-          batch_size = 1000,
-      ):
-          import numpy
-          import tensorflow as tf
-
-          model = tf.saved_model.load(export_dir=model_path)
-
-          dataset = tf.data.experimental.make_csv_dataset(
-              file_pattern=dataset_path,
-              batch_size=batch_size,
-              label_name=label_column_name,
-              header=True,
-              num_epochs=1,
-              shuffle=False,
-              ignore_errors=False,
-          )
-
-          def stack_feature_batches(features_batch):
-              # Need to stack individual feature columns to create a single feature tensor
-              # Need to cast all column tensor types to float to prevent errors.
-              list_of_feature_batches = list(
-                  tf.cast(x=feature_batch, dtype=tf.float32)
-                  for feature_batch in features_batch.values()
-              )
-              return tf.stack(list_of_feature_batches, axis=-1)
-
-          def transform_features_and_drop_labels(features_batch, labels_batch):
-              return stack_feature_batches(features_batch)
-
-          dataset_map_fn = (
-              transform_features_and_drop_labels
-              if label_column_name
-              else stack_feature_batches
-          )
-
-          dataset = dataset.map(dataset_map_fn)
-
-          with open(predictions_path, "w") as predictions_file:
-              for features_batch in dataset:
-                  predictions_tensor = model(features_batch)
-                  numpy.savetxt(predictions_file, predictions_tensor.numpy())
-
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Predict with TensorFlow model on CSV data', description='')
-      _parser.add_argument("--dataset", dest="dataset_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--predictions", dest="predictions_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = predict_with_TensorFlow_model_on_CSV_data(**_parsed_args)
-    args:
-    - --dataset
-    - {inputPath: dataset}
-    - --model
-    - {inputPath: model}
-    - if:
-        cond: {isPresent: label_column_name}
-        then:
-        - --label-column-name
-        - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - --predictions
-    - {outputPath: predictions}

community-content/pipeline_components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml

@@ -1,170 +0,0 @@
-name: Train model using Keras on CSV
-metadata:
-  annotations: {author: Alexey Volkov <alexey.volkov@ark-kun.com>, canonical_location: 'https://raw.githubusercontent.com/Ark-kun/pipeline_components/master/components/tensorflow/Train_model_using_Keras/on_CSV/component.yaml'}
-inputs:
-- {name: training_data, type: CSV}
-- {name: model, type: TensorflowSavedModel}
-- {name: label_column_name, type: String}
-- {name: loss_function_name, type: String, default: mean_squared_error, optional: true}
-- {name: number_of_epochs, type: Integer, default: '1', optional: true}
-- {name: learning_rate, type: Float, default: '0.1', optional: true}
-- {name: optimizer_name, type: String, default: Adadelta, optional: true}
-- {name: optimizer_parameters, type: JsonObject, optional: true}
-- {name: batch_size, type: Integer, default: '32', optional: true}
-- {name: metric_names, type: JsonArray, optional: true}
-- {name: random_seed, type: Integer, default: '0', optional: true}
-outputs:
-- {name: trained_model, type: TensorflowSavedModel}
-implementation:
-  container:
-    image: tensorflow/tensorflow:2.8.0
-    command:
-    - sh
-    - -ec
-    - |
-      program_path=$(mktemp)
-      printf "%s" "$0" > "$program_path"
-      python3 -u "$program_path" "$@"
-    - |
-      def _make_parent_dirs_and_return_path(file_path: str):
-          import os
-          os.makedirs(os.path.dirname(file_path), exist_ok=True)
-          return file_path
-
-      def train_model_using_Keras_on_CSV(
-          training_data_path,
-          model_path,
-          trained_model_path,
-          label_column_name,
-          loss_function_name = "mean_squared_error",
-          number_of_epochs = 1,
-          learning_rate = 0.1,
-          optimizer_name = "Adadelta",
-          optimizer_parameters = None,
-          batch_size = 32,
-          metric_names = None,
-          random_seed = 0,
-      ):
-          import tensorflow as tf
-          tf.random.set_seed(seed=random_seed)
-
-          # Loading model using Keras. Model loaded using TensorFlow does not have .fit.
-          #model = tf.saved_model.load(export_dir=model_path)
-          keras_model = tf.keras.models.load_model(filepath=model_path)
-
-          optimizer_parameters = optimizer_parameters or {}
-          optimizer_parameters["learning_rate"] = learning_rate
-          optimizer_config = {
-              "class_name": optimizer_name,
-              "config": optimizer_parameters,
-          }
-          optimizer = tf.keras.optimizers.get(optimizer_config)
-          loss = tf.keras.losses.get(loss_function_name)
-
-          training_dataset = tf.data.experimental.make_csv_dataset(
-              file_pattern=training_data_path,
-              batch_size=batch_size,
-              label_name=label_column_name,
-              header=True,
-              # Need to specify num_epochs=1 otherwise the training becomes infinite
-              num_epochs=1,
-              shuffle=True,
-              shuffle_seed=random_seed,
-              ignore_errors=True,
-          )
-          def stack_feature_batches(features_batch, labels_batch):
-              # Need to stack individual feature columns to create a single feature tensor
-              # Need to cast all column tensor types to float to prevent error:
-              # TypeError: Tensors in list passed to 'values' of 'Pack' Op have types [int32, float32, float32, int32, int32] that don't all match.
-              list_of_feature_batches = list(tf.cast(x=feature_batch, dtype=tf.float32) for feature_batch in features_batch.values())
-              return tf.stack(list_of_feature_batches, axis=-1), labels_batch
-
-          training_dataset = training_dataset.map(stack_feature_batches)
-
-          # Need to compile the model to prevent error:
-          # ValueError: No gradients provided for any variable: [..., ...].
-          keras_model.compile(
-              optimizer=optimizer,
-              loss=loss,
-              metrics=metric_names,
-          )
-          keras_model.fit(
-              training_dataset,
-              epochs=number_of_epochs,
-          )
-
-          # Using tf.keras.models.save_model instead of tf.saved_model.save to prevent downstream error:
-          #tf.saved_model.save(keras_model, trained_model_path)
-          # ValueError: Unable to create a Keras model from this SavedModel.
-          # This SavedModel was created with `tf.saved_model.save`, and lacks the Keras metadata.
-          # Please save your Keras model by calling `model.save`or `tf.keras.models.save_model`.
-          # See https://github.com/keras-team/keras/issues/16451
-          tf.keras.models.save_model(keras_model, trained_model_path)
-
-      import json
-      import argparse
-      _parser = argparse.ArgumentParser(prog='Train model using Keras on CSV', description='')
-      _parser.add_argument("--training-data", dest="training_data_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--model", dest="model_path", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--label-column-name", dest="label_column_name", type=str, required=True, default=argparse.SUPPRESS)
-      _parser.add_argument("--loss-function-name", dest="loss_function_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--number-of-epochs", dest="number_of_epochs", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--learning-rate", dest="learning_rate", type=float, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-name", dest="optimizer_name", type=str, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--optimizer-parameters", dest="optimizer_parameters", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--batch-size", dest="batch_size", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--metric-names", dest="metric_names", type=json.loads, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--random-seed", dest="random_seed", type=int, required=False, default=argparse.SUPPRESS)
-      _parser.add_argument("--trained-model", dest="trained_model_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
-      _parsed_args = vars(_parser.parse_args())
-
-      _outputs = train_model_using_Keras_on_CSV(**_parsed_args)
-    args:
-    - --training-data
-    - {inputPath: training_data}
-    - --model
-    - {inputPath: model}
-    - --label-column-name
-    - {inputValue: label_column_name}
-    - if:
-        cond: {isPresent: loss_function_name}
-        then:
-        - --loss-function-name
-        - {inputValue: loss_function_name}
-    - if:
-        cond: {isPresent: number_of_epochs}
-        then:
-        - --number-of-epochs
-        - {inputValue: number_of_epochs}
-    - if:
-        cond: {isPresent: learning_rate}
-        then:
-        - --learning-rate
-        - {inputValue: learning_rate}
-    - if:
-        cond: {isPresent: optimizer_name}
-        then:
-        - --optimizer-name
-        - {inputValue: optimizer_name}
-    - if:
-        cond: {isPresent: optimizer_parameters}
-        then:
-        - --optimizer-parameters
-        - {inputValue: optimizer_parameters}
-    - if:
-        cond: {isPresent: batch_size}
-        then:
-        - --batch-size
-        - {inputValue: batch_size}
-    - if:
-        cond: {isPresent: metric_names}
-        then:
-        - --metric-names
-        - {inputValue: metric_names}
-    - if:
-        cond: {isPresent: random_seed}
-        then:
-        - --random-seed
-        - {inputValue: random_seed}
-    - --trained-model
-    - {outputPath: trained_model}

community-content/pytorch_efficient_training/README.md

@@ -1,29 +0,0 @@
-# PyTorch Efficient Training Examples
-
-This folder provides PyTorch efficient training examples using ResNet-50 and ImageNet data.
-
-## Requirements
-
-```shell
-pip install --upgrade pip
-pip install -r requirements.txt
-```
-
-## Description
-
-* resnet.py - Train ResNet-50 on single GPU.
-* resnet_dp.py - Train ResNet-50 on single node multiple GPUs with `DataParallel` strategy.
-* resnet_ddp.py - Train ResNet-50 on single node multiple GPUs with `DistributedDataParallel` strategy.
-* resnet_ddp_wds.py - Train ResNet-50 on single node multiple GPUs with `DistributedDataParallel` strategy and `Webdataset`.
-* shard_imagenet.py - Shard ImagNet individual files into `tar` files.
-
-## Benchmark
-
-When run the benchmark on Nvidia T4 GPUs using ImageNet validation dataset, you can get the result like:
-Strategy              | Seconds/Epoch - Local Data | Seconds/Epoch - Cloud Data
---------------------- | -------------------------- | --------------------------
-On 1 GPU              | 489                        | 804 (2x slower)
-On 4 GPUs (DP)        | 157                        | 738 (5x slower)
-On 4 GPUs (DDP)       | 134                        | 432 (3x slower)
-On 4 GPUs (DDP + WDS) | 131                        | 133 (same performance)
-

community-content/pytorch_efficient_training/requirements.txt

@@ -1 +0,0 @@
-webdataset == 0.2.26

community-content/pytorch_efficient_training/resnet.py

@@ -1,197 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on single GPU."""
-
-import argparse
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image, target = image.to(device), target.to(device)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image, target = image.to(device), target.to(device)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def run_training(args):
-  """Run training and evaluation."""
-  # Create model.
-  model = resnet50(weights=None)
-  model = model.to(args.device)
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=True,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True)
-  print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-        f'num workers: {train_dataloader.num_workers}, '
-        f'batch size: {args.train_batch_size}, '
-        f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True)
-  print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-        f'num workers: {eval_dataloader.num_workers}, '
-        f'batch size: {args.eval_batch_size}, '
-        f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-  print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  args.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-
-  print('Launch job on 1 GPU')
-  run_training(args)
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_ddp.py

@@ -1,234 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DDP."""
-
-import argparse
-import os
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torch.distributed as dist
-import torch.multiprocessing as mp
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  torch.cuda.set_device(gpu)
-  model.to(args.device)
-  model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
-  model = nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_sampler = torch.utils.data.distributed.DistributedSampler(
-      train_dataset, num_replicas=args.gpus, rank=gpu)
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      sampler=train_sampler)
-  if gpu == 0:
-    print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-          f'num workers: {train_dataloader.num_workers}, '
-          f'global batch size: {args.train_batch_size * args.gpus}, '
-          f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_sampler = torch.utils.data.distributed.DistributedSampler(
-      eval_dataset, num_replicas=args.gpus, rank=gpu)
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True,
-      sampler=eval_sampler)
-  if gpu == 0:
-    print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-          f'num workers: {eval_dataloader.num_workers}, '
-          f'batch size: {args.eval_batch_size}, '
-          f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-    train_sampler.set_epoch(epoch)
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with DDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_ddp_wds.py

@@ -1,249 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DDP."""
-
-import argparse
-import functools
-import itertools
-import math
-import os
-import time
-
-import torch
-from torch import nn
-import torch.distributed as dist
-import torch.multiprocessing as mp
-import torchmetrics
-from torchvision.models import resnet50
-from torchvision.transforms import transforms
-import webdataset as wds
-
-
-def wds_split(src, rank, world_size):
-  """Shards split function for webdataset."""
-  # The context of caller of this function is within multiple processes
-  # (by DDP world_size) and multiple workers (by dataloader_num_workers).
-  # So we totally have (world_size * num_workers) workers for processing data.
-  # NOTE: Raw data should be sharded to enough shards to make sure one process
-  # can handle at least one shard, otherwise the process may hang.
-  worker_id = 0
-  num_workers = 1
-  worker_info = torch.utils.data.get_worker_info()
-  if worker_info:
-    worker_id = worker_info.id
-    num_workers = worker_info.num_workers
-  for s in itertools.islice(src, rank * num_workers + worker_id, None,
-                            world_size * num_workers):
-    yield s
-
-
-def identity(x):
-  return x
-
-
-def create_wds_dataloader(rank, args, mode):
-  """Create webdataset dataset and dataloader."""
-  if mode == 'train':
-    transform = transforms.Compose([
-        transforms.RandomResizedCrop(224),
-        transforms.RandomHorizontalFlip(),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.train_data_path
-    data_size = args.train_data_size
-    batch_size_local = args.train_batch_size
-    batch_size_global = args.train_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we pad the last batch for train.
-    batches = int(math.ceil(data_size / batch_size_global))
-  else:
-    transform = transforms.Compose([
-        transforms.Resize(256),
-        transforms.CenterCrop(224),
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
-    data_path = args.eval_data_path
-    data_size = args.eval_data_size
-    batch_size_local = args.eval_batch_size
-    batch_size_global = args.eval_batch_size * args.gpus
-    # Since webdataset disallows partial batch, we drop the last batch for eval.
-    batches = int(data_size / batch_size_global)
-
-  dataset = wds.DataPipeline(
-      wds.SimpleShardList(data_path),
-      functools.partial(wds_split, rank=rank, world_size=args.gpus),
-      wds.tarfile_to_samples(),
-      wds.decode('pil'),
-      wds.to_tuple('jpg;png;jpeg cls'),
-      wds.map_tuple(transform, identity),
-      wds.batched(batch_size_local, partial=False),
-  )
-  num_workers = args.dataloader_num_workers
-  dataloader = wds.WebLoader(
-      dataset=dataset,
-      batch_size=None,
-      shuffle=False,
-      num_workers=num_workers,
-      persistent_workers=True if num_workers > 0 else False,
-      pin_memory=True).repeat(nbatches=batches)
-  print(f'{mode} dataloader | samples: {data_size}, '
-        f'num_workers: {num_workers}, '
-        f'local batch size: {batch_size_local}, '
-        f'global batch size: {batch_size_global}, '
-        f'batches: {batches}')
-  return dataloader
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image = image.to(device, non_blocking=True)
-    target = target.to(device, non_blocking=True)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image = image.to(device, non_blocking=True)
-      target = target.to(device, non_blocking=True)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def worker(gpu, args):
-  """Run training and evaluation."""
-  # Init process group.
-  print(f'Initiating process {gpu}')
-  dist.init_process_group(
-      backend='nccl',
-      init_method='env://',
-      world_size=args.gpus,
-      rank=gpu)
-
-  # Create model.
-  model = resnet50(weights=None)
-  torch.cuda.set_device(gpu)
-  model.to(args.device)
-  model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
-  model = nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
-
-  # Create dataloader.
-  train_dataloader = create_wds_dataloader(gpu, args, 'train')
-  eval_dataloader = create_wds_dataloader(gpu, args, 'eval')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    if gpu == 0:
-      print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    if gpu == 0:
-      print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    if gpu == 0:
-      print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-
-  if gpu == 0:
-    print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--train_data_size',
-      default=50000,
-      type=int,
-      help='data size for training')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  parser.add_argument(
-      '--eval_data_size',
-      default=50000,
-      type=int,
-      help='data size for evaluation')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '8888'
-
-  args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-  print(f'Launch job on {args.gpus} GPUs with DDP')
-  mp.spawn(worker, nprocs=args.gpus, args=(args,))
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/resnet_dp.py

@@ -1,207 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Train resnet on multiple GPUs with DP."""
-
-import argparse
-import time
-
-from PIL import Image
-import torch
-from torch import nn
-import torchmetrics
-import torchvision
-from torchvision.models import resnet50
-
-
-class ImageFolder(torchvision.datasets.ImageFolder):
-  """Class for loading imagenet."""
-
-  def __init__(self, image_list_file, transform=None, target_transform=None):
-    self.samples = self._make_dataset(image_list_file)
-    self.loader = self._loader
-
-    self.imgs = self.samples
-    self.targets = [s[1] for s in self.samples]
-
-    self.transform = transform
-    self.target_transform = target_transform
-
-  def _make_dataset(self, image_list_file):
-    items = []
-    with open(image_list_file, 'r') as f:
-      for line in f:
-        item = line.strip().split(' ')
-        items.append((item[0], int(item[1])))
-    return items
-
-  def _loader(self, image_path):
-    with open(image_path, 'rb') as f:
-      img = Image.open(f)
-      img = img.convert('RGB')
-      return img
-
-
-def train(model, device, dataloader, optimizer):
-  model.train()
-  for image, target in dataloader:
-    image, target = image.to(device), target.to(device)
-    pred = model(image)
-    # pred.shape (N, C), target.shape (N)
-    loss = nn.functional.cross_entropy(pred, target)
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-  return loss
-
-
-def evaluate(model, device, dataloader, metric):
-  model.eval()
-  with torch.no_grad():
-    for image, target in dataloader:
-      image, target = image.to(device), target.to(device)
-      pred = model(image)
-      metric.update(pred, target)
-  accuracy = metric.compute()
-  metric.reset()
-  return accuracy
-
-
-def run_training(args):
-  """Run training and evaluation."""
-  # Create model.
-  model = resnet50(weights=None)
-  model = nn.DataParallel(model)
-  model = model.to(args.device)
-
-  # Create train dataloader.
-  train_dataset = ImageFolder(
-      image_list_file=args.train_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.RandomResizedCrop(224),
-          torchvision.transforms.RandomHorizontalFlip(),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  train_dataloader = torch.utils.data.DataLoader(
-      dataset=train_dataset,
-      batch_size=args.train_batch_size,
-      shuffle=True,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True)
-  print(f'Train dataloader | samples: {len(train_dataloader.dataset)}, '
-        f'num workers: {train_dataloader.num_workers}, '
-        f'global batch size: {args.train_batch_size}, '
-        f'batches/epoch: {len(train_dataloader)}')
-
-  # Create eval dataloader.
-  eval_dataset = ImageFolder(
-      image_list_file=args.eval_data_path,
-      transform=torchvision.transforms.Compose([
-          torchvision.transforms.Resize(256),
-          torchvision.transforms.CenterCrop(224),
-          torchvision.transforms.ToTensor(),
-          torchvision.transforms.Normalize(
-              mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-      ]))
-  eval_dataloader = torch.utils.data.DataLoader(
-      dataset=eval_dataset,
-      batch_size=args.eval_batch_size,
-      shuffle=False,
-      num_workers=args.dataloader_num_workers,
-      pin_memory=True,
-      drop_last=True)
-  print(f'Eval dataloader | samples: {len(eval_dataloader.dataset)}, '
-        f'num workers: {eval_dataloader.num_workers}, '
-        f'global batch size: {args.eval_batch_size}, '
-        f'batches/epoch: {len(eval_dataloader)}')
-
-  # Optimizer.
-  optimizer = torch.optim.SGD(model.parameters(), 0.1)
-
-  # Main loop.
-  metric = torchmetrics.classification.Accuracy(top_k=1).to(args.device)
-  for epoch in range(1, args.epochs + 1):
-    print(f'Running epoch {epoch}')
-
-    start = time.time()
-    train(model, args.device, train_dataloader, optimizer)
-    end = time.time()
-    print(f'Training finished in {(end - start):>0.3f} seconds')
-
-    start = time.time()
-    evaluate(model, args.device, eval_dataloader, metric)
-    end = time.time()
-    print(f'Evaluation finished in {(end - start):>0.3f} seconds')
-  print('Done')
-
-
-def create_args():
-  """Create main args."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--gpus',
-      default=4,
-      type=int,
-      help='number of gpus to use')
-  parser.add_argument(
-      '--epochs',
-      default=1,
-      type=int,
-      help='number of total epochs to run')
-  parser.add_argument(
-      '--dataloader_num_workers',
-      default=2,
-      type=int,
-      help='number of workders for dataloader')
-  parser.add_argument(
-      '--train_data_path',
-      default='',
-      type=str,
-      help='path to training data')
-  parser.add_argument(
-      '--train_batch_size',
-      default=32,
-      type=int,
-      help='batch size for training per gpu')
-  parser.add_argument(
-      '--eval_data_path',
-      default='',
-      type=str,
-      help='path to evaluation data')
-  parser.add_argument(
-      '--eval_batch_size',
-      default=32,
-      type=int,
-      help='batch size for evaluation per gpu')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-
-  args.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-  args.train_batch_size *= args.gpus
-  args.eval_batch_size *= args.gpus
-  args.dataloader_num_workers *= args.gpus
-
-  print(f'Launch job on {args.gpus} GPU with nn.DataParallel')
-  run_training(args)
-
-
-if __name__ == '__main__':
-  main()

community-content/pytorch_efficient_training/shard_imagenet.py

@@ -1,98 +0,0 @@
-# Copyright 2022 Google LLC
-#
-# Licensed under the Apache License, Version 2.0 (the \"License\");
-# you may not use this file except in compliance with the License.\n",
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an \"AS IS\" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-r"""Main function to shard ImageNet dataset.
-
-Example usage:
-python3 -u shard_imagenet.py \
---image_list_file=/home/jupyter/data/imagenet/train_list.txt \
---output_pattern=/home/jupyter/data/imagenet/validation-%06d.tar
-"""
-
-import argparse
-import os
-import random
-import webdataset as wds  # version: 0.2.26
-
-
-# NOTE: only supports writing to local path,
-# need gcsfuse mounting if want to write to gcs bucket.
-def write_shards(args):
-  """Shard individual data files."""
-  output_dir = os.path.dirname(args.output_pattern)
-  if not os.path.isdir(output_dir):
-    os.makedirs(output_dir)
-
-  items = []
-  # Image list file is a text file, each line is a pair (image_path, label).
-  with open(args.image_list_file, 'r') as f:
-    for line in f:
-      item = line.strip().split(' ')
-      items.append((item[0], int(item[1])))
-  # Shuffle items to avoid any large sequences of a single class
-  # in the dataset.
-  random.shuffle(items)
-
-  def _read_image(image_path):
-    with open(image_path, 'rb') as f:
-      return f.read()
-
-  with wds.ShardWriter(pattern=args.output_pattern,
-                       maxcount=args.max_images_per_shard,
-                       maxsize=args.max_bytes_per_shard) as sink:
-    for i, (image_path, target) in enumerate(items):
-      key = str(i)
-      image = _read_image(image_path)
-      sample = {'__key__': key, 'jpg': image, 'cls': target}
-      sink.write(sample)
-    if len(items) != sink.total:
-      raise ValueError('Items read {} != items written {}'.format(
-          len(items), sink.total))
-
-
-def create_args():
-  """Creates arg parser."""
-  parser = argparse.ArgumentParser(
-      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-  parser.add_argument(
-      '--image_list_file',
-      default='',
-      type=str,
-      help='path to image list file')
-  parser.add_argument(
-      '--output_pattern',
-      default='',
-      type=str,
-      help='the pattern for output shards, like /path/to/train-%06d.tar')
-  parser.add_argument(
-      '--max_images_per_shard',
-      default=10 * 1024,
-      type=int,
-      help='max number of images per shard')
-  parser.add_argument(
-      '--max_bytes_per_shard',
-      default=300 * 1024 * 1024,
-      type=int,
-      help='max bytes per shard')
-  args = parser.parse_args()
-  return args
-
-
-def main():
-  args = create_args()
-  write_shards(args)
-
-
-if __name__ == '__main__':
-  main()

