Merge branch 'main' into auto_logging

* feat: DIY autologging

* feat: DIY autologging

Co-authored-by: gericdong <itseric@google.com>

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,13 +17,16 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import json
 import git
 import operator
 import os
 import pathlib
 import re
 import subprocess
+import utils
 from typing import List, Optional
+from utils import util
 
 import execute_notebook_helper
 import execute_notebook_remote
@@ -35,6 +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
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -66,6 +70,7 @@ class NotebookExecutionResult:
     log_url: str
     output_uri: str
     build_id: str
+    logs_bucket: str
     error_message: Optional[str]
 
     @property
@@ -97,6 +102,7 @@ def _process_notebook(
             "VPC_NETWORK": variable_vpc_network,
         },
     )
+    unique_strings_preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
 
     # Use no-execute preprocessor
     (
@@ -110,6 +116,35 @@ def _process_notebook(
         nbformat.write(nb, new_file)
 
 
+def _get_notebook_python_version(notebook_path: str) -> str:
+    """
+    Get the python version for running the notebook if it is specified in
+    the notebook.
+    """
+    python_version = PYTHON_VERSION
+
+    # Load the notebook
+    file = open(notebook_path)
+    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"])
+
+            # Look for the python version specification pattern
+            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)
+                break
+
+    return python_version
+
+
 def _create_tag(filepath: str) -> str:
     tag = os.path.basename(os.path.normpath(filepath))
     tag = re.sub("[^0-9a-zA-Z_.-]+", "-", tag)
@@ -160,6 +195,7 @@ def process_and_execute_notebook(
         output_uri=notebook_output_uri,
         log_url="",
         build_id="",
+        logs_bucket="",
         error_message=None,
     )
 
@@ -167,6 +203,12 @@ def process_and_execute_notebook(
     time_start = datetime.datetime.now()
     operation = None
     try:
+        # Get the python version for running the notebook if specified
+        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
         _process_notebook(
             notebook_path=notebook,
@@ -193,11 +235,13 @@ 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,
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
         result.build_id = operation_metadata.build.id
         result.log_url = operation_metadata.build.log_url
+        result.logs_bucket = operation_metadata.build.logs_bucket
 
         # Block and wait for the result
         operation_result = operation.result()
@@ -339,7 +383,7 @@ def process_and_execute_notebooks(
         seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
     )
 
-    if len(notebooks) > 1:
+    if len(notebooks) >= 1:
         notebook_execution_results: List[NotebookExecutionResult] = []
 
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
@@ -404,6 +448,7 @@ def process_and_execute_notebooks(
                         result.log_url,
                         result.output_uri,
                         result.output_uri_web,
+                        result.logs_bucket,
                     ]
                     for result in results_sorted
                 ],
@@ -414,10 +459,35 @@ def process_and_execute_notebooks(
                     "log_url",
                     "output_uri",
                     "output_uri_web",
+                    "logs_bucket",
                 ],
             )
         )
 
+        if len(notebooks) == 1:
+            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"
+
+            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)
+
+            if match is not None:
+                match_index = match.span()[0]
+                print(log_contents[match_index:])
+            else:
+                print(log_contents)
+
         print("\n=== END RESULTS===\n")
 
         total_notebook_duration = functools.reduce(
@@ -433,25 +503,5 @@ def process_and_execute_notebooks(
         # Raise error if any notebooks failed
         if not all([result.is_pass for result in results_sorted]):
             raise RuntimeError("Notebook failures detected. See logs for details")
-
-    elif len(notebooks) == 1:
-        notebook = notebooks[0]
-
-        # Pre-process notebook by substituting variable names
-        _process_notebook(
-            notebook_path=notebook,
-            variable_project_id=variable_project_id,
-            variable_region=variable_region,
-            variable_service_account=variable_service_account,
-            variable_vpc_network=variable_vpc_network,
-        )
-
-        execute_notebook_helper.execute_notebook(
-            notebook_source=notebook,
-            output_file_or_uri="/".join(
-                [artifacts_bucket, pathlib.Path(notebook).name]
-            ),
-            should_log_output=True,
-        )
     else:
         print("No notebooks modified in this pull request.")

.cloud-build/execute_notebook_remote.py

@@ -40,6 +40,7 @@ def execute_notebook_remote(
     private_pool_region: Optional[str],
     tag: Optional[str],
     timeout_in_seconds: Optional[int] = None,
+    python_version: Optional[str] = None
 ) -> operation.Operation:
     """Create and execute a single notebook on Google Cloud Build"""
     # Load build steps from YAML
@@ -50,8 +51,12 @@ def execute_notebook_remote(
         "_PYTHON_IMAGE": container_uri,
         "_NOTEBOOK_GCS_URI": notebook_uri,
         "_NOTEBOOK_OUTPUT_GCS_URI": notebook_output_uri,
+        "_PYTHON_VERSION" : f"python{python_version}"
     }
 
+    if python_version is not None:
+      substitutions["_PYTHON_VERSION"] = "python" + python_version
+
     build = cloudbuild_v1.Build()
 
     options: Optional[client_options.ClientOptions] = None

.cloud-build/notebook-execution-test-cloudbuild-single.yaml

@@ -10,21 +10,21 @@ steps:
     entrypoint: /bin/sh
     args:
     - -c
-    - python3 .cloud-build/CheckPythonVersion.py -q
+    - ${_PYTHON_VERSION} .cloud-build/CheckPythonVersion.py -q
   # Create a virtual environment
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - python3 -m venv workspace/env
+    - ${_PYTHON_VERSION} -m venv workspace/env
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
     - . workspace/env/bin/activate &&
-      python3 -m pip -q install -U pip &&
-      python3 -m pip -q install -U -r .cloud-build/requirements.txt
+      python -m pip -q install -U pip &&
+      python -m pip -q install -U -r .cloud-build/requirements.txt
   # Install Python dependencies and run testing script
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
@@ -32,7 +32,7 @@ steps:
     - -c
     - |
       . workspace/env/bin/activate &&
-      python3 .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"
+      python .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"
     env:
     - 'IS_TESTING=1'
 timeout: 86400s

.cloud-build/test_notebook_vm.txt

@@ -1,5 +1,5 @@
 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/pipelines/metrics_viz_run_compare_kfp.ipynb
-notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
+notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
+.cloud-build/tests/python_version_test.ipynb

.cloud-build/test_single_notebook_vm.txt

@@ -1 +1 @@
-notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb
+notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb

.cloud-build/tests/python_version_test.ipynb

@@ -0,0 +1,61 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "57a3d44ed8a8"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.7\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 $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c6516f90311b"
+      },
+      "outputs": [],
+      "source": [
+        "# test if the right python version is being used\n",
+        "import sys\n",
+        "\n",
+        "actual_python_version = f\"{sys.version_info.major}.{sys.version_info.minor}\"\n",
+        "print(f\"Runtime python version: {actual_python_version}\")\n",
+        "\n",
+        "assert actual_python_version == \"3.7\", \"Wrong python version!\""
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "python_version_test.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

.cloud-build/utils/NotebookProcessors.py

@@ -14,6 +14,8 @@
 # limitations under the License.
 
 from typing import Dict
+import random
+import string
 
 from nbconvert.preprocessors import Preprocessor
 
@@ -63,3 +65,30 @@ 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" with a uuid.
+
+    @staticmethod
+    def update_unique_strings(content: str):
+        # Replace strings that end with "-unique" with a uuid.
+
+        return content.replace('-unique"', f'-{generate_uuid()}"')
+
+    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

@@ -40,65 +40,3 @@ 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

@@ -0,0 +1,14 @@
+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

@@ -0,0 +1,63 @@
+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

@@ -3,7 +3,7 @@ import subprocess
 import tarfile
 import uuid
 from datetime import datetime
-from typing import Optional
+from typing import Optional, Union
 
 from google.auth import credentials as auth_credentials
 from google.cloud import storage
@@ -58,3 +58,34 @@ def archive_code_and_upload(staging_bucket: str):
     print(f"Uploaded source code archive to {source_archived_file_gcs}")
 
     return source_archived_file_gcs
+
+
+def download_blob_into_memory(
+  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
+    download_as_text is set to True.
+    """
+
+    storage_client = storage.Client()
+
+    bucket = storage_client.bucket(bucket_name)
+
+    # Construct a client side representation of a blob.
+    blob = bucket.blob(blob_name)
+
+    # Download the blob content
+    if download_as_text:
+      contents = blob.download_as_text()
+    else:
+      contents = blob.download_as_bytes()
+
+    print(
+        f"Downloaded storage object {blob_name} from bucket {bucket_name}."
+    )
+
+    return contents
+

.github/workflows/linter/Dockerfile

@@ -0,0 +1,20 @@
+# To use this image, run this command with the desired notebook args from the top-level vertex-ai-samples directory:
+# 1. To lint all changed notebooks:
+# docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest
+# 2. To lint specific notebooks:
+# docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest notebooks/1.ipynb notebooks/2.ipynb
+
+FROM python:3.10
+
+WORKDIR setup
+
+COPY ./requirements.txt .
+COPY ./run_linter.sh .
+
+# Install dependencies.
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+
+WORKDIR app
+
+ENTRYPOINT ["/setup/run_linter.sh"]

.github/workflows/linter/run_linter.sh

@@ -47,12 +47,22 @@ done
 
 echo "Test mode: $is_test"
 
+# Read in user-provided notebooks
+notebooks=()
+for arg in "$@"; do
+    if [[ $arg == *.ipynb ]]; then
+        notebooks+=("$arg")
+    fi
+done
+
 # Only check notebooks in test folders modified in this pull request.
 # Note: Use process substitution to persist the data in the array
-notebooks=()
-while read -r file || [ -n "$line" ]; do
-    notebooks+=("$file")
-done < <(git diff --name-only main... | grep '\.ipynb$')
+if [ ${#notebooks[@]} -eq 0 ]; then
+    echo "Checking for changed notebooked using git"
+    while read -r file || [ -n "$line" ]; do
+        notebooks+=("$file")
+    done < <(git diff --name-only main... | grep '\.ipynb$')
+fi
 
 problematic_notebooks=()
 if [ ${#notebooks[@]} -gt 0 ]; then

community-content/CODEOWNERS

@@ -6,3 +6,4 @@
 /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

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

@@ -0,0 +1,83 @@
+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

@@ -0,0 +1,73 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/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/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,114 @@
+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

@@ -0,0 +1,95 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/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/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,132 @@
+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

@@ -0,0 +1,106 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/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/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,115 @@
+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

@@ -0,0 +1,94 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_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")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,257 @@
+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

@@ -0,0 +1,224 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1e2558325f4c708aca75827c8acc13d230ee7e9f/components/pandas/Binarize_column/in_CSV_format/component.yaml")
+split_rows_into_subsets_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/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/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# PyTorch
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/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/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# XGBoost
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_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")
+
+# Scikit-learn
+#train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/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/Ark-kun/pipeline_components/cb44b75c9c062fcc40c2b905b2024b4493dbc62b/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# Vertex AI
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,68 @@
+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

@@ -0,0 +1,57 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,97 @@
+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

@@ -0,0 +1,85 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/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/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,116 @@
+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

@@ -0,0 +1,97 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/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/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,99 @@
+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

@@ -0,0 +1,85 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_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")
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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

@@ -0,0 +1,238 @@
+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

@@ -0,0 +1,208 @@
+# 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/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/storage/download/workaround_for_buggy_KFPv2_compiler/component.yaml")
+select_columns_using_Pandas_on_CSV_data_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/8c78aae096806cff3bc331a40566f42f5c3e9d4b/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/Ark-kun/pipeline_components/23405971f5f16a41b16c343129b893c52e4d1d48/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/Ark-kun/pipeline_components/daae5a4abaa35e44501818b1534ed7827d7da073/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/Ark-kun/pipeline_components/9ca0f9eecf5f896f65b8538bbd809747052617d1/components/tensorflow/Create_fully_connected_network/component.yaml")
+train_model_using_Keras_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/c504a4010348c50eaaf6d4337586ccc008f4dcef/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/Ark-kun/pipeline_components/59c759ce6f543184e30db6817d2a703879bc0f39/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Tensorflow_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# PyTorch
+create_fully_connected_pytorch_network_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/1a2ef3eeb77bc278f33cad0dd29008ea2431e191/components/PyTorch/Create_fully_connected_network/component.yaml")
+train_pytorch_model_from_csv_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/d8c4cf5e6403bc65bcf8d606e6baf87e2528a3dc/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/Ark-kun/pipeline_components/46d51383e6554b7f3ab4fd8cf614d8c2b422fb22/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_PyTorch_model_archive/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# XGBoost
+train_XGBoost_model_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/58d3a47f904f32a64af8403330ba7e2134cae46d/components/XGBoost/Train/component.yaml")
+xgboost_predict_on_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/4694ec97baccf59284c2a1db4aa2250c22291eab/components/XGBoost/Predict/component.yaml")
+upload_XGBoost_model_to_Google_Cloud_Vertex_AI_op = components.load_component_from_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")
+
+# Scikit-learn
+train_linear_regression_model_using_scikit_learn_from_CSV_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/f807e02b54d4886c65a05f40848fd51c72407f40/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/Ark-kun/pipeline_components/c6a8b67d1ada2cc17665c99ff6b410df588bee28/components/google-cloud/Vertex_AI/Models/Upload_Scikit-learn_pickle_model/workaround_for_buggy_KFPv2_compiler/component.yaml")
+
+# Vertex AI
+deploy_model_to_endpoint_op = components.load_component_from_url("https://raw.githubusercontent.com/Ark-kun/pipeline_components/27a5ea25e849c9e8c0cb6ed65518bc3ece259aaf/components/google-cloud/Vertex_AI/Models/Deploy_to_endpoint/workaround_for_buggy_KFPv2_compiler/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/cpr-examples/timm_serving/.gitignore

@@ -2,4 +2,5 @@ cpr_model_server.py
 entrypoint.py
 state_dict.pth
 config.json
-**/__pycache__
+**/__pycache__
+!testdata/**

community-content/cpr-examples/timm_serving/README.md

@@ -2,7 +2,7 @@
 
 ## About CPR
 
-CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/custom-prediction-routine/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
+CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/main/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
 