notebooks/ci_notebook_ingestion.md

@@ -1,102 +0,0 @@
-# Administrative Howto notes on CI Notebook Ingestion
-
-
-This readme covers administrative actions that are performed on an as-needed basis.
-
-## Team: vertex-ai-owners
-
-Members of the vertex-ai-owners (git team) have administrative privileges. 
-
-
-### Viewing members
-
-1. Goto the repo
-2. From top-level menu, select: (Settings -> Collaborators and Teams)[https://github.com/GoogleCloudPlatform/vertex-ai-samples/settings/access]
-
-
-### Adding a new member
-
-If another member needs to be added:
-   - Have the new member make a request to join the team.
-   - vertex-ai-owners with the `Maintainer` tag may add the new member.
-
-   
-## Executing CI notebook ingestion checks on a PR
-   
-### Killing a stuck PR
-
-If the CI notebook ingestion test is stuck (not terminating), you can kill the process by:
-
-1. Goto the PR
-2. Under checks, find the entry: vertex-ai-notebook-execution-test (python-docs-samples-tests) In progress —> Summary
-3. Select Details
-4. At bottom of details page, select: View more details on Google Cloud Build
-5. In Cloud Build history page, select Cancel on the top menu bar.
-
-### Restart a PR test
-
-There are two ways to restart the CI notebook ingestion tests on an open PR.
-
-1. In Cloud Build history page, select Rebuild on the top menu bar.
-2. or, in a comment in the PR enter: /gcbrun
-
-## Bypassing CI notebook ingestion checks on a PR
-
-We strongly discourage this, unless there is a compelling reason that would impact the integrity of the quality process.
-
-There are two ways of doing this. In both cases, you do:
-
-1. Goto the repo
-2. From top-level menu, select: (Settings -> Branches)[https://github.com/GoogleCloudPlatform/vertex-ai-samples/settings/branches]
-3. Under Branch Protection Rules, select the `main` branch.
-
-### Allowing a member to disable requirements for merging
-
-Specific member(s) can be assigned the ability to override requirements and merge a PR, by:
-
-1. Select Edit for the `main` branch in Branch Protection Rules.
-2. Find the entry "Allow specified actors to bypass required pull requests".
-3. Under this entry, add the member's git LDAP.
-4. Select SAVE.
-5. The "Squash and Merge" button will now be enabled on all PRs viewed by that member.
-
-### Temporarily disable checks.
-
-You can disable requirement checks temporarily on all PRs. 
-
-1. Select Edit for the `main` branch in Branch Protection Rules.
-2. Uncheck:
-  - Require approvals
-  - Require review from Code Owners
-  - Require status checks to pass before merging
-3. Select SAVE
-4. Now all members will see a green "Squash and Merge" on all PRs viewed by that member.
-
-To reverse, recheck the settings you unchecked above.
-
-## Linting
-
-To execute the identical lint image locally, from the CI notebook ingestion checks, do:
-
-1. Goto the corresponding local folder in the repo.
-2. Run: `docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest <your_notebooks>`
-
-## Install dependency issues
-
-Some packages (and combinations) have dependencies that fail on the virgin VM image used for the CI notebook ingestion test.
-
-### TFDV
-
-If the notebook installs and uses tensorflow_data_validation, install as follows:
-
-! pip3 install -q {USER_FLAG} google-cloud-aiplatform \
-                              tensorflow-data-validation \
-                              protobuf==3.20.3
-
-! pip3 install -q {USER_FLAG} cachetools==5.2.0
-
-
-
-
-   
-   

notebooks/community/CODEOWNERS

@@ -12,18 +12,17 @@
 
 /managed_notebooks/
 /bigquery_ml/ @polong
+/sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
 /pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb @brianchunkang
 /explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
 /matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
 /matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
 /matching_engine/stream_update_for_matching_engine.ipynb @peterping666
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
-/sdk/sdk_pytorch_torchrun_custom_container_training_imagenet.ipynb @brianchunkang
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu
 /prediction @googleapis/vertex-prediction-team
 /vertex_endpoints/tf_hub_obj_detection/deploy_tfhub_object_detection_on_vertex_endpoints.ipynb @entrpn
-/vertex_endpoints/find_ideal_machine_type/find_ideal_machine_type/find_ideal_machine_type.ipynb @entrpn
 /vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
 /vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
 /notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
@@ -35,5 +34,3 @@
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_bqml_custom_model_versioning.ipynb @inardini
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_automl_model_versioning.ipynb @inardini
 /notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb @halio-g
-/notebooks/community/experiments/vertex_ai_model_experimentation.ipynb @inardini @asobran
-/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_anomaly_detection.ipynb @inardini

notebooks/community/ml_ops/stage1/README.md

@@ -28,7 +28,7 @@ The first stage in MLOps is the collection and preparation for the purpose of de
 
 ### Get Started
 
-[Get started with Dataflow](get_started_dataflow.ipynb)
+[Get started with Dataflow](community/ml_ops/stage1/get_started_dataflow.ipynb)
 
 In this tutorial, you learn how to use `Dataflow` for training with `Vertex AI`.
 
@@ -41,7 +41,7 @@ The steps performed include:
     - tabular data
     - image data
 
-[Get started with Vertex AI datasets](get_started_vertex_datasets.ipynb)
+[Get started with Vertex AI datasets](community/ml_ops/stage1/get_started_vertex_datasets.ipynb)
 
 In this tutorial, you learn how to use `Vertex AI Dataset` for training with `Vertex AI`.
 
@@ -62,7 +62,7 @@ The steps performed include:
 - Generate a TFRecord feature specification using TensorFlow Transform from the data schema.
 - Export a dataset and convert to TFRecords.
 
-[Get started with BigQuery datasets](get_started_bq_datasets.ipynb)
+[Get started with BigQuery datasets](community/ml_ops/stage1/get_started_bq_datasets.ipynb)
 
 In this tutorial, you learn how to use `BigQuery` as a dataset for training with `Vertex AI`.
 
@@ -76,7 +76,7 @@ The steps performed include:
 - Create a `BigQuery` dataset from CSV files.
 - Extract data from `BigQuery` table into a `DMatrix` -- compatible for custom training `XGBoost` models.
 
-[Get started with Vertex AI Data Labeling](get_started_with_data_labeling.ipynb)
+[Get started with Vertex AI Data Labeling](community/ml_ops/stage1/get_started_with_data_labeling.ipynb)
 
 In this tutorial, you learn how to use the `Vertex AI Data Labeling` service.
 
@@ -90,7 +90,7 @@ The steps performed include:
 
 
 
-[Create an unlabelled Vertex AI AutoML text entity extraction dataset from PDFs using Vision API](get_started_with_visionapi_and_vertex_datasets.ipynb)
+[Create an unlabelled Vertex AI AutoML text entity extraction dataset from PDFs using Vision API](community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb)
 
 In this tutorial, you learn to use `Vision API` to extract text from PDF files stored on a Cloud Storage bucket. You then process the results and create an unlabelled `Vertex AI Dataset`, compatible with `AutoML`, for text entity extraction.
 

notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb

@@ -48,7 +48,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb target='_blank'>",
+        "    <a href=\"https://github.com/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",

notebooks/community/ml_ops/stage2/get_started_with_vertex_experiments_autologging_xgboost.ipynb

@@ -1,929 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "copyright"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2022 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "title"
-      },
-      "source": [
-        "# E2E ML on GCP: MLOps stage 2 : Get started with autologging using Vertex AI Experiments for XGBoost models\n",
-        "\n",
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_vertex_experiments_autologging_xgboost.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_vertex_experiments_autologging_xgboost.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_with_vertex_experiments_autologging_xgboost.ipynb\">\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
-        "      Open in Vertex AI Workbench\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>\n",
-        "<br/><br/><br/>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "overview:automl"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "\n",
-        "This tutorial demonstrates how to use the `Vertex AI Experiments` with DIY code to implement automatic logging of parameters and metrics for experiments."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "objective:automl,training,batch_prediction"
-      },
-      "source": [
-        "### Objective\n",
-        "\n",
-        "In this tutorial, you learn how to create an experiment for training an XGBoost model, and automatically log parameters and metrics using the enclosed do-it-yourself (DIY) code.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "\n",
-        "- `Vertex AI Experiments`\n",
-        "\n",
-        "The steps performed include:\n",
-        "\n",
-        "- Construct the DIY autologging code.\n",
-        "- Construct training package with call to autologging.\n",
-        "- Train a model.\n",
-        "- View the experiment\n",
-        "- Delete the experiment."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:custom,boston,lrg"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the [Iris dataset](https://www.tensorflow.org/datasets/catalog/iris) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of Iris flower species from a class of three species: setosa, virginica, or versicolor."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "costs"
-      },
-      "source": [
-        "### Costs\n",
-        "\n",
-        "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
-        "* Vertex AI\n",
-        "* Cloud Storage\n",
-        "\n",
-        "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
-        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
-        "to generate a cost estimate based on your projected usage."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_local"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "If you are using Colab or Vertex Workbench AI Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "\n",
-        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
-        "\n",
-        "- The Cloud Storage SDK\n",
-        "- Git\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
-        "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
-        "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
-        "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
-        "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
-        "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_aip:mbsdk"
-      },
-      "source": [
-        "## Installation\n",
-        "\n",
-        "Install the following packages to execute this notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform \\\n",
-        "                                             xgboost \\\n",
-        "                                             scikit-learn \\\n",
-        "                                             numpy"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "restart"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "restart"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "before_you_begin:nogpu"
-      },
-      "source": [
-        "## Before you begin\n",
-        "\n",
-        "### GPU runtime\n",
-        "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "project_id"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "region"
-      },
-      "source": [
-        "#### Region\n",
-        "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "region"
-      },
-      "outputs": [],
-      "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### UUID\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gcp_authenticate"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \n",
-        "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "**Click Create service account**.\n",
-        "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "gcp_authenticate"
-      },
-      "outputs": [],
-      "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_vars"
-      },
-      "source": [
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "59963fb7178f"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aiplatform\n",
-        "import numpy as np\n",
-        "import xgboost as xgb\n",
-        "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
-        "\n",
-        "# to suppress lint message (unused)\n",
-        "precision_score, recall_score"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "source": [
-        "## Initialize Vertex AI SDK for Python\n",
-        "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, location=REGION)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ae8f31c8c617"
-      },
-      "source": [
-        "## DIY code for autologging XGBoost models\n",
-        "\n",
-        "The code below implements autologging for XGBoost models.\n",
-        "\n",
-        "- `autologging()`: Initializes the experiment and uses heap injection to replace `xgboost.train()` symbols on the heap with the redirect wrapper function `VertexXGBtrain`.\n",
-        "\n",
-        "- `VertexXGBtrain`: A wrapper function for XGBoost train() function. Automatically logs hyperparameters and calls the underlyig function.\n",
-        "\n",
-        "- `VertexSKLaccuracy_score`: A wrapper function for scikit-learn accuracy_score() function. Automatically calls underlying function and logs the metrics results."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8eb012e5d7ef"
-      },
-      "outputs": [],
-      "source": [
-        "def autolog(\n",
-        "    project: str = None,\n",
-        "    location: str = None,\n",
-        "    staging_bucket: str = None,\n",
-        "    experiment: str = None,\n",
-        "    run: str = None,\n",
-        "    framework: str = \"tf\",\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Enable automatic logging of parameters and metrics in Vertex AI Experiments,\n",
-        "    for corresponding framework.\n",
-        "\n",
-        "        project: The project ID\n",
-        "        location : The region\n",
-        "        staging_bucket: temporary bucket\n",
-        "        experiment: The name of the experiment\n",
-        "        run: The name of the run within the experiment\n",
-        "        framework: The ML framework for which a model is being trained.\n",
-        "    \"\"\"\n",
-        "    # autologging\n",
-        "    if framework == \"tf\":\n",
-        "        try:\n",
-        "            globals()[\"Sequential\"] = VertexTFSequential\n",
-        "            if \"tf\" in globals():\n",
-        "                tf.keras.Sequential = VertexTFSequential\n",
-        "            if \"tensorflow\" in globals():\n",
-        "                tensorflow.keras.Sequential = VertexTFSequential\n",
-        "        except:\n",
-        "            pass\n",
-        "\n",
-        "        try:\n",
-        "            globals()[\"Model\"] = VertexTFModel\n",
-        "            if \"tf\" in globals():\n",
-        "                tf.keras.Model = VertexTFModel\n",
-        "            if \"tensorflow\" in globals():\n",
-        "                tensorflow.keras.Model = VertexTFModel\n",
-        "        except:\n",
-        "            pass\n",
-        "    elif framework == \"xgb\":\n",
-        "        global real_xgb_train\n",
-        "        global real_accuracy_score, real_precision_score, real_recall_score\n",
-        "        import sklearn\n",
-        "\n",
-        "        try:\n",
-        "            if \"xgboost\" in globals():\n",
-        "                real_xgb_train = xgboost.train\n",
-        "                xgboost.train = VertexXGBtrain\n",
-        "        except:\n",
-        "            pass\n",
-        "\n",
-        "        try:\n",
-        "            if \"xgb\" in globals():\n",
-        "                real_xgb_train = xgb.train\n",
-        "                xgb.train = VertexXGBtrain\n",
-        "        except:\n",
-        "            pass\n",
-        "\n",
-        "        try:\n",
-        "            global accuracy_score, precision_score, recall_score\n",
-        "            if \"accuracy_score\" in globals():\n",
-        "                real_accuracy_score = sklearn.metrics.accuracy_score\n",
-        "                sklearn.metrics.accuracy_score = VertexSKLaccuracy_score\n",
-        "                accuracy_score = VertexSKLaccuracy_score\n",
-        "            if \"precision_score\" in globals():\n",
-        "                real_precision_score = sklearn.metrics.precision_score\n",
-        "                sklearn.metrics.precision_score = VertexSKLprecision_score\n",
-        "                precision_score = VertexSKLprecision_score\n",
-        "            if \"recall_score\" in globals():\n",
-        "                real_recall_score = sklearn.metrics.recall_score\n",
-        "                sklearn.metrics.recall_score = VertexSKLrecall_score\n",
-        "                recall_score = VertexSKLrecall_score\n",
-        "        except:\n",
-        "            pass\n",
-        "\n",
-        "    if project:\n",
-        "        aiplatform.init(\n",
-        "            project=project, location=location, staging_bucket=staging_bucket\n",
-        "        )\n",
-        "\n",
-        "    if experiment:\n",
-        "        aiplatform.init(experiment=experiment)\n",
-        "    if run:\n",
-        "        aiplatform.start_run(run)\n",
-        "\n",
-        "\n",
-        "def VertexXGBtrain(\n",
-        "    params,\n",
-        "    dtrain,\n",
-        "    num_boost_round=10,\n",
-        "    evals=None,\n",
-        "    obj=None,\n",
-        "    maximize=None,\n",
-        "    early_stopping_rounds=None,\n",
-        "    evals_result=None,\n",
-        "    verbose_eval=True,\n",
-        "    callbacks=None,\n",
-        "    custom_metric=None,\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Wrapper function for autologging training parameters with Vertex AI Experiments\n",
-        "    Args:\n",
-        "        same as underlying xgb.train() method\n",
-        "    \"\"\"\n",
-        "    global real_xgb_train\n",
-        "\n",
-        "    aiplatform.log_params({\"train.num_boost_round\": int(num_boost_round)})\n",
-        "\n",
-        "    if params:\n",
-        "        if \"booster\" in params:\n",
-        "            aiplatform.log_params({\"train.booster\": int(params[\"booster\"])})\n",
-        "\n",
-        "        # booster parameters\n",
-        "        if \"eta\" in params:\n",
-        "            aiplatform.log_params({\"train.eta\": int(params[\"eta\"])})\n",
-        "        if \"max_depth\" in params:\n",
-        "            aiplatform.log_params({\"train.max_depth\": int(params[\"max_depth\"])})\n",
-        "        if \"max_leaf_nodes\" in params:\n",
-        "            aiplatform.log_params(\n",
-        "                {\"train.max_leaf_nodes\": int(params[\"max_leaf_nodes\"])}\n",
-        "            )\n",
-        "        if \"gamma\" in params:\n",
-        "            aiplatform.log_params({\"train.gamma\": int(params[\"gamma\"])})\n",
-        "        if \"alpha\" in params:\n",
-        "            aiplatform.log_params({\"train.alpha\": int(params[\"alpha\"])})\n",
-        "\n",
-        "    return real_xgb_train(\n",
-        "        params=params,\n",
-        "        dtrain=dtrain,\n",
-        "        num_boost_round=num_boost_round,\n",
-        "        evals=evals,\n",
-        "        obj=obj,\n",
-        "        maximize=maximize,\n",
-        "        early_stopping_rounds=early_stopping_rounds,\n",
-        "        evals_result=evals_result,\n",
-        "        verbose_eval=verbose_eval,\n",
-        "        callbacks=callbacks,\n",
-        "        custom_metric=custom_metric,\n",
-        "    )\n",
-        "\n",
-        "\n",
-        "def VertexSKLaccuracy_score(labels, predictions):\n",
-        "    \"\"\"\n",
-        "    Wrapper function for autologging training metrics with Vertex AI Experiments\n",
-        "    Args:\n",
-        "        same as underlying accuracy_score function\n",
-        "    \"\"\"\n",
-        "    global real_accuracy_score\n",
-        "    accuracy = real_accuracy_score(labels, predictions)\n",
-        "    aiplatform.log_metrics({\"accuracy\": accuracy})\n",
-        "    return accuracy\n",
-        "\n",
-        "\n",
-        "def VertexSKLprecision_score(\n",
-        "    y_true,\n",
-        "    y_pred,\n",
-        "    *,\n",
-        "    labels=None,\n",
-        "    pos_label=1,\n",
-        "    average=\"binary\",\n",
-        "    sample_weight=None,\n",
-        "    zero_division=\"warn\",\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Wrapper function for autologging training metrics with Vertex AI Experiments\n",
-        "    Args:\n",
-        "        same as underlying precision_score function\n",
-        "    \"\"\"\n",
-        "    global real_precision_score\n",
-        "    precision = real_precision_score(\n",
-        "        y_true,\n",
-        "        y_pred,\n",
-        "        labels=labels,\n",
-        "        pos_label=pos_label,\n",
-        "        average=average,\n",
-        "        sample_weight=sample_weight,\n",
-        "        zero_division=zero_division,\n",
-        "    )\n",
-        "    aiplatform.log_metrics({\"precision\": precision})\n",
-        "    return precision\n",
-        "\n",
-        "\n",
-        "def VertexSKLrecall_score(\n",
-        "    y_true,\n",
-        "    y_pred,\n",
-        "    *,\n",
-        "    labels=None,\n",
-        "    pos_label=1,\n",
-        "    average=\"binary\",\n",
-        "    sample_weight=None,\n",
-        "    zero_division=\"warn\",\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    Wrapper function for autologging training metrics with Vertex AI Experiments\n",
-        "    Args:\n",
-        "        same as underlying recall_score function\n",
-        "    \"\"\"\n",
-        "    global real_recall_score\n",
-        "    recall = real_recall_score(\n",
-        "        y_true,\n",
-        "        y_pred,\n",
-        "        labels=labels,\n",
-        "        pos_label=pos_label,\n",
-        "        average=average,\n",
-        "        sample_weight=sample_weight,\n",
-        "        zero_division=zero_division,\n",
-        "    )\n",
-        "    aiplatform.log_metrics({\"recall\": recall})\n",
-        "    return recall\n",
-        "\n",
-        "\n",
-        "class VertexXGBBooster(xgb.Booster):\n",
-        "    \"\"\"\n",
-        "    WIP\n",
-        "    \"\"\"\n",
-        "\n",
-        "    def __init__(self, params=None, cache=None, model_file=None):\n",
-        "        super().__init__(params, cache, model_file)\n",
-        "\n",
-        "    def boost(\n",
-        "        self, dtrain: xgb.core.DMatrix, grad: np.ndarray, hess: np.ndarray\n",
-        "    ) -> None:\n",
-        "        return super().boost(dtrain, grad, hess)\n",
-        "\n",
-        "    def eval(\n",
-        "        self, data: xgb.core.DMatrix, name: str = \"eval\", iteration: int = 0\n",
-        "    ) -> str:\n",
-        "        return super().eval(data, name, iteration)\n",
-        "\n",
-        "    def update(self, dtrain: xgb.core.DMatrix, iteration: int, fobj=None) -> None:\n",
-        "        return super().update(dtrain, iteration, fobj)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ce76826902c0"
-      },
-      "source": [
-        "### Train the XGBoost model with Vertex AI Experiments\n",
-        "\n",
-        "In the following code, you build, train and evaluate an XGBoost tabular model. The Python script includes the following calls to integrate `Vertex AI Experiments`:\n",
-        "\n",
-        "- command-line arguments: The arguments `experiment` and `run` are used to pass in the experiment and run names for the experiment.\n",
-        "- `autologging()`: Initializes the experiment and does the heap injection.\n",
-        "- `aiplatform.start_execution()`: Initializes a context for linking artifacts.\n",
-        "- `aiplatform.end_run()`: Ends the experiment.\n",
-        "\n",
-        "*Note:* The functions `xgb.train` and `accuracy_score` will be redirected to `VertexXGBtrain` and VertexSKLaccuracy_score, respectively, by heap injection. When subsequent calls are made to the `train()` and `accuracy()` function,s they will be executed as the corresponding `VertexXGBtrain` and `VertexSKLaccuracy_score` functions."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "WiSnFuDoox9W"
-      },
-      "outputs": [],
-      "source": [
-        "EXPERIMENT_NAME = f\"myexperiment{UUID}\"\n",
-        "RUN_NAME = \"run-1\"\n",
-        "\n",
-        "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
-        "DATASET_DATA_URL = DATASET_DIR + \"/iris_data.csv\"\n",
-        "DATASET_LABELS_URL = DATASET_DIR + \"/iris_target.csv\"\n",
-        "\n",
-        "BOOSTED_ROUNDS = 20\n",
-        "\n",
-        "import logging\n",
-        "import os\n",
-        "import subprocess\n",
-        "import sys\n",
-        "\n",
-        "import hypertune\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "import xgboost as xgb\n",
-        "from sklearn.model_selection import train_test_split\n",
-        "\n",
-        "\n",
-        "def get_data():\n",
-        "    # gsutil outputs everything to stderr so we need to divert it to stdout.\n",
-        "    subprocess.check_call(\n",
-        "        [\"gsutil\", \"cp\", DATASET_DATA_URL, \"data.csv\"], stderr=sys.stdout\n",
-        "    )\n",
-        "    # gsutil outputs everything to stderr so we need to divert it to stdout.\n",
-        "    subprocess.check_call(\n",
-        "        [\"gsutil\", \"cp\", DATASET_LABELS_URL, \"labels.csv\"], stderr=sys.stdout\n",
-        "    )\n",
-        "\n",
-        "    # Load data into pandas, then use `.values` to get NumPy arrays\n",
-        "    data = pd.read_csv(\"data.csv\").values\n",
-        "    labels = pd.read_csv(\"labels.csv\").values\n",
-        "\n",
-        "    # Convert one-column 2D array into 1D array for use with XGBoost\n",
-        "    labels = labels.reshape((labels.size,))\n",
-        "\n",
-        "    train_data, test_data, train_labels, test_labels = train_test_split(\n",
-        "        data, labels, test_size=0.2, random_state=7\n",
-        "    )\n",
-        "\n",
-        "    # Load data into DMatrix object\n",
-        "    dtrain = xgb.DMatrix(train_data, label=train_labels)\n",
-        "    return dtrain, test_data, test_labels\n",
-        "\n",
-        "\n",
-        "def train_model(dtrain):\n",
-        "    logging.info(\"Start training ...\")\n",
-        "    # Train XGBoost model\n",
-        "    params = {\"max_depth\": 3, \"objective\": \"multi:softmax\", \"num_class\": 3}\n",
-        "    model = xgb.train(params=params, dtrain=dtrain, num_boost_round=BOOSTED_ROUNDS)\n",
-        "    logging.info(\"Training completed\")\n",
-        "    return model\n",
-        "\n",
-        "\n",
-        "def evaluate_model(model, test_data, test_labels):\n",
-        "    dtest = xgb.DMatrix(test_data)\n",
-        "    pred = model.predict(dtest)\n",
-        "    predictions = [round(value) for value in pred]\n",
-        "    # evaluate predictions\n",
-        "    accuracy = accuracy_score(test_labels, predictions)\n",
-        "\n",
-        "    logging.info(f\"Evaluation completed with model accuracy: {accuracy}\")\n",
-        "\n",
-        "    # report metric for hyperparameter tuning\n",
-        "    hpt = hypertune.HyperTune()\n",
-        "    hpt.report_hyperparameter_tuning_metric(\n",
-        "        hyperparameter_metric_tag=\"accuracy\", metric_value=accuracy\n",
-        "    )\n",
-        "    return accuracy\n",
-        "\n",
-        "\n",
-        "# autologging\n",
-        "autolog(experiment=EXPERIMENT_NAME, run=RUN_NAME, framework=\"xgb\")\n",
-        "\n",
-        "with aiplatform.start_execution(\n",
-        "    schema_title=\"system.ContainerExecution\", display_name=\"example_training\"\n",
-        ") as execution:\n",
-        "    dtrain, test_data, test_labels = get_data()\n",
-        "    model = train_model(dtrain)\n",
-        "    accuracy = evaluate_model(model, test_data, test_labels)\n",
-        "\n",
-        "aiplatform.end_run()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5f40912e6500"
-      },
-      "source": [
-        "#### Get the experiment results\n",
-        "\n",
-        "Next, you use the experiment name as a parameter to the method `get_experiment_df()` to get the results of the experiment as a pandas dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "7e9671712230"
-      },
-      "outputs": [],
-      "source": [
-        "experiment_df = aiplatform.get_experiment_df()\n",
-        "experiment_df = experiment_df[experiment_df.experiment_name == EXPERIMENT_NAME]\n",
-        "experiment_df.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e508c159d712"
-      },
-      "source": [
-        "#### Delete the experiment\n",
-        "\n",
-        "Since the experiment was created within a training script, to delete the experiment you use the `list()` method to obtain all the experiments for the project, and then filter on the experiment name."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "1a1b5fcbfde0"
-      },
-      "outputs": [],
-      "source": [
-        "experiments = aiplatform.Experiment.list()\n",
-        "for experiment in experiments:\n",
-        "    if experiment.name == EXPERIMENT_NAME:\n",
-        "        experiment.delete()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cleanup:mbsdk"
-      },
-      "source": [
-        "# Cleaning up\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
-        "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9eb897e0e728"
-      },
-      "outputs": [],
-      "source": [
-        "# There are no resources to cleanup"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "get_started_with_vertex_experiments_autologging_xgboost.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/stage3/README.md

@@ -34,7 +34,7 @@ The third stage in MLOps is formalization to develop an automated pipeline proce
 ### Get Started
 
 
-[Get started with Vertex AI Model Registry](get_started_with_model_registry.ipynb)
+[Get started with Vertex AI Model Registry](community/ml_ops/stage3/get_started_with_model_registry.ipynb)
 
 In this tutorial, you learn how to use `Vertex AI Model Registry` to create and register multiple versions of a model.
 