 ## Using this example
 
@@ -34,6 +34,23 @@ Finally, install the Python modules required to build and run the model server:
 pip install -r requirements.txt
 ```
 
+### Auth
+
+This example uses Google Cloud Storage for hosting model artifacts and Artifact Registry to store the container image. 
+You'll need to authorize yourself before you can interact with these.
+
+First, log in to GCP with application default credentials:
+```sh
+gcloud auth application-default login
+```
+
+Next, if you haven't done so already, set up the [gcloud credential helper](https://cloud.google.com/artifact-registry/docs/docker/authentication)
+for the Artifact Registry region where you intend to host the image.  
+```
+gcloud auth configure-docker <region>-docker.pkg.dev
+```
+
+
 ### Predictor
 
 The `TimmPredictor` class in `timm_serving/predictor.py` implements most of the important logic for the server.

community-content/cpr-examples/timm_serving/config.py

@@ -60,9 +60,9 @@ class CPRConfig(object):
     image: str = "timm_predictor:latest"
     artifact_local_dir: str = ""
     region: str = "us-central1"
-    project_id: str = "samthrasher-experimental"
+    project_id: str = "<your project ID here>"
     repository: str = "cpr-images"
-    artifact_gcs_dir: str = "gs://samthrasher-cpr-example/timm-vit224/"
+    artifact_gcs_dir: str = "gs://<your bucket ID here>/timm-vit224/"
     model_name: str = ""
     endpoint_name: str = ""
     machine_type: str = "n1-standard-2"

community-content/cpr-examples/timm_serving/requirements.txt

@@ -5,4 +5,4 @@ timm==0.5.4
 smart_open==6.0.0
 
 google-cloud-storage>=1.26.0,<2.0.0dev
-google-cloud-aiplatform[prediction] @ git+https://github.com/googleapis/python-aiplatform.git@custom-prediction-routine
+google-cloud-aiplatform[prediction]>=1.16.0

community-content/cpr-examples/timm_serving/test.py

@@ -70,7 +70,10 @@ class PredictorUnitTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.predictor = predictor.TimmPredictor()
 
     def test_load_from_saved_state_dict_ok(self):
@@ -170,7 +173,10 @@ class ServerEndToEndTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.local_model = cpr.LocalModel(
             serving_container_spec=aiplatform.gapic.ModelContainerSpec(
                 image_uri=self.config.image

community-content/cpr-examples/timm_serving/testdata/bad_model_1/state_dict.pth

@@ -0,0 +1 @@
+blah

notebooks/community/CODEOWNERS

@@ -7,7 +7,7 @@
 /gapic @andrewferlitsch
 /gapic/custom/showcase_custom_image_classification_online_explain_example_based_api.ipynb @inardini
 /ml_ops @andrewferlitsch
-/model_monitoring/* @mco-gh
+/model_monitoring/* @andrewferlitsch
 /structured_data/rapid_prototyping_* @rafael-carvalho
 
 /managed_notebooks/
@@ -17,6 +17,7 @@
 /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
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu
@@ -27,4 +28,10 @@
 /notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
 /notebooks/community/neo4j/graph_paysim.ipynb @benofben @laeg
 /notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb @mansari
-/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb @fhirschmann
+/notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb @fhirschmann
+/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/ml_ops/README.md

@@ -14,5 +14,5 @@ The purpose of this set of notebooks and markdown files is to demonstrate Google
 4. [Evaluation](stage4)
 5. [Deployment](stage5)
 6. [Serving](stage6)
-7. Monitoring
+7. Monitoring(stage7)
 8. Continuous Training

notebooks/community/ml_ops/setup.md

@@ -0,0 +1,43 @@
+## Before you begin
+
+### Set up your Google Cloud project
+
+**The following steps are required, regardless of your notebook environment.**
+
+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 $300 free credit towards your compute/storage costs.
+
+1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).
+
+1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).
+
+1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).
+
+1. Enter your project ID in the cell below. Then run the cell to make sure the
+Cloud SDK uses the right project for all the commands in this notebook.
+
+**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.
+
+### Set up your local development environment
+
+**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.
+
+**Otherwise**, make sure your environment meets this notebook's requirements. You need the following:
+
+- The Cloud Storage SDK
+- Python 3
+- virtualenv
+- Jupyter notebook running in a virtual environment with Python 3
+
+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:
+
+1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).
+
+2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).
+
+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.
+
+4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.
+
+5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.
+
+6. Open this notebook in the Jupyter Notebook Dashboard.

notebooks/community/ml_ops/setup.py

@@ -0,0 +1,112 @@
+import os
+import sys
+import argparse
+import subprocess
+import random
+import string
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--bucket', dest='bucket_required', action='store_true', 
+                    default=False, help='Bucket required')
+parser.add_argument('--email', dest='email_required', action='store_true', 
+                    default=False, help='Email required')
+parser.add_argument('--sa', dest='sa_required', action='store_true', 
+                    default=False, help='Service account required')
+parser.add_argument('--packages', dest='extra_packages',
+                    default='', type=str, help='additional required packages')
+args = parser.parse_args()
+
+extra_pkgs = args.extra_packages
+
+
+# Installation
+
+
+# The Vertex AI Workbench Notebook product has specific requirements
+IS_WORKBENCH_NOTEBOOK = os.getenv("DL_ANACONDA_HOME")
+IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(
+    "/opt/deeplearning/metadata/env_version"
+)
+IS_COLAB = "google.colab" in sys.modules
+
+# Vertex AI Notebook requires dependencies to be installed with '--user'
+USER_FLAG = ""
+if IS_WORKBENCH_NOTEBOOK:
+    USER_FLAG = "--user"
+
+# not used
+'''
+print("Installing packages")
+os.system(f"pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform {args.extra_packages}")
+print("Done installation")
+'''
+
+# Authenticate
+if IS_COLAB:
+    from google.colab import auth as google_auth
+
+    google_auth.authenticate_user()
+
+
+# project ID
+if IS_WORKBENCH_NOTEBOOK:
+    shell_output = subprocess.check_output("gcloud config list --format 'value(core.project)' 2>/dev/null", shell=True)
+    PROJECT_ID = shell_output[0:-1].decode('utf-8')
+    print("PROJECT ID: ", PROJECT_ID)
+else:
+    PROJECT_ID = input("Enter PROJECT_ID: ")
+    os.system(f"gcloud config set project {PROJECT_ID}")
+
+# email
+if args.email_required:
+    shell_output = subprocess.check_output("gcloud config list --format 'value(core.account)' 2>/dev/null", shell=True)
+    EMAIL_ADDR = shell_output[0:-1].decode('utf-8')
+    if EMAIL_ADDR == '':
+            EMAIL_ADDR = input("Enter Email Address: ")
+    print("EMAIL_ADDR: ", EMAIL_ADDR)
+
+# region
+shell_output = subprocess.check_output("gcloud config list --format 'value(ai.region)'", shell=True)
+REGION = shell_output[0:-1].decode('utf-8')
+if REGION == '':
+    REGION = input("Enter REGION: ")
+print("REGION: ", REGION)
+
+# multi-region
+MULTI_REGION = REGION.split('-')[0]
+
+    
+# UUID
+# Generate a uuid of a specifed length(default=8)
+def generate_uuid(length: int = 8) -> str:
+    return "".join(random.choices(string.ascii_lowercase + string.digits, k=length))
+
+
+UUID = generate_uuid()
+print("UUID", UUID)
+    
+# Bucket
+if args.bucket_required:
+    BUCKET_NAME = PROJECT_ID + "aip-" + UUID
+    BUCKET_URI = f"gs://{BUCKET_NAME}"
+    os.system(f"gsutil mb -l {REGION} {BUCKET_URI}")
+    print("BUCKET_URI", BUCKET_URI)
+    
+    
+# Project Number
+if args.sa_required:
+    if IS_WORKBENCH_NOTEBOOK:
+        shell_output = subprocess.check_output("gcloud auth list 2>/dev/null", shell=True)
+        SERVICE_ACCOUNT = shell_output[:-1].decode('utf-8').split('\n')[2].strip()
+        PROJECT_NUMBER = SERVICE_ACCOUNT.split('-')[0]
+    else:
+        shell_output = subprocess.check_output(f"gcloud projects describe {PROJECT_ID}", shell=True)
+        try:
+            PROJECT_NUMBER = shell_output[:-1].decode('utf-8').split('\n')[7].split(':')[-1].strip().replace("'", "")
+            SERVICE_ACCOUNT = f"{PROJECT_NUMBER}-compute@developer.gserviceaccount.com"
+        except:
+            PROJECT_NUMBER = input("Enter project number: ")
+            SERVICE_ACCOUNT = f"{PROJECT_NUMBER}-compute@developer.gserviceaccount.com"
+    
+    print("SERVICE_ACCOUNT", SERVICE_ACCOUNT)
+    print("PROJECT_NUMBER", PROJECT_NUMBER)

notebooks/community/ml_ops/stage1/README.md

@@ -28,50 +28,46 @@ The first stage in MLOps is the collection and preparation for the purpose of de
 
 ### Get Started
 
-[Get started with Vertex AI datasets](get_started_vertex_datasets.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`.
 
-```
 The steps performed include:
-- Create a Vertex AI `Dataset` resource for:
-    - image data
-    - text data
-    - video data
-    - tabular data
-    - forecasting data
-- Search `Dataset` resources using a filter.
-- Read a sample of a `BigQuery` dataset into a dataframe.
-- Generate statistics and data schema using TensorFlow Data Validation from the samples in the dataframe.
-- Detect anomalies in new data using TensorFlow Data Validation.
-- Generate a TFRecord feature specification using TensorFlow Transform from the data schema.
-- Export a dataset and convert to TFRecords.
-```
 
-[Get started with Dataflow](get_started_dataflow.ipynb)
-
-```
-The steps performed include:
 - Offline preprocessing of data:
     - Serially - w/o dataflow
     - Parallel - with dataflow
 - Upstream preprocessing of data:
     - tabular data
     - image data
-```
 
-[Create an unlabelled Vertex AI AutoML text entity extraction dataset from pdfs using Vision API](get_started_with_visionapi_and_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`.
 
-```
 The steps performed include:
-1. Using `Vision API` to perform Optical Character Recognition (OCR) to extract text from PDF files.
-2. Processing the results and saving them to text files.
-3. Generating a `Vertex AI Dataset` import file.
-4. Creating a new unlabelled text entity extraction `Vertex AI Dataset` resource in `Vertex AI`.
-```
 
-[Get started with BigQuery datasets](get_started_bq_datasets.ipynb)
+- Create a Vertex AI `Dataset` resource for:
+    - image data
+    - text data
+    - video data
+    - tabular data
+    - forecasting data
+
+
+- Search `Dataset` resources using a filter.
+- Read a sample of a `BigQuery` dataset into a dataframe.
+- Generate statistics and data schema using TensorFlow Data Validation from the samples in the dataframe.
+- Detect anomalies in new data using TensorFlow Data Validation.
+- Generate a TFRecord feature specification using TensorFlow Transform from the data schema.
+- Export a dataset and convert to TFRecords.
+
+[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`.
 
-```
 The steps performed include:
+
 - Create a Vertex AI `Dataset` resource from `BigQuery` table -- compatible for `AutoML` training.
 - Extract a copy of the dataset from `BigQuery` to a CSV file in Cloud Storage -- compatible for `AutoML` or custom training.
 - Select rows from a `BigQuery` dataset into a `pandas` dataframe -- compatible for custom training.
@@ -79,19 +75,32 @@ The steps performed include:
 - Select rows from extracted CSV files into a `tf.data.Dataset` -- compatible for custom training `TensorFlow` models.
 - 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.
 
-```
 The steps performed include:
+
 - Create a Specialist Pool for data labelers.
 - Create a data labeling job.
 - Submit the data labeling job.
 - List data labeling jobs.
 - Cancel a data labeling job.
 
-```
+
+
+[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.
+
+The steps performed include:
+
+1. Using `Vision API` to perform Optical Character Recognition (OCR) to extract text from PDF files.
+2. Processing the results and saving them to text files.
+3. Generating a `Vertex AI Dataset` import file.
+4. Creating a new unlabelled text entity extraction `Vertex AI Dataset` resource in `Vertex AI`.
+
 
 ### E2E Stage Example
 

notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb

@@ -120,7 +120,7 @@
         "    - XGBoost model training:\n",
         "      - Use BigQuery ML built-in XGBoost training.\n",
         "      - Alternatively, create a DMatrix generator from CSV files extracted from BigQuery table.\n",
-        "    - Pytorch model training:\n",
+        "    - PyTorch model training:\n",
         "        - Extract the BigQuery to a pandas dataframe.\n",
         "        - Preprocess the data in the dataframe.\n",
         "        - Create a DataLoader generator from the pandas dataframe.\n",
@@ -191,13 +191,8 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "# Install the packages\n",
-        "! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install -U xgboost $USER_FLAG -q\n",
-        "! pip3 install -U tensorflow $USER_FLAG -q\n",
-        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q"
+        "extra_pkgs = \"tensorflow tensorflow-io==0.18 pyarrow xgboost google-cloud-bigquery\"\n",
+        "! pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform $extra_pkgs"
       ]
     },
     {
@@ -219,9 +214,9 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "import sys\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    # Automatically restart kernel after installs\n",
         "    import IPython\n",
         "\n",
@@ -232,274 +227,42 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "84cd83853240"
+        "id": "fc8fb52b5cca"
       },
       "source": [
-        "## Before you begin\n",
+        "### Common setup\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 $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "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`."
+        "Now, execute the common setup for the notebook tutorials."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_project_id"
+        "id": "001a0fcd5d78"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "# Common code setup for notebook tutorials\n",
+        "\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.py -O setup.py\n",
+        "\n",
+        "%run setup.py --bucket"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "autoset_project_id"
+        "id": "d809f07a8935"
       },
       "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",
+        "# Other Common setup instructions for notebook tutorials\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",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.md -O setup.md\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": [
-        "#### 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": {
-        "id": "77c385f0db59"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Vertex AI Workbench 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",
-        "\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": "535223fa4b84"
-      },
-      "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 = False\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",
-        "        IS_COLAB = True\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": "bucket:custom"
-      },
-      "source": [
-        "### Create a Cloud Storage bucket\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you create a dataset resource using the Vertex SDK, you can provide a Cloud Storage bucket that contains the data. Vertex AI creates the dataset resource from the data. In this tutorial, Vertex AI also creates a dataset resource from your data in the Cloud Storage bucket.\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,
-      "metadata": {
-        "id": "bucket"
-      },
-      "outputs": [],
-      "source": [
-        "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": "create_bucket"
-      },
-      "source": [
-        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "create_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! 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"
+        "%load setup.md"
       ]
     },
     {
@@ -620,7 +383,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"NOAA historical weather data\" + \"_\" + UUID,\n",
         "    bq_source=[IMPORT_FILE],\n",
         "    labels={\"user_metadata\": BUCKET_URI[5:]},\n",
         ")\n",
@@ -695,7 +458,7 @@
         "gcs_source = IMPORT_FILES\n",
         "\n",
         "dataset = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"NOAA historical weather data\" + \"_\" + UUID,\n",
         "    gcs_source=gcs_source,\n",
         "    labels={\"user_metadata\": BUCKET_URI[5:]},\n",
         ")\n",
@@ -737,10 +500,10 @@
         "    or BQ_MY_DATASET is None\n",
         "    or BQ_MY_DATASET == \"[your-dataset-name]\"\n",
         "):\n",
-        "    BQ_MY_DATASET = \"mlops_dataset_\" + TIMESTAMP\n",
+        "    BQ_MY_DATASET = \"mlops_dataset_\" + UUID\n",
         "\n",
         "if BQ_MY_TABLE == \"\" or BQ_MY_TABLE is None or BQ_MY_TABLE == \"[your-view-name]\":\n",
-        "    BQ_MY_TABLE = \"mlops_view_\" + TIMESTAMP"
+        "    BQ_MY_TABLE = \"mlops_view_\" + UUID"
       ]
     },
     {

notebooks/community/ml_ops/stage1/get_started_dataflow.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://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\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/stage1/get_started_dataflow.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",
@@ -186,13 +186,9 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
-        "! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
-        "! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
-        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
-        "! pip3 install --upgrade apache-beam[gcp] $USER_FLAG -q"