@@ -46,7 +46,7 @@ The steps performed include:
 - Deleting a model version.
 - Retraining the next model version.
 
-[Get started with Dataflow pipeline components](get_started_with_dataflow_pipeline_components.ipynb)
+[Get started with Dataflow pipeline components](community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataflow`.
 
@@ -56,7 +56,7 @@ The steps performed include:
 - Encapsulate the Apache Beam data pipeline with a Dataflow component in a Vertex AI pipeline.
 - Execute a Vertex AI pipeline.
 
-[Get started with Apache Airflow and Vertex AI Pipelines](get_started_with_airflow_and_vertex_pipelines.ipynb)
+[Get started with Apache Airflow and Vertex AI Pipelines](community/ml_ops/stage3/get_started_with_airflow_and_vertex_pipelines.ipynb)
 
 In this tutorial, you learn how to use Apache Airflow with `Vertex AI Pipelines`.
 
@@ -67,7 +67,7 @@ The steps performed include:
 - Create a `Vertex AI Pipeline` that triggers the Airflow DAG.
 - Execute the `Vertex AI Pipeline`.
 
-[Get started with Kubeflow Pipelines](get_started_with_kubeflow_pipelines.ipynb)
+[Get started with Kubeflow Pipelines](community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb)
 
 In this tutorial, you learn how to use `Kubeflow Pipelines`(KFP).
 
@@ -80,7 +80,7 @@ The steps performed include:
 - Building sequential, parallel, multiple output components.
 - Building control flow into pipelines.
 
-[Get started with Vertex AI custom training pipeline components](get_started_with_custom_training_pipeline_components.ipynb)
+[Get started with Vertex AI custom training pipeline components](community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Vertex AI Training`.
 
@@ -98,7 +98,7 @@ The steps performed include:
     - Deploying a Vertex AI custom trained model.
 - Execute a Vertex AI pipeline.
 
-[Get started with Dataproc Serverless pipeline components](get_started_with_dataproc_serverless_pipeline_components.ipynb)
+[Get started with Dataproc Serverless pipeline components](community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb)
 
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataproc Serverless` service. 
@@ -111,7 +111,7 @@ The steps performed include:
 - `DataprocSparkSqlBatchOp` for running Spark SQL batch workloads.
 - `DataprocSparkRBatchOp` for running SparkR batch workloads.
 
-[Get started with Vertex AI Hyperparameter Tuning pipeline components](get_started_with_hpt_pipeline_components.ipynb)
+[Get started with Vertex AI Hyperparameter Tuning pipeline components](community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Vertex AI Hyperparameter Tuning`.
 
@@ -125,7 +125,7 @@ The steps performed include:
       - Upload the model artifacts to a `Vertex AI Model` resource.
 - Execute a Vertex AI pipeline.
 
-[Get started with machine management for Vertex AI Pipelines](get_started_with_machine_management.ipynb)
+[Get started with machine management for Vertex AI Pipelines](community/ml_ops/stage3/get_started_with_machine_management.ipynb)
 
 In this tutorial, you convert a self-contained custom training component into a `Vertex AI CustomJob`, whereby:
 
@@ -139,7 +139,7 @@ The steps performed in this tutorial include:
 - Convert the self-contained training component into a `Vertex AI CustomJob`.
 - Execute pipeline using customjob-level settings for machine resources 
 
-[Get started with TFX pipelines](get_started_with_tfx_pipeline.ipynb)
+[Get started with TFX pipelines](community/ml_ops/stage3/get_started_with_tfx_pipeline.ipynb)
 
 In this tutorial, you learn how to use TensorFlow Extended (TFX) with `Vertex AI Pipelines`.
 
@@ -150,7 +150,7 @@ The steps performed include:
 - Execute the pipeline on Google Cloud using `Vertex AI Training`
 - Execute the pipeline using `Vertex AI Pipelines`.
 
-[Get started with BigQuery ML pipeline components](get_started_with_bqml_pipeline_components.ipynb)
+[Get started with BigQuery ML pipeline components](community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `BigQuery ML`.
 
@@ -165,7 +165,7 @@ The steps performed include:
 - Execute a Vertex AI pipeline.
 - Make a prediction with the deployed Vertex AI model.
 
-[Get started with AutoML tabular pipeline workflows](get_started_with_automl_tabular_pipeline_workflow.ipynb)
+[Get started with AutoML tabular pipeline workflows](community/ml_ops/stage3/get_started_with_automl_tabular_pipeline_workflow.ipynb)
 
 In this tutorial, you learn how to use `AutoML Tabular Pipeline Template` for training, exporting and tuning an AutoML tabular model.
 
@@ -183,7 +183,7 @@ The steps performed include:
 - Deploy exported OSS TF model.
 - Make a prediction.
 
-[Get started with rapid prototyping with AutoML and BigQuery ML](cget_started_with_rapid_prototyping_bqml_automl.ipynb)
+[Get started with rapid prototyping with AutoML and BigQuery ML](community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb)
 
 In this tutorial, you learn how to use `Vertex AI Predictions` for rapid prototyping a model.
 
@@ -196,7 +196,7 @@ The steps performed include:
 - Deploying the best trained model.
 - Testing the deployed model infrastructure.
 
-[Get started with AutoML pipeline components](get_started_with_automl_pipeline_components.ipynb)
+[Get started with AutoML pipeline components](community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Vertex AI AutoML`.
 
@@ -209,7 +209,7 @@ The steps performed include:
 - Execute a Vertex AI pipeline.
 
 
-[Get started with BigQuery and TFDV pipeline components](get_started_with_bq_tfdv_pipeline_components.ipynb)
+[Get started with BigQuery and TFDV pipeline components](community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb)
 
 In this tutorial, you learn how to use build lightweight Python components for BigQuery and TensorFlow Data Validation.
 

notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb

@@ -72,7 +72,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataproc Serverless` service. The documentation for the components can be found [here](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.26/google_cloud_pipeline_components.v1.dataproc.html).\n",
+        "In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataproc Serverless` service. The documentation for the components can be found [here](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html).\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -759,14 +759,14 @@
         "\n",
         "In this example, the `DataprocPySparkBatchOp` component takes the following parameters:\n",
         "\n",
+        "- `batch_id`: The batch ID to use for the Dataproc Batch workload.\n",
         "- `project_id`: The project ID.\n",
         "- `location`: The region.\n",
         "- `main_python_file_uri`: The URI of the main Python file.\n",
         "- `service_account`: The service account that runs the workload.\n",
         "- `args`: The arguments to pass to the PySpark program.\n",
-        "- `batch_id`: (Optional) The batch ID to use for the Dataproc Batch workload.\n",
         "\n",
-        "Learn more about the [Dataproc Serverless PySpark batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.26/google_cloud_pipeline_components.v1.dataproc.html#google_cloud_pipeline_components.v1.dataproc.DataprocPySparkBatchOp)."
+        "Learn more about the [Dataproc Serverless PySpark batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html#google_cloud_pipeline_components.experimental.dataproc.DataprocPySparkBatchOp)."
       ]
     },
     {
@@ -799,16 +799,16 @@
         "    service_account: str = SERVICE_ACCOUNT,\n",
         "    args: list = ARGS,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.v1.dataproc import \\\n",
+        "    from google_cloud_pipeline_components.experimental.dataproc import \\\n",
         "        DataprocPySparkBatchOp\n",
         "\n",
         "    _ = DataprocPySparkBatchOp(\n",
         "        project=project_id,\n",
         "        location=location,\n",
+        "        batch_id=batch_id,\n",
         "        main_python_file_uri=main_python_file_uri,\n",
         "        service_account=service_account,\n",
         "        args=args,\n",
-        "        batch_id=batch_id,  # `batch_id` is optional\n",
         "    )\n",
         "\n",
         "\n",
@@ -979,15 +979,15 @@
         "\n",
         "In this example, the `DataprocSparkBatchOp` component takes the following parameters:\n",
         "\n",
+        "- `batch_id`: The batch ID to use for the Dataproc Batch workload.\n",
         "- `project_id`: The project ID.\n",
         "- `location`: The region.\n",
         "- `main_class`: The main class.\n",
         "- `jar_file_uris`: The URIs of any required JARs to include in the executor and driver CLASSPATH.\n",
         "- `service_account`: The service account that runs the workload.\n",
         "- `args`: The arguments to pass to the Spark program.\n",
-        "- `batch_id`: (Optional) The batch ID to use for the Dataproc Batch workload.\n",
         "\n",
-        "Learn more about the [Dataproc Serverless Spark batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.26/google_cloud_pipeline_components.v1.dataproc.html#google_cloud_pipeline_components.v1.dataproc.DataprocSparkBatchOp)."
+        "Learn more about the [Dataproc Serverless Spark batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html#google_cloud_pipeline_components.experimental.dataproc.DataprocSparkBatchOp)."
       ]
     },
     {
@@ -1019,17 +1019,17 @@
         "    service_account: str = SERVICE_ACCOUNT,\n",
         "    args: list = ARGS,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.v1.dataproc import \\\n",
+        "    from google_cloud_pipeline_components.experimental.dataproc import \\\n",
         "        DataprocSparkBatchOp\n",
         "\n",
         "    _ = DataprocSparkBatchOp(\n",
         "        project=project_id,\n",
         "        location=location,\n",
+        "        batch_id=batch_id,\n",
         "        main_class=main_class,\n",
         "        jar_file_uris=jar_file_uris,\n",
         "        service_account=service_account,\n",
         "        args=args,\n",
-        "        batch_id=batch_id,  # `batch_id` is optional\n",
         "    )\n",
         "\n",
         "\n",
@@ -1281,14 +1281,14 @@
         "\n",
         "In this example, the `DataprocSparkSqlBatchOp` component takes the following parameters:\n",
         "\n",
+        "- `batch_id`: The batch ID to use for the Dataproc Batch workload.\n",
         "- `project_id`: The project ID.\n",
         "- `location`: The region.\n",
         "- `query_file_uri`: The URI of the file containing the SQL queries.\n",
         "- `query_variables`: The mapping of query variable names to values (equivalent to the Spark SQL command  `SET name=\"value\";`).\n",
         "- `service_account`: The service account that runs the workload.\n",
-        "- `batch_id`: (Optional) The batch ID to use for the Dataproc Batch workload.\n",
         "\n",
-        "Learn more about the [Dataproc Serverless Spark SQL batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.26/google_cloud_pipeline_components.v1.dataproc.html#google_cloud_pipeline_components.v1.dataproc.DataprocSparkSqlBatchOp)."
+        "Learn more about the [Dataproc Serverless Spark SQL batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html#google_cloud_pipeline_components.experimental.dataproc.DataprocSparkSqlBatchOp)."
       ]
     },
     {
@@ -1326,16 +1326,16 @@
         "    query_variables: dict = QUERY_VARIABLES,\n",
         "    service_account: str = SERVICE_ACCOUNT,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.v1.dataproc import \\\n",
+        "    from google_cloud_pipeline_components.experimental.dataproc import \\\n",
         "        DataprocSparkSqlBatchOp\n",
         "\n",
         "    _ = DataprocSparkSqlBatchOp(\n",
         "        project=project_id,\n",
         "        location=location,\n",
+        "        batch_id=batch_id,\n",
         "        query_file_uri=query_file_uri,\n",
         "        query_variables=query_variables,\n",
         "        service_account=service_account,\n",
-        "        batch_id=batch_id,  # `batch_id` is optional\n",
         "    )\n",
         "\n",
         "\n",
@@ -1502,14 +1502,14 @@
         "\n",
         "In this example, the `DataprocSparkRBatchOp` component takes the following parameters:\n",
         "\n",
+        "- `batch_id`: The batch ID to use for the Dataproc Batch workload.\n",
         "- `project_id`: The project ID.\n",
         "- `location`: The region.\n",
         "- `main_r_file_uri`: The URI of the main R file.\n",
         "- `service_account`: The service account that runs the workload.\n",
         "- `args`: The arguments to pass to the Spark program.\n",
-        "- `batch_id`: (Optional) The batch ID to use for the Dataproc Batch workload.\n",
         "\n",
-        "Learn more about the [Dataproc Serverless SparkR batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.26/google_cloud_pipeline_components.v1.dataproc.html#google_cloud_pipeline_components.v1.dataproc.DataprocSparkRBatchOp)."
+        "Learn more about the [Dataproc Serverless SparkR batch component](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html#google_cloud_pipeline_components.experimental.dataproc.DataprocSparkRBatchOp)."
       ]
     },
     {
@@ -1539,15 +1539,15 @@
         "    service_account: str = SERVICE_ACCOUNT,\n",
         "    args: list = ARGS,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.v1.dataproc import \\\n",
+        "    from google_cloud_pipeline_components.experimental.dataproc import \\\n",
         "        DataprocSparkRBatchOp\n",
         "\n",
         "    _ = DataprocSparkRBatchOp(\n",
         "        project=project_id,\n",
         "        location=location,\n",
+        "        batch_id=batch_id,\n",
         "        main_r_file_uri=main_r_file_uri,\n",
         "        args=args,\n",
-        "        batch_id=batch_id,  # `batch_id` is optional\n",
         "    )\n",
         "\n",
         "\n",

notebooks/community/model_monitoring/batch_prediction_model_monitoring.ipynb

@@ -35,17 +35,17 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/batch_prediction_model_monitoring.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_monitoring/batch_prediction_model_monitoring.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Open in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/batch_prediction_model_monitoring.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_monitoring/batch_prediction_model_monitoring.ipynb\">\n",
         "        <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td><td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai-platform/notebooks/deploy-notebook?name=Model%20Monitoring&download_url=https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fofficial%2Fmodel_monitoring%2Fbatch_prediction_model_monitoring.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/ai-platform/notebooks/deploy-notebook?name=Model%20Monitoring&download_url=https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2Fmodel_monitoring%2Fbatch_prediction_model_monitoring.ipynb\">\n",
         "       <img src=\"https://www.gstatic.com/cloud/images/navigation/vertex-ai.svg\" alt=\"Google Cloud Notebooks\">Open in Workbench AI Notebook\n",
         "    </a>\n",
         "  </td> \n",
@@ -173,11 +173,9 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install Python package dependencies.\n",
-        "! pip3 install -q {USER_FLAG} google-cloud-aiplatform \\\n",
-        "                              tensorflow-data-validation \\\n",
-        "                              protobuf==3.20.3\n",
-        "\n",
-        "! pip3 install -q {USER_FLAG} cachetools==5.2.0"
+        "! pip3 install -q {USER_FLAG} tensorflow-data-validation \\\n",
+        "                              google-api-core \\\n",
+        "                              google-cloud-aiplatform"
       ]
     },
     {
@@ -885,8 +883,6 @@
       },
       "outputs": [],
       "source": [
-        "import time\n",
-        "\n",
         "# If auto-testing, wait for request completion\n",
         "if os.getenv(\"IS_TESTING\"):\n",
         "    time.sleep(1800)"

notebooks/notebook_template.ipynb

@@ -31,8 +31,6 @@
       "source": [
         "# [TODO] Add your H1 title heading here\n",
         "\n",
-        "{TODO: Update the links below.} \n",
-        "\n",
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
@@ -55,17 +53,6 @@
         "</table>"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "24743cf4a1e1"
-      },
-      "source": [
-        "**_NOTE_**: This notebook has been tested in the following environment:\n",
-        "\n",
-        "* Python version = 3.9"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -124,7 +111,7 @@
         "This tutorial uses billable components of Google Cloud:\n",
         "\n",
         "* Vertex AI\n",
-        "* {TODO: BigQuery}\n",
+        "* {TODO: BigQyuery}\n",
         "* Cloud Storage\n",
         "\n",
         "{TODO: Include links to pricing documentation for each product you listed above.\n",
@@ -138,6 +125,62 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gCuSR8GkAgzl"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "24743cf4a1e1"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gCuSR8GkAgzl"
+      },
+      "source": [
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -159,32 +202,51 @@
       },
       "outputs": [],
       "source": [
-        "# Install the packages\n",
-        "! pip3 install --user --upgrade google-cloud-aiplatform"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "# TODO: Add remaining package installs here. All packages should be on a single pip install to resolve dependencies"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "58707a750154"
+        "id": "hhq5zEbGg0XX"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
+        "### Restart the kernel\n",
+        "\n",
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "f200f10a1da3"
+        "id": "EzrelQZ22IZj"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "# Automatically restart kernel after installs\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -201,11 +263,16 @@
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "3. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). {TODO: Update the APIs needed for your tutorial. Edit the API names, and update the link to append the API IDs, separating each one with a comma. For example, container.googleapis.com,cloudbuild.googleapis.com}\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). {TODO: Update the APIs needed for your tutorial. Edit the API names, and update the link to append the API IDs, separating each one with a comma. For example, container.googleapis.com,cloudbuild.googleapis.com}\n",
         "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk)."
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
@@ -216,10 +283,7 @@
       "source": [
         "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
@@ -230,10 +294,57 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "riG_qUokg0XZ"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_gcloud_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "23988890fef6"
+      },
+      "source": [
+        "#### Get your project number {TODO: Include these cells if the notebook uses a project number}\n",
         "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "Now that the project ID is set, you get your corresponding project number."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2d6950574e1d"
+      },
+      "outputs": [],
+      "source": [
+        "shell_output = ! gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
+        "PROJECT_NUMBER = shell_output[0]\n",
+        "print(\"Project Number:\", PROJECT_NUMBER)"
       ]
     },
     {
@@ -244,18 +355,63 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "id": "region"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "06571eb4063b"
+      },
+      "source": [
+        "#### UUID\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial.\n",
+        "\n",
+        "{TODO: replace the `TIMESTAMP` with `UUID` in official notebooks}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "697568e92bd6"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -266,68 +422,64 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "74ccc9e52986"
-      },
-      "source": [
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "de775a3773ba"
-      },
-      "source": [
-        "**2. Local JupyterLab instance, uncomment and run:**"
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. \n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": null,
       "metadata": {
-        "id": "254614fa0c46"
+        "id": "PyQmSRbKA8r-"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ef21552ccea8"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {
-        "id": "603adbbf0532"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f6b2ccc891ed"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
       ]
     },
     {
@@ -338,9 +490,20 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets.\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "- *{Note to notebook author: For any user-provided strings that need to be unique (like bucket names or model ID's), append \"-unique\" to the end so proper testing can occur}*"
+        "\n",
+        "{TODO: Adjust wording in the first paragraph to fit your use case - explain how your tutorial uses the Cloud Storage bucket. The example below shows how Vertex AI uses the bucket for training.}\n",
+        "\n",
+        "When you submit a training job using the Vertex AI SDK, you upload a Python package\n",
+        "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
+        "the code from this package. In this tutorial, Vertex AI also saves the\n",
+        "trained model that results from your job in the same bucket. Using this model artifact, you can then\n",
+        "create Vertex AI model and endpoint resources in order to serve\n",
+        "online predictions.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Cloud Storage buckets."
       ]
     },
     {
@@ -351,7 +514,21 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cf221059d072"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -377,7 +554,99 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "960505627ddf"
+        "id": "ucvCsknMCims"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vhOb7YnwClBb"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account {TODO: Include these cells if the notebook specifies a service account}\n",
+        "\n",
+        "{TODO: What uses service account in the notebook; e.g., You use a service account to create Vertex AI Pipeline jobs.}. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    else:  # IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access for {TODO; e.g., Vertex AI Pipelines}\n",
+        "\n",
+        "Run the following commands to grant your service account access to {TODO; i.e., read and write pipeline artifacts} in the bucket that you created in the previous step. You only need to run this step once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XoEqT2Y4DJmf"
       },
       "source": [
         "### Import libraries"
@@ -387,11 +656,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "PyQmSRbKA8r-"
+        "id": "pRUOFELefqf1"
       },
       "outputs": [],
       "source": [
-        "from google.cloud import aiplatform"
+        "import google.cloud.aiplatform as aiplatform\n",
+        "\n",
+        "# TODO: import remaining libraries; e.g., tensorflow"
       ]
     },
     {
@@ -402,7 +673,7 @@
       "source": [
         "### Initialize Vertex AI SDK for Python\n",
         "\n",
-        "Initialize the Vertex AI SDK for Python for your project."
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -434,21 +705,21 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "id": "sx_vKniMq9ZX"
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
         "# Delete endpoint resource\n",
-        "# e.g. `endpoint.delete()`\n",
+        "! gcloud ai endpoints delete $ENDPOINT_NAME --quiet --region $REGION\n",
         "\n",
         "# Delete model resource\n",
-        "# e.g. `model.delete()`\n",
+        "! gcloud ai models delete $MODEL_NAME --quiet\n",
         "\n",
         "# Delete Cloud Storage objects that were created\n",
+        "! gsutil -m rm -r $JOB_DIR\n",
+        "\n",
         "delete_bucket = False\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil -m rm -r $BUCKET_URI"

notebooks/official/CODEOWNERS

@@ -38,7 +38,3 @@
 /model_evaluation/automl_tabular_regression_model_evaluation.ipynb @soheilazangeneh
 /tabular_workflows/tabnet_on_vertex_pipelines.ipynb @sakagarwal
 /tabular_workflows/wide_and_deep_on_vertex_pipelines.ipynb @sakagarwal
-/model_evaluation/custom_tabular_classification_model_evaluation.ipynb @soheilazangeneh
-/sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
-/automl/sdk_automl_forecasting_hierarchical_batch.ipynb @ivanmkc
-/prediction/custom_batch_prediction_feature_filter.ipynb @soheilazangeneh