+        "extra_pkgs = \"tensorflow==2.5 tensorflow-data-validation==1.2 tensorflow-transform==1.2 \\\n",
+        "              tensorflow-io==0.18 pyarrow pandas apache-beam[gcp] google-cloud-bigquery\"\n",
+        "! pip3 install --upgrade --quiet {USER_FLAG} google-cloud-aiplatform $extra_pkgs"
       ]
     },
     {
@@ -214,9 +210,9 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "import sys\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
+        "if \"google.colab\" in sys.modules:\n",
         "    # Automatically restart kernel after installs\n",
         "    import IPython\n",
         "\n",
@@ -227,279 +223,42 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "84cd83853240"
+        "id": "fc8fb52b5cca"
       },
       "source": [
-        "## Before you begin\n",
+        "### Common setup\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 $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "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`."
+        "Now, execute the common setup for the notebook tutorials."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_project_id"
+        "id": "001a0fcd5d78"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "# Common code setup for notebook tutorials\n",
+        "\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.py -O setup.py\n",
+        "\n",
+        "%run setup.py --bucket"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "autoset_project_id"
+        "id": "d809f07a8935"
       },
       "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",
+        "# Other Common setup instructions for notebook tutorials\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",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.md -O setup.md\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": [
-        "#### 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": {
-        "id": "77c385f0db59"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Vertex AI Workbench 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",
-        "\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": "535223fa4b84"
-      },
-      "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 = False\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",
-        "        IS_COLAB = True\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": "bucket:custom"
-      },
-      "source": [
-        "### Create a Cloud Storage bucket\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you submit a custom training job using the Vertex 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. You can then\n",
-        "create an `Endpoint` resource based on this output in order to serve\n",
-        "online predictions.\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,
-      "metadata": {
-        "id": "bucket"
-      },
-      "outputs": [],
-      "source": [
-        "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": "create_bucket"
-      },
-      "source": [
-        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "create_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! 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"
+        "%load setup.md "
       ]
     },
     {
@@ -1319,7 +1078,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_storage = True\n",
+        "delete_storage = False\n",
         "\n",
         "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
         "    if \"BUCKET_URI\" in globals():\n",

notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb

@@ -33,12 +33,12 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.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://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.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/stage1/get_started_with_data_labeling.ipynb

@@ -212,7 +212,7 @@
         "\n",
         "3. [Enable the Vertex AI APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)\n",
         "\n",
-        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebooks.\n",
+        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Vertex AI Workbench Notebooks.\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",
@@ -374,15 +374,8 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "32e1cd21a5d5"
-      },
-      "source": [
+        "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",

notebooks/community/ml_ops/stage1/mlops_data_management.ipynb

@@ -39,18 +39,15 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/mlops_data_management.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://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/mlops_data_management.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/>"
+        "<br/><br/><br/>\n",
+        "\n",
+        "*Note: This notebook is not supported for execution in Colab*"
       ]
     },
     {
@@ -169,21 +166,20 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "ONCE_ONLY = True\n",
+        "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade apache-beam[gcp]==2.33.0 $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG -q\n",
-        "    ! pip3 install future $USER_FLAG -q"
+        "    ! pip3 install -U {USER_FLAG} -q tensorflow==2.5 \\\n",
+        "                                     tensorflow-data-validation==1.2 \\\n",
+        "                                     tensorflow-transform==1.2 \\\n",
+        "                                     tensorflow-io==0.18 \n",
+        "    \n",
+        "    ! pip3 install --upgrade {USER_FLAG} -q google-cloud-aiplatform[tensorboard] \\\n",
+        "                                            google-cloud-pipeline-components \\\n",
+        "                                            google-cloud-bigquery \\\n",
+        "                                            google-cloud-logging \\\n",
+        "                                            apache-beam[gcp] \\\n",
+        "                                            pyarrow \\\n",
+        "                                            cloudml-hypertune\n"
       ]
     },
     {
@@ -355,7 +351,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\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",
@@ -417,7 +413,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you submit a custom training job using the Vertex SDK, you upload a Python package\n",
+        "When you submit a custom 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. You can then\n",

notebooks/community/ml_ops/stage2/README.md

@@ -35,44 +35,59 @@ The second stage in MLOps is experimenting in developing one or more baseline mo
 
 ### Get Started
 
+[Get started with Vertex AI Training for R](community/ml_ops/stage2/get_started_vertex_training_r.ipynb)
 
-[Get started with Vertex AI Training for Pytorch](get_started_vertex_training_pytorch.ipynb)
+In this tutorial, you learn how to use `Vertex AI Training` for training a R custom model.
 
-```
 The steps performed include:
-- Single node training using a Python package.
+
+- Locally train an R model in a notebook using %%R magic commands
+- Create a deployment image with trained R model and serving functions.
+- Test the deployment image locally.
+- Create a `Vertex AI Model` resource for the deployment image with embedded R model.
+- Deploy the deployment image with embedded R model to a `Vertex AI Endpoint` resource.
+- Test the deployment image with embedded R model.
+- Create a R-to-Python training package.
+- Create a training image for training the model.
+- Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package.
+
+[Get started with Logging](community/ml_ops/stage2/get_started_with_logging.ipynb)
+
+In this tutorial, you learn how to use Python and Cloud logging awhen training with `Vertex AI`.
+
+The steps performed include:
+
+- Use Python logging to log training configuration/results locally.
+- Use Google Cloud Logging to log training configuration/results in cloud storage.
+
+[Get started with Vertex AI Hyperparameter Tuning for XGBoost] (community/ml_ops/stage2/get_started_vertex_hpt_xgboost.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Hyperparameter Tuning` for training a XGBoost custom model.
+
+The steps performed include:
+
+- Training using a Python package.
 - Report accuracy when hyperparameter tuning.
 - Save the model artifacts to Cloud Storage using GCSFuse.
 - Create a `Vertex AI Model` resource.
-```
 
-[Get started with prebuilt TFHub models](get_started_with_tfhub_models.ipynb)
+[Get started with Vertex AI Training for XGBoost](community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Training` for training a XGBoost custom model.
 
-```
 The steps performed include:
-- Download a TensorFlow Hub prebuilt model.
-- Add the task component as a classifier for the CIFAR-10 dataset.
-- Fine tune locally the model with transfer learning training.
-- Construct a custom training script:
-    - Get training data from TensorFlow Datasets
-    - Get model architecture from TensorFlow Hub
-    - Train then model
-    - Save model artifacts and upload as Vertex AI Model resource.
-```
 
-[Get started with Vertex AI TensorBoard](get_started_vertex_tensorboard.ipynb)
+- Training using a Python package.
+- Report accuracy when hyperparameter tuning.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Create a `Vertex AI Model` resource.
+
+[Get started with TabNet builtin algorithm for training tabular models](community/ml_ops/stage2/get_started_with_tabnet.ipynb)
+
+In this notebook, you learn how to run `Vertex AI TabNet` built algorithm for training custom tabular models.
 
-```
 The steps performed include:
-- Create a TensorBoard callback when training a model.
-- Using Tensorboard with locally trained model.
-- Using Vertex AI TensorBoard with Vertex AI Training.
-```
 
-[Get started with TabNet builtin algorithm for training tabular models](get_started_with_tabnet.ipynb)
-
-```
-The steps performed include:
 - Get the training data.
 - Configure training parameters for the `Vertex AI TabNet` container.
 - Train the model using `Vertex AI Training` using CSV data.
@@ -82,50 +97,107 @@ The steps performed include:
 - Hyperparameter tuning the `Vertex AI TabNet` model.
 - Train the model using `Vertex AI Training` using BigQuery table.
 
-```
+[Get started with prebuilt TFHub models](community/ml_ops/stage2/get_started_with_tfhub_models.ipynb)
 
-[Get started with Vertex AI Vizier](get_started_vertex_vizier.ipynb)
+In this tutorial, you learn how to use `Vertex AI Training` with prebuilt models from TensorFlow Hub.
 
-```
 The steps performed include:
+
+- Download a TensorFlow Hub prebuilt model.
+- Add the task component as a classifier for the CIFAR-10 dataset.
+- Fine tune locally the model with transfer learning training.
+- Construct a custom training script:
+    - Get training data from TensorFlow Datasets
+    - Get model architecture from TensorFlow Hub
+    - Train then model
+    - Save model artifacts and upload as Vertex AI Model resource.
+
+[Get started with BigQuery ML Training](community/ml_ops/stage2/get_started_bqml_training.ipynb)
+
+In this tutorial, you learn how to use `BigQueryML` (BQML) for training with `Vertex AI`.
+
+The steps performed include:
+
+- Create a local BigQuery table in your project
+- Train a BQML model
+- Evaluate the BQML model
+- Export the BQML model as a cloud model
+- Upload the exported model as a `Vertex AI Model` resource
+- Hyperparameter tune a BQML model with `Vertex AI Vizier`
+- Automatically register a BQML model to `Vertex AI Model Registry`
+
+[Get started with Vertex AI Vizier](community/ml_ops/stage2/get_started_vertex_vizier.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Vizier` for when training with `Vertex AI`.
+
+The steps performed include:
+
 - Hyperparameter tuning with Random algorithm.
 - Hyperparameter tuning with Vizier (Bayesian) algorithm.
-```
+- Suggesting trials and updating results for Vizier study
 
-[Automl image classfication training with customer managed encryption keys (CMEK)](get_started_with_cmek_training.ipynb)
+[Get started with distributed training using DASK](community/ml_ops/stage2/get_started_with_distributed_training_xgboost.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Training` for distributed training of XGBoost model using the OSS package DASK. Additionally, you learn to construct and deploy a custom serving container using a Flask web server.
 
-```
 The steps performed include:
-- Creating a customer managed encryption key.
-- Creating an image dataset with CMEK encryption.
-- Train an AutoML model with CMEK encryption.
-```
 
-[Get started with Vertex AI distributed training](get_started_vertex_distributed_training.ipynb)
+- Construct an XGBoost training script using DASK for distributed training.
+- Construct a custom training container.
+- Configure a distributed custom training job.
+- Execute the custom training job.
+- Construct a custom serving container using Flask.
+- Upload the trained XGBoost model as a `Vertex AI Model` resource.
+- Create a `Vertex AI Endpoint` resource.
+- Deploy the `Vertex AI Model` resource to `Vertex AI Endpoint` resource.
+- Make a prediction.
+
+[Get started with Vertex AI TensorBoard](community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI TensorBoard` when training with `Vertex AI`.
 
-```
 The steps performed include:
-- `MirroredStrategy`: Train on a single VM with multiple GPUs.
-- `MultiWorkerMirroredStrategy`: Train on multiple VMs with automatic setup of replicas.
-- `MultiWorkerMirroredStrategy`: Train on multiple VMs with fine grain control of replicas.
-- `ReductionServer`: Train on multiple VMS and sync updates across VMS with `Vertex AI Reduction Server`.
-- `TPUTraining`: Train with multiple Cloud TPUs.
-```
 
-[Get started with Vertex AI Training for scikit-learn](get_started_vertex_training_sklearn.ipynb)
+- Create a TensorBoard callback when training a model.
+- Using TensorBoard with locally trained model.
+- Using Vertex AI TensorBoard with Vertex AI Training.
+
+[Get started with Vertex AI Training for R using R Kernel](community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI`, using an R kernel, for training and deploying an R custom model.
 
-```
 The steps performed include:
-- Training using a Python package.
-- Report accuracy when hyperparameter tuning.
-- Save the model artifacts to Cloud Storage using GCSFuse.
-- Create a `Vertex AI Model` resource.
-```
 
-[Get started with Vertex AI Experiments](get_started_vertex_experiments.ipynb)
+- Create a custom R training script
+- Create a custom R serving script
+- Create a custom R deployment (serving) container.
+- Train the model using `Vertex AI` custom training.
+- Create an `Endpoint` resouce.
+- Deploy the `Model` resource (trained R model) to the `Endpoint` resource.
+- Make an online prediction.
+
+
+[Get started Vision API test preprocessing and AutoML text model generation](community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb)
+
+In this tutorial, you create an `AutoML` text entity extraction model pre-existing extracted data by generating a custom import file. You deploy this mode for online prediction from a Python script using the `BigQuery`, `Vision AI`, Cloud Storage and `Vertex AI SDK` for Python. 
 
-```
 The steps performed include:
+
+- Preprocess training files using `Vision AI` APIs to extract the text from PDF files.
+- Create a custom import file that includes annotation data based on the sample `BigQuery` dataset.
+- Create a `Vertex AI Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Deploy the `Vertex AI Model` resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model`.
+
+[Get started with Vertex AI Experiments](community/ml_ops/stage2/get_started_vertex_experiments.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Experiments` when training with `Vertex AI`.
+
+The steps performed include:
+
 - Local (notebook) Training
     - Create an experiment
     - Create a first run in the experiment
@@ -142,23 +214,23 @@ The steps performed include:
     - Create a `Vertex AI Training` custom job
     - Execute the custom job
     - Visualize the experiment results
-```
 
-[Get started with Vertex AI Hyperparameter Tuning for XGBoost](get_started_vertex_hpt_xgboost.ipynb)
+[AutoML Image Classfication Training with Customer Managed Encryption Keys (CMEK)](community/ml_ops/stage2/get_started_with_cmek_training.ipynb)
+
+In this tutorial, you learn how to use a customer managed encryption key (CMEK) for `Vertex AI AutoML` training.
 
-```
 The steps performed include:
-- Training using a Python package.
-- Report accuracy when hyperparameter tuning.
-- Save the model artifacts to Cloud Storage using GCSFuse.
-- Create a `Vertex AI Model` resource.
 
-```
+- Creating a customer managed encryption key.
+- Creating an image dataset with CMEK encryption.
+- Train an AutoML model with CMEK encryption.
 
-[Get started with Vertex AI Feature Store](get_started_vertex_feature_store.ipynb)
+[Get started with Vertex AI Feature Store](community/ml_ops/stage2/get_started_vertex_feature_store.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Feature Store` when training and predicting with `Vertex AI`.
 
-```
 The steps performed include:
+
 - Creating a Vertex AI `Featurestore` resource.
     - Creating `EntityType` resources for the `Featurestore` resource.
     - Creating `Feature` resources for each `EntityType` resource.
@@ -167,96 +239,26 @@ The steps performed include:
     - From a pandas DataFrame.
 - Perform online serving from a `Featurestore` resource.
 - Perform batch serving from a `Featurestore` resource.
-```
 
-[Get started with Vertex AI Training for R](get_started_vertex_training_r.ipynb)
+[Get started with AutoML Training](community/ml_ops/stage2/get_started_automl_training.ipynb)
+
+In this tutorial, you learn how to use `AutoML` for training with `Vertex AI`.
 
-```
 The steps performed include:
-- Locally train an R model in a notebook using %%R magic commands
-- Create a deployment image with trained R model and serving functions.
-- Test the deployment image locally.
-- Create a `Vertex AI Model` resource for the deployment image with embedded R model.