notebooks/official/automl/automl-text-classification.ipynb

@@ -2,7 +2,7 @@
   "cells": [
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 54,
       "metadata": {
         "id": "ur8xi4C7S06n"
       },
@@ -128,29 +128,100 @@
         "to generate a cost estimate based on your projected usage"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "lWEdiXsJg0XY"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "**Note:** This notebook does not require a GPU runtime."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a5cb73702a9b"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Workbench AI Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gCuSR8GkAgzl"
+      },
+      "source": [
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "db52a0a61fca"
       },
       "source": [
-        "### Installation\n",
+        "### Install additional packages\n",
         "\n",
         "Install the following packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 55,
       "metadata": {
         "id": "b75757581291"
       },
       "outputs": [],
       "source": [
-        "# install packages\n",
-        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
-        "                                    google-cloud-storage \\\n",
-        "                                    jsonlines "
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform google-cloud-storage jsonlines -q"
       ]
     },
     {
@@ -159,22 +230,27 @@
         "id": "e9255e3b156f"
       },
       "source": [
-        "### Colab Only: Uncomment the following cell to restart the kernel"
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 56,
       "metadata": {
         "id": "0c0b2427998a"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -183,27 +259,62 @@
         "id": "435b8e413535"
       },
       "source": [
-        "### Before you begin\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
         "\n",
         "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "-  Run `gcloud config list`\n",
-        "-  Run `gcloud projects list`\n",
-        "-  See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "be175254a715"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "be175254a715"
+        "id": "db65832f7c1b"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ea86e5a1da1d"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# set the project id\n",
         "! gcloud config set project $PROJECT_ID"
       ]
     },
@@ -215,19 +326,54 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. \n",
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
         "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 4,
       "metadata": {
         "id": "ae43d96c4b1b"
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5f4f5cccf897"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "953fa6e5ddda"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
     {
@@ -238,54 +384,56 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**1. Vertex AI Workbench** \n",
-        "- Do nothing as you are already authenticated.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
-        "**2. Local JupyterLab Instance,** uncomment and run."
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "fbc9cd30cc4b"
+        "id": "oM1iC_MfAts1"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd0da2c26879"
-      },
-      "source": [
-        "**3. Colab,** uncomment and run:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a336a05c6149"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0461097edfa5"
-      },
-      "source": [
-        "**4. Service Account or other**\n",
-        "- See all the authentication options here: [Google Cloud Platform Jupyter Notebook Authentication Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_authentication_guide.ipynb)"
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -296,21 +444,38 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets."
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 6,
       "metadata": {
         "id": "d2de92accb67"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"your-bucket-name-unique\"  # @param {type:\"string\"}\n",
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {
+        "id": "5ba09496accc"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -331,6 +496,26 @@
         "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c4cf2cdebb50"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {
+        "id": "96ad3d416327"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -342,15 +527,14 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 10,
       "metadata": {
         "id": "152013538e59"
       },
       "outputs": [],
       "source": [
         "import jsonlines\n",
-        "from google.cloud import aiplatform, storage\n",
-        "from google.cloud.aiplatform import jobs"
+        "from google.cloud import aiplatform, storage"
       ]
     },
     {
@@ -366,7 +550,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 11,
       "metadata": {
         "id": "740cd5c67c79"
       },
@@ -387,7 +571,7 @@
         "\n",
         "Using the Python SDK, you create a dataset and import the dataset in one call to `TextDataset.create()`, as shown in the following cell.\n",
         "\n",
-        "Creating and importing data is a long-running operation. This next step can take a while. The `create()` method waits for the operation to complete, outputting statements as the operation progresses. The statements contain the full name of the dataset that you use in the following section.\n",
+        "Creating and importing data is a long-running operation. This next step can take a while. The `create()` method waits for the operation to complete, outputting statements as the operation progresses. The statements contain the full name of the dataset that you will use in the following section.\n",
         "\n",
         "**Note**: You can close the noteboook while you wait for this operation to complete. "
       ]
@@ -402,7 +586,7 @@
       "source": [
         "# Use a timestamp to ensure unique resources\n",
         "src_uris = \"gs://cloud-ml-data/NL-classification/happiness.csv\"\n",
-        "display_name = \"e2e-text-dataset-unique\"\n",
+        "display_name = f\"e2e-text-dataset-{TIMESTAMP}\"\n",
         "\n",
         "text_dataset = aiplatform.TextDataset.create(\n",
         "    display_name=display_name,\n",
@@ -412,14 +596,21 @@
         ")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5b3cc427353a"
+      },
+      "source": [
+        "## Train your text classification model\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "68f10356cab9"
       },
       "source": [
-        "## Train your text classification model\n",
-        "\n",
         "Now you can begin training your model. Training the model is a two part process:\n",
         "\n",
         "1. **Define the training job.** You must provide a display name and the type of training you want when you define the training job.\n",
@@ -436,14 +627,14 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 16,
       "metadata": {
         "id": "0aa0f01805ea"
       },
       "outputs": [],
       "source": [
         "# Define the training job\n",
-        "training_job_display_name = \"e2e-text-training-job-unique\"\n",
+        "training_job_display_name = f\"e2e-text-training-job-{TIMESTAMP}\"\n",
         "job = aiplatform.AutoMLTextTrainingJob(\n",
         "    display_name=training_job_display_name,\n",
         "    prediction_type=\"classification\",\n",
@@ -459,7 +650,7 @@
       },
       "outputs": [],
       "source": [
-        "model_display_name = \"e2e-text-classification-model-unique\"\n",
+        "model_display_name = f\"e2e-text-classification-model-{TIMESTAMP}\"\n",
         "\n",
         "# Run the training job\n",
         "model = job.run(\n",
@@ -520,7 +711,7 @@
       },
       "outputs": [],
       "source": [
-        "deployed_model_display_name = \"e2e-deployed-text-classification-model-unique\"\n",
+        "deployed_model_display_name = f\"e2e-deployed-text-classification-model-{TIMESTAMP}\"\n",
         "\n",
         "endpoint = model.deploy(\n",
         "    deployed_model_display_name=deployed_model_display_name, sync=True\n",
@@ -582,7 +773,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 23,
       "metadata": {
         "id": "e4b838cbcd99"
       },
@@ -621,7 +812,7 @@
         "# Instantiate the Storage client and create the new bucket\n",
         "# from google.cloud import  storage\n",
         "storage_client = storage.Client()\n",
-        "bucket = storage_client.get_bucket(BUCKET_NAME)\n",
+        "bucket = storage_client.bucket(BUCKET_NAME)\n",
         "# Iterate over the prediction instances, creating a new TXT file\n",
         "# for each.\n",
         "input_file_data = []\n",
@@ -688,7 +879,7 @@
         "id": "cd014de40e2f"
       },
       "source": [
-        "## Batch prediction job"
+        "## BatchPredictionJob"
       ]
     },
     {
@@ -699,6 +890,8 @@
       },
       "outputs": [],
       "source": [
+        "from google.cloud.aiplatform import jobs\n",
+        "\n",
         "batch_job = jobs.BatchPredictionJob(batch_prediction_job_name)\n",
         "print(f\"Batch prediction job state: {str(batch_job.state)}\")"
       ]
@@ -779,7 +972,7 @@
         "id": "e375109b7e40"
       },
       "source": [
-        "## Review results"
+        "## JsonLines"
       ]
     },
     {
@@ -855,22 +1048,16 @@
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI\n",
         "\n",
-        "# Delete batch\n",
         "batch_job.delete()\n",
-        "\n",
-        "# Undeploy endpoint\n",
         "endpoint.undeploy_all()\n",
-        "\n",
         "# `force` parameter ensures that models are undeployed before deletion\n",
         "endpoint.delete()\n",
         "\n",
-        "# Delete model\n",
         "model.delete()\n",
         "\n",
-        "# Delete text dataset\n",
         "text_dataset.delete()\n",
         "\n",
-        "# Delete training job\n",
+        "# Training job\n",
         "job.delete()"
       ]
     },
@@ -880,7 +1067,7 @@
         "id": "fa6a8c434c79"
       },
       "source": [
-        "## Next steps\n",
+        "## Next Steps\n",
         "\n",
         "After completing this tutorial, see the following documentation pages to learn more about Vertex AI:\n",
         "\n",

notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb

@@ -640,7 +640,9 @@
         "prediction_type = \"classification\"\n",
         "optimization_objective = \"minimize-log-loss\"\n",
         "target_column = \"deposit\"\n",
-        "data_source_csv_filenames = \"gs://cloud-samples-data/vertex-ai/tabular-workflows/datasets/bank-marketing/train.csv\"\n",
+        "data_source_csv_filenames = (\n",
+        "    \"gs://cloud-samples-data/vertex-ai/tabular-workflows/datasets/bank-marketing/train.csv\"\n",
+        ")\n",
         "data_source_bigquery_table_path = None  # format: bq://bq_project.bq_dataset.bq_table\n",
         "\n",
         "timestamp_split_key = None  # timestamp column name when using timestamp split\n",

notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# Copyright 2021 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -45,8 +45,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb\" target='_blank'>      \n",
-        "    <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>                    \n",
@@ -66,17 +66,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK to create image object detection models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:salads,iod"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -85,7 +74,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML image object detection model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "In this tutorial, you learn how to create an AutoML image object detection model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -101,6 +90,17 @@
         "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:salads,iod"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -121,6 +121,39 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_local"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
+        "\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -129,7 +162,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Cloud Storage, Bigquery and Vertex AI SDKs for Python."
+        "Install the latest version of Vertex AI SDK for Python."
       ]
     },
     {
@@ -140,10 +173,44 @@
       },
       "outputs": [],
       "source": [
-        "# Install the packages.\n",
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                         google-cloud-storage     \\\n",
-        "                         tensorflow -q"
+        "import os\n",
+        "\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d6Pa6Sybv5mK"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U --upgrade tensorflow google-cloud-storage $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9_zWlX10v5mL"
+      },
+      "source": [
+        "Install the latest version of *tensorflow* library."
       ]
     },
     {
@@ -152,7 +219,9 @@
         "id": "restart"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel"
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -163,20 +232,14 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "013daf3de88e"
-      },
-      "source": [
-        "## Before you begin"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -185,12 +248,28 @@
         "id": "before_you_begin:nogpu"
       },
       "source": [
-        "### Set your project ID\n",
+        "## Before you begin\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -201,10 +280,56 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "import os\n",
         "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "PROJECT_ID = \"\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "# Get your Google Cloud project ID from gcloud\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "W2F5WRyhv5mO"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d7-MjQafv5mO"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_gcloud_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
@@ -215,7 +340,16 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
       ]
     },
     {
@@ -226,7 +360,41 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "timestamp"
+      },
+      "source": [
+        "#### UUID\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PzKW-zT_v5mR"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -237,68 +405,53 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
-      "cell_type": "markdown",
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "id": "FvQeFm3Gv5mR"
       },
-      "source": [
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ad1138a125ea"
-      },
-      "source": [
-        "**2. Local JupyterLab instance, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ce6043da7b33"
-      },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0367eac06a10"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "21ad4dbb4a61"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c13224697bfb"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -309,7 +462,11 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets."
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
@@ -320,7 +477,20 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -340,7 +510,27 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "N9JY-esPv5mU"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -349,7 +539,10 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Import libraries"
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
       ]
     },
     {
@@ -382,7 +575,7 @@
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI, location=REGION)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME, location=REGION)"
       ]
     },
     {
@@ -471,9 +664,8 @@
       },
       "outputs": [],
       "source": [
-        "DISPLAY_NAME = \"salads_unique\"\n",
         "dataset = aiplatform.ImageDataset.create(\n",
-        "    display_name=DISPLAY_NAME,\n",
+        "    display_name=\"Salads\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
         ")\n",
@@ -521,7 +713,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLImageTrainingJob(\n",
-        "    display_name=DISPLAY_NAME,\n",
+        "    display_name=\"salads_\" + UUID,\n",
         "    prediction_type=\"object_detection\",\n",
         "    multi_label=False,\n",
         "    model_type=\"CLOUD\",\n",
@@ -564,7 +756,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=DISPLAY_NAME,\n",
+        "    model_display_name=\"salads_\" + UUID,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -594,8 +786,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "filter_name = f\"display_name={DISPLAY_NAME}\"\n",
-        "models = aiplatform.Model.list(filter=filter_name)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=salads_\" + UUID)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -714,7 +905,6 @@
       "outputs": [],
       "source": [
         "import json\n",
-        "import os\n",
         "\n",
         "import tensorflow as tf\n",
         "\n",
@@ -767,7 +957,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=DISPLAY_NAME,\n",
+        "    job_display_name=\"salads_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    machine_type=\"n1-standard-4\",\n",

notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb

@@ -44,7 +44,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -74,14 +74,6 @@
         "\n",
         "In this tutorial, you learn how to create an AutoML tabular regression model and deploy it for batch prediction using the Vertex AI SDK for Python. You can alternatively create and deploy models using the `gcloud` command-line tool or batch using the Cloud Console.\n",
         "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "\n",
-        "- Vertex AI Datasets (Tabular)\n",
-        "- Vertex AI Training (AutoML Tabular Training)\n",
-        "- Vertex AI Model Registry\n",
-        "- Vertex AI Endpoint\n",
-        "- Vertex AI Batch predictions\n",
-        "\n",
         "The steps performed include:\n",
         "\n",
         "- Create a Vertex AI `Dataset` resource.\n",
@@ -115,11 +107,45 @@
         "\n",
         "* Vertex AI\n",
         "* Cloud Storage\n",
-        "* BigQuery / BigQuery ML\n",
         "\n",
         "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage\n",
-        "pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_local"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Vertex AI Workbench, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
+        "\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
       ]
     },
     {
@@ -130,22 +156,66 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the following packages required to execute this notebook."
+        "Install the latest version of the Vertex AI SDK for Python."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "870f1b093d9c"
+        "id": "install_aip:mbsdk"
       },
       "outputs": [],
       "source": [
-        "# Install the packages\n",
-        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
-        "                                    'google-cloud-bigquery[bqstorage,pandas]' \\\n",
-        "                                    google-cloud-storage \n",
-        "                                    "
+        "import os\n",
+        "\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest version of *google-cloud-storage*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b2f8bf1a1c31"
+      },
+      "source": [
+        "Install the latest version of *google-cloud-bigquery*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fb18bb35a386"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U \"google-cloud-bigquery[pandas]\" $USER_FLAG"
       ]
     },
     {
@@ -154,7 +224,9 @@
         "id": "restart"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
+        "### Restart the kernel\n",
+        "\n",
+        "After installing the packages, restart the notebook kernel."
       ]
     },
     {
@@ -165,11 +237,14 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -179,12 +254,27 @@
       },
       "source": [
         "## Before you begin\n",
-        "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -195,10 +285,33 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_gcloud_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
@@ -209,7 +322,15 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable, which is used for operations throughout the rest of this notebook. The following regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -223,6 +344,30 @@
         "REGION = \"[your-region]\"  # @param {type: \"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "timestamp"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "timestamp"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -231,53 +376,53 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated.\n",
-        "**2. Local JupyterLab instance, uncomment and run:**\n"
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "457c78b08293"
+        "id": "gcp_authenticate"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d3e571ce6c56"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "984a0526fb68"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2c549a59cca4"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        ! gcloud auth login"
       ]
     },
     {
@@ -300,8 +445,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aiplatform\n",
-        "from google.cloud import bigquery"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -378,6 +522,8 @@
       },
       "outputs": [],
       "source": [
+        "from google.cloud import bigquery\n",
+        "\n",
         "# Create client in default region\n",
         "bq_client = bigquery.Client(\n",
         "    project=PROJECT_ID,\n",
@@ -394,13 +540,13 @@
       "outputs": [],
       "source": [
         "# Create training dataset in default region\n",
-        "TRAINING_INPUT_DATASET_ID = \"gsod_training_unique\"\n",
+        "TRAINING_INPUT_DATASET_ID = f\"gsod_training_{TIMESTAMP}\"\n",
         "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{TRAINING_INPUT_DATASET_ID}\")\n",
         "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
         "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")\n",
         "\n",
         "# Create test dataset in default region\n",
-        "PREDICTION_INPUT_DATASET_ID = \"gsod_prediction_unique\"\n",
+        "PREDICTION_INPUT_DATASET_ID = f\"gsod_prediction_{TIMESTAMP}\"\n",
         "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{PREDICTION_INPUT_DATASET_ID}\")\n",
         "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
         "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")"
@@ -479,7 +625,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"NOAA historical weather data_unique\",\n",
+        "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
         "    bq_source=[f\"bq://{TRAINING_INPUT_TABLE_ID}\"],\n",
         ")\n",
         "\n",
@@ -550,7 +696,7 @@
       "outputs": [],
       "source": [
         "training_job = aiplatform.AutoMLTabularTrainingJob(\n",
-        "    display_name=\"job_unique\",\n",
+        "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    optimization_prediction_type=\"regression\",\n",
         "    optimization_objective=\"minimize-rmse\",\n",
         "    column_specs=COLUMN_SPECS,\n",
@@ -580,7 +726,7 @@
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline will take upto 3 hours."
+        "The execution of the training pipeline will take upto 20 minutes."
       ]
     },
     {
@@ -593,7 +739,7 @@
       "source": [
         "model = training_job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"model_unique\",\n",
+        "    model_display_name=\"gsod_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.6,\n",
         "    validation_fraction_split=0.2,\n",
         "    test_fraction_split=0.2,\n",
@@ -659,7 +805,7 @@
       "outputs": [],
       "source": [
         "# Create results dataset in default region\n",
-        "RESULTS_DATASET_ID = \"gsod_results_unique\"\n",
+        "RESULTS_DATASET_ID = f\"gsod_results_{TIMESTAMP}\"\n",
         "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{RESULTS_DATASET_ID}\")\n",
         "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
         "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")"
@@ -683,9 +829,7 @@
         "- `machine_type`: The type of machine to use for training.\n",
         "- `accelerator_type`: The hardware accelerator type.\n",
         "- `accelerator_count`: The number of accelerators to attach to a worker replica.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete.\n",
-        "\n",
-        "Batch prediction job takes roughly 1 hour to finish."
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
       ]
     },
     {
@@ -778,8 +922,17 @@
         "\n",
         "bq_client.delete_dataset(\n",
         "    f\"{PROJECT_ID}.{RESULTS_DATASET_ID}\", delete_contents=True, not_found_ok=True\n",
-        ")\n",
-        "\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
         "# Delete Vertex AI resources\n",
         "dataset.delete()\n",
         "model.delete()\n",

notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb

@@ -33,13 +33,13 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "<a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb\" target='_blank'>      \n",
-        "    <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_regression_online_bq.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
@@ -116,6 +116,39 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_local"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
+        "\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -135,8 +168,35 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                            google-cloud-storage"
+        "import os\n",
+        "\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library as well."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -145,7 +205,9 @@
         "id": "restart"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel"
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -156,11 +218,14 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -177,11 +242,20 @@
         "\n",
         "### Set up your Google Cloud project\n",
         "\n",
-        "**If you dont know your project ID,** try the following\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "- Run `gcloud config list`\n",
-        "- Run `gcloud projects list`\n",
-        "- See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)\n"
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -192,10 +266,33 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# Set the project ID\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_gcloud_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
@@ -206,7 +303,16 @@
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI Regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
       ]
     },
     {
@@ -220,6 +326,30 @@
         "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "timestamp"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "timestamp"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -228,64 +358,53 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**1. Vertex AI workbench** \n",
-        "- Do nothing as you are already authenticated.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
-        "**2. Local JupyterLab Instance, uncomment and run:**"
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "457c78b08293"
+        "id": "gcp_authenticate"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d3e571ce6c56"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "984a0526fb68"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "764c0ac706e1"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "- See all the authentication options here: [Google Cloud Platform Jupyter Notebook Authentication Guide](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_authentication_guide.ipynb)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "276cfd2c6167"
-      },
-      "source": [
-        "### Create a Cloud Storage bucket\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets"
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -296,7 +415,20 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://test-bucket-unique\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -319,12 +451,35 @@
         "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "setup_vars"
       },
       "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -336,11 +491,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "import google.cloud.aiplatform as aiplatform\n",
-        "\n",
-        "display_name = \"gsod_unique\""
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -423,7 +574,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"NOAA historical weather data_unique\",\n",
+        "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
         ")\n",
         "\n",
@@ -494,7 +645,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLTabularTrainingJob(\n",
-        "    display_name=display_name,\n",
+        "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    optimization_prediction_type=\"regression\",\n",
         "    optimization_objective=\"minimize-rmse\",\n",
         "    column_transformations=TRANSFORMATIONS,\n",
@@ -537,7 +688,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=display_name,\n",
+        "    model_display_name=\"gsod_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.6,\n",
         "    validation_fraction_split=0.2,\n",
         "    test_fraction_split=0.2,\n",
@@ -554,22 +705,33 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model training has finished, you can review the evaluation scores for it using the list_model_evaluations() method."
+        "After your model has finished training, you can review the evaluation scores for it.\n",
+        "\n",
+        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "4f674dcea72c"
+        "id": "evaluate_the_model:mbsdk"
       },
       "outputs": [],
       "source": [
-        "model_evaluations = model.list_model_evaluations()\n",
-        "if len(model_evaluations) > 0:\n",
-        "    eval_res = model_evaluations[0].to_dict()\n",
-        "    evaluation_metrics = eval_res[\"metrics\"]\n",
-        "print(evaluation_metrics)"
+        "# Get model resource ID\n",
+        "models = aiplatform.Model.list(filter=\"display_name=gsod_\" + TIMESTAMP)\n",
+        "\n",
+        "# Get a reference to the Model Service client\n",
+        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
+        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
+        "    client_options=client_options\n",
+        ")\n",
+        "\n",
+        "model_evaluations = model_service_client.list_model_evaluations(\n",
+        "    parent=models[0].resource_name\n",
+        ")\n",
+        "model_evaluation = list(model_evaluations)[0]\n",
+        "print(model_evaluation)"
       ]
     },
     {
@@ -719,22 +881,23 @@
       },
       "outputs": [],
       "source": [
-        "# Delete the dataset using the Vertex dataset object\n",
-        "dataset.delete()\n",
+        "delete_all = True\n",
         "\n",
-        "# Delete the model using the Vertex model object\n",
-        "model.delete()\n",
+        "if delete_all:\n",
+        "    # Delete the dataset using the Vertex dataset object\n",
+        "    dataset.delete()\n",
         "\n",
-        "# Delete the endpoint using the Vertex endpoint object\n",
-        "endpoint.delete()\n",
+        "    # Delete the model using the Vertex model object\n",
+        "    model.delete()\n",
         "\n",
-        "# Delete the AutoML trainig job\n",
-        "job.delete()\n",
+        "    # Delete the endpoint using the Vertex endpoint object\n",
+        "    endpoint.delete()\n",
         "\n",
-        "delete_bucket = False\n",
+        "    # Delete the AutoML trainig job\n",
+        "    job.delete()\n",
         "\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -r $BUCKET_URI"
+        "    if os.getenv(\"IS_TESTING\"):\n",
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb

@@ -44,8 +44,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb\" target='_blank'>     \n",
-        "    <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_text_entity_extraction_online.ipynb\">\n",
+        "     <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",

notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb

@@ -29,7 +29,7 @@
         "id": "title"
       },
       "source": [
-        "# Vertex AI SDK: Training an AutoML text sentiment analysis model for online predictions\n",
+        "# Vertex SDK: AutoML training text sentiment analysis model for online prediction\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -44,8 +44,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb\" target='_blank'>\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_text_sentiment_analysis_online.ipynb\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
@@ -61,7 +60,8 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy an [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) text sentiment analysis model and get online predictions from it."
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create text sentiment analysis models and do online prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
@@ -72,23 +72,16 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to create an AutoML text sentiment analysis model and deploy it for online predictions from a Python script using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "- Vertex AI Datasets\n",
-        "- Vertex AI Training (AutoML)\n",
-        "- Vertex AI Model Registry\n",
-        "- Vertex AI Endpoints\n",
+        "In this tutorial, you learn how to create an AutoML text sentiment analysis model and deploy for online prediction from a Python script using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Vertex AI Dataset` resource.\n",
-        "- Create a training job for the AutoML model on the dataset.\n",
-        "- View the model evaluation metrics.\n",
-        "- Deploy the `Vertex AI Model` resource to a serving `Vertex AI Endpoint`.\n",
-        "- Make a prediction request to the deployed model.\n",
-        "- Undeploy the model from endpoint.\n",
-        "- Perform clean up process."
+        "- Create a Vertex `Dataset` resource.\n",
+        "- Create a training job for the model.\n",
+        "- View the model evaluation.\n",
+        "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
+        "- Make a prediction.\n",
+        "- Undeploy the `Model`."
       ]
     },
     {
@@ -99,7 +92,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Crowdflower Claritin-Twitter dataset](https://data.world/crowdflower/claritin-twitter) that consists of tweets tagged with sentiment, the author's gender, and whether or not they mention any of the top 10 adverse events reported to the FDA. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket. In this tutorial, you use the tweets data to build an AutoML text sentiment analysis model on Google Cloud platform."
+        "The dataset used for this tutorial is the [Crowdflower Claritin-Twitter dataset](https://data.world/crowdflower/claritin-twitter) that consists of tweets tagged with sentiment, the author's gender, and whether or not they mention any of the top 10 adverse events reported to the FDA. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. In this tutorial, you will use the tweets' data to build an AutoML-text-sentiment-analysis model on Google Cloud platform."
       ]
     },
     {
@@ -130,34 +123,29 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
         "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
-        "* The Google Cloud SDK\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
         "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
         "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
         "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
         "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
       ]
     },
     {
@@ -168,7 +156,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the latest version of Vertex SDK for Python."
       ]
     },
     {
@@ -181,19 +169,35 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install -U google-cloud-storage $USER_FLAG -q"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library as well.\n",
+        "\n",
+        "**Note**: You may encounter a PIP dependency error during the installation of the Google Cloud Storage package. This can be ignored as it will not affect the proper running of this script."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -204,7 +208,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages. The following cell will restart the kernel."
       ]
     },
     {
@@ -215,7 +219,6 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -234,33 +237,26 @@
       "source": [
         "## Before you begin\n",
         "\n",
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "1. [Enable the Vertex AI, Compute Engine, and Cloud Storage APIs.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "af794e75b7e3"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -340,9 +336,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### UUID\n",
+        "#### Timestamp\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -353,16 +349,9 @@
       },
       "outputs": [],
       "source": [
-        "import random\n",
-        "import string\n",
+        "from datetime import datetime\n",
         "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
     {
@@ -373,31 +362,23 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
         "\n",
-        "2. Click **Create service account**.\n",
+        "**Click Create service account**.\n",
         "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
         "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
         "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
@@ -416,11 +397,8 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -430,7 +408,7 @@
         "    # path to your service account key and run this cell to authenticate your GCP\n",
         "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -443,9 +421,9 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you initialize your Vertex AI SDK, you provide a Cloud Storage bucket to the SDK to serve as a staging bucket for the session. \n",
+        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets."
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
@@ -456,8 +434,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -468,9 +445,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -490,7 +466,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_NAME"
       ]
     },
     {
@@ -510,7 +486,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil ls -al $BUCKET_NAME"
       ]
     },
     {
@@ -519,7 +495,10 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Import libraries"
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "### Import libraries and define constants"
       ]
     },
     {
@@ -539,9 +518,9 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "### Initialize Vertex AI SDK for Python\n",
+        "## Initialize Vertex SDK for Python\n",
         "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+        "Initialize the Vertex SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -552,7 +531,18 @@
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML text sentiment analysis model."
       ]
     },
     {
@@ -561,9 +551,9 @@
         "id": "import_file:u_dataset,csv"
       },
       "source": [
-        "### Define the constants\n",
+        "#### Location of Cloud Storage training data.\n",
         "\n",
-        "Set the constants that you use in this tutorial."
+        "Now set the variable `IMPORT_FILE` to the location of the CSV index file in Cloud Storage."
       ]
     },
     {
@@ -574,9 +564,7 @@
       },
       "outputs": [],
       "source": [
-        "# Set the location of the CSV index file in Cloud Storage.\n",
         "IMPORT_FILE = \"gs://cloud-samples-data/language/claritin.csv\"\n",
-        "# Set the max. sentiment score\n",
         "SENTIMENT_MAX = 4"
       ]
     },
@@ -586,11 +574,11 @@
         "id": "quick_peek:csv"
       },
       "source": [
-        "## Take a quick peek at your data\n",
+        "#### Quick peek at your data\n",
         "\n",
-        "This tutorial uses a version of the `Crowdflower Claritin-Twitter` dataset which is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "This tutorial uses a version of the Crowdflower Claritin-Twitter dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
         "\n",
-        "Start by taking a quick peek at the data. Further, count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then print the first few rows."
+        "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows."
       ]
     },
     {
@@ -616,12 +604,12 @@
         "id": "create_dataset:text,tst"
       },
       "source": [
-        "## Create the Dataset\n",
+        "### Create the Dataset\n",
         "\n",
-        "Now, create a `Vertex AI Dataset` resource using the `create` method of the `TextDataset` class, which takes the following parameters:\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
         "\n",
-        "- `display_name`: The human readable name for the dataset resource.\n",
-        "- `gcs_source`: A list of one or more dataset index files to import the data items into the dataset resource.\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
         "- `import_schema_uri`: The data labeling schema for the data items.\n",
         "\n",
         "This operation may take several minutes."
@@ -636,7 +624,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TextDataset.create(\n",
-        "    display_name=\"Crowdflower Claritin-Twitter\" + \"_\" + UUID,\n",
+        "    display_name=\"Crowdflower Claritin-Twitter\" + \"_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.sentiment,\n",
         ")\n",
@@ -650,18 +638,15 @@
         "id": "create_automl_pipeline:text,tst"
       },
       "source": [
-        "## Create and run training job\n",
+        "### Create and run training pipeline\n",
         "\n",
-        "In this section, to train an AutoML model, you perform these steps:\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
         "\n",
-        "1) create a training job.\n",
-        "2) run the job.\n",
+        "#### Create training pipeline\n",
         "\n",
-        "### Create a training job\n",
+        "An AutoML training pipeline is created with the `AutoMLTextTrainingJob` class, with the following parameters:\n",
         "\n",
-        "An AutoML training job is created with the `AutoMLTextTrainingJob` class, with the following parameters:\n",
-        "\n",
-        "- `display_name`: The human readable name for the training job resource.\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
         "- `prediction_type`: The type task to train the model for.\n",
         "  - `classification`: A text classification model.\n",
         "  - `sentiment`: A text sentiment analysis model.\n",
@@ -679,7 +664,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLTextTrainingJob(\n",
-        "    display_name=\"claritin_\" + UUID,\n",
+        "    display_name=\"claritin_\" + TIMESTAMP,\n",
         "    prediction_type=\"sentiment\",\n",
         "    sentiment_max=SENTIMENT_MAX,\n",
         ")\n",
@@ -693,7 +678,7 @@
         "id": "run_automl_pipeline:text"
       },
       "source": [
-        "### Run the training job\n",
+        "#### Run the training pipeline\n",
         "\n",
         "Next, you run the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
@@ -705,7 +690,7 @@
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline take upto 180 minutes."
+        "The execution of the training pipeline will take upto 180 minutes."
       ]
     },
     {
@@ -718,7 +703,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"claritin_\" + UUID,\n",
+        "    model_display_name=\"claritin_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -732,10 +717,9 @@
       },
       "source": [
         "## Review model evaluation scores\n",
+        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "Once your model training has finished, you can review the evaluation scores.\n",
-        "\n",
-        "Firstly, you need to get a reference to the newly created model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project and filter."
+        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
       ]
     },
     {
@@ -747,7 +731,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=claritin_\" + UUID)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=claritin_\" + TIMESTAMP)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -770,9 +754,7 @@
       "source": [
         "## Deploy the model\n",
         "\n",
-        "Next, deploy your model to serve online predictions. To deploy the model, you invoke the `deploy` method of the model resource which in turn returns you the deployed endpoint.\n",
-        "\n",
-        "**Note:** Normally, an endpoint is created beforehand and is given as a reference while model deployment. By default, `deploy()` method creates an endpoint when an endpoint reference is not given."
+        "Next, deploy your model for online prediction. To deploy the model, you invoke the `deploy` method."
       ]
     },
     {
@@ -792,9 +774,9 @@
         "id": "make_prediction"
       },
       "source": [
-        "## Send online prediction requests\n",
+        "## Send a online prediction request\n",
         "\n",
-        "In this step, you prepare some test instances from the dataset and send an online prediction request to your deployed model."
+        "Send a online prediction to your deployed model."
       ]
     },
     {
@@ -803,9 +785,9 @@
         "id": "get_test_item"
       },
       "source": [
-        "### Create test instances\n",
+        "### Get test item\n",
         "\n",
-        "You use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model. It is just to demonstrate how to make a prediction."
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -831,21 +813,21 @@
         "id": "predict_request:mbsdk,tst"
       },
       "source": [
-        "### Make the prediction request\n",
+        "### Make the prediction\n",
         "\n",
-        "Now that your model is deployed to an endpoint, you can send online prediction requests to the endpoint resource.\n",
+        "Now that your `Model` resource is deployed to an `Endpoint` resource, you can do online predictions by sending prediction requests to the `Endpoint` resource.\n",
         "\n",
-        "#### Request format\n",
+        "#### Request\n",
         "\n",
-        "The format of each instance should be in JSON as below:\n",
+        "The format of each instance is:\n",
         "\n",
         "     { 'content': text_string }\n",
         "\n",
-        "Since the `predict()` method can take multiple instances, send your request as a list of one test instance.\n",
+        "Since the predict() method can take multiple items (instances), send your single test item as a list of one test item.\n",
         "\n",
         "#### Response\n",
         "\n",
-        "The response from the `predict()` call is a Python dictionary with the following entries:\n",
+        "The response from the predict() call is a Python dictionary with the following entries:\n",
         "\n",
         "- `ids`: The internal assigned unique identifiers for each prediction request.\n",
         "- `sentiment`: The sentiment value.\n",
@@ -874,7 +856,7 @@
       "source": [
         "## Undeploy the model\n",
         "\n",
-        "After you explore the predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
+        "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
       ]
     },
     {
@@ -901,11 +883,11 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Vertex AI Dataset\n",
-        "- Vertex AI Model\n",
-        "- Vertex AI Endpoint\n",
+        "- Dataset\n",
+        "- Model\n",
+        "- Endpoint\n",
         "- AutoML Training Job\n",
-        "- Cloud Storage Bucket (set `delete_bucket` to **True** to delete the bucket)"
+        "- Cloud Storage Bucket"
       ]
     },
     {
@@ -916,8 +898,6 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = False\n",
-        "\n",
         "# Delete the dataset using the Vertex dataset object\n",
         "dataset.delete()\n",
         "\n",
@@ -931,8 +911,8 @@
         "job.delete()\n",
         "\n",
         "# Delete the Cloud storage bucket\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -r $BUCKET_URI"
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_NAME"
       ]
     }
   ],

notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb

@@ -29,10 +29,9 @@
         "id": "title"
       },
       "source": [
-        "# Vertex AI SDK: AutoML training video action recognition model for batch prediction\n",
+        "# Vertex SDK: AutoML training video action recognition model for batch prediction\n",
         "\n",
         "<table align=\"left\">\n",
-        "\n",
         "  <td>\n",
         "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
@@ -45,11 +44,10 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb\" target='_blank'>\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_action_recognition_batch.ipynb\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
-        "  </td>                                                                                               \n",
+        "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -76,16 +74,9 @@
         "\n",
         "In this tutorial, you learn how to create an AutoML video action recognition model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
         "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "\n",
-        "- Vertex AI Dataset\n",
-        "- Vertex AI Model\n",
-        "- Vertex AI Batch Prediction\n",
-        "\n",
-        "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Vertex AI Dataset` resource.\n",
+        "- Create a Vertex `Dataset` resource.\n",
         "- Train the model.\n",
         "- View the model evaluation.\n",
         "- Make a batch prediction.\n",
@@ -105,7 +96,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset from MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket. The trained model will predict the start frame where an action of golf swing begins."
+        "The dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset from MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model will predict the start frame where an action of golf swing begins."
       ]
     },
     {
@@ -136,38 +127,29 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook.\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
         "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
         "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
         "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
         "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
         "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
       ]
     },
     {
@@ -178,7 +160,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the following packages required to execute this notebook. \n"
+        "Install the latest version of Vertex SDK for Python."
       ]
     },
     {
@@ -191,17 +173,35 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform google-cloud-storage"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library as well.\n",
+        "\n",
+        "**Note**: You may encounter a PIP dependency error during the installation of the Google Cloud Storage package. This can be ignored as it will not affect the proper running of this script."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -212,7 +212,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages. The following cell will restart the kernel."
       ]
     },
     {
@@ -223,7 +223,6 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -242,33 +241,26 @@
       "source": [
         "## Before you begin\n",
         "\n",
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -317,7 +309,7 @@
         "#### Region\n",
         "\n",
         "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
         "\n",
         "- Americas: `us-central1`\n",
         "- Europe: `europe-west4`\n",
@@ -325,7 +317,7 @@
         "\n",
         "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
         "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
       ]
     },
     {
@@ -348,9 +340,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### UUID\n",
+        "#### Timestamp\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial.\n"
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -361,16 +353,9 @@
       },
       "outputs": [],
       "source": [
-        "import random\n",
-        "import string\n",
+        "from datetime import datetime\n",
         "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
     {
@@ -381,31 +366,23 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
         "\n",
-        "2. Click **Create service account**.\n",
+        "**Click Create service account**.\n",
         "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
         "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
         "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
@@ -424,11 +401,8 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -451,9 +425,9 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you run a Vertex AI pipeline job using the Cloud SDK, your job stores the pipeline artifacts to a Cloud Storage bucket. In this tutorial, you create a Vertex AI Pipeline job that saves the artifacts like evaluation metrics and feature attributes to a Cloud Storage bucket.\n",
+        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets."
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
@@ -464,8 +438,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -476,9 +449,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -498,7 +470,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_NAME"
       ]
     },
     {
@@ -518,7 +490,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil ls -al $BUCKET_NAME"
       ]
     },
     {
@@ -527,6 +499,9 @@
         "id": "setup_vars"
       },
       "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -538,11 +513,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "import os\n",
-        "\n",
-        "import google.cloud.aiplatform as aiplatform\n",
-        "from google.cloud import storage"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -551,9 +522,9 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "## Initialize Vertex AI SDK for Python\n",
+        "## Initialize Vertex SDK for Python\n",
         "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+        "Initialize the Vertex SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -564,7 +535,7 @@
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
       ]
     },
     {
@@ -575,8 +546,15 @@
       "source": [
         "# Tutorial\n",
         "\n",
-        "Now you are ready to start creating your own AutoML video action recognition model.\n",
-        "\n",
+        "Now you are ready to start creating your own AutoML video action recognition model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,csv"
+      },
+      "source": [
         "#### Location of Cloud Storage training data.\n",
         "\n",
         "Now set the variable `IMPORT_FILES` to the location of the CSV index files in Cloud Storage."
@@ -651,7 +629,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"Golf Swings\" + \"_\" + UUID,\n",
+        "    display_name=\"Golf Swings\" + \"_\" + TIMESTAMP,\n",
         "    gcs_source=IMPORT_FILES,\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.action_recognition,\n",
         ")\n",
@@ -667,19 +645,17 @@
       "source": [
         "### Create and run training pipeline\n",
         "\n",
-        "To train an AutoML model, you perform two steps: \n",
-        "1. create a training pipeline.\n",
-        "2. run the pipeline.\n",
+        "To train an AutoML model, you perform two steps: 1) create a training pipeline, and 2) run the pipeline.\n",
         "\n",
-        "#### Create the training pipeline\n",
+        "#### Create training pipeline\n",
         "\n",
         "An AutoML training pipeline is created with the `AutoMLVideoTrainingJob` class, with the following parameters:\n",
         "\n",
         "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
         "- `prediction_type`: The type task to train the model for.\n",
-        "    - `classification`: A video classification model.\n",
-        "    - `object_tracking`: A video object tracking model.\n",
-        "    - `action_recognition`: A video action recognition model."
+        "  - `classification`: A video classification model.\n",
+        "  - `object_tracking`: A video object tracking model.\n",
+        "  - `action_recognition`: A video action recognition model."
       ]
     },
     {
@@ -691,7 +667,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"golf_\" + UUID,\n",
+        "    display_name=\"golf_\" + TIMESTAMP,\n",
         "    prediction_type=\"action_recognition\",\n",
         ")\n",
         "\n",
@@ -728,7 +704,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"golf_\" + UUID,\n",
+        "    model_display_name=\"golf_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -741,7 +717,9 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n"
+        "After your model has finished training, you can review the evaluation scores for it.\n",
+        "\n",
+        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
       ]
     },
     {
@@ -752,9 +730,18 @@
       },
       "outputs": [],
       "source": [
-        "# Get evaluations\n",
-        "model_evaluations = model.list_model_evaluations()\n",
+        "# Get model resource ID\n",
+        "models = aiplatform.Model.list(filter=\"display_name=golf_\" + TIMESTAMP)\n",
         "\n",
+        "# Get a reference to the Model Service client\n",
+        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
+        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
+        "    client_options=client_options\n",
+        ")\n",
+        "\n",
+        "model_evaluations = model_service_client.list_model_evaluations(\n",
+        "    parent=models[0].resource_name\n",
+        ")\n",
         "model_evaluation = list(model_evaluations)[0]\n",
         "print(model_evaluation)"
       ]
@@ -767,11 +754,18 @@
       "source": [
         "## Send a batch prediction request\n",
         "\n",
-        "Send a batch prediction request to your registered model.\n",
-        "\n",
+        "Send a batch prediction to your deployed model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_items:batch_prediction"
+      },
+      "source": [
         "### Get test item(s)\n",
         "\n",
-        "Now send a batch prediction request to your Vertex AI model. You use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model as we just want to demonstrate how to make a prediction."
+        "Now do a batch prediction to your Vertex model. You will use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model as we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -805,7 +799,7 @@
       "source": [
         "### Make a batch input file\n",
         "\n",
-        "Now make a batch input file, which you store in your local Cloud Storage bucket. The batch input file can be either CSV or JSONL. You use JSONL in this tutorial. For JSONL file, you make one dictionary entry per line for each video. The dictionary contains the key/value pairs:\n",
+        "Now make a batch input file, which you store in your local Cloud Storage bucket. The batch input file can be either CSV or JSONL. You will use JSONL in this tutorial. For JSONL file, you make one dictionary entry per line for each video. The dictionary contains the key/value pairs:\n",
         "\n",
         "- `content`: The Cloud Storage path to the video.\n",
         "- `mimeType`: The content type. In our example, it is a `avi` file.\n",
@@ -821,8 +815,12 @@
       },
       "outputs": [],
       "source": [
+        "import json\n",
+        "\n",
+        "from google.cloud import storage\n",
+        "\n",
         "test_filename = \"test.jsonl\"\n",
-        "gcs_input_uri = BUCKET_URI + \"/\" + test_filename\n",
+        "gcs_input_uri = BUCKET_NAME + \"/\" + test_filename\n",
         "\n",
         "# Configure the test-data\n",
         "data_1 = {\n",
@@ -839,7 +837,7 @@
         "}\n",
         "\n",
         "# Upload the test-data to Cloud storage bucket\n",
-        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_URI.replace(\"gs://\", \"\"))\n",
+        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_NAME.replace(\"gs://\", \"\"))\n",
         "blob = bucket.blob(blob_name=test_filename)\n",
         "data = json.dumps(data_1) + \"\\n\" + json.dumps(data_2) + \"\\n\"\n",
         "blob.upload_from_string(data)\n",
@@ -857,7 +855,7 @@
       "source": [
         "### Make the batch prediction request\n",
         "\n",
-        "Now that your Vertex AI Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
+        "Now that your Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
         "\n",
         "- `job_display_name`: The human readable name for the batch prediction job.\n",
         "- `gcs_source`: A list of one or more batch request input files.\n",
@@ -874,9 +872,9 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"golf_\" + UUID,\n",
+        "    job_display_name=\"golf_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    gcs_destination_prefix=BUCKET_NAME,\n",
         "    sync=False,\n",
         ")\n",
         "\n",
@@ -943,7 +941,7 @@
         "\n",
         "for prediction_result in prediction_results:\n",
         "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\".replace(\n",
-        "        BUCKET_URI + \"/\", \"\"\n",
+        "        BUCKET_NAME + \"/\", \"\"\n",
         "    )\n",
         "    data = bucket.get_blob(gfile_name).download_as_string()\n",
         "    data = json.loads(data)\n",
@@ -990,10 +988,9 @@
         "# Delete the batch prediction job using the Vertex batch prediction object\n",
         "batch_predict_job.delete()\n",
         "\n",
-        "# Delete Cloud Storage objects\n",
-        "delete_bucket = False\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil -m rm -r $BUCKET_URI"
+        "# Delete the Cloud Storage bucket\n",
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_NAME"
       ]
     }
   ],

notebooks/official/automl/sdk_automl_video_classification_batch.ipynb

@@ -44,8 +44,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_video_classification_batch.ipynb\" target='_blank'>            \n",
-        "    <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\"> \n",
+        "          <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_classification_batch.ipynb\">\n",
+        "            <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\"> \n",
         "Open in Vertex AI Workbench \n",
         "    </a>\n",
         "  </td>\n",

notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb

@@ -18,7 +18,7 @@
         "#\n",
         "# Unless required by applicable law or agreed to in writing, software\n",
         "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,  either express or implied.\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
         "# See the License for the specific language governing permissions and\n",
         "# limitations under the License."
       ]
@@ -44,7 +44,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_video_object_tracking_batch.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -73,11 +73,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to create an AutoML video object tracking model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "\n",
-        "- Vertex AI\n",
+        "In this tutorial, you learn how to create an AutoML video object tracking model from a Python script, and then do a batch prediction using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -101,7 +97,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Traffic](https://storage.googleapis.com/automl-video-demo-data/traffic_videos/traffic_videos_labels.csv) dataset. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
+        "The dataset used for this tutorial is the [Traffic](https://storage.googleapis.com/automl-video-demo-data/traffic_videos/traffic_videos_labels.csv) dataset. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {
@@ -132,11 +128,12 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
         "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
         "- The Cloud Storage SDK\n",
+        "- Git\n",
         "- Python 3\n",
         "- virtualenv\n",
         "- Jupyter notebook running in a virtual environment with Python 3\n",
@@ -164,7 +161,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the following packages required to execute this notebook."
+        "Install the latest version of Vertex SDK for Python."
       ]
     },
     {
@@ -177,19 +174,33 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    USER_FLAG = \"--user\"\n",
         "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform google-cloud-storage $USER_FLAG -q"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library as well."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -200,9 +211,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages.\n",
-        "\n",
-        "**Note: You may get a message saying \"Your session crashed for an unknown reason.\", this is expected. Once this cell has finished running, continue on. You do not need to re-run any of the cells above.**"
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -245,43 +254,30 @@
         "\n",
         "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
         "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "6. (optional) You may also specify a service account to use to run Vertex AI Pipelines in the project.\n",
-        "\n",
         "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "dcdfccf50581"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "PROJECT_ID = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "5bf9979b96ff"
+        "id": "autoset_project_id"
       },
       "outputs": [],
       "source": [
@@ -296,7 +292,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "09021c90b34c"
+        "id": "set_gcloud_project_id"
       },
       "outputs": [],
       "source": [
@@ -342,9 +338,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### UUID\n",
+        "#### Timestamp\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -355,16 +351,9 @@
       },
       "outputs": [],
       "source": [
-        "import random\n",
-        "import string\n",
+        "from datetime import datetime\n",
         "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
     {
@@ -375,23 +364,23 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated.\n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "- In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
         "\n",
-        "- **Click Create service account**.\n",
+        "**Click Create service account**.\n",
         "\n",
-        "- In the **Service account name** field, enter a name, and click **Create**.\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
         "\n",
-        "- In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "- Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
         "\n",
-        "- Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
@@ -410,11 +399,8 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -424,7 +410,7 @@
         "    # path to your service account key and run this cell to authenticate your GCP\n",
         "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -437,7 +423,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
@@ -446,31 +432,29 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "f78cf4290843"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_URI = \"\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "219a24ea078b"
+        "id": "autoset_bucket"
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "a8a62bec0259"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -480,7 +464,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "91c46850b49b"
+        "id": "create_bucket"
       },
       "outputs": [],
       "source": [
@@ -490,7 +474,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "4e69d430073b"
+        "id": "validate_bucket"
       },
       "source": [
         "Finally, validate access to your Cloud Storage bucket by examining its contents:"
@@ -500,7 +484,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "835eaacd691f"
+        "id": "validate_bucket"
       },
       "outputs": [],
       "source": [
@@ -513,6 +497,9 @@
         "id": "setup_vars"
       },
       "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -537,9 +524,9 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "## Initialize Vertex AI SDK for Python\n",
+        "## Initialize Vertex SDK for Python\n",
         "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+        "Initialize the Vertex SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -640,7 +627,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"Traffic\" + \"_\" + UUID,\n",
+        "    display_name=\"Traffic\" + \"_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.object_tracking,\n",
         ")\n",
@@ -678,7 +665,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"traffic_\" + UUID,\n",
+        "    display_name=\"traffic_\" + TIMESTAMP,\n",
         "    prediction_type=\"object_tracking\",\n",
         ")\n",
         "\n",
@@ -702,7 +689,7 @@
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline will take upto 4 hours."
+        "The execution of the training pipeline will take upto 5 hours."
       ]
     },
     {
@@ -715,7 +702,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"traffic_\" + UUID,\n",
+        "    model_display_name=\"traffic_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -741,28 +728,22 @@
       },
       "outputs": [],
       "source": [
-        "model_evaluations = model.list_model_evaluations()\n",
+        "# Get model resource ID\n",
+        "models = aiplatform.Model.list(filter=\"display_name=traffic_\" + TIMESTAMP)\n",
+        "\n",
+        "# Get a reference to the Model Service client\n",
+        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
+        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
+        "    client_options=client_options\n",
+        ")\n",
+        "\n",
+        "model_evaluations = model_service_client.list_model_evaluations(\n",
+        "    parent=models[0].resource_name\n",
+        ")\n",
         "model_evaluation = list(model_evaluations)[0]\n",
         "print(model_evaluation)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b3377983702b"
-      },
-      "outputs": [],
-      "source": [
-        "# Print the evaluation metrics\n",
-        "for evaluation in model_evaluations:\n",
-        "    evaluation = evaluation.to_dict()\n",
-        "    print(\"Model's evaluation metrics from Training:\\n\")\n",
-        "    metrics = evaluation[\"metrics\"]\n",
-        "    for metric in metrics.keys():\n",
-        "        print(f\"metric: {metric}, value: {metrics[metric]}\\n\")"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -893,7 +874,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"traffic_\" + UUID,\n",
+        "    job_display_name=\"traffic_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",
@@ -985,9 +966,13 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
+        "- Pipeline\n",
         "- Model\n",
+        "- Endpoint\n",
         "- AutoML Training Job\n",
         "- Batch Job\n",
+        "- Custom Job\n",
+        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1011,8 +996,7 @@
         "# Delete the batch prediction job using the Vertex batch prediction object\n",
         "batch_predict_job.delete()\n",
         "\n",
-        "delete_bucket = False\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "if os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }

notebooks/official/bigquery_ml/bqml-online-prediction.ipynb

@@ -282,17 +282,6 @@
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3c8049930470"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -301,11 +290,15 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "PROJECT_ID = \"[YOUR-PROJECT-ID]\"\n",
+        "\n",
+        "# Get your Google Cloud project ID from gcloud\n",
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
         "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
+        "    print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
@@ -325,7 +318,8 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {

notebooks/official/custom/sdk-custom-image-classification-batch.ipynb

@@ -123,6 +123,48 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a5cb73702a9b"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Workbench AI Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -142,194 +184,306 @@
       },
       "outputs": [],
       "source": [
-        "# Install the packages\n",
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                        google-cloud-storage \\\n",
-        "                        pillow  \\\n",
-        "                        numpy    "
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install {USER_FLAG} --upgrade pillow -q\n",
+        "! pip3 install {USER_FLAG} --upgrade numpy -q"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "d98bc9fdd80d"
+        "id": "restart"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed everything, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "0dbf29389c65"
+        "id": "bzPxhxS5lugp"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "013daf3de88e"
+        "id": "before_you_begin"
       },
       "source": [
-        "## Before you begin"
+        "## Before you begin\n",
+        "\n",
+        "### Select a GPU runtime\n",
+        "\n",
+        "**Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select \"Runtime --> Change runtime type > GPU\"**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "3. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8bc8a29f9001"
+        "id": "project_id"
       },
       "source": [
         "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "e61aaa036444"
+        "id": "autoset_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "USd_pUT0lugr"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "09021c90b34c"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "c4a624c8099d"
+        "id": "88dd74c4c84e"
       },
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "f83bd6013894"
+        "id": "5c615e53149f"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "08bfd1eb44ef"
+        "id": "timestamp"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c-pX32xalugs"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "af349043f23b"
-      },
-      "source": [
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ad1138a125ea"
-      },
-      "source": [
-        "**2. Local JupyterLab instance, uncomment and run:**"
+        "**If you are using Workbench AI Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "ce6043da7b33"
+        "id": "vF60K5v1lugs"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0367eac06a10"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "21ad4dbb4a61"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c13224697bfb"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ddbea904fbe5"
+        "id": "bucket:custom"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets."
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you submit a training job using the Cloud SDK, you upload a Python package\n",
+        "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
+        "the code from this package. In this tutorial, Vertex AI also saves the\n",
+        "trained model that results from your job in the same bucket. Using this model artifact, you can then create Vertex AI model resources.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Cloud Storage buckets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "751138cf3bd5"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "58cb4f5895f0"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -339,11 +493,31 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "5e1288505682"
+        "id": "Oz8J0vmSlugt"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oadE10x2lugu"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -364,6 +538,7 @@
       "outputs": [],
       "source": [
         "import os\n",
+        "import sys\n",
         "\n",
         "from google.cloud import aiplatform"
       ]
@@ -390,17 +565,54 @@
         "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "accelerators:training,prediction"
+      },
+      "source": [
+        "#### Set hardware accelerators\n",
+        "\n",
+        "You can set hardware accelerators for training and prediction.\n",
+        "\n",
+        "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
+        "\n",
+        "    (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "\n",
+        "\n",
+        "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
+        "\n",
+        "Learn more about [hardware accelerator support for your region](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\n",
+        "\n",
+        "*Note*: TF releases before 2.3 for GPU support will fail to load the custom model in this tutorial. It is a known issue and fixed in TF 2.3. This is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xd5PLXDTlugv"
+      },
+      "outputs": [],
+      "source": [
+        "TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "\n",
+        "DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "container:training,prediction"
       },
       "source": [
-        "### Set pre-built containers\n",
+        "#### Set pre-built containers\n",
         "\n",
-        "Vertex AI provides pre-built containers to run training and prediction.\n",
+        "Set the pre-built Docker container image for training and prediction.\n",
         "\n",
-        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers) and [Pre-built containers for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers)"
+        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/ai-platform-unified/docs/training/pre-built-containers).\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
       ]
     },
     {
@@ -411,11 +623,64 @@
       },
       "outputs": [],
       "source": [
-        "TRAIN_VERSION = \"tf-cpu.2-9\"\n",
-        "DEPLOY_VERSION = \"tf2-cpu.2-9\"\n",
+        "TRAIN_VERSION = \"tf-gpu.2-1\"\n",
+        "DEPLOY_VERSION = \"tf2-gpu.2-1\"\n",
         "\n",
-        "TRAIN_IMAGE = \"us-docker.pkg.dev/vertex-ai/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"us-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(DEPLOY_VERSION)"
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
+        "\n",
+        "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
+        "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "machine:training,prediction"
+      },
+      "source": [
+        "#### Set machine types\n",
+        "\n",
+        "Next, set the machine types to use for training and prediction.\n",
+        "\n",
+        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure your compute resources for training and prediction.\n",
+        " - `machine type`\n",
+        "     - `n1-standard`: 3.75GB of memory per vCPU\n",
+        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+        "\n",
+        "*Note: The following is not supported for training:*\n",
+        "\n",
+        " - `standard`: 2 vCPUs\n",
+        " - `highcpu`: 2, 4 and 8 vCPUs\n",
+        "\n",
+        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YAXwbqKKlugv"
+      },
+      "outputs": [],
+      "source": [
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "TRAIN_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Train machine type\", TRAIN_COMPUTE)\n",
+        "\n",
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Deploy machine type\", DEPLOY_COMPUTE)"
       ]
     },
     {
@@ -470,11 +735,13 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_unique\"\n",
+        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
         "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
-        "\n",
-        "TRAIN_STRATEGY = \"single\"\n",
+        "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
+        "    TRAIN_STRATEGY = \"single\"\n",
+        "else:\n",
+        "    TRAIN_STRATEGY = \"mirror\"\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -656,15 +923,26 @@
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
         ")\n",
         "\n",
-        "MODEL_DISPLAY_NAME = \"model_unique\"\n",
+        "MODEL_DISPLAY_NAME = \"cifar10-\" + TIMESTAMP\n",
         "\n",
         "# Start the training\n",
-        "\n",
-        "model = job.run(\n",
-        "    model_display_name=MODEL_DISPLAY_NAME,\n",
-        "    args=CMDARGS,\n",
-        "    replica_count=1,\n",
-        ")"
+        "if TRAIN_GPU:\n",
+        "    model = job.run(\n",
+        "        model_display_name=MODEL_DISPLAY_NAME,\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        accelerator_type=TRAIN_GPU.name,\n",
+        "        accelerator_count=TRAIN_NGPU,\n",
+        "    )\n",
+        "else:\n",
+        "    model = job.run(\n",
+        "        model_display_name=MODEL_DISPLAY_NAME,\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        accelerator_count=0,\n",
+        "    )"
       ]
     },
     {
@@ -833,7 +1111,7 @@
         "MAX_NODES = 1\n",
         "\n",
         "# The name of the job\n",
-        "BATCH_PREDICTION_JOB_NAME = \"cifar10_batch_prediction_unique\"\n",
+        "BATCH_PREDICTION_JOB_NAME = \"cifar10_batch-\" + TIMESTAMP\n",
         "\n",
         "# Folder in the bucket to write results to\n",
         "DESTINATION_FOLDER = \"batch_prediction_results\"\n",
@@ -849,9 +1127,11 @@
         "    gcs_source=BATCH_PREDICTION_GCS_SOURCE,\n",
         "    gcs_destination_prefix=BATCH_PREDICTION_GCS_DEST_PREFIX,\n",
         "    model_parameters=None,\n",
+        "    machine_type=DEPLOY_COMPUTE,\n",
+        "    accelerator_type=DEPLOY_GPU,\n",
+        "    accelerator_count=DEPLOY_NGPU,\n",
         "    starting_replica_count=MIN_NODES,\n",
         "    max_replica_count=MAX_NODES,\n",
-        "    machine_type=\"n1-standard-4\",\n",
         "    sync=True,\n",
         ")"
       ]

notebooks/official/custom/sdk-custom-image-classification-online.ipynb

@@ -142,176 +142,308 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install --upgrade --quiet google-cloud-aiplatform google-cloud-storage pillow numpy\n"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install {USER_FLAG} --upgrade pillow -q\n",
+        "! pip3 install {USER_FLAG} --upgrade numpy -q"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "d98bc9fdd80d"
+        "id": "restart"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed everything, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "0dbf29389c65"
+        "id": "bzPxhxS5lugp"
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "import os\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "eec0fc7a0963"
+        "id": "before_you_begin"
       },
       "source": [
         "## Before you begin\n",
         "\n",
+        "### Select a GPU runtime\n",
+        "\n",
+        "**Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select \"Runtime --> Change runtime type > GPU\"**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "3. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "project_id"
+      },
+      "source": [
         "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "e3ce64be5527"
+        "id": "autoset_project_id"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "USd_pUT0lugr"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "250cb8c648d5"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "7f2e7f78a864"
+        "id": "2aa333eca058"
       },
       "source": [
         "#### Region\n",
         "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "369a2258dd59"
+        "id": "d8b34ef9a3d0"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "6a94297012d5"
+        "id": "timestamp"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c-pX32xalugs"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\n",
+        "**If you are using Workbench AI Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
         "\n",
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "28e3c4539627"
-      },
-      "source": [
-        "**2. Local JupyterLab instance, uncomment and run:**\n"
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "fbc9cd30cc4b"
+        "id": "vF60K5v1lugs"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "79efab26ad02"
-      },
-      "source": [
-        "**3. Colab, uncomment and run:**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a336a05c6149"
-      },
-      "outputs": [],
-      "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e3c28b6b796b"
-      },
-      "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "70a42f1033a3"
+        "id": "bucket:custom"
       },
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets."
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you submit a training job using the Cloud SDK, you upload a Python package\n",
+        "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
+        "the code from this package. In this tutorial, Vertex AI also saves the\n",
+        "trained model that results from your job in the same bucket. Using this model artifact, you can then\n",
+        "create Vertex AI model and endpoint resources in order to serve\n",
+        "online predictions.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Cloud Storage buckets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "7c12c0866590"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0cb016da6de3"
+        "id": "create_bucket"
       },
       "source": [
         "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
@@ -321,11 +453,31 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "eddb0b63434c"
+        "id": "Oz8J0vmSlugt"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oadE10x2lugu"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -334,6 +486,10 @@
         "id": "setup_vars"
       },
       "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "\n",
         "### Import libraries and define constants"
       ]
     },
@@ -346,10 +502,9 @@
       "outputs": [],
       "source": [
         "import os\n",
+        "import sys\n",
         "\n",
-        "import numpy as np\n",
-        "from google.cloud import aiplatform\n",
-        "from PIL import Image"
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -374,17 +529,56 @@
         "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "accelerators:training,prediction"
+      },
+      "source": [
+        "#### Set hardware accelerators\n",
+        "\n",
+        "You can set hardware accelerators for both training and prediction.\n",
+        "\n",
+        "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Tesla K80 GPUs allocated to each VM, you would specify:\n",
+        "\n",
+        "    (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "\n",
+        "See the [locations where accelerators are available](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\n",
+        "\n",
+        "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
+        "\n",
+        "*Note*: TensorFlow releases earlier than 2.3 for GPU support fail to load the custom model in this tutorial. This issue is caused by static graph operations that are generated in the serving function. This is a known issue, which is fixed in TensorFlow 2.3. If you encounter this issue with your own custom models, use a container image for TensorFlow 2.3 or later with GPU support."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xd5PLXDTlugv"
+      },
+      "outputs": [],
+      "source": [
+        "TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "\n",
+        "DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "container:training,prediction"
       },
       "source": [
-        "### Set pre-built containers\n",
+        "#### Set pre-built containers\n",
         "\n",
-        "Vertex AI provides pre-built containers to run training and prediction.\n",
         "\n",
-        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers) and [Pre-built containers for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers)"
+        "Set the pre-built Docker container image for training and prediction.\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/ai-platform-unified/docs/training/pre-built-containers).\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
       ]
     },
     {
@@ -395,11 +589,75 @@
       },
       "outputs": [],
       "source": [
-        "TRAIN_VERSION = \"tf-cpu.2-9\"\n",
-        "DEPLOY_VERSION = \"tf2-cpu.2-9\"\n",
+        "TRAIN_VERSION = \"tf-gpu.2-1\"\n",
+        "DEPLOY_VERSION = \"tf2-gpu.2-1\"\n",
         "\n",
-        "TRAIN_IMAGE = \"us-docker.pkg.dev/vertex-ai/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"us-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(DEPLOY_VERSION)"
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
+        "\n",
+        "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
+        "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "machine:training,prediction"
+      },
+      "source": [
+        "#### Set machine types\n",
+        "\n",
+        "Next, set the machine types to use for training and prediction.\n",
+        "\n",
+        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure your compute resources for training and prediction.\n",
+        " - `machine type`\n",
+        "     - `n1-standard`: 3.75GB of memory per vCPU\n",
+        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+        "\n",
+        "*Note: The following is not supported for training:*\n",
+        "\n",
+        " - `standard`: 2 vCPUs\n",
+        " - `highcpu`: 2, 4 and 8 vCPUs\n",
+        "\n",
+        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YAXwbqKKlugv"
+      },
+      "outputs": [],
+      "source": [
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "TRAIN_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Train machine type\", TRAIN_COMPUTE)\n",
+        "\n",
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Deploy machine type\", DEPLOY_COMPUTE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:custom"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own custom-trained model with CIFAR10."
       ]
     },
     {
@@ -408,17 +666,21 @@
         "id": "train_custom_model"
       },
       "source": [
-        "# Tutorial\n",
-        "\n",
-        "Now you are ready to start creating your own custom-trained model with CIFAR10.\n",
         "## Train a model\n",
         "\n",
         "There are two ways you can train a custom model using a container image:\n",
         "\n",
         "- **Use a Google Cloud prebuilt container**. If you use a prebuilt container, you will additionally specify a Python package to install into the container image. This Python package contains your code for training a custom model.\n",
         "\n",
-        "- **Use your own custom container image**. If you use your own container, the container needs to contain your code for training a custom model.\n",
-        "\n",
+        "- **Use your own custom container image**. If you use your own container, the container needs to contain your code for training a custom model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "train_custom_job_args"
+      },
+      "source": [
         "### Define the command args for the training script\n",
         "\n",
         "Prepare the command-line arguments to pass to your training script.\n",
@@ -439,10 +701,13 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_unique\"\n",
+        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
         "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
-        "TRAIN_STRATEGY = \"single\"\n",
+        "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
+        "    TRAIN_STRATEGY = \"single\"\n",
+        "else:\n",
+        "    TRAIN_STRATEGY = \"mirror\"\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -620,18 +885,30 @@
         "    display_name=JOB_NAME,\n",
         "    script_path=\"task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
-        "    requirements=[\"tensorflow_datasets\"],\n",
+        "    requirements=[\"tensorflow_datasets==1.3.0\"],\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
         ")\n",
         "\n",
-        "MODEL_DISPLAY_NAME = \"cifar10_unique\"\n",
+        "MODEL_DISPLAY_NAME = \"cifar10-\" + TIMESTAMP\n",
         "\n",
         "# Start the training\n",
-        "model = job.run(\n",
-        "    model_display_name=MODEL_DISPLAY_NAME,\n",
-        "    args=CMDARGS,\n",
-        "    replica_count=1,\n",
-        ")"
+        "if TRAIN_GPU:\n",
+        "    model = job.run(\n",
+        "        model_display_name=MODEL_DISPLAY_NAME,\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        accelerator_type=TRAIN_GPU.name,\n",
+        "        accelerator_count=TRAIN_NGPU,\n",
+        "    )\n",
+        "else:\n",
+        "    model = job.run(\n",
+        "        model_display_name=MODEL_DISPLAY_NAME,\n",
+        "        args=CMDARGS,\n",
+        "        replica_count=1,\n",
+        "        machine_type=TRAIN_COMPUTE,\n",
+        "        accelerator_count=0,\n",
+        "    )"
       ]
     },
     {
@@ -685,20 +962,44 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_NAME = \"cifar10_deployed_unique\"\n",
+        "DEPLOYED_NAME = \"cifar10_deployed-\" + TIMESTAMP\n",
         "\n",
         "TRAFFIC_SPLIT = {\"0\": 100}\n",
         "\n",
         "MIN_NODES = 1\n",
         "MAX_NODES = 1\n",
         "\n",
+        "if DEPLOY_GPU:\n",
+        "    endpoint = model.deploy(\n",
+        "        deployed_model_display_name=DEPLOYED_NAME,\n",
+        "        traffic_split=TRAFFIC_SPLIT,\n",
+        "        machine_type=DEPLOY_COMPUTE,\n",
+        "        accelerator_type=DEPLOY_GPU.name,\n",
+        "        accelerator_count=DEPLOY_NGPU,\n",
+        "        min_replica_count=MIN_NODES,\n",
+        "        max_replica_count=MAX_NODES,\n",
+        "    )\n",
+        "else:\n",
+        "    endpoint = model.deploy(\n",
+        "        deployed_model_display_name=DEPLOYED_NAME,\n",
+        "        traffic_split=TRAFFIC_SPLIT,\n",
+        "        machine_type=DEPLOY_COMPUTE,\n",
+        "        accelerator_type=DEPLOY_COMPUTE.name,\n",
+        "        accelerator_count=0,\n",
+        "        min_replica_count=MIN_NODES,\n",
+        "        max_replica_count=MAX_NODES,\n",
+        "    )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Make an online prediction request\n",
         "\n",
-        "endpoint = model.deploy(\n",
-        "    deployed_model_display_name=DEPLOYED_NAME,\n",
-        "    traffic_split=TRAFFIC_SPLIT,\n",
-        "    min_replica_count=MIN_NODES,\n",
-        "    max_replica_count=MAX_NODES,\n",
-        ")"
+        "Send an online prediction request to your deployed model."
       ]
     },
     {
@@ -707,9 +1008,6 @@
         "id": "get_test_item:test"
       },
       "source": [
-        "## Make an online prediction request\n",
-        "\n",
-        "Send an online prediction request to your deployed model.\n",
         "### Get test data\n",
         "\n",
         "Download images from the CIFAR dataset and preprocess them.\n",
@@ -755,6 +1053,9 @@
       },
       "outputs": [],
       "source": [
+        "import numpy as np\n",
+        "from PIL import Image\n",
+        "\n",
         "# Load image data\n",
         "IMAGE_DIRECTORY = \"cifar_test_images\"\n",
         "\n",
@@ -865,6 +1166,10 @@
       },
       "outputs": [],
       "source": [
+        "delete_training_job = True\n",
+        "delete_model = True\n",
+        "delete_endpoint = True\n",
+        "\n",
         "# Warning: Setting this to true will delete everything in your bucket\n",
         "delete_bucket = False\n",
         "\n",

notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb

@@ -959,7 +959,6 @@
         "    script_path=\"custom/trainer/task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    requirements=[\"gcsfs==0.7.1\", \"tensorflow-datasets==4.4\"],\n",
-        "    location=REGION,\n",
         ")\n",
         "\n",
         "print(job)"