-- Deploy the deployment image with embedded R model to a `Vertex AI Endpoint` resource.
-- Test the deployment image with embedded R model.
-- Create a R-to-Python training package.
-- Create a training image for training the model.
-- Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package.
-```
 
-[Get started with logging](get_started_with_logging.ipynb)
-
-```
-The steps performed include:
-- Use Python logging to log training configuration/results locally.
-- Use Google Cloud Logging to log training configuration/results in cloud storage.
-```
-
-[Get started with Vertex AI Training for R using R Kernel](get_started_vertex_training_r_using_r_kernel.ipynb)
-
-```
-The steps performed include:
-- Create a custom R training script
-- Create a custom R serving script
-- Create a custom R deployment (serving) container.
-- Train the model using `Vertex AI` custom training.
-- Create an `Endpoint` resouce.
-- Deploy the `Model` resource (trained R model) to the `Endpoint` resource.
-- Make an online prediction.
-
-```
-
-[Get started with BigQuery ML training](get_started_bqml_training.ipynb)
-
-```
-The steps performed include:
-- Create a local BigQuery table in your project
-- Train a BQML model
-- Evaluate the BQML model
-- Export the BQML model as a cloud model
-- Upload the exported model as a `Vertex AI Model` resource
-- Hyperparameter tune a BQML model with `Vertex AI Vizier`
-- Automatically register a BQML model to `Vertex AI Model Registry`
-
-```
-
-[Get started with AutoML training](get_started_automl_training.ipynb)
-
-```
-The steps performed include:
 - Train an image model
 - Export the image model as an edge model
 - Train a tabular model
 - Export the tabular model as a cloud model
 - Train a text model
 - Train a video model
-```
 
-[Get started with Vertex AI Training for XGBoost](get_started_vertex_training_xgboost.ipynb)
+[Get started with Vertex AI Training for LightGBM](community/ml_ops/stage2/get_started_vertex_training_lightgbm.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Training` for training a LightGBM custom model.
 
-```
 The steps performed include:
-- Training using a Python package.
-- Report accuracy when hyperparameter tuning.
-- Save the model artifacts to Cloud Storage using GCSFuse.
-- Create a `Vertex AI Model` resource.
 
-```
-
-[Get started with Vertex AI Training](get_started_vertex_training.ipynb)
-
-```
-The steps performed include:
-- Training using a single Python script.
-- Training using a Python package.
-- Training using a custom training image.
-- Laying out a training package.
-```
-
-[Get started with Vertex AI Training for LightGBM](get_started_vertex_training_lightgbm.ipynb)
-
-```
-The steps performed include:
 - Training using a Python package.
 - Save the model artifacts to Cloud Storage using GCSFuse.
 - Construct a FastAPI prediction server.
@@ -264,21 +266,51 @@ The steps performed include:
 - Test the deployment image locally.
 - Create a `Vertex AI Model` resource.
 
-```
+[Get started with Vertex AI Training for Scikit-Learn](community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb)
 
-[Get started Vision API test preprocessing and AutoML text model generation](get_started_with_visionapi_and_automl.ipynb)
+In this tutorial, you learn how to use `Vertex AI Training` for training a Scikit-Learn custom model.
 
-```
 The steps performed include:
-- Preprocess training files using `Vision AI` APIs to extract the text from PDF files.
-- Create a custom import file that includes annotation data based on the sample `BigQuery` dataset.
-- Create a `Vertex AI Dataset` resource.
-- Train the model.
-- View the model evaluation.
-- Deploy the `Vertex AI Model` resource to a serving `Endpoint` resource.
-- Make a prediction.
-- Undeploy the `Model`.
-```
+
+- Training using a Python package.
+- Report accuracy when hyperparameter tuning.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Create a `Vertex AI Model` resource.
+
+[Get started with Vertex AI Training](community/ml_ops/stage2/get_started_vertex_training.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Training` for custom models when training with `Vertex AI`.
+
+The steps performed include:
+
+- Training using a single Python script.
+- Training using a Python package.
+- Training using a custom training image.
+- Laying out a training package.
+
+
+[Get started with Vertex AI Training for Pytorch](community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Training` for training a Pytorch custom model.
+
+The steps performed include:
+
+- Single node training using a Python package.
+- Report accuracy when hyperparameter tuning.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Create a `Vertex AI Model` resource.
+
+[Get started with Vertex AI Distributed Training](community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Distributed Training` for when training with `Vertex AI`.
+
+The steps performed include:
+
+- `MirroredStrategy`: Train on a single VM with multiple GPUs.
+- `MultiWorkerMirroredStrategy`: Train on multiple VMs with automatic setup of replicas.
+- `MultiWorkerMirroredStrategy`: Train on multiple VMs with fine grain control of replicas.
+- `ReductionServer`: Train on multiple VMS and sync updates across VMS with `Vertex AI Reduction Server`.
+- `TPUTraining`: Train with multiple Cloud TPUs.
 
 ### E2E Stage Example
 

notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb

@@ -78,6 +78,7 @@
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
         "- `AutoML Training`\n",
+        "- `Vertex AI Datasets`\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -498,7 +499,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "id": "import_aip:mbsdk"
       },
@@ -568,6 +569,142 @@
         "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_preparation:image,u_dataset"
+      },
+      "source": [
+        "### Data preparation\n",
+        "\n",
+        "The Vertex `Dataset` resource for images has some requirements for your data:\n",
+        "\n",
+        "- Images must be stored in a Cloud Storage bucket.\n",
+        "- Each image file must be in an image format (PNG, JPEG, BMP, ...).\n",
+        "- There must be an index file stored in your Cloud Storage bucket that contains the path and label for each image.\n",
+        "- The index file must be either CSV or JSONL.\n",
+        "\n",
+        "Learn more about [Preparing image data](https://cloud.google.com/vertex-ai/docs/datasets/prepare-image)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_import_format:icn,u_dataset,csv"
+      },
+      "source": [
+        "#### CSV\n",
+        "\n",
+        "For image classification, the CSV index file has the requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the Cloud Storage path to the image.\n",
+        "- Second column is the label.\n",
+        "- Any remaining columns are additional labels for multi-label image classification.\n",
+        "\n",
+        "For image object detection, the CSV index file has the requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the Cloud Storage path to the image.\n",
+        "- Second column is the label.\n",
+        "- Third/Fourth columns are the upper left corner of bounding box. Coordinates are normalized, between 0 and 1.\n",
+        "- Fifth/Sixth/Seventh columns are not used and should be 0.\n",
+        "- Eighth/Ninth columns are the lower right corner of the bounding box.\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each row may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "The `ml_use` assignment is specified by prepending a column for specifying the assignment -- as the first column. The value may be one of: training, test, or validation."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_import_format:isg,u_dataset,jsonl"
+      },
+      "source": [
+        "#### JSONL\n",
+        "\n",
+        "For image classification, the JSONL index file has the requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `image_gcs_uri` is the Cloud Storage path to the image.\n",
+        "- The key/value pair `display_name` is the label for the image.\n",
+        "\n",
+        "    { 'image_gcs_uri': image, \n",
+        "      'classification_annotations': \n",
+        "          { 'display_name': label\n",
+        "          }\n",
+        "    }\n",
+        "    \n",
+        "For multi-label, the labels are specified as a list of `display_name` key/value pairs:\n",
+        "\n",
+        "    { 'image_gcs_uri': image, \n",
+        "      'classification_annotations': [\n",
+        "          { 'display_name': label1\n",
+        "          },\n",
+        "          { 'display_name': labelN\n",
+        "          },\n",
+        "       ]\n",
+        "    }\n",
+        "    \n",
+        "For object detection, the JSONL index file has the requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `image_gcs_uri` is the Cloud Storage path to the image.\n",
+        "- The key/value pair `bounding_box_annotations` is a list of:\n",
+        "    - `display_name`: The label of the object\n",
+        "    - `x_min`, `y_min`, `x_max`, `y_max`: The coordinates for the bounding box\n",
+        "\n",
+        "{\n",
+        "  \"image_gcs_uri\": image,\n",
+        "  \"bounding_box_annotations\": [\n",
+        "    {\n",
+        "      \"display name\": label,\n",
+        "      \"x_min\": \"X_MIN\",\n",
+        "      \"y_min\": \"Y_MIN\",\n",
+        "      \"x_max\": \"X_MAX\",\n",
+        "      \"y_max\": \"Y_MAX\"\n",
+        "      }\n",
+        "    },\n",
+        "    {\n",
+        "      \"displayName\": \"OBJECT2_LABEL\",\n",
+        "      \"x_min\": \"X_MIN\",\n",
+        "      \"y_min\": \"Y_MIN\",\n",
+        "      \"x_max\": \"X_MAX\",\n",
+        "      \"y_max\": \"Y_MAX\"\n",
+        "    }\n",
+        "  ]\n",
+        "}\n",
+        "\n",
+        "\n",
+        "For image segmentation, the JSONL index file has the requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `image_gcs_uri` is the Cloud Storage path to the image.\n",
+        "- The key/value pair `category_mask_uri`  is the Cloud Storage path to the mask image in PNG format.\n",
+        "- The key/value pair `'annotation_spec_colors'` is a list mapping mask colors to a label.\n",
+        "  - The key/value pair pair `display_name` is the label for the pixel color mask.\n",
+        "  - The key/value pair pair `color` are the RGB normalized pixel values (between 0 and 1) of the mask for the corresponding label.\n",
+        "\n",
+        "    { 'image_gcs_uri': image, \n",
+        "      'segmentation_annotations': { 'category_mask_uri': mask_image, 'annotation_spec_colors' : [ \n",
+        "          { 'display_name': label, 'color': {\"red\": value, \"blue\", value, \"green\": value} }, ...\n",
+        "      ] \n",
+        "    }\n",
+        "    \n",
+        "##### ML_USE\n",
+        "\n",
+        "Each JSONL object may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "\"data_item_resource_labels\": {\n",
+        "      \"aiplatform.googleapis.com/ml_use\": \"training|test|validation\"\n",
+        "    }\n",
+        "\n",
+        "*Note*: The dictionary key fields may alternatively be in camelCase. For example, 'image_gcs_uri' can also be 'imageGcsUri'."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1068,6 +1205,42 @@
         "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_preparation:tabular,u_dataset"
+      },
+      "source": [
+        "### Data preparation\n",
+        "\n",
+        "The Vertex AI `Dataset` resource for tabular has a couple of requirements for your tabular data.\n",
+        "\n",
+        "- Must be in a CSV file or a BigQuery table.\n",
+        "\n",
+        "Learn more about [Preparing tabular data](https://cloud.google.com/vertex-ai/docs/datasets/prepare-tabular)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_import_format:lbn,u_dataset,csv"
+      },
+      "source": [
+        "#### CSV\n",
+        "\n",
+        "For tabular models, the CSV file has a few requirements:\n",
+        "\n",
+        "- The first row must be the heading -- note how this is different from Image, Text and Video where the requirement is no heading.\n",
+        "- All but one column are features.\n",
+        "- One column is the label, which you will specify when you subsequently create the training pipeline.\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each row may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "The `ml_use` assignment is specified by prepending a column for specifying the assignment -- as the first column. The value may be one of: training, test, or validation."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1427,6 +1600,155 @@
         "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_preparation:text,u_dataset"
+      },
+      "source": [
+        "### Data preparation\n",
+        "\n",
+        "The Vertex AI `Dataset` resource for text has a couple of requirements for your text data.\n",
+        "\n",
+        "- Text examples must be stored in a CSV or JSONL file.\n",
+        "\n",
+        "Learn more about [Preparing text data](https://cloud.google.com/vertex-ai/docs/datasets/prepare-text)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_import_format:tcn,u_dataset,csv"
+      },
+      "source": [
+        "#### CSV\n",
+        "\n",
+        "For text classification, the CSV file has a few requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the text example or Cloud Storage path to text file (.txt suffix).\n",
+        "- Second column the label.\n",
+        "- Any remaining columns are additional labels for multi-label text classification.\n",
+        "\n",
+        "For text sentiment analysis, the CSV file has a few requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the text example or Cloud Storage path to text file (.txt suffix).\n",
+        "- Second column is the sentiment value.\n",
+        "- Third column is the maximum possible sentiment value.\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each row may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "The `ml_use` assignment is specified by prepending a column for specifying the assignment -- as the first column. The value may be one of: training, test, or validation."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "766c838de8a0"
+      },
+      "source": [
+        "#### JSONL \n",
+        "\n",
+        "For text classification, the JSONL file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `text_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "- The key/value pair `text_content` is the alternate way of specifying the text as inlined.\n",
+        "- The key/value pair `display_name` is the label for the text.\n",
+        "\n",
+        "{\n",
+        "  \"classification_annotation\": {\n",
+        "    \"display_name\": label\n",
+        "  },\n",
+        "  \"text_content\": text\n",
+        "}\n",
+        "{\n",
+        "  \"classification_annotation\": {\n",
+        "    \"display_name\": label\n",
+        "  },\n",
+        "  \"text_gcs_uri\": \"gcs_uri_to_file\"\n",
+        "}\n",
+        "\n",
+        "    \n",
+        "For multi-label, the labels are specified as a list of `display_name` key/value pairs:\n",
+        "\n",
+        "      'classification_annotations': [\n",
+        "          { 'display_name': label1\n",
+        "          },\n",
+        "          { 'display_name': labelN\n",
+        "          },\n",
+        "       ]\n",
+        "\n",
+        "For text sentiment analysis, the JSONL file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `text_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "- The key/value pair `text_content` is the alternate way of specifying the text as inlined.\n",
+        "- The key/value pair `sentiment` is the sentiment value as an integer value greater than 0.\n",
+        "- The key/value pair `sentiment_max`is the maximum possible value for the sentiment.\n",
+        "\n",
+        "{\n",
+        "  \"sentiment_annotation\": {\n",
+        "    \"sentiment\": number,\n",
+        "    \"sentiment_max\": number\n",
+        "  },\n",
+        "  \"text_content\": text,\n",
+        "}\n",
+        "{\n",
+        "  \"sentiment_annotation\": {\n",
+        "    \"sentiment\": number,\n",
+        "    \"sentiment_max\": number\n",
+        "  },\n",
+        "  \"text_gcs_uri\": \"gcs_uri_to_file\"\n",
+        "}\n",
+        "\n",
+        "\n",
+        "For text entity extraction, the JSONL file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `text_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "- The key/value pair `text_content` is the alternate way of specifying the text as inlined.\n",
+        "- The key/value pair `start_offset` is the character offset of the start of the text.\n",
+        "- The key/value pair `end_offset` is the character offset of the end of the text.\n",
+        "- The key/value pair `display_name` is the label for the text.\n",
+        "\n",
+        "{\n",
+        "    \"text_segment_annotations\": [\n",
+        "      {\n",
+        "        \"start_offset\":number,\n",
+        "        \"end_offset\":number,\n",
+        "        \"display_name\": label\n",
+        "      },\n",
+        "      ...\n",
+        "    ],\n",
+        "    \"textContent\": \"inline_text\"\n",
+        "}\n",
+        "{\n",
+        "    \"textSegmentAnnotations\": [\n",
+        "      {\n",
+        "        \"start_offset\": number,\n",
+        "        \"end_offset\": number,\n",
+        "        \"displayName\": label\n",
+        "      },\n",
+        "      ...\n",
+        "    ],\n",
+        "    \"text_gcs_uri\": \"gcs_uri_to_file\"\n",
+        "}\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each JSONL object may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "\"data_item_resource_labels\": {\n",
+        "      \"aiplatform.googleapis.com/ml_use\": \"training|test|validation\"\n",
+        "    }\n",
+        "\n",
+        "*Note*: The dictionary key fields may alternatively be in camelCase. For example, 'text_gcs_uri' can also be 'textGcsUri'."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1749,6 +2071,144 @@
         "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "data_preparation:text,u_dataset"
+      },
+      "source": [
+        "### Data preparation\n",
+        "\n",
+        "The Vertex AI `Dataset` resource for text has a couple of requirements for your text data.\n",
+        "\n",
+        "- Text examples must be stored in a CSV or JSONL file.\n",
+        "\n",
+        "Learn more about [Preparing video data](https://cloud.google.com/vertex-ai/docs/datasets/prepare-video)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "427212b48840"
+      },
+      "source": [
+        "#### CSV\n",
+        "\n",
+        "For video classification, the CSV file has a few requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the Cloud Storage path to video file.\n",
+        "- Second column the label.\n",
+        "- Third column is the start time (seconds) in the video to classify.\n",
+        "- Fourth column is the end time (seconds) in the video to classify.\n",
+        "\n",
+        "For multi-label classification, each label is a separate row entry.\n",
+        "\n",
+        "For video object tracking, the CSV file has a few requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- First column is the Cloud Storage path to video file.\n",
+        "- Second column the label.\n",
+        "- Third column is unused (blank).\n",
+        "- Fourth column is the start time (seconds) in the video to start tracking the object.\n",
+        "- The fifth through eighth columns are the vertices of the object to track.\n",
+        "    - x_min\n",
+        "    - y_min\n",
+        "    - x_max\n",
+        "    - y_max\n",
+        "    \n",
+        "For action recognition, the CSV file has a few requirements:\n",
+        "\n",
+        "- No heading.\n",
+        "- Each row can be one of the following four formats:\n",
+        "\n",
+        "VIDEO_URI, TIME_SEGMENT_START, TIME_SEGMENT_END, LABEL, ANNOTATION_FRAME_TIMESTAMP\n",
+        "\n",
+        "VIDEO_URI, , , LABEL, ANNOTATION_FRAME_TIMESTAMP\n",
+        "\n",
+        "VIDEO_URI, TIME_SEGMENT_START, TIME_SEGMENT_END, LABEL, ANNOTATION_SEGMENT_START, ANNOTATION_SEGMENT_END\n",
+        "\n",
+        "VIDEO_URI, , , LABEL, ANNOTATION_SEGMENT_START, ANNOTATION_SEGMENT_END\n",
+        "\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each row may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/10/10.\n",
+        "\n",
+        "The `ml_use` assignment is specified by prepending a column for specifying the assignment -- as the first column. The value may be one of: training, or test."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "461301339727"
+      },
+      "source": [
+        "#### JSONL\n",
+        "\n",
+        "For video classification, the CSV file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `video_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "- The key/value pair `display_name` is the label for the text.\n",
+        "- The key/value pair `start_time` is the start time (seconds) for classifying.\n",
+        "- The key/value pair `end_time` is the end time (seconds) for classifying.\n",
+        "\n",
+        "\n",
+        "    {\n",
+        "        \"video_gcs_uri\": video,\n",
+        "        \"time_segment_annotations\": [{\n",
+        "            \"display_name\": label,\n",
+        "            \"start_time\": \"start_time_of_segment\",\n",
+        "            \"end_time\": \"end_time_of_segment\"\n",
+        "        }]\n",
+        "    }\n",
+        "\n",
+        "For video object tracking, the CSV file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `video_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "\n",
+        "    {\n",
+        "        \"video_gcs_uri\": video,\n",
+        "        \"temporal_bounding_box_annotations\": [{\n",
+        "            \"display_name\": label,\n",
+        "            \"x_min\": \"leftmost_coordinate_of_the_bounding box\",\n",
+        "            \"x_max\": \"rightmost_coordinate_of_the_bounding box\",\n",
+        "            \"y_min\": \"topmost_coordinate_of_the_bounding box\",\n",
+        "            \"y_max\": \"bottommost_coordinate_of_the_bounding box\",\n",
+        "            \"time_offset\": \"timeframe_object-detected\"\n",
+        "        }]\n",
+        "    }\n",
+        "\n",
+        "For video action recognition, the CSV file has a few requirements:\n",
+        "\n",
+        "- Each data item is a separate JSON object, on a separate line.\n",
+        "- The key/value pair `video_gcs_uri` is the Cloud Storage path to the text file.\n",
+        "\n",
+        "    {\n",
+        "      \"video_gcs_uri': video,\n",
+        "      \"time_segments\": [{\n",
+        "        \"start_time\": \"start_time_of_fully_annotated_segment\",\n",
+        "        \"end_time\": \"end_time_of_segment\"}],\n",
+        "      \"time_segment_annotations\": [{\n",
+        "        \"display_name\": label,\n",
+        "        \"start_time\": \"start_time_of_segment\",\n",
+        "        \"end_time\": \"end_time_of_segment\"\n",
+        "      }]\n",
+        "    }\n",
+        "\n",
+        "##### ML_USE\n",
+        "\n",
+        "Each JSONL object may additionally specify which split to assign the data item to when the dataset is split for training; otherwise, the dataset will be randomly split: 80/20.\n",
+        "\n",
+        "\"data_item_resource_labels\": {\n",
+        "      \"aiplatform.googleapis.com/ml_use\": \"training|test\"\n",
+        "    }\n",
+        "\n",
+        "*Note*: The dictionary key fields may alternatively be in camelCase. For example, 'video_gcs_uri' can also be 'videoGcsUri'."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb

@@ -73,7 +73,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `BigQueryML` (BQML) for training with `Vertex AI`.\n",
+        "In this tutorial, you learn how to use `BigQueryML` for training with `Vertex AI`.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -84,12 +84,12 @@
         "The steps performed include:\n",
         "\n",
         "- Create a local BigQuery table in your project\n",
-        "- Train a BQML model\n",
-        "- Evaluate the BQML model\n",
-        "- Export the BQML model as a cloud model\n",
+        "- Train a BigQuery ML model\n",
+        "- Evaluate the BigQuery ML model\n",
+        "- Export the BigQuery ML model as a cloud model\n",
         "- Upload the exported model as a `Vertex AI Model` resource\n",
-        "- Hyperparameter tune a BQML model with `Vertex AI Vizier`\n",
-        "- Automatically register a BQML model to `Vertex AI Model Registry`"
+        "- Hyperparameter tune a BigQuery ML model with `Vertex AI Vizier`\n",
+        "- Automatically register a BigQuery ML model to `Vertex AI Model Registry`"
       ]
     },
     {
@@ -749,9 +749,9 @@
         "id": "bqml_create_model"
       },
       "source": [
-        "### Train BQML model\n",
+        "### Train BigQuery ML model\n",
         "\n",
-        "Next, you create and train a BQML tabular classification model from the public dataset penguins and store the model in your project using the `CREATE MODEL` statement. The model configuration is specified in the `OPTIONS` statement as follows:\n",
+        "Next, you create and train a BigQuery ML tabular classification model from the public dataset penguins and store the model in your project using the `CREATE MODEL` statement. The model configuration is specified in the `OPTIONS` statement as follows:\n",
         "\n",
         "- `model_type`: The type and archictecture of tabular model to train, e.g., DNN classification.\n",
         "- `labels`: The column which are the labels.\n",
@@ -800,9 +800,9 @@
         "id": "bqml_eval_model"
       },
       "source": [
-        "### Evaluate the trained BQML model\n",
+        "### Evaluate the trained BigQuery ML model\n",
         "\n",
-        "Next, retrieve the model evaluation for the trained BQML model.\n",
+        "Next, retrieve the model evaluation for the trained BigQuery ML model.\n",
         "\n",
         "Learn more about [The ML.EVALUATE function](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate)."
       ]
@@ -833,9 +833,9 @@
         "id": "bqml_export_model"
       },
       "source": [
-        "### Export the model from BQML\n",
+        "### Export the model from BigQuery ML\n",
         "\n",
-        "The model you trained in BQML is a TensorFlow model. Next, you export the TensorFlow model artifacts in TF.SavedModel format."
+        "The model you trained in BigQuery ML is a TensorFlow model. Next, you export the TensorFlow model artifacts in TF.SavedModel format."
       ]
     },
     {
@@ -1028,9 +1028,9 @@
         "id": "bqml_create_model:vizier"
       },
       "source": [
-        "### Hyperparameter Tune and train a BQML model\n",
+        "### Hyperparameter Tune and train a BigQuery ML model\n",
         "\n",
-        "Next, you train a BQML tabular classification model with hyperparameter tuning using the `Vertex AI Vizier` service. The hyperparameter settings are specified in the `OPTIONS` statement as follows:\n",
+        "Next, you train a BigQuery ML tabular classification model with hyperparameter tuning using the `Vertex AI Vizier` service. The hyperparameter settings are specified in the `OPTIONS` statement as follows:\n",
         "\n",
         "- `HPARAM_TUNING_ALGORITHM`: The algorithm for selecting the next trial parameters.\n",
         "- `num_trials`: The number of trials.\n",
@@ -1083,9 +1083,9 @@
         "id": "bqml_eval_model"
       },
       "source": [
-        "### Evaluate the BQML trained model\n",
+        "### Evaluate the BigQuery ML trained model\n",
         "\n",
-        "Next, retrieve the model evaluation results for the trained BQML model.\n",
+        "Next, retrieve the model evaluation results for the trained BigQuery ML model.\n",
         "\n",
         "Learn more about [The ML.EVALUATE function](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate)."
       ]
@@ -1142,9 +1142,9 @@
         "id": "bqml_create_model:xai"
       },
       "source": [
-        "### Train a BQML model with Explainability\n",
+        "### Train a BigQuery ML model with Explainability\n",
         "\n",
-        "Next, you train the same BQML model, but this time you enable Vertex AI Explainability on the model predictions by adding the option:\n",
+        "Next, you train the same BigQuery ML model, but this time you enable Vertex AI Explainability on the model predictions by adding the option:\n",
         "\n",
         "- `ENABLE_GLOBAL_EXPLAIN`"
       ]

notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb

@@ -87,7 +87,7 @@
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
         "- `Vertex AI Experiments`\n",
-        "- `Vertex AI ML Metadata`\n",
+        "- `Vertex ML Metadata`\n",
         "- `Vertex AI Training`\n",
         "\n",
         "The steps performed include:\n",

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.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/notebook_template.ipynb\">\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_vertex_tensorboard.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/community/ml_ops/stage2/get_started_vertex_training_lightgbm.ipynb

@@ -48,7 +48,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_lightgbm.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_lightgbm.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_vertex_training_pytorch.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training for Pytorch\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training for PyTorch\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -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/notebook_template.ipynb\">\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_vertex_training_pytorch.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",
@@ -62,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for Pytorch."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for PyTorch."
       ]
     },
     {
@@ -73,7 +73,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Vertex AI Training` for training a Pytorch custom model.\n",
+        "In this tutorial, you learn how to use `Vertex AI Training` for training a PyTorch custom model.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -97,7 +97,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [CIFAR10 dataset](https://pytorch.org/vision/stable/datasets.html#cifar) from [Pytorch Datasets](https://pytorch.org/vision/stable/datasets.html). The version of the dataset is built into TensorFlow. The trained model predicts which type of class an image is from ten classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, or truck."
+        "The dataset used for this tutorial is the [CIFAR10 dataset](https://pytorch.org/vision/stable/datasets.html#cifar) from [PyTorch Datasets](https://pytorch.org/vision/stable/datasets.html). The version of the dataset is built into TensorFlow. The trained model predicts which type of class an image is from ten classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, or truck."
       ]
     },
     {
@@ -672,17 +672,17 @@
         "id": "pytorch_intro"
       },
       "source": [
-        "## Introduction to Pytorch training\n",
+        "## Introduction to PyTorch training\n",
         "\n",
-        "The Pytorch package supports both single node and distributed model training.\n",
+        "The PyTorch package supports both single node and distributed model training.\n",
         "\n",
-        "Once you have trained a Pytorch model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource.\n",
-        "The Pytorch package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
+        "Once you have trained a PyTorch model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource.\n",
+        "The PyTorch package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
         "\n",
         "1. Save the in-memory model to the local filesystem (e.g., model.pth).\n",
         "2. Use gsutil to copy the local copy to the specified Cloud Storage location.\n",
         "\n",
-        "*Note*: You can do hyperparameter tuning with a Pytorch model."
+        "*Note*: You can do hyperparameter tuning with a PyTorch model."
       ]
     },
     {
@@ -1069,9 +1069,9 @@
         "id": "docker_write,prediction,pytorch"
       },
       "source": [
-        "### Make Pytorch container for prediction\n",
+        "### Make PyTorch container for prediction\n",
         "\n",
-        "Currently, Vertex AI does not have a predefined container for making predictions with a deployed Pytorch model. No problem, you can assemble your own custom container. Typically, one would base the container on the `Torch Server`. For demonstration purpose, you build a placeholder container (not complete) that includes the latest `Torch Server` image, and push it to the `Container Registry`."
+        "Currently, Vertex AI does not have a predefined container for making predictions with a deployed PyTorch model. No problem, you can assemble your own custom container. Typically, one would base the container on the `Torch Server`. For demonstration purpose, you build a placeholder container (not complete) that includes the latest `Torch Server` image, and push it to the `Container Registry`."
       ]
     },
     {

notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb

@@ -43,7 +43,7 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.sandbox.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.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",
@@ -109,7 +109,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is [California Housing Dataset](https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html). The data contains information from the 1990 California census. The data set is publicly available from Google Cloud Storage at `gs://cloud-samples-data/ai-platform-unified/datasets/tabular/california-housing-tabular-regression.csv`. The dataset is used to train a Random Forest regressor to predict a median housing price, given a longitude and lattitude along with data from the corresponding census block group. A block group is the smallest geographical unit for which the U.S. Census Bureau publishes sample data (a block group typically has a population of 600 to 3,000 people).\n"
+        "The dataset used for this tutorial is [California Housing Dataset](https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html). The data contains information from the 1990 California census. The data set is publicly available from Cloud Storage at `gs://cloud-samples-data/ai-platform-unified/datasets/tabular/california-housing-tabular-regression.csv`. The dataset is used to train a Random Forest regressor to predict a median housing price, given a longitude and lattitude along with data from the corresponding census block group. A block group is the smallest geographical unit for which the U.S. Census Bureau publishes sample data (a block group typically has a population of 600 to 3,000 people).\n"
       ]
     },
     {

notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb

@@ -44,7 +44,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\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_vertex_training_sklearn.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/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb

@@ -297,25 +297,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
+        "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### 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 timestamp for each instance session, and append the timestamp 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 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": "JYtXOocrox9Q"
+        "id": "4e166d927e36"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\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()"