notebooks/official/feature_store/sdk-feature-store-pandas.ipynb

@@ -29,7 +29,7 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
-        "# Using Vertex AI Feature Store with Pandas Dataframe\n",
+        "# Using Vertex AI Feature Store with pandas DataFrame\n",
         "\n",
         "<table align=\"left\">\n",
         "    <td>\n",
@@ -73,17 +73,13 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this notebook, you learn how to use `Vertex AI Feature Store` with pandas Dataframe.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services and resources:\n",
-        "\n",
-        "- Vertex AI Feature Store\n",
+        "In this notebook, you learn how to use `Vertex AI Feature Store` with pandas DataFrame.\n",
         "\n",
         "The steps performed include:\n",
         "\n",
         "- Ingest Feature values from Pandas DataFrame into Feature Store's Entity types.\n",
-        "- Read Entity feature values from Online Feature Store into Pandas DataFrame.\n",
-        "- Batch serve feature values from your Feature Store into Pandas DataFrame.\n",
+        "- Read Entity Feature values from Online Feature Store into Pandas DataFrame.\n",
+        "- Batch serve Feature values from your Feature Store into Pandas DataFrame.\n",
         "\n",
         "You also learn how Vertex AI Feature Store can be useful in the below scenarios:\n",
         "\n",
@@ -99,7 +95,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "This tutorial is a part of the Feature Store tutorial notebooks. It uses a movie recommendation dataset as an example for demonstrating various functionalities of Feature Store. The original task is to train a model to predict if a user is going to watch a movie, and serve the model online."
+        "This tutorial uses a movie recommendation dataset as an example throughout all the notebooks including this one. The original task is to train a model to predict if a user is going to watch a movie and serve the model online."
       ]
     },
     {
@@ -150,15 +146,12 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
+        "# The Google Cloud Notebook product has specific requirements\n",
+        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "    \n",
         "! pip install -U {USER_FLAG} --upgrade google-cloud-aiplatform \\\n",
@@ -215,7 +208,7 @@
         "\n",
         "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
         "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
         "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
@@ -280,7 +273,7 @@
         "#### Region\n",
         "\n",
         "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
         "\n",
         "- Americas: `us-central1`\n",
         "- Europe: `europe-west4`\n",
@@ -288,7 +281,7 @@
         "\n",
         "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
         "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
       ]
     },
     {
@@ -311,29 +304,10 @@
         "id": "dr--iN2kAylZ"
       },
       "source": [
-        "#### UUID\n",
+        "### Authenticate your Google Cloud account\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4e166d927e36"
-      },
-      "outputs": [],
-      "source": [
-        "import random\n",
-        "import string\n",
-        "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
       ]
     },
     {
@@ -342,11 +316,6 @@
         "id": "sBCra4QMA2wR"
       },
       "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
-        "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -364,7 +333,7 @@
         "into the filter box, and select\n",
         "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "5. Click **Create**. A JSON file that contains your key downloads to your\n",
         "local environment.\n",
         "\n",
         "6. Enter the path to your service account key as the\n",
@@ -379,19 +348,19 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "import sys\n",
+        "\n",
         "# If you are running this notebook in Colab, run this cell and follow the\n",
         "# instructions to authenticate your GCP account. This provides access to your\n",
         "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
         "# requests.\n",
         "\n",
-        "import os\n",
-        "import sys\n",
+        "# The Google Cloud Notebook product has specific requirements\n",
+        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
+        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -401,7 +370,7 @@
         "    # path to your service account key and run this cell to authenticate your GCP\n",
         "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -410,7 +379,7 @@
         "id": "XoEqT2Y4DJmf"
       },
       "source": [
-        "### Import libraries"
+        "### Import libraries and define constants"
       ]
     },
     {
@@ -424,31 +393,18 @@
         "import datetime\n",
         "\n",
         "import pandas as pd\n",
-        "from avro.datafile import DataFileReader\n",
-        "from avro.io import DatumReader\n",
-        "from google.cloud import aiplatform"
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "138407556b22"
+        "id": "9UvxYyGUimKw"
       },
       "source": [
-        "### Initialize Vertex AI SDK for Python\n",
-        "\n",
-        "Initialize the Vertex AI SDK for Python for your project and region."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8d2077ffee78"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+        "## Create Feature Store Resources"
       ]
     },
     {
@@ -457,12 +413,11 @@
         "id": "buQBIv3ZL3A0"
       },
       "source": [
-        "## Create a Feature Store\n",
+        "### Create Feature Store\n",
         "\n",
-        "The method to create a Feature Store in Vertex AI returns a\n",
-        "[long-running operation](https://google.aip.dev/151) (LRO). An LRO starts an asynchronous job. LROs are returned for other API methods too, such as updating or deleting a featurestore. \n",
-        "\n",
-        "Running the code cell below creates a featurestore and prints the process' logs."
+        "The method to create a Feature Store returns a\n",
+        "[long-running operation](https://google.aip.dev/151) (LRO). An LRO starts an asynchronous job. LROs are returned for other API\n",
+        "methods too, such as updating or deleting a featurestore. Running the code cell creates a featurestore and prints the process logs."
       ]
     },
     {
@@ -473,9 +428,9 @@
       },
       "outputs": [],
       "source": [
-        "# Create featurestore\n",
         "movie_predictions_feature_store = aiplatform.Featurestore.create(\n",
-        "    featurestore_id=f\"movie_predictions_{UUID}\", online_store_fixed_node_count=1\n",
+        "    featurestore_id=\"movie_predictions\",\n",
+        "    online_store_fixed_node_count=1,\n",
         ")"
       ]
     },
@@ -485,7 +440,7 @@
         "id": "EpmJq75zXjmT"
       },
       "source": [
-        "## Create Entity types\n",
+        "### Create Entity Types\n",
         "\n",
         "Entity types can be created within the Featurestore class. Below, you create the `Users` entity type and `Movies` entity type. Process logs are printed in the output for each cell."
       ]
@@ -498,7 +453,6 @@
       },
       "outputs": [],
       "source": [
-        "# Create users entity type\n",
         "users_entity_type = movie_predictions_feature_store.create_entity_type(\n",
         "    entity_type_id=\"users\",\n",
         "    description=\"Users entity\",\n",
@@ -513,7 +467,6 @@
       },
       "outputs": [],
       "source": [
-        "# Create movies entity type\n",
         "movies_entity_type = movie_predictions_feature_store.create_entity_type(\n",
         "    entity_type_id=\"movies\",\n",
         "    description=\"Movies entity\",\n",
@@ -526,11 +479,8 @@
         "id": "FJW4q-0jO2Xf"
       },
       "source": [
-        "## Create Features\n",
-        "Features can be created within each entity type. Add defined features to the `Users` entity type and `Movies` entity type by using the following methods.\n",
-        "\n",
-        "### Add features using *create_feature* method\n",
-        "Provide the feature information like id, type and description to the `create_feature` method of entity type."
+        "### Create Features\n",
+        "Features can be created within each entity type. Add defining features to the `Users` entity type and `Movies` entity type by using the following methods."
       ]
     },
     {
@@ -541,21 +491,18 @@
       },
       "outputs": [],
       "source": [
-        "# Create age feature\n",
         "users_feature_age = users_entity_type.create_feature(\n",
         "    feature_id=\"age\",\n",
         "    value_type=\"INT64\",\n",
         "    description=\"User age\",\n",
         ")\n",
         "\n",
-        "# Create gender feature\n",
         "users_feature_gender = users_entity_type.create_feature(\n",
         "    feature_id=\"gender\",\n",
         "    value_type=\"STRING\",\n",
         "    description=\"User gender\",\n",
         ")\n",
         "\n",
-        "# Create liked_genres feature\n",
         "users_feature_liked_genres = users_entity_type.create_feature(\n",
         "    feature_id=\"liked_genres\",\n",
         "    value_type=\"STRING_ARRAY\",\n",
@@ -563,18 +510,6 @@
         ")"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ecb141839033"
-      },
-      "source": [
-        "### Add features using batch method\n",
-        "You can also create features using a config map in a dictionary format and the `batch_create_features` method. This way, you can add multiple features at once. \n",
-        "\n",
-        "Below, you define and create *title*, *genres* and *average_rating* features using the batch method."
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -596,8 +531,17 @@
         "        \"value_type\": \"DOUBLE\",\n",
         "        \"description\": \"The average rating for the movie, range is [1.0-5.0]\",\n",
         "    },\n",
-        "}\n",
-        "\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YhfOKJL_BvuM"
+      },
+      "outputs": [],
+      "source": [
         "movie_features = movies_entity_type.batch_create_features(\n",
         "    feature_configs=movies_feature_configs,\n",
         ")"
@@ -609,15 +553,18 @@
         "id": "K3n5XdK8Xjmw"
       },
       "source": [
-        "## Ingest Feature values into Entity types from dataframes\n",
+        "## Ingest Feature Values into Entity Type from a Pandas DataFrame\n",
         "\n",
-        "You need to ingest feature values into your entity type containing the features. It is so that you can later `read` (online) or `batch serve` (offline) the feature values from the entity type. \n",
-        "\n",
-        "In this step, you learn how to ingest feature values from a Pandas dataframe into an entity type. You can also import feature values from BigQuery or Google Cloud Storage.\n",
-        "\n",
-        "### Get data from source\n",
-        "\n",
-        "Define the public data sources for users and movies and copy them locally into *avro* files."
+        "You need to ingest feature values into your entity type containing the features, so you can later `read` (online) or `batch serve` (offline) the feature values from the entity type. In this step, you will learn how to ingest feature values from a Pandas DataFrame into an entity type. We can also import feature values from BigQuery or Google Cloud Storage.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BlqJ-QdTcs6W"
+      },
+      "source": [
+        "#### Get data from source files"
       ]
     },
     {
@@ -636,8 +583,17 @@
         ")\n",
         "\n",
         "USERS_AVRO_FN = \"users.avro\"\n",
-        "MOVIES_AVRO_FN = \"movies.avro\"\n",
-        "\n",
+        "MOVIES_AVRO_FN = \"movies.avro\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "KqIH_bS-5OW5"
+      },
+      "outputs": [],
+      "source": [
         "! gsutil cp $GCS_USERS_AVRO_URI $USERS_AVRO_FN\n",
         "! gsutil cp $GCS_MOVIES_AVRO_URI $MOVIES_AVRO_FN"
       ]
@@ -648,9 +604,7 @@
         "id": "Fd6Z0jfR5OW5"
       },
       "source": [
-        "### Load data from avro files \n",
-        "\n",
-        "Load users and movies data from avro files into Pandas dataframes."
+        "#### Load Avro Files into Pandas DataFrames"
       ]
     },
     {
@@ -661,7 +615,10 @@
       },
       "outputs": [],
       "source": [
-        "# Define a class for reading the avro data\n",
+        "from avro.datafile import DataFileReader\n",
+        "from avro.io import DatumReader\n",
+        "\n",
+        "\n",
         "class AvroReader:\n",
         "    def __init__(self, data_file):\n",
         "        self.avro_reader = DataFileReader(open(data_file, \"rb\"), DatumReader())\n",
@@ -679,7 +636,6 @@
       },
       "outputs": [],
       "source": [
-        "# Load users data from avro file\n",
         "users_avro_reader = AvroReader(data_file=USERS_AVRO_FN)\n",
         "users_source_df = users_avro_reader.to_dataframe()\n",
         "print(users_source_df)"
@@ -693,7 +649,6 @@
       },
       "outputs": [],
       "source": [
-        "# Load movies data from avro file\n",
         "movies_avro_reader = AvroReader(data_file=MOVIES_AVRO_FN)\n",
         "movies_source_df = movies_avro_reader.to_dataframe()\n",
         "print(movies_source_df)"
@@ -705,9 +660,7 @@
         "id": "bgb0WGwX5OW6"
       },
       "source": [
-        "### Ingest Feature values into Entity types\n",
-        "\n",
-        "Load the feature values into `users` entity type providing the id fields and time field."
+        "#### Ingest Feature Values into _Users_ Entity Type"
       ]
     },
     {
@@ -732,7 +685,7 @@
         "id": "PCAdQ3cF5OW6"
       },
       "source": [
-        "Load the feature values into `movie` entity type providing the id fields and time field."
+        "#### Ingest Feature Values into _Movies_ Entity Type"
       ]
     },
     {
@@ -757,12 +710,10 @@
         "id": "pIYLZwao5OW6"
       },
       "source": [
-        "## Read/serve Entity's feature values online from Feature Store\n",
+        "## Read/Online Serve Entity's Feature Values from Vertex AI Online Feature Store\n",
         "\n",
         "Feature Store allows [online serving](https://cloud.google.com/vertex-ai/docs/featurestore/serving-online)\n",
-        "which lets you read feature values for small batches of entities. It works well when you want to read values of selected features from an entity or multiple entities in an entity type.\n",
-        "\n",
-        "### Read feature values for users"
+        "which lets you read feature values for small batches of entities. It works well when you want to read values of selected features from an entity or multiple entities in an entity type."
       ]
     },
     {
@@ -779,15 +730,6 @@
         "print(users_read_df)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b2cfa09ef11d"
-      },
-      "source": [
-        "### Read feature values for movies"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -809,13 +751,18 @@
         "id": "AK2Glzkq5OW7"
       },
       "source": [
-        "## Batch serve feature values from Feature Store\n",
+        "## Batch Serve Feature Values from Vertex AI Feature Store\n",
         "\n",
-        "Batch Serving is used to fetch a large batch of feature values for high-throughput, and is typically used for training a model or batch prediction. In this section, you learn how to prepare training examples by using the Feature Store's batch serve function.\n",
-        "\n",
-        "### Read instances from source file\n",
-        "\n",
-        "Define the source file and destination file. "
+        "Batch Serving is used to fetch a large batch of feature values for high-throughput, and is typically used for training a model or batch prediction. In this section, you learn how to prepare training examples by using the Feature Store's batch serve function."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hxsotHUe5OW7"
+      },
+      "source": [
+        "#### Read instances from source file"
       ]
     },
     {
@@ -830,15 +777,6 @@
         "READ_INSTANCES_CSV_FN = \"data.csv\""
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3f2c558b649f"
-      },
-      "source": [
-        "Copy the instances from the source file to the destination file locally."
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -856,9 +794,7 @@
         "id": "T5DW1MFt5OW7"
       },
       "source": [
-        "### Load the instances\n",
-        "\n",
-        "Load the instances from CSV file into a Pandas dataframe."
+        "#### Load CSV file into a Pandas DataFrame"
       ]
     },
     {
@@ -879,9 +815,7 @@
         "id": "LsgNNH8G5OW8"
       },
       "source": [
-        "### Change the data type\n",
-        "\n",
-        "Change the data type of the timestamp field from `Timestamp` to `Datetime64`."
+        "#### Change the Dtype of `Timestamp` to `Datetime64`"
       ]
     },
     {
@@ -903,9 +837,7 @@
         "id": "ao1dC5Pc5OW8"
       },
       "source": [
-        "### Batch serve feature values from Feature Store\n",
-        "\n",
-        "Serve the batch response to a dataframe and display the data."
+        "#### Batch Serve Feature Values from Movie Predictions Feature Store"
       ]
     },
     {
@@ -926,21 +858,43 @@
         "movie_predictions_df"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "29gLNORP5OW8"
+      },
+      "source": [
+        "## Read the Updated Feature Values"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "XN84znoI5OW8"
       },
       "source": [
-        "## Read the latest feature values\n",
-        "\n",
-        "In Feature Store, you access the latest or the last available feature values unless a specific time is provided. Now, you test this feature by ingesting new data to the entity types and reading it from the Feature Store.\n",
-        "\n",
-        "### Ingest updated feature values\n",
-        "\n",
-        "Now, you update the feature values by running the following cell. \n",
-        "\n",
-        "**Note:** For comparison, you can try printing the feature values read from the entity types earlier (those in `movies_read_df` variable). "
+        "#### Feature Values from last ingestion\n",
+        "Recall read from the Entity Type shows Feature Values from the last ingestion."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "wtmshq_n5OW9"
+      },
+      "outputs": [],
+      "source": [
+        "print(movies_read_df)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "feTUJjqG5OW9"
+      },
+      "source": [
+        "#### Ingest updated Feature Values"
       ]
     },
     {
@@ -951,13 +905,21 @@
       },
       "outputs": [],
       "source": [
-        "# Create a dataframe for the new data\n",
         "update_movies_df = pd.DataFrame(\n",
         "    data=[[\"movie_03\", 4.3], [\"movie_04\", 4.8]],\n",
         "    columns=[\"movie_id\", \"average_rating\"],\n",
         ")\n",
-        "\n",
-        "# Ingest the new data from the dataframe\n",
+        "print(update_movies_df)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aKKhSzUc5OW9"
+      },
+      "outputs": [],
+      "source": [
         "movies_entity_type.ingest_from_df(\n",
         "    feature_ids=[\"average_rating\"],\n",
         "    feature_time=datetime.datetime.now(),\n",
@@ -972,9 +934,8 @@
         "id": "s47WCIvL5OW9"
       },
       "source": [
-        "### Fetch the latest feature values\n",
-        "\n",
-        "Reading from the entity type gives you the updated feature values from the latest ingestion."
+        "#### Latest Feature Values\n",
+        "Read from the Entity Type shows updated Feature values from the latest ingestion."
       ]
     },
     {
@@ -992,18 +953,23 @@
         "print(update_movies_read_df)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "wsvCRzn_5OW9"
+      },
+      "source": [
+        "## Point-in-Time Correctness"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "R1YGRNsW5OW9"
       },
       "source": [
-        "## Point-in-time correctness\n",
-        "\n",
-        "Vertex AI Feature Store captures feature values for a feature at a specific point in time. In case there are missing values in your past data, you can backfill them using batch serving.\n",
-        "\n",
-        "### Missing data\n",
-        "Recall that response from the batch serve from last ingestion has some missing data in it."
+        "#### Missing data\n",
+        "Recall Batch Serve from the last ingestion has some missing data in it."
       ]
     },
     {
@@ -1014,7 +980,6 @@
       },
       "outputs": [],
       "source": [
-        "# Print the response\n",
         "print(movie_predictions_df)"
       ]
     },
@@ -1024,9 +989,7 @@
         "id": "abQRF6mx5OW-"
       },
       "source": [
-        "### Backfill/correct point-in-time data\n",
-        "\n",
-        "Impute the missing data based on the timestamps."
+        "#### Backfill/Correct point-in-time data"
       ]
     },
     {
@@ -1037,7 +1000,6 @@
       },
       "outputs": [],
       "source": [
-        "# Impute the users data\n",
         "backfill_users_df = pd.DataFrame(\n",
         "    data=[[\"bob\", 34, \"Male\", [\"Drama\"], \"2020-02-13 09:35:15\"]],\n",
         "    columns=[\"user_id\", \"age\", \"gender\", \"liked_genres\", \"update_time\"],\n",
@@ -1054,7 +1016,6 @@
       },
       "outputs": [],
       "source": [
-        "# Impute the movies data\n",
         "backfill_movies_df = pd.DataFrame(\n",
         "    data=[[\"movie_04\", 4.2, \"The Dark Knight\", \"Action\", \"2020-02-13 09:35:15\"]],\n",
         "    columns=[\"movie_id\", \"average_rating\", \"title\", \"genres\", \"update_time\"],\n",
@@ -1069,9 +1030,7 @@
         "id": "WXb4JUhu5OW-"
       },
       "source": [
-        "### Ingest the backfilled/corrected data\n",
-        "\n",
-        "Ingest the imputed point-in-time data from dataframe to the entity types in feature store."
+        "#### Ingest backfilled/corrected point-in-time data from dataframe"
       ]
     },
     {
@@ -1082,7 +1041,6 @@
       },
       "outputs": [],
       "source": [
-        "# Ingest the users data\n",
         "users_entity_type.ingest_from_df(\n",
         "    feature_ids=[\"age\", \"gender\", \"liked_genres\"],\n",
         "    feature_time=\"update_time\",\n",
@@ -1099,7 +1057,6 @@
       },
       "outputs": [],
       "source": [
-        "# Ingest the users data\n",
         "movies_entity_type.ingest_from_df(\n",
         "    feature_ids=[\"average_rating\", \"title\", \"genres\"],\n",
         "    feature_time=\"update_time\",\n",
@@ -1114,8 +1071,8 @@
         "id": "1e62Ku6W5OW_"
       },
       "source": [
-        "### Fetch the latest data\n",
-        "Batch serve the latest ingested data with backfill/correction to a dataframe to ensure the feature store is updated. "
+        "#### Latest ingestion with imputed missing data\n",
+        "Batch Serve from the latest ingestion with backfill/correction has reduced missing data."
       ]
     },
     {
@@ -1147,7 +1104,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:"
+        "You can also keep the project but delete the featurestore by running the code below:"
       ]
     },
     {
@@ -1158,7 +1115,6 @@
       },
       "outputs": [],
       "source": [
-        "# Delete the feature store\n",
         "movie_predictions_feature_store.delete(force=True)"
       ]
     }

notebooks/official/matching_engine/README.md

@@ -1,6 +1,5 @@
-## Vertex-AI: Matching Engine Notebook
 
-<a id="sdk_matching_engine_for_indexing"></a>[Create Vertex AI Matching Engine index](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb)
+[Create Vertex AI Matching Engine index](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb)
 
 Learn how to create Approximate Nearest Neighbor (ANN) Index, query against indexes, and validate the performance of the index.
 
@@ -12,20 +11,29 @@ The steps performed include:
 * Perform online query
 * Compute recall
 
-    <details>
-    <summary>Example code snippet from the Notebook:</summary>
-    
-    * Create an IndexEndpoint with VPC Network
-        ```python
-        # [START aiplatform_sdk_matching_engine_for_indexing]
-        VPC_NETWORK = "[your-network-name]"
-        VPC_NETWORK_FULL = "projects/{}/global/networks/{}".format(PROJECT_NUMBER, VPC_NETWORK)
-        my_index_endpoint = aiplatform.MatchingEngineIndexEndpoint.create(
-            display_name="index_endpoint_for_demo",
-            description="index endpoint description",
-            network=VPC_NETWORK_FULL,
-        )
-        # [END aiplatform_sdk_matching_engine_for_indexing]
-        ```
-        [:notebook: sdk_matching_engine_for_indexing.ipynb](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb)
-    </details>
+
+[Introduction to builtin Swivel embedding algorithm](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/intro-swivel.ipynb)
+
+Learn how to train custom embeddings using Vertex AI Pipelines and deploy the model for serving.
+
+The steps performed include:
+
+1. **Setup**: Importing the required libraries and setting your global variables.
+2. **Configure parameters**: Setting the appropriate parameter values for the pipeline job.
+3. **Train on Vertex AI Pipelines**: Create a Swivel job to Vertex Pipelines using pipeline template.
+4. **Deploy on Vertex AI Prediction**: Importing and deploying the trained model to a callable endpoint.
+5. **Predict**: Calling the deployed endpoint using online prediction.
+6. **Cleaning up**: Deleting resources created by this tutorial.
+
+[Introduction to builtin Two-towers embedding algorithm](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/matching_engine/two-tower-model-introduction.ipynb)
+
+Learn how to run the two-tower model.
+
+The steps performed include:
+1. **Setup**: Importing the required libraries and setting your global variables.
+2. **Configure parameters**: Setting the appropriate parameter values for the training job.
+3. **Train on Vertex AI Training**: Submitting a training job.
+4. **Deploy on Vertex AI Prediction**: Importing and deploying the trained model to a callable endpoint.
+5. **Predict**: Calling the deployed endpoint using online or batch prediction.
+6. **Hyperparameter tuning**: Running a hyperparameter tuning job.
+7. **Cleaning up**: Deleting resources created by this tutorial.

notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb

@@ -98,172 +98,171 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "f0f1bea346db"
+        "id": "5e2eba58ad71"
       },
       "source": [
-        "## Installation\n",
+        "### Costs \n",
         "\n",
-        "Install the latest version of Cloud Storage, BigQuery and Vertex AI SDKs for Python."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "dfbccc635a17"
-      },
-      "outputs": [],
-      "source": [
-        "# Install the packages\n",
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                        google-cloud-storage"
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "5b08ba354c6e"
-      },
-      "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bea801acf6b5"
-      },
-      "outputs": [],
-      "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
-        "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dd28c9e4f067"
+        "id": "d1e95a984673"
       },
       "source": [
         "## Before you begin\n",
-        "#### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, try the following:\n",
-        "* Run `gcloud config list`.\n",
-        "* Run `gcloud projects list`.\n",
-        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "80c0215f05a0"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "### Set up your Google Cloud project\n",
         "\n",
-        "# Set the project id\n",
-        "! gcloud config set project {PROJECT_ID}"
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager).\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API, and Service Networking API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,servicenetworking.googleapis.com).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "4f4512bf63b3"
-      },
-      "source": [
-        "#### Region\n",
-        "\n",
-        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "474be5183c27"
-      },
-      "outputs": [],
-      "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "949271bfebe3"
+        "id": "2b9daa35336a"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+        "**If you are using a Vertex AI Workbench notebook**, your environment is already\n",
+        "authenticated. Skip this step."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "b65b4ce80d9a"
+        "id": "c6bed8c6a6b3"
       },
       "source": [
-        "**1. Vertex AI Workbench**\n",
-        "* Do nothing as you are already authenticated."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "985cdbfe7372"
-      },
-      "source": [
-        "**2. Local JupyterLab instance, uncomment and run:**"
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "fbc9cd30cc4b"
+        "id": "3e2b43c2d2bf"
       },
       "outputs": [],
       "source": [
-        "# ! gcloud auth login"
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "# The Vertex AI Workbench notebook product has specific requirements\n",
+        "IS_VERTEX_AI_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# If on a Vertex AI Workbench notebook, then don't execute this code\n",
+        "if not IS_VERTEX_AI_WORKBENCH_NOTEBOOK:\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, log in using gcloud\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        ! gcloud auth login"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "79efab26ad02"
+        "id": "WReHDGG5g0XY"
       },
       "source": [
-        "**3. Colab, uncomment and run:**"
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "a336a05c6149"
+        "id": "beb72f394541"
       },
       "outputs": [],
       "source": [
-        "# from google.colab import auth\n",
-        "# auth.authenticate_user()"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Get your Google Cloud project ID from gcloud\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0c0a44fa330f"
+        "id": "f4c6d0a9e66c"
       },
       "source": [
-        "**4. Service account or other**\n",
-        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
+        "Otherwise, set your project ID here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1dc3fa9ac4f7"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"<your_project_id>\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -272,8 +271,7 @@
         "id": "4962667eec8e"
       },
       "source": [
-        "### Prepare a VPC network\n",
-        "To reduce any network overhead that might lead to unnecessary increase in overhead latency, it is best to call the ANN endpoints from your VPC via a direct [VPC Peering](https://cloud.google.com/vertex-ai/docs/general/vpc-peering) connection. \n",
+        "* **Prepare a VPC network**.  To reduce any network overhead that might lead to unnecessary increase in overhead latency, it is best to call the ANN endpoints from your VPC via a direct [VPC Peering](https://cloud.google.com/vertex-ai/docs/general/vpc-peering) connection. \n",
         "  * The following section describes how to setup a VPC Peering connection if you don't have one. \n",
         "  * This is a one-time initial setup task. You can also reuse existing VPC network and skip this section."
       ]
@@ -286,8 +284,7 @@
       },
       "outputs": [],
       "source": [
-        "# VPC_NETWORK = \"[your-vpc-network-name]\"  # @param {type:\"string\"}\n",
-        "VPC_NETWORK = \"matching-engine-test\"  # @param {type:\"string\"}\n",
+        "VPC_NETWORK = \"[your-vpc-network-name]\"  # @param {type:\"string\"}\n",
         "\n",
         "PEERING_RANGE_NAME = \"ann-haystack-range\""
       ]
@@ -366,7 +363,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip install --upgrade --quiet google-cloud-aiplatform grpcio-tools h5py"
+        "! pip install -U google-cloud-aiplatform"
       ]
     },
     {
@@ -378,13 +375,27 @@
         "Install the `h5py` to prepare sample dataset, and the `grpcio-tools` for querying against the index. "
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-h5sqwOEZ5Yq"
+      },
+      "outputs": [],
+      "source": [
+        "! pip install -U grpcio-tools\n",
+        "! pip install -U h5py"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "hhq5zEbGg0XX"
       },
       "source": [
-        "### Colab only: Uncomment the following cell to restart the kernel."
+        "### Restart the kernel\n",
+        "\n",
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -395,11 +406,37 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
-        "# import IPython\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
         "\n",
-        "# app = IPython.Application.instance()\n",
-        "# app.kernel.do_shutdown(True)"
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "q7tcBkCDI1_M"
+      },
+      "source": [
+        "### Random ID\n",
+        "\n",
+        "To avoid name collisions between users on resources created, create a random ID for each instance session, and append the id onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "HpIK91y1IzDr"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "RANDOM_ID = \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))"
       ]
     },
     {
@@ -410,7 +447,15 @@
       "source": [
         "### Create a Cloud Storage bucket\n",
         "\n",
-        "Create a storage bucket to store intermediate artifacts such as datasets."
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Cloud Storage buckets.\n",
+        "\n",
+        "You may also change the `REGION` variable, which is used for operations\n",
+        "throughout the rest of this notebook. Make sure to [choose a region where Vertex AI services are\n",
+        "available](https://cloud.google.com/vertex-ai/docs/general/locations#available_regions). You may\n",
+        "not use a Multi-Regional Storage bucket for training with Vertex AI."
       ]
     },
     {
@@ -421,7 +466,23 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://your-bucket-name-unique\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cf221059d072"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + RANDOM_ID\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -444,6 +505,84 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ucvCsknMCims"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vhOb7YnwClBb"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XoEqT2Y4DJmf"
+      },
+      "source": [
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Y9Uo3tifg1kx"
+      },
+      "source": [
+        "Import the Vertex AI (unified) client library into your Python environment. \n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f2d05ab4126a"
+      },
+      "outputs": [],
+      "source": [
+        "import h5py"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "76f7b9ffde0b"
+      },
+      "source": [
+        "Use gcloud to retrieve the project number."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pRUOFELefqf1"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_NUMBER = !gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
+        "PROJECT_NUMBER = PROJECT_NUMBER[0]\n",
+        "\n",
+        "PARENT = \"projects/{}/locations/{}\".format(PROJECT_ID, REGION)\n",
+        "\n",
+        "print(\"PROJECT_ID: {}\".format(PROJECT_ID))\n",
+        "print(\"REGION: {}\".format(REGION))\n",
+        "\n",
+        "!gcloud config set project {PROJECT_ID} --quiet\n",
+        "!gcloud config set ai_platform/region {REGION} --quiet"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -488,8 +627,6 @@
       },
       "outputs": [],
       "source": [
-        "import h5py\n",
-        "\n",
         "# The number of nearest neighbors to be retrieved from database for each query.\n",
         "NUM_NEIGHBOURS = 10\n",
         "\n",
@@ -515,42 +652,22 @@
         "id": "aQIQSyF9GtSv"
       },
       "source": [
-        "#### Save the train split in JSONL format.\n",
-        "\n",
-        "The data must be formatted in JSONL format, which means each embedding dictionary is written as a JSON string on its own line.\n",
-        "\n",
-        "Additionally, to demonstrate the filtering functionality, the `restricts` key is set such that each embedding has a different `class`, `even` or `odd`. These are used during the later matching step to filter for results.\n",
-        "See additional information of filtering here: https://cloud.google.com/vertex-ai/docs/matching-engine/filtering"
+        "Save the train split in JSONL format.\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "57fe2ce4b50f"
+        "id": "18wCiTwfG40P"
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
         "with open(\"glove100.json\", \"w\") as f:\n",
-        "    embeddings_formatted = [\n",
-        "        json.dumps(\n",
-        "            {\n",
-        "                \"id\": str(index),\n",
-        "                \"embedding\": [str(value) for value in train[index]],\n",
-        "                \"restricts\": [\n",
-        "                    {\n",
-        "                        \"namespace\": \"class\",\n",
-        "                        \"allow_list\": [\"even\" if index % 2 == 0 else \"odd\"],\n",
-        "                    }\n",
-        "                ],\n",
-        "            }\n",
-        "        )\n",
-        "        + \"\\n\"\n",
-        "        for index, embedding in enumerate(train)\n",
-        "    ]\n",
-        "    f.writelines(embeddings_formatted)"
+        "    for i in range(len(train)):\n",
+        "        f.write('{\"id\":\"' + str(i) + '\",')\n",
+        "        f.write('\"embedding\":[' + \",\".join(str(x) for x in train[i]) + \"]}\")\n",
+        "        f.write(\"\\n\")"
       ]
     },
     {
@@ -613,7 +730,7 @@
       "source": [
         "Create the ANN index configuration:\n",
         "\n",
-        "To learn more about configuring the index, see [Input data format and structure](https://cloud.google.com/vertex-ai/docs/matching-engine/match-eng-setup#input-data-format).\n"
+        "Please read the documentation to understand the various configuration parameters that can be used to tune the index\n"
       ]
     },
     {
@@ -625,6 +742,7 @@
       "outputs": [],
       "source": [
         "import os\n",
+        "import sys\n",
         "\n",
         "from google.cloud import aiplatform\n",
         "\n",
@@ -640,7 +758,7 @@
       "outputs": [],
       "source": [
         "tree_ah_index = aiplatform.MatchingEngineIndex.create_tree_ah_index(\n",
-        "    display_name=DISPLAY_NAME_BRUTE_FORCE,\n",
+        "    display_name=DISPLAY_NAME,\n",
         "    contents_delta_uri=EMBEDDINGS_INITIAL_URI,\n",
         "    dimensions=DIMENSIONS,\n",
         "    approximate_neighbors_count=150,\n",
@@ -760,21 +878,8 @@
       "outputs": [],
       "source": [
         "with open(\"glove100_incremental.json\", \"w\") as f:\n",
-        "    index = 0\n",
         "    f.write(\n",
-        "        json.dumps(\n",
-        "            {\n",
-        "                \"id\": str(index),\n",
-        "                \"embedding\": [str(0) for _ in train[index]],\n",
-        "                \"restricts\": [\n",
-        "                    {\n",
-        "                        \"namespace\": \"class\",\n",
-        "                        \"allow_list\": [\"even\" if index % 2 == 0 else \"odd\"],\n",
-        "                    }\n",
-        "                ],\n",
-        "            }\n",
-        "        )\n",
-        "        + \"\\n\"\n",
+        "        '{\"id\":\"0\",\"embedding\":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]}\\n'\n",
         "    )"
       ]
     },
@@ -860,10 +965,6 @@
       },
       "outputs": [],
       "source": [
-        "# Retrieve the project number\n",
-        "PROJECT_NUMBER = !gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
-        "PROJECT_NUMBER = PROJECT_NUMBER[0]\n",
-        "\n",
         "VPC_NETWORK = \"[your-network-name]\"\n",
         "VPC_NETWORK_FULL = \"projects/{}/global/networks/{}\".format(PROJECT_NUMBER, VPC_NETWORK)\n",
         "VPC_NETWORK_FULL"
@@ -922,7 +1023,7 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_INDEX_ID = \"tree_ah_glove_deployed_unique\""
+        "DEPLOYED_INDEX_ID = f\"tree_ah_glove_deployed_{RANDOM_ID}\""
       ]
     },
     {
@@ -957,7 +1058,7 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_BRUTE_FORCE_INDEX_ID = \"glove_brute_force_deployed_unique\""
+        "DEPLOYED_BRUTE_FORCE_INDEX_ID = f\"glove_brute_force_deployed_{RANDOM_ID}\""
       ]
     },
     {
@@ -983,9 +1084,16 @@
       "source": [
         "## Create Online Queries\n",
         "\n",
-        "After you built your indexes, you may query against the deployed index through the online querying gRPC API (Match service) within the virtual machine instances from the same region (for example 'us-central1' in this tutorial).\n",
-        "\n",
-        "The `filter` parameter is an optional way to filter for a subset of embeddings. In this case, only embeddings that have the `class` set as `even` are returned."
+        "After you built your indexes, you may query against the deployed index through the online querying gRPC API (Match service) within the virtual machine instances from the same region (for example 'us-central1' in this tutorial).  "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "IcXa9lSuB9AT"
+      },
+      "source": [
+        "Test your query:"
       ]
     },
     {
@@ -996,16 +1104,9 @@
       },
       "outputs": [],
       "source": [
-        "# Test query\n",
-        "from google.cloud.aiplatform.matching_engine.matching_engine_index_endpoint import \\\n",
-        "    Namespace\n",
-        "\n",
         "# Test query\n",
         "response = my_index_endpoint.match(\n",
-        "    deployed_index_id=DEPLOYED_INDEX_ID,\n",
-        "    queries=test[:1],\n",
-        "    num_neighbors=NUM_NEIGHBOURS,\n",
-        "    filter=[Namespace(\"class\", [\"even\"])],\n",
+        "    deployed_index_id=DEPLOYED_INDEX_ID, queries=test[:1], num_neighbors=NUM_NEIGHBOURS\n",
         ")\n",
         "\n",
         "response"

notebooks/official/migration/UJ1 Vertex SDK AutoML Image Classification.ipynb

@@ -45,7 +45,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/migration/UJ1 Vertex SDK AutoML Image Classification.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ1 Vertex SDK AutoML Image Classification.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",

notebooks/official/migration/UJ10 Vertex SDK Custom Scikit-Learn with pre-built training container.ipynb

@@ -33,67 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "<a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ10 Vertex SDK Custom Scikit-Learn with pre-built training container.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ10%20Vertex%20SDK%20Custom%20Scikit-Learn%20with%20pre-built%20training%20container.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "<a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ10 Vertex SDK Custom Scikit-Learn with pre-built training container.ipynb\" target='_blank'>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ10%20Vertex%20SDK%20Custom%20Scikit-Learn%20with%20pre-built%20training%20container.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
-        "     <td>\n",
-        "<a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/migration/UJ10 Vertex SDK Custom Scikit-Learn with pre-built training container.ipynb\" target='_blank'>\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
-        "      Open in Vertex AI Workbench\n",
-        "    </a>\n",
-        "  </td>         \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "7a8a13b86a8b"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "\n",
-        "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom tabular classification scikit-learn model for batch prediction."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "618cfedf829a"
-      },
-      "source": [
-        "### Objective\n",
-        "\n",
-        "In this tutorial, you learn to use `Vertex AI Training` to create a custom trained model and use `Vertex AI Batch Prediction` to do a batch prediction on the trained model.\n",
-        "\n",
-        "\n",
-        "You learn how to create a custom-trained model from a Python script in a Docker container using the Vertex AI SDK for Python, and then do a prediction on the deployed model by sending data.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services:\n",
-        "\n",
-        "- `Vertex AI Training`\n",
-        "- `Vertex AI Batch Prediction`\n",
-        "- `Vertex AI Model` resource\n",
-        "- `Vertex AI Endpoint` resource\n",
-        "\n",
-        "The steps performed include:\n",
-        "\n",
-        "- Create a `Vertex AI` custom job for training a scikit-learn model.\n",
-        "- Upload the trained model artifacts as a `Model` resource.\n",
-        "- Make a batch prediction.\n",
-        "- Deploy model to a endpoint\n",
-        "- Make a online prediction"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -102,7 +55,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the UCI Machine Learning [US Census Data (1990) dataset](https://archive.ics.uci.edu/ml/datasets/US+Census+Data+(1990)).The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket.\n",
+        "The dataset used for this tutorial is the UCI Machine Learning [US Census Data (1990) dataset](https://archive.ics.uci.edu/ml/datasets/US+Census+Data+(1990)).The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket.\n",
         "\n",
         "The dataset predicts whether a persons income will be above $50K USD."
       ]
@@ -135,37 +88,29 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
         "\n",
-        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
-        "* Python version = 3.9\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
         "\n",
-        "* The Google Cloud SDK\n",
+        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
         "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
         "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
         "\n",
-        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
       ]
     },
     {
@@ -176,7 +121,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the following packages required to execute this notebook. "
+        "Install the latest version of Vertex SDK for Python."
       ]
     },
     {
@@ -189,18 +134,45 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "# Google Cloud Notebook\n",
+        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    USER_FLAG = \"--user\"\n",
+        "else:\n",
+        "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform google-cloud-storage tensorflow $USER_FLAG -q"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest GA version of *google-cloud-storage* library as well."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_tensorflow"
+      },
+      "outputs": [],
+      "source": [
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
       ]
     },
     {
@@ -222,7 +194,6 @@
       },
       "outputs": [],
       "source": [
-        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -241,33 +212,26 @@
       "source": [
         "## Before you begin\n",
         "\n",
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5aee4379e8e5"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
     {
@@ -335,10 +299,7 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -347,9 +308,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### UUID\n",
+        "#### Timestamp\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -360,16 +321,9 @@
       },
       "outputs": [],
       "source": [
-        "import random\n",
-        "import string\n",
+        "from datetime import datetime\n",
         "\n",
-        "\n",
-        "# Generate a uuid of a specifed length(default=8)\n",
-        "def generate_uuid(length: int = 8) -> str:\n",
-        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
-        "\n",
-        "\n",
-        "UUID = generate_uuid()"
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
     {
@@ -380,31 +334,23 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
         "\n",
-        "2. Click **Create service account**.\n",
+        "**Click Create service account**.\n",
         "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
         "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
         "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
       ]
     },
     {
@@ -423,11 +369,8 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -437,7 +380,7 @@
         "    # path to your service account key and run this cell to authenticate your GCP\n",
         "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -463,8 +406,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -475,9 +417,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
-        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -497,7 +438,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+        "! gsutil mb -l $REGION $BUCKET_NAME"
       ]
     },
     {
@@ -517,7 +458,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_URI"
+        "! gsutil ls -al $BUCKET_NAME"
       ]
     },
     {
@@ -526,6 +467,9 @@
         "id": "setup_vars"
       },
       "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -537,11 +481,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "import os\n",
-        "\n",
-        "import google.cloud.aiplatform as aip\n",
-        "import tensorflow as tf"
+        "import google.cloud.aiplatform as aip"
       ]
     },
     {
@@ -563,7 +503,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
       ]
     },
     {
@@ -592,13 +532,10 @@
       "outputs": [],
       "source": [
         "TRAIN_VERSION = \"scikit-learn-cpu.0-23\"\n",
-        "DEPLOY_VERSION = \"sklearn-cpu.1-0\"\n",
+        "DEPLOY_VERSION = \"sklearn-cpu.0-23\"\n",
         "\n",
-        "TRAIN_IMAGE = \"us-docker.pkg.dev/vertex-ai/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"us-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
-        "\n",
-        "print(\"Training:\", TRAIN_IMAGE)\n",
-        "print(\"Deployment:\", DEPLOY_IMAGE)"
+        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
+        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)"
       ]
     },
     {
@@ -611,7 +548,7 @@
         "\n",
         "Next, set the machine type to use for training and prediction.\n",
         "\n",
-        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you use for for training and prediction.\n",
+        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training and prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -663,7 +600,7 @@
         "\n",
         "#### Package layout\n",
         "\n",
-        "Before you start the training, you look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
+        "Before you start the training, you will look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
         "\n",
         "- PKG-INFO\n",
         "- README.md\n",
@@ -679,7 +616,7 @@
         "\n",
         "#### Package Assembly\n",
         "\n",
-        "In the following cells, you assemble the training package."
+        "In the following cells, you will assemble the training package."
       ]
     },
     {
@@ -700,7 +637,7 @@
         "setup_cfg = \"[egg_info]\\n\\ntag_build =\\n\\ntag_date = 0\"\n",
         "! echo \"$setup_cfg\" > custom/setup.cfg\n",
         "\n",
-        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'tensorflow_datasets',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
+        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'tensorflow_datasets==1.3.0',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
         "! echo \"$setup_py\" > custom/setup.py\n",
         "\n",
         "pkg_info = \"Metadata-Version: 1.0\\n\\nName: US Census Data (1990) tabular binary classification\\n\\nVersion: 0.0.0\\n\\nSummary: Demostration training script\\n\\nHome-page: www.google.com\\n\\nAuthor: Google\\n\\nAuthor-email: aferlitsch@google.com\\n\\nLicense: Public\\n\\nDescription: Demo\\n\\nPlatform: Vertex\"\n",
@@ -742,6 +679,7 @@
         "parser.add_argument('--model-dir', dest='model_dir',\n",
         "                    default=os.getenv('AIP_MODEL_DIR'), type=str, help='Model dir.')\n",
         "args = parser.parse_args()\n",
+        "\n",
         "print('Python Version = {}'.format(sys.version))\n",
         "\n",
         "# Public bucket holding the census data\n",
@@ -857,9 +795,6 @@
         "subdirs = args.model_dir.split('/')[3:]\n",
         "subdir = subdirs[0]\n",
         "subdirs.pop(0)\n",
-        "\n",
-        "\n",
-        "\n",
         "for comp in subdirs:\n",
         "    subdir = os.path.join(subdir, comp)\n",
         "\n",
@@ -868,7 +803,7 @@
         "\n",
         "# Upload the model to GCS\n",
         "bucket = storage.Client().bucket(bucket)\n",
-        "blob = bucket.blob(subdir + 'model.joblib')\n",
+        "blob = bucket.blob(subdir + '/model.joblib')\n",
         "blob.upload_from_filename('model.joblib')"
       ]
     },
@@ -894,7 +829,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_census.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_census.tar.gz"
       ]
     },
     {
@@ -945,10 +880,10 @@
       "outputs": [],
       "source": [
         "job = aip.CustomTrainingJob(\n",
-        "    display_name=\"census_\" + UUID,\n",
+        "    display_name=\"census_\" + TIMESTAMP,\n",
         "    script_path=\"custom/trainer/task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
-        "    requirements=[\"gcsfs\", \"tensorflow-datasets\"],\n",
+        "    requirements=[\"gcsfs==0.7.1\", \"tensorflow-datasets==4.4\"],\n",
         ")\n",
         "\n",
         "print(job)"
@@ -989,7 +924,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, UUID)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
         "\n",
         "\n",
         "job.run(\n",
@@ -1036,7 +971,7 @@
       "outputs": [],
       "source": [
         "model = aip.Model.upload(\n",
-        "    display_name=\"census_\" + UUID,\n",
+        "    display_name=\"census_\" + TIMESTAMP,\n",
         "    artifact_uri=MODEL_DIR,\n",
         "    serving_container_image_uri=DEPLOY_IMAGE,\n",
         "    sync=False,\n",
@@ -1086,7 +1021,7 @@
       "source": [
         "### Make test items\n",
         "\n",
-        "You use synthetic data as test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+        "You will use synthetic data as a test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -1141,7 +1076,7 @@
       "source": [
         "### Make the batch input file\n",
         "\n",
-        "Now make a batch input file, which you store in your local Cloud Storage bucket.  Each instance in the prediction request is a list of the form:\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket.  Each instance in the prediction request is a list of the form:\n",
         "\n",
         "                        [ [ content_1], [content_2] ]\n",
         "\n",
@@ -1156,7 +1091,11 @@
       },
       "outputs": [],
       "source": [
-        "gcs_input_uri = BUCKET_URI + \"/\" + \"test.jsonl\"\n",
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "gcs_input_uri = BUCKET_NAME + \"/\" + \"test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    for i in INSTANCES:\n",
         "        f.write(json.dumps(i) + \"\\n\")\n",
@@ -1195,9 +1134,9 @@
         "MAX_NODES = 1\n",
         "\n",
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"census_\" + UUID,\n",
+        "    job_display_name=\"census_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    gcs_destination_prefix=BUCKET_NAME,\n",
         "    instances_format=\"jsonl\",\n",
         "    predictions_format=\"jsonl\",\n",
         "    model_parameters=None,\n",
@@ -1309,6 +1248,8 @@
       },
       "outputs": [],
       "source": [
+        "import json\n",
+        "\n",
         "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
         "\n",
         "prediction_results = list()\n",
@@ -1322,7 +1263,8 @@
         "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
         "        for line in gfile.readlines():\n",
         "            line = json.loads(line)\n",
-        "            print(line)"
+        "            print(line)\n",
+        "            break"
       ]
     },
     {
@@ -1381,7 +1323,7 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_NAME = \"census-\" + UUID\n",
+        "DEPLOYED_NAME = \"census-\" + TIMESTAMP\n",
         "\n",
         "TRAFFIC_SPLIT = {\"0\": 100}\n",
         "\n",
@@ -1415,6 +1357,15 @@
         "    INFO:google.cloud.aiplatform.models:Endpoint model deployed. Resource name: projects/759209241365/locations/us-central1/endpoints/4867177336350441472"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "endpoints_predict:migration,new,mbsdk"
+      },
+      "source": [
+        "### [predictions.online-prediction-automl](https://cloud.google.com/vertex-ai/docs/predictions/online-predictions-automl)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1423,7 +1374,7 @@
       "source": [
         "### Make test item\n",
         "\n",
-        "You use synthetic data as a test data item. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+        "You will use synthetic data as a test data item. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -1540,10 +1491,13 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
+        "- Pipeline\n",
         "- Model\n",
         "- Endpoint\n",
         "- AutoML Training Job\n",
         "- Batch Job\n",
+        "- Custom Job\n",
+        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1551,25 +1505,64 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "74ddbf65df4c"
+        "id": "cleanup:mbsdk"
       },
       "outputs": [],
       "source": [
-        "# delete endpoint\n",
-        "endpoint.delete()\n",
+        "delete_all = True\n",
         "\n",
-        "# Delete the model using the Vertex model object\n",
-        "model.delete()\n",
+        "if delete_all:\n",
+        "    # Delete the dataset using the Vertex dataset object\n",
+        "    try:\n",
+        "        if \"dataset\" in globals():\n",
+        "            dataset.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
         "\n",
-        "# Delete the AutoML or Pipeline training job\n",
-        "job.delete()\n",
+        "    # Delete the model using the Vertex model object\n",
+        "    try:\n",
+        "        if \"model\" in globals():\n",
+        "            model.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
         "\n",
-        "# Delete the batch prediction job using the Vertex batch prediction object\n",
-        "batch_predict_job.delete()\n",
+        "    # Delete the endpoint using the Vertex endpoint object\n",
+        "    try:\n",
+        "        if \"endpoint\" in globals():\n",
+        "            endpoint.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
         "\n",
-        "delete_bucket = False\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil -m rm -r $BUCKET_URI"
+        "    # Delete the AutoML or Pipeline trainig job\n",
+        "    try:\n",
+        "        if \"dag\" in globals():\n",
+        "            dag.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
+        "\n",
+        "    # Delete the custom trainig job\n",
+        "    try:\n",
+        "        if \"job\" in globals():\n",
+        "            job.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
+        "\n",
+        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
+        "    try:\n",
+        "        if \"batch_predict_job\" in globals():\n",
+        "            batch_predict_job.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
+        "\n",
+        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
+        "    try:\n",
+        "        if \"hpt_job\" in globals():\n",
+        "            hpt_job.delete()\n",
+        "    except Exception as e:\n",
+        "        print(e)\n",
+        "\n",
+        "    if \"BUCKET_NAME\" in globals():\n",
+        "        ! gsutil rm -r $BUCKET_NAME"
       ]
     }
   ],