       ]
     },
     {
@@ -362,12 +369,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -402,7 +408,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -413,8 +420,9 @@
       },
       "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"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -749,6 +757,7 @@
         "import hypertune\n",
         "import argparse\n",
         "import logging\n",
+        "import numpy as np\n",
         "\n",
         "from sklearn.model_selection import train_test_split\n",
         "from sklearn.metrics import accuracy_score\n",
@@ -790,16 +799,23 @@
         "def train_model(dtrain):\n",
         "    logging.info(\"Start training ...\")\n",
         "    # Train XGBoost model\n",
-        "    model = xgb.train({}, dtrain, num_boost_round=args.boost_rounds)\n",
+        "    params = {\n",
+        "        'objective': 'multi:softprob',\n",
+        "        'num_class': 3\n",
+        "    }\n",
+        "    model = xgb.train(params, dtrain, num_boost_round=args.boost_rounds)\n",
         "    logging.info(\"Training completed\")\n",
         "    return model\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",
+        "    predictions = [np.around(value) for value in pred]\n",
         "    # evaluate predictions\n",
-        "    accuracy = accuracy_score(test_labels, predictions)\n",
+        "    try:\n",
+        "        accuracy = accuracy_score(test_labels, predictions)\n",
+        "    except:\n",
+        "        accuracy = 0.0\n",
         "    logging.info(f\"Evaluation completed with model accuracy: {accuracy}\")\n",
         "\n",
         "    # report metric for hyperparameter tuning\n",
@@ -893,7 +909,7 @@
       },
       "outputs": [],
       "source": [
-        "DISPLAY_NAME = \"iris_\" + TIMESTAMP\n",
+        "DISPLAY_NAME = \"iris_\" + UUID\n",
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
@@ -932,7 +948,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, UUID)\n",
         "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
         "\n",
         "ROUNDS = 20\n",
@@ -983,7 +999,7 @@
       "source": [
         "if TRAIN_GPU:\n",
         "    model = job.run(\n",
-        "        model_display_name=\"iris_\" + TIMESTAMP,\n",
+        "        model_display_name=\"iris_\" + UUID,\n",
         "        args=CMDARGS,\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
@@ -994,7 +1010,7 @@
         "    )\n",
         "else:\n",
         "    model = job.run(\n",
-        "        model_display_name=\"iris_\" + TIMESTAMP,\n",
+        "        model_display_name=\"iris_\" + UUID,\n",
         "        args=CMDARGS,\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
@@ -1095,7 +1111,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = False\n",
+        "delete_bucket = True\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"

notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb

@@ -84,7 +84,8 @@
         "The steps performed include:\n",
         "\n",
         "- Hyperparameter tuning with Random algorithm.\n",
-        "- Hyperparameter tuning with Vizier (Bayesian) algorithm."
+        "- Hyperparameter tuning with Vizier (Bayesian) algorithm.\n",
+        "- Suggesting trials and updating results for Vizier study"
       ]
     },
     {
@@ -187,7 +188,8 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q"
+        "! pip3 install --upgrade $USER_FLAG -q google-cloud-aiplatform \\\n",
+        "                                       google-vizier==0.0.4"
       ]
     },
     {
@@ -329,25 +331,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
+        "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### 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 timestamp for each instance session, and append the timestamp 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 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"
+        "id": "4e166d927e36"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\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()"
       ]
     },
     {
@@ -358,7 +367,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\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",
@@ -446,7 +455,7 @@
       "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"
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -509,7 +518,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "from google.cloud.aiplatform.vizier import Study, pyvizier"
       ]
     },
     {
@@ -534,35 +544,6 @@
         "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "aip_constants"
-      },
-      "source": [
-        "#### Vertex AI constants\n",
-        "\n",
-        "Setup up the following constants for Vertex AI:\n",
-        "\n",
-        "- `API_ENDPOINT`: The Vertex AI API service endpoint for `Dataset`, `Model`, `Job`, `Pipeline` and `Endpoint` services.\n",
-        "- `PARENT`: The Vertex AI location root path for `Dataset`, `Model`, `Job`, `Pipeline` and `Endpoint` resources."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "aip_constants"
-      },
-      "outputs": [],
-      "source": [
-        "# API service endpoint\n",
-        "API_ENDPOINT = \"{}-aiplatform.googleapis.com\".format(REGION)\n",
-        "\n",
-        "# Vertex location root path for your dataset, model and endpoint resources\n",
-        "PARENT = \"projects/\" + PROJECT_ID + \"/locations/\" + REGION"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -626,7 +607,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -1031,7 +1012,7 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
+        "JOB_NAME = \"custom_job_\" + UUID\n",
         "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
@@ -1094,9 +1075,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP, worker_pool_specs=worker_pool_spec\n",
-        ")"
+        "job = aip.CustomJob(display_name=\"boston_\" + UUID, worker_pool_specs=worker_pool_spec)"
       ]
     },
     {
@@ -1128,7 +1107,7 @@
         "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
         "\n",
         "hpt_job = aip.HyperparameterTuningJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    custom_job=job,\n",
         "    metric_spec={\n",
         "        \"val_loss\": \"minimize\",\n",
@@ -1309,7 +1288,7 @@
       "outputs": [],
       "source": [
         "job = aip.CustomJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    worker_pool_specs=worker_pool_spec,\n",
         "    base_output_dir=MODEL_DIR,\n",
         ")"
@@ -1344,7 +1323,7 @@
         "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
         "\n",
         "hpt_job = aip.HyperparameterTuningJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    custom_job=job,\n",
         "    metric_spec={\n",
         "        \"val_loss\": \"minimize\",\n",
@@ -1513,22 +1492,25 @@
         "id": "vizier_client"
       },
       "source": [
-        "### Create Vizier client\n",
+        "### Specify the algorithm used to suggest trial parameters\n",
         "\n",
-        "Create a client side connection to the Vertex AI Vizier service."
+        "First, you create a `StudyConfig`, and specify the algorithm to suggest the next trial.\n",
+        "\n",
+        "    GRID_SEARCH: grid search\n",
+        "    RANDOM_SEARCH: random search\n",
+        "    ALGORIGTHM_UNSPECIFIED: Vizier bayesian algorithm"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vizier_client"
+        "id": "d7dd26490358"
       },
       "outputs": [],
       "source": [
-        "vizier_client = aip.gapic.VizierServiceClient(\n",
-        "    client_options=dict(api_endpoint=API_ENDPOINT)\n",
-        ")"
+        "problem = pyvizier.StudyConfig()\n",
+        "problem.algorithm = pyvizier.Algorithm.RANDOM_SEARCH"
       ]
     },
     {
@@ -1543,7 +1525,15 @@
         "\n",
         "In the following example, the goal is to maximize y = x^2 with x in the range of \\[-10. 10\\]. This example has only one parameter and uses an easily calculated function to help demonstrate how to use Vizier.\n",
         "\n",
-        "First, you will create the study using the `create_study()` method."
+        "First, you specify the metrics to minimize or maximize in the study as a list to the property `metric_information`. Then you specify the parameters to the study using the `add_XXX_params()` method for the corresponding data type:\n",
+        "\n",
+        "    - add_bool_param\n",
+        "    - add_categorical_param\n",
+        "    - add_discrete_param\n",
+        "    - add_float_param\n",
+        "    - add_int_param\n",
+        "\n",
+        "You create the study using the `create_or_load()` method."
       ]
     },
     {
@@ -1554,28 +1544,19 @@
       },
       "outputs": [],
       "source": [
-        "STUDY_DISPLAY_NAME = \"xpow2\" + TIMESTAMP\n",
+        "STUDY_DISPLAY_NAME = \"xpow2\" + UUID\n",
         "\n",
-        "param_x = {\n",
-        "    \"parameter_id\": \"x\",\n",
-        "    \"double_value_spec\": {\"min_value\": -10.0, \"max_value\": 10.0},\n",
-        "}\n",
+        "problem.metric_information.append(\n",
+        "    pyvizier.MetricInformation(name=\"y\", goal=pyvizier.ObjectiveMetricGoal.MAXIMIZE)\n",
+        ")\n",
         "\n",
-        "metric_y = {\"metric_id\": \"y\", \"goal\": \"MAXIMIZE\"}\n",
+        "params = problem.search_space.select_root()\n",
+        "params.add_float_param(\"x\", -10.0, 10.0, scale_type=pyvizier.ScaleType.LINEAR)\n",
         "\n",
-        "study = {\n",
-        "    \"display_name\": STUDY_DISPLAY_NAME,\n",
-        "    \"study_spec\": {\n",
-        "        \"algorithm\": \"RANDOM_SEARCH\",\n",
-        "        \"parameters\": [param_x],\n",
-        "        \"metrics\": [metric_y],\n",
-        "    },\n",
-        "}\n",
+        "study = Study.create_or_load(display_name=STUDY_DISPLAY_NAME, problem=problem)\n",
         "\n",
-        "study = vizier_client.create_study(parent=PARENT, study=study)\n",
         "STUDY_NAME = study.name\n",
-        "\n",
-        "print(STUDY_NAME)"
+        "print(\"STUDY_NAME: {}\".format(STUDY_NAME))"
       ]
     },
     {
@@ -1586,9 +1567,7 @@
       "source": [
         "### Get Vizier study\n",
         "\n",
-        "You can get a study using the method `get_study()`, with the following key/value pairs:\n",
-        "\n",
-        "- `name`: The name of the study."
+        "You can get a study using the method `list()`."
       ]
     },
     {
@@ -1599,9 +1578,8 @@
       },
       "outputs": [],
       "source": [
-        "study = vizier_client.get_study({\"name\": STUDY_NAME})\n",
-        "\n",
-        "print(study)"
+        "studies = Study.list()\n",
+        "print(studies[0].gca_resource)"
       ]
     },
     {
@@ -1612,11 +1590,9 @@
       "source": [
         "### Get suggested trial\n",
         "\n",
-        "Next, query the Vizier service for a suggested trial(s) using the method `suggest_trials`, with the following key/value pairs:\n",
+        "Next, query the Vizier service for a suggested trial(s) using the method `suggest()`, with the following key/value pairs:\n",
         "\n",
-        "- `parent`: The name of the study.\n",
-        "- `suggestion_count`: The number of trials to suggest.\n",
-        "- `client_id`: blah\n",
+        "- `count`: The number of trials to suggest.\n",
         "\n",
         "This call is a long running operation. The method `result()` from the response object will wait until the call has completed."
       ]
@@ -1625,18 +1601,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vizier_suggest_trial"
+        "id": "11ff2c4562cb"
       },
       "outputs": [],
       "source": [
         "SUGGEST_COUNT = 1\n",
-        "CLIENT_ID = \"1001\"\n",
         "\n",
-        "response = vizier_client.suggest_trials(\n",
-        "    {\"parent\": STUDY_NAME, \"suggestion_count\": SUGGEST_COUNT, \"client_id\": CLIENT_ID}\n",
-        ")\n",
-        "\n",
-        "trials = response.result().trials\n",
+        "trials = study.suggest(count=SUGGEST_COUNT)\n",
         "\n",
         "print(trials)\n",
         "\n",
@@ -1679,12 +1650,10 @@
       "source": [
         "RESULT = 0.01\n",
         "\n",
-        "vizier_client.add_trial_measurement(\n",
-        "    {\n",
-        "        \"trial_name\": TRIAL_ID,\n",
-        "        \"measurement\": {\"metrics\": [{\"metric_id\": \"y\", \"value\": RESULT}]},\n",
-        "    }\n",
-        ")"
+        "measurement = pyvizier.Measurement()\n",
+        "measurement.metrics[\"y\"] = RESULT\n",
+        "\n",
+        "trials[0].add_measurement(measurement)"
       ]
     },
     {
@@ -1695,7 +1664,7 @@
       "source": [
         "### Delete the Vizier study\n",
         "\n",
-        "The method 'delete_study()' will delete the study."
+        "The method 'delete()' will delete the study."
       ]
     },
     {
@@ -1706,7 +1675,7 @@
       },
       "outputs": [],
       "source": [
-        "vizier_client.delete_study({\"name\": STUDY_NAME})"
+        "study.delete()"
       ]
     },
     {

notebooks/community/ml_ops/stage2/get_started_with_logging.ipynb

@@ -73,7 +73,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use Python and Cloud logging awhen training with `Vertex AI`.\n",
+        "In this tutorial, you learn how to use Python and Cloud logging when training with `Vertex AI`.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",

notebooks/community/ml_ops/stage2/get_started_with_vertex_experiments_autologging_tf.ipynb

@@ -0,0 +1,974 @@
+{
+  "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 TensorFlow 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_tf.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_tf.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_tf.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 a TensorFlow 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": "2739272aae1b"
+      },
+      "source": [
+        "### Model\n",
+        "\n",
+        "The model used for this tutorial is a pretrain TensorFlow model that was trained on the [Boston Housing Prices dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html). The version of the dataset this tutorial is built into TensorFlow. The trained model predicts the median price of a house in units of 1K USD."
+      ]
+    },
+    {
+      "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",
+        "                                             tensorflow==2.5 \\\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 tensorflow as tf"
+      ]
+    },
+    {
+      "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 TensorFlow Keras models\n",
+        "\n",
+        "The code below implements autologging for TensorFlow models using the Keras API.\n",
+        "\n",
+        "- `autologging()`: Initializes the experiment and uses heap injection to replace TF.keras `Sequential` and `Model` symbols on the heap with the redirect wrapper classes `VertexTFSequential` and `VertexTFModel`, respectively.\n",
+        "\n",
+        "- `VertexTFSequential`: A subclass of the tf.keras.Sequential class.\n",
+        "    - `compile()`: overridden method of super class. Automatically logs specified hyperparameters and calls the underlying `compile()` method.\n",
+        "    - `fit()`: overridden method of super class. Automatically logs specified hyperparameters, calls the underlying `fit()` method, and logs the resulting metrics.\n",
+        "    - `evaluate()`: overridden method of super class. Calls the underlying `evaluate()` method, and logs the resulting metrics.\n",
+        "- `VertexTFModel`: A subclass of the tf.keras.Model class."
+      ]
+    },
+    {
+      "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",
+        "\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",
+        "class VertexTFSequential(tf.keras.Sequential):\n",
+        "    \"\"\"\n",
+        "    Sublass of the tensorflow.keras.Sequential model type. Overrides with pass thru of\n",
+        "    underlying super class methods to automatically log parameters/metrics for Vertex AI experiments.\n",
+        "\n",
+        "        compile():\n",
+        "        fit():\n",
+        "        evaluate():\n",
+        "    \"\"\"\n",
+        "\n",
+        "    def __init__(self, layers):\n",
+        "        return super().__init__(layers)\n",
+        "\n",
+        "    def compile(\n",
+        "        self,\n",
+        "        optimizer=\"rmsprop\",\n",
+        "        loss=None,\n",
+        "        metrics=None,\n",
+        "        loss_weights=None,\n",
+        "        weighted_metrics=None,\n",
+        "        run_eagerly=None,\n",
+        "        steps_per_execution=None,\n",
+        "    ):\n",
+        "        try:\n",
+        "            learning_rate = optimizer.learning_rate.numpy()\n",
+        "            aiplatform.log_params({\"train.learning_rate\": float(learning_rate)})\n",
+        "        except:\n",
+        "            pass\n",
+        "        return super().compile(\n",
+        "            loss=loss,\n",
+        "            optimizer=optimizer,\n",
+        "            metrics=metrics,\n",
+        "            loss_weights=loss_weights,\n",
+        "            weighted_metrics=weighted_metrics,\n",
+        "            run_eagerly=run_eagerly,\n",
+        "            steps_per_execution=steps_per_execution,\n",
+        "        )\n",
+        "\n",
+        "    def fit(\n",
+        "        self,\n",
+        "        x=None,\n",
+        "        y=None,\n",
+        "        batch_size=None,\n",
+        "        epochs=1,\n",
+        "        verbose=\"auto\",\n",
+        "        callbacks=None,\n",
+        "        validation_split=0.0,\n",
+        "        validation_data=None,\n",
+        "        shuffle=True,\n",
+        "        class_weight=None,\n",
+        "        sample_weight=None,\n",
+        "        initial_epoch=0,\n",
+        "        steps_per_epoch=None,\n",
+        "        validation_steps=None,\n",
+        "        validation_batch_size=None,\n",
+        "        validation_freq=1,\n",
+        "        max_queue_size=10,\n",
+        "        workers=1,\n",
+        "        use_multiprocessing=False,\n",
+        "    ):\n",
+        "        aiplatform.log_params({\"train.epochs\": int(epochs)})\n",
+        "        if batch_size:\n",
+        "            aiplatform.log_params({\"train.batch_size\": int(batch_size)})\n",
+        "        if steps_per_epoch:\n",
+        "            aiplatform.log_params({\"train.steps\": int(steps_per_epoch)})\n",
+        "\n",
+        "        history = super().fit(\n",
+        "            x=x,\n",
+        "            y=y,\n",
+        "            batch_size=batch_size,\n",
+        "            epochs=epochs,\n",
+        "            verbose=verbose,\n",
+        "            callbacks=callbacks,\n",
+        "            validation_split=validation_split,\n",
+        "            validation_data=validation_data,\n",
+        "            shuffle=shuffle,\n",
+        "            class_weight=class_weight,\n",
+        "            sample_weight=sample_weight,\n",
+        "            initial_epoch=initial_epoch,\n",
+        "            steps_per_epoch=steps_per_epoch,\n",
+        "            validation_steps=validation_steps,\n",
+        "            validation_batch_size=validation_batch_size,\n",
+        "            validation_freq=validation_freq,\n",
+        "            max_queue_size=max_queue_size,\n",
+        "            workers=workers,\n",
+        "            use_multiprocessing=use_multiprocessing,\n",
+        "        )\n",
+        "\n",
+        "        for key, val in history.history.items():\n",
+        "            aiplatform.log_metrics({f\"train.{key}\": val[-1]})\n",
+        "        return history\n",
+        "\n",
+        "    def evaluate(\n",
+        "        self,\n",
+        "        x=None,\n",
+        "        y=None,\n",
+        "        batch_size=None,\n",
+        "        verbose=1,\n",
+        "        sample_weight=None,\n",
+        "        steps=None,\n",
+        "        callbacks=None,\n",
+        "        max_queue_size=10,\n",
+        "        workers=1,\n",
+        "        use_multiprocessing=False,\n",
+        "        return_dict=False,\n",
+        "    ):\n",
+        "\n",
+        "        metrics = super().evaluate(\n",
+        "            x=x,\n",
+        "            y=y,\n",
+        "            batch_size=batch_size,\n",
+        "            verbose=verbose,\n",
+        "            sample_weight=sample_weight,\n",
+        "            steps=steps,\n",
+        "            callbacks=callbacks,\n",
+        "            max_queue_size=max_queue_size,\n",
+        "            workers=workers,\n",
+        "            use_multiprocessing=use_multiprocessing,\n",
+        "            return_dict=return_dict,\n",
+        "        )\n",
+        "\n",
+        "        aiplatform.log_metrics({\"eval.loss\": metrics[0]})\n",
+        "        for _ in range(1, len(metrics)):\n",
+        "            aiplatform.log_metrics({\"eval.metric\": metrics[_]})\n",
+        "        return metrics\n",
+        "\n",
+        "\n",
+        "class VertexTFModel(tf.keras.Model):\n",
+        "    \"\"\"\n",
+        "    Sublass of the tensorflow.keras.Model model type. Overrides with pass thru of\n",
+        "    underlying super class methods to automatically log parameters/metrics for Vertex AI experiments.\n",
+        "\n",
+        "        compile():\n",
+        "        fit():\n",
+        "        evaluate():\n",
+        "    \"\"\"\n",
+        "\n",
+        "    def __init__(self, inputs, outputs):\n",
+        "        return super().__init__(inputs, outputs)\n",
+        "\n",
+        "    def compile(\n",
+        "        self,\n",
+        "        optimizer=\"rmsprop\",\n",
+        "        loss=None,\n",
+        "        metrics=None,\n",
+        "        loss_weights=None,\n",
+        "        weighted_metrics=None,\n",
+        "        run_eagerly=None,\n",
+        "        steps_per_execution=None,\n",
+        "    ):\n",
+        "        try:\n",
+        "            learning_rate = optimizer.learning_rate.numpy()\n",
+        "            aiplatform.log_params({\"train.learning_rate\": float(learning_rate)})\n",
+        "        except:\n",
+        "            pass\n",
+        "        return super().compile(\n",
+        "            loss=loss,\n",
+        "            optimizer=optimizer,\n",
+        "            metrics=metrics,\n",
+        "            loss_weights=loss_weights,\n",
+        "            weighted_metrics=weighted_metrics,\n",
+        "            run_eagerly=run_eagerly,\n",
+        "            steps_per_execution=steps_per_execution,\n",
+        "        )\n",
+        "\n",
+        "    def fit(\n",
+        "        self,\n",
+        "        x=None,\n",
+        "        y=None,\n",
+        "        batch_size=None,\n",
+        "        epochs=1,\n",
+        "        verbose=\"auto\",\n",
+        "        callbacks=None,\n",
+        "        validation_split=0.0,\n",
+        "        validation_data=None,\n",
+        "        shuffle=True,\n",
+        "        class_weight=None,\n",
+        "        sample_weight=None,\n",
+        "        initial_epoch=0,\n",
+        "        steps_per_epoch=None,\n",
+        "        validation_steps=None,\n",
+        "        validation_batch_size=None,\n",
+        "        validation_freq=1,\n",
+        "        max_queue_size=10,\n",
+        "        workers=1,\n",
+        "        use_multiprocessing=False,\n",
+        "    ):\n",
+        "        aiplatform.log_params({\"train.epochs\": int(epochs)})\n",
+        "        if batch_size:\n",
+        "            aiplatform.log_params({\"train.batch_size\": int(batch_size)})\n",
+        "        if steps_per_epoch:\n",
+        "            aiplatform.log_params({\"train.steps\": int(steps_per_epoch)})\n",
+        "\n",
+        "        history = super().fit(\n",
+        "            x=x,\n",
+        "            y=y,\n",
+        "            batch_size=batch_size,\n",
+        "            epochs=epochs,\n",
+        "            verbose=verbose,\n",
+        "            callbacks=callbacks,\n",
+        "            validation_split=validation_split,\n",
+        "            validation_data=validation_data,\n",
+        "            shuffle=shuffle,\n",
+        "            class_weight=class_weight,\n",
+        "            sample_weight=sample_weight,\n",
+        "            initial_epoch=initial_epoch,\n",
+        "            steps_per_epoch=steps_per_epoch,\n",
+        "            validation_steps=validation_steps,\n",
+        "            validation_batch_size=validation_batch_size,\n",
+        "            validation_freq=validation_freq,\n",
+        "            max_queue_size=max_queue_size,\n",
+        "            workers=workers,\n",
+        "            use_multiprocessing=use_multiprocessing,\n",
+        "        )\n",
+        "\n",
+        "        for key, val in history.history.items():\n",
+        "            aiplatform.log_metrics({f\"train.{key}\": val[-1]})\n",
+        "        return history\n",
+        "\n",
+        "    def evaluate(\n",
+        "        self,\n",
+        "        x=None,\n",
+        "        y=None,\n",
+        "        batch_size=None,\n",
+        "        verbose=1,\n",
+        "        sample_weight=None,\n",
+        "        steps=None,\n",
+        "        callbacks=None,\n",
+        "        max_queue_size=10,\n",
+        "        workers=1,\n",
+        "        use_multiprocessing=False,\n",
+        "        return_dict=False,\n",
+        "    ):\n",
+        "\n",
+        "        metrics = super().evaluate(\n",
+        "            x=x,\n",
+        "            y=y,\n",
+        "            batch_size=batch_size,\n",
+        "            verbose=verbose,\n",
+        "            sample_weight=sample_weight,\n",
+        "            steps=steps,\n",
+        "            callbacks=callbacks,\n",
+        "            max_queue_size=max_queue_size,\n",
+        "            workers=workers,\n",
+        "            use_multiprocessing=use_multiprocessing,\n",
+        "            return_dict=return_dict,\n",
+        "        )\n",
+        "\n",
+        "        aiplatform.log_metrics({\"eval.loss\": metrics[0]})\n",
+        "        for _ in range(1, len(metrics)):\n",
+        "            aiplatform.log_metrics({\"eval.metric\": metrics[_]})\n",
+        "        return metrics"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ce76826902c0"
+      },
+      "source": [
+        "### Train the model with Vertex AI Experiments\n",
+        "\n",
+        "In the following code, you build, train and evaluate a TensorFlow 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 initializer `Sequential` will be redirected to `VertexTFSequential` by heap injection. When subsequent calls are made to the compile(), fit() and evaluate() methods, they will be executed as the corresponding `VertexTFSequential` methods."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "427846783ed6"
+      },
+      "outputs": [],
+      "source": [
+        "EXPERIMENT_NAME = f\"myexperiment{UUID}\"\n",
+        "RUN_NAME = \"run-1\"\n",
+        "\n",
+        "\n",
+        "def make_dataset():\n",
+        "\n",
+        "    # Scaling Boston Housing data features\n",
+        "    def scale(feature):\n",
+        "        max = np.max(feature)\n",
+        "        feature = (feature / max).astype(np.float)\n",
+        "        return feature, max\n",
+        "\n",
+        "    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.boston_housing.load_data(\n",
+        "        path=\"boston_housing.npz\", test_split=0.2, seed=113\n",
+        "    )\n",
+        "    params = []\n",
+        "\n",
+        "    for _ in range(13):\n",
+        "        x_train[_], max = scale(x_train[_])\n",
+        "        x_test[_], _ = scale(x_test[_])\n",
+        "        params.append(max)\n",
+        "\n",
+        "    return (x_train, y_train), (x_test, y_test)\n",
+        "\n",
+        "\n",
+        "# Build the Keras model\n",
+        "def build_and_compile_dnn_model(lr):\n",
+        "    model = tf.keras.Sequential(\n",
+        "        [\n",
+        "            tf.keras.layers.Dense(128, activation=\"relu\", input_shape=(13,)),\n",
+        "            tf.keras.layers.Dense(128, activation=\"relu\"),\n",
+        "            tf.keras.layers.Dense(1, activation=\"linear\"),\n",
+        "        ]\n",
+        "    )\n",
+        "\n",
+        "    model.compile(\n",
+        "        loss=\"mse\",\n",
+        "        optimizer=tf.keras.optimizers.RMSprop(learning_rate=lr),\n",
+        "        metrics=[tf.keras.metrics.RootMeanSquaredError()],\n",
+        "    )\n",
+        "    return model\n",
+        "\n",
+        "\n",
+        "# autologging\n",
+        "autolog(experiment=EXPERIMENT_NAME, run=RUN_NAME)\n",
+        "\n",
+        "with aiplatform.start_execution(\n",
+        "    schema_title=\"system.ContainerExecution\", display_name=\"example_training\"\n",
+        ") as execution:\n",
+        "    BATCH_SIZE = 16\n",
+        "\n",
+        "    model = build_and_compile_dnn_model(lr=0.01)\n",
+        "\n",
+        "    # Train the model\n",
+        "    (x_train, y_train), (x_test, y_test) = make_dataset()\n",
+        "    model.fit(x_train, y_train, epochs=10, batch_size=BATCH_SIZE)\n",
+        "\n",
+        "    model.evaluate(x_test, y_test)\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_tf.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb

@@ -116,7 +116,7 @@
         "\n",
         "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://console.cloud.google.com/marketplace/product/global-patents/labeled-patents) from Google Public Data Sets. \n",
         "\n",
-        "This dataset includes data extracted from over 300 patent documents issued in the US and EU. The dataset includes links to Google Cloud Storage blobs for the first page of each patent, in addition to a number of extracted entities. \n",
+        "This dataset includes data extracted from over 300 patent documents issued in the US and EU. The dataset includes links to Cloud Storage blobs for the first page of each patent, in addition to a number of extracted entities. \n",
         "\n",
         "The data is published as a [public dataset](https://cloud.google.com/bigquery/public-data) on `BigQuery`."
       ]

notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb

@@ -39,18 +39,15 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/mlops_experimentation.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://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/mlops_experimentation.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/>"
+        "<br/><br/><br/>\n",
+        "\n",
+        "*Note: This notebook is not supported for execution in Colab*"
       ]
     },
     {
@@ -216,20 +213,18 @@
         "\n",
         "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG -q"
+        "    ! pip3 install -U {USER_FLAG} -q tensorflow==2.5 \\\n",
+        "                                     tensorflow-data-validation==1.2 \\\n",
+        "                                     tensorflow-transform==1.2 \\\n",
+        "                                     tensorflow-io==0.18 \n",
+        "    \n",
+        "    ! pip3 install --upgrade {USER_FLAG} -q google-cloud-aiplatform[tensorboard] \\\n",
+        "                                            google-cloud-pipeline-components \\\n",
+        "                                            google-cloud-bigquery \\\n",
+        "                                            google-cloud-logging \\\n",
+        "                                            apache-beam[gcp] \\\n",
+        "                                            pyarrow \\\n",
+        "                                            cloudml-hypertune"
       ]
     },
     {
@@ -444,12 +439,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",

notebooks/community/ml_ops/stage3/README.md

@@ -33,10 +33,144 @@ The third stage in MLOps is formalization to develop an automated pipeline proce
 
 ### Get Started
 
-[Get started with AutoML Tabular Pipeline Workflows](get_started_with_automl_tabular_pipeline_workflow.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.
+
 The steps performed include:
+
+- Create and register a first version of a model to `Vertex AI Model Registry`.
+- Create and register a second version of a model to `Vertex AI Model Registry`.
+- Updating the model version which is the default (blessed).
+- Deleting a model version.
+- Retraining the next model version.
+
+[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`.
+
+The steps performed include:
+
+- Build an Apache Beam data pipeline.
+- 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](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`.
+
+The steps performed include:
+
+- Create Cloud Composer environment.
+- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
+- Create a `Vertex AI Pipeline` that triggers the Airflow DAG.
+- Execute the `Vertex AI Pipeline`.
+
+[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).
+
+The steps performed include:
+
+- Building KFP lightweight Python function components.
+- Assembling and compiling KFP components into a pipeline.
+- Executing a KFP pipeline using Vertex AI Pipelines.
+- Loading component and pipeline definitions from a source code repository.
+- Building sequential, parallel, multiple output components.
+- Building control flow into pipelines.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training a Vertex AI custom trained model.
+    - Test the serving binary with a batch prediction job.
+    - Deploying a Vertex AI custom trained model.
+- Execute a Vertex AI pipeline.
+- Construct a pipeline for:
+     - Construct a custom training component.
+     - Convert custom training component to CustomTrainingJobOp.
+     - Training a Vertex AI custom trained model using the converted component.
+    - Deploying a Vertex AI custom trained model.
+- Execute a Vertex AI pipeline.
+
+[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. 
+
+
+The steps performed include:
+
+- `DataprocPySparkBatchOp` for running PySpark batch workloads.
+- `DataprocSparkBatchOp` for running Spark batch workloads.
+- `DataprocSparkSqlBatchOp` for running Spark SQL batch workloads.
+- `DataprocSparkRBatchOp` for running SparkR batch workloads.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Hyperparameter tune/train a custom model.
+    - Retrieve the tuned hyperparameter values and metrics to optimize.
+    - If the metrics exceed a specified threshold.
+      - Get the location of the model artifacts for the best tuned model.
+      - Upload the model artifacts to a `Vertex AI Model` resource.
+- Execute a Vertex AI pipeline.
+
+[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:
+
+    - The training job and artifacts are trackable.
+    - Set machine resources, such as machine-type, cpu/gpu, memory, disk, etc.
+
+The steps performed in this tutorial include:
+
+- Create a custom component with a self-contained training job.
+- Execute pipeline using component-level settings for machine resources
+- 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](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`.
+
+The steps performed include:
+
+- Create a TFX e2e pipeline.
+- Execute the pipeline locally.
+- Execute the pipeline on Google Cloud using `Vertex AI Training`
+- Execute the pipeline using `Vertex AI Pipelines`.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training BigQuery ML model.
+    - Evaluating the BigQuery ML model.
+    - Exporting the BigQuery ML model.
+    - Importing the BigQuery ML model to a Vertex AI model.
+    - Deploy the Vertex AI model.
+- Execute a Vertex AI pipeline.
+- Make a prediction with the deployed Vertex AI model.
+
+[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.
+
+The steps performed include:
+
 - Define training specification.
     - Dataset specification
     - Hyperparameter overide specification
@@ -49,162 +183,41 @@ The steps performed include:
 - Deploy exported OSS TF model.
 - Make a prediction.
 
-```
+[Get started with rapid prototyping with AutoML and BigQuery ML](community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb)
 
-[Get started with Vertex AI Model Registry](get_started_with_model_registry.ipynb)
+In this tutorial, you learn how to use `Vertex AI Predictions` for rapid prototyping a model.
 
-```
 The steps performed include:
-- Create and register a first version of a model to `Vertex AI Model Registry`.
-- Create and register a second version of a model to `Vertex AI Model Registry`.
-- Updating the model version which is the default (blessed).
-- Deleting a model version.
-- Retraining the next model version.
-```
 
-[Get started with Dataproc serverless pipeline components](get_started_with_dataproc_serverless_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- `DataprocPySparkBatchOp` for running PySpark batch workloads.
-- `DataprocSparkBatchOp` for running Spark batch workloads.
-- `DataprocSparkSqlBatchOp` for running Spark SQL batch workloads.
-- `DataprocSparkRBatchOp` for running SparkR batch workloads.
-
-```
-
-[Get started with TFX pipelines](get_started_with_tfx_pipeline.ipynb)
-
-```
-The steps performed include:
-- Create a TFX e2e pipeline.
-- Execute the pipeline locally.
-- Execute the pipeline on Google Cloud using `Vertex AI Training`
-- Execute the pipeline using `Vertex AI Pipelines`.
-```
-
-[Get started with Vertex AI Hyperparameter Tuning pipeline components](get_started_with_hpt_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Construct a pipeline for:
-    - Hyperparameter tune/train a custom model.
-    - Retrieve the tuned hyperparameter values and metrics to optimize.
-    - If the metrics exceed a specified threshold.
-      - Get the location of the model artifacts for the best tuned model.
-      - Upload the model artifacts to a `Vertex AI Model` resource.
-- Execute a Vertex AI pipeline.
-
-```
-
-[Get started with Apache Airflow and Vertex AI Pipelines](get_started_with_airflow_and_vertex_pipelines.ipynb)
-
-```
-The steps performed include:
-- Create Cloud Composer environment.
-- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
-- Create a `Vertex AI Pipeline` that triggers the Airflow DAG.
-- Execute the `Vertex AI Pipeline`.
-
-```
-
-[Get started with Vertex AI custom training pipeline components](get_started_with_custom_training_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Construct a pipeline for:
-    - Training a Vertex AI custom trained model.
-    - Test the serving binary with a batch prediction job.
-    - Deploying a Vertex AI custom trained model.
-- Execute a Vertex AI pipeline.
-- Construct a pipeline for:
-     - Construct a custom training component.
-     - Convert custom training component to CustomTrainingJobOp.
-     - Training a Vertex AI custom trained model using the converted component.
-    - Deploying a Vertex AI custom trained model.
-- Execute a Vertex AI pipeline.
-```
-
-[Get started with AutoML pipeline components](get_started_with_automl_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Construct a pipeline for:
-    - Training a Vertex AI AutoML trained model.
-    - Test the serving binary with a batch prediction job.
-    - Deploying a Vertex AI AutoML trained model.
-- Execute a Vertex AI pipeline.
-
-```
-
-[Get started with Kubeflow pipelines](get_started_with_kubeflow_pipelines.ipynb)
-
-```
-The steps performed include:
-- Building KFP lightweight Python function components.
-- Assembling and compiling KFP components into a pipeline.
-- Executing a KFP pipeline using Vertex AI Pipelines.
-- Loading component and pipeline definitions from a source code repository.
-- Building sequential, parallel, multiple output components.
-- Building control flow into pipelines.
-
-```
-
-[Get started with machine management for Vertex AI Pipelines](get_started_with_machine_management.ipynb)
-
-```
-The steps performed in this tutorial include:
-- Create a custom component with a self-contained training job.
-- Execute pipeline using component-level settings for machine resources
-- Convert the self-contained training component into a `Vertex AI CustomJob`.
-- Execute pipeline using customjob-level settings for machine resources 
-
-```
-
-[Get started with BigQuery and TFDV pipeline components](get_started_with_bq_tfdv_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Build and execute a pipeline component for creating a Vertex AI Tabular Dataset from a BigQuery table.
-- Build and execute a pipeline component for generating TFDV statistics and schema from a Vertex AI Tabular Dataset.
-- Execute a Vertex AI pipeline.
-```
-
-[Get started with Dataflow pipeline components](get_started_with_dataflow_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Build an Apache Beam data pipeline.
-- Encapsulate the Apache Beam data pipeline with a Dataflow component in a Vertex AI pipeline.
-- Execute a Vertex AI pipeline.
-```
-
-[Get started with BigQuery ML pipeline components](get_started_with_bqml_pipeline_components.ipynb)
-
-```
-The steps performed include:
-- Construct a pipeline for:
-    - Training BigQuery ML model.
-    - Evaluating the BigQuery ML model.
-    - Exporting the BigQuery ML model.
-    - Importing the BigQuery ML model to a Vertex AI model.
-    - Deploy the Vertex AI model.
-- Execute a Vertex AI pipeline.
-- Make a prediction with the deployed Vertex AI model.
-```
-
-[Get started with rapid prototyping with AutoML and BigQuery ML](get_started_with_rapid_prototyping_bqml_automl.ipynb)
-
-```
-The steps performed include:
 - Creating a BigQuery and Vertex AI training dataset.
 - Training a BigQuery ML and AutoML model.
 - Extracting evaluation metrics from the BigQueryML and AutoML models.
 - Selecting the best trained model.
 - Deploying the best trained model.
 - Testing the deployed model infrastructure.
-```
 
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training a Vertex AI AutoML trained model.
+    - Test the serving binary with a batch prediction job.
+    - Deploying a Vertex AI AutoML trained model.
+- Execute a Vertex AI pipeline.
+
+
+[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.
+
+The steps performed include:
+
+- Build and execute a pipeline component for creating a Vertex AI Tabular Dataset from a BigQuery table.
+- Build and execute a pipeline component for generating TFDV statistics and schema from a Vertex AI Tabular Dataset.
+- Execute a Vertex AI pipeline.
 
 ### E2E Stage Example
 

notebooks/community/ml_ops/stage3/get_started_with_airflow_and_vertex_pipelines.ipynb

@@ -568,7 +568,6 @@
       },
       "outputs": [],
       "source": [
-        "import kfp\n",
         "from google.cloud import aiplatform\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
@@ -1000,11 +999,7 @@
         "    from google.auth.transport.requests import Request\n",
         "    from google.oauth2 import id_token\n",
         "\n",
-        "    IAM_SCOPE = \"https://www.googleapis.com/auth/iam\"\n",
-        "    OAUTH_TOKEN_URI = \"https://www.googleapis.com/oauth2/v4/token\"\n",
-        "\n",
         "    data = '{\"replace_microseconds\":\"false\"}'\n",
-        "    context = None\n",
         "\n",
         "    \"\"\"Makes a POST request to the Composer DAG Trigger API\n",
         "\n",

notebooks/community/ml_ops/stage3/get_started_with_automl_tabular_pipeline_workflow.ipynb

@@ -44,7 +44,7 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_tabular_pipeline_workflow.ipynb\">\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/stage3/get_started_with_automl_tabular_pipeline_workflow.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/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb

@@ -39,9 +39,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
         "<img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> \n",
-        "        Colab logo Run in Colab\n",
+        "        Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",

notebooks/community/ml_ops/stage3/get_started_with_machine_management.ipynb

@@ -81,7 +81,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you convert a self-contained custom training component into a `Vertex AI CustomJob`, whereby:\n",
+        "In this tutorial, you learn how to convert a self-contained custom training component into a `Vertex AI CustomJob`, whereby:\n",
         "\n",
         "    - The training job and artifacts are trackable.\n",
         "    - Set machine resources, such as machine-type, cpu/gpu, memory, disk, etc.\n",
@@ -569,7 +569,6 @@
       "source": [
         "import json\n",
         "\n",
-        "import numpy as np\n",
         "from google.cloud import aiplatform\n",
         "from google_cloud_pipeline_components.v1.custom_job import \\\n",
         "    create_custom_training_job_from_component\n",
@@ -797,7 +796,6 @@
         "    epochs: int,\n",
         ") -> str:\n",
         "    import numpy as np\n",
-        "    import tensorflow as tf\n",
         "\n",
         "    def get_data():\n",
         "        from tensorflow.keras.datasets import mnist\n",
@@ -904,7 +902,7 @@
         "        },\n",
         "    ).after(training_job_task)\n",
         "\n",
-        "    model_upload = ModelUploadOp(\n",
+        "    _ = ModelUploadOp(\n",
         "        project=project,\n",
         "        display_name=\"mnist_model\",\n",
         "        unmanaged_container_model=import_unmanaged_model_task.outputs[\"artifact\"],\n",
@@ -1180,7 +1178,7 @@
         "        },\n",
         "    ).after(training_job_task)\n",
         "\n",
-        "    model_upload = ModelUploadOp(\n",
+        "    _ = ModelUploadOp(\n",
         "        project=project,\n",
         "        display_name=\"mnist_model\",\n",
         "        unmanaged_container_model=import_unmanaged_model_task.outputs[\"artifact\"],\n",

notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb

@@ -60,7 +60,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI Pipelines to rapid prototype a model using both AutoML and BQML, do an evaluation comparison, for a baseline, before progressing to a custom model.\n",
+        "This tutorial demonstrates how to use Vertex AI Pipelines to rapid prototype a model using both AutoML and BigQuery ML, do an evaluation comparison, for a baseline, before progressing to a custom model.\n",
         "\n",
         "<img src=\"https://storage.googleapis.com/rafacarv-public-bucket-do-not-delete/abalone/automl_and_bqml.png\" />"
       ]
@@ -834,7 +834,7 @@
       "source": [
         "### Create component: Split the dataset into train, test and eval\n",
         "\n",
-        "For this pipeline, you set aside a portion of the dataset for test evaluation. While both AutoML and BQML will automatically split then datasets, in this example you will explicitly split the datasets into:\n",
+        "For this pipeline, you set aside a portion of the dataset for test evaluation. While both AutoML and BigQuery ML will automatically split then datasets, in this example you will explicitly split the datasets into:\n",
         "\n",
         "- TRAIN\n",
         "- EVALUATE\n",
@@ -1000,11 +1000,11 @@
         "- Construct the CREATE MODEL query using a static Python function `_create_model_query()`, which runs in the context of the pipeline.\n",
         "- Call the prebuilt component `BigQueryCreateModelOp`, with the constructed query, to train the BigQuery ML model.\n",
         "\n",
-        "For this tutorial, you use a simple linear regression model on BQML. \n",
+        "For this tutorial, you use a simple linear regression model on BigQuery ML. \n",
         "\n",
-        "For a full list of models supported by BQML, look here: [End-to-end user journey for each model](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-e2e-journey).\n",
+        "For a full list of models supported by BigQuery ML, look here: [End-to-end user journey for each model](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-e2e-journey).\n",
         "\n",
-        "As pointed out before, BQML and AutoML use different split terminologies, so we do an adaptation of the <i>split_col</i> column directly on the SELECT portion of the CREATE model query:\n",
+        "As pointed out before, BigQuery ML and AutoML use different split terminologies, so we do an adaptation of the <i>split_col</i> column directly on the SELECT portion of the CREATE model query:\n",
         "\n",
         "> When the value of DATA_SPLIT_METHOD is 'CUSTOM', the corresponding column should be of type BOOL. The rows with TRUE or NULL values are used as evaluation data. Rows with FALSE values are used as training data."
       ]

notebooks/community/ml_ops/stage3/mlops_formalization.ipynb

@@ -658,8 +658,6 @@
       },
       "outputs": [],
       "source": [
-        "from typing import NamedTuple\n",
-        "\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
         "from kfp.v2.dsl import component"
@@ -1866,7 +1864,7 @@
         "        exported_tfrec_prefix=exported_tfrec_prefix,\n",
         "    ).after(dataflow_wait_op)\n",
         "\n",
-        "    dataset_op = gcc_aip.TabularDatasetCreateOp(\n",
+        "    _ = gcc_aip.TabularDatasetCreateOp(\n",
         "        project=project,\n",
         "        display_name=display_name,\n",
         "        bq_source=bq_table,\n",
@@ -2285,7 +2283,7 @@
         "        },\n",
         "    ).after(model_build_op)\n",
         "\n",
-        "    model_upload = ModelUploadOp(\n",
+        "    _ = ModelUploadOp(\n",
         "        project=project,\n",
         "        display_name=display_name,\n",
         "        unmanaged_container_model=import_unmanaged_model_task.outputs[\"artifact\"],\n",
@@ -3205,7 +3203,7 @@
         "\n",
         "    with dsl.Condition(warmup == \"True\", name=\"warmup-model\"):\n",
         "\n",
-        "        warmup_op = gcc_aip.CustomPythonPackageTrainingJobRunOp(\n",
+        "        _ = gcc_aip.CustomPythonPackageTrainingJobRunOp(\n",
         "            project=project,\n",
         "            display_name=display_name,\n",
         "            # Warmup Training\n",
@@ -3249,7 +3247,7 @@
         "            display_name=display_name,\n",
         "        ).after(training_op)\n",
         "\n",
-        "        deploy_op = ModelDeployOp(\n",
+        "        _ = ModelDeployOp(\n",
         "            model=training_op.outputs[\"model\"],\n",
         "            endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "            dedicated_resources_min_replica_count=1,\n",

notebooks/community/ml_ops/stage4/README.md

@@ -42,104 +42,192 @@ This stage may be done entirely by MLOps. We recommend:
 
 ### Get Started
 
-[Get started with Vertex Explainable AI](get_started_with_vertex_xai.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.
+
 The steps performed include:
-- Train an AutoML tabular model.
-    - Do a batch prediction with explanations.
-    - Do an online prediction with explanations.
-- Train an custom TensorFlow tabular model.
-    - Manually set configuration metadata.
-    - Do a batch prediction with explanations.
-    - Do an online prediction with explanations.
-    - Automatically set configuration metadata.
-- Train an custom TensorFlow image model.
-    - Manually set configuration metadata.
-    - Do a batch prediction with explanations.
-    - Do an online prediction with explanations.
-- Train an custom XGBoost tabular model.
-    - Manually set configuration metadata.
-    - Do an online prediction with explanations.
-- Train an custom scikit-learn tabular model.
-    - Manually set configuration metadata.
-    - Do an online prediction with explanations.
 
-```
+- Create and register a first version of a model to `Vertex AI Model Registry`.
+- Create and register a second version of a model to `Vertex AI Model Registry`.
+- Updating the model version which is the default (blessed).
+- Deleting a model version.
+- Retraining the next model version.
 
-[Get started with Google Artifact Registry](get_started_with_google_artifact_registry.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`.
 
-```
 The steps performed include:
-- Creating a private Docker repository.
-- Tagging a container image, specific to the private Docker repository.
-- Pushing a container image to the private Docker repository.
-- Pulling a container image from the private Docker repository.
-- Deleting a private Docker repository.
-```
 
-[Get started with AutoML training and ML Metadata](get_started_with_vertex_ml_metadata_and_automl.ipynb)
+- Build an Apache Beam data pipeline.
+- 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](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`.
 
-```
 The steps performed include:
-- Create a `Dataset` resource.
-- Create a corresponding `google.VertexDataset` artifact.
-- Train a model using `AutoML`.
-- Create a corresponding `google.VertexModel` artifact.
-- Create an `Endpoint` resource.
-- Create a corresponding `google.Endpoint` artifact.
-- Deploy the train model to the `Endpoint`.
-- Create an execution and context for the `AutoML` training job and deployment.
-- Add the corresponding artifacts and context to the execution.
-- Add artifact links (event) to the execution.
-- Display the execution graph.
-```
 
-[Get started with Vertex AI ML Metadata](get_started_with_vertex_ml_metadata.ipynb)
+- Create Cloud Composer environment.
+- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
+- Create a `Vertex AI Pipeline` that triggers the Airflow DAG.
+- Execute the `Vertex AI Pipeline`.
+
+[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).
 
-```
 The steps performed include:
-- Create a `Metadatastore` resource.
-- Create (record)/List an `Artifact`, with artifacts and metadata.
-- Create (record)/List an `Execution`.
-- Create (record)/List a `Context`.
-- Add `Artifact` to `Execution` as events.
-- Add `Execution` and `Artifact` into the `Context`
-- Delete `Artifact`, `Execution` and `Context`.
-- Create and run a `Vertex AI Pipeline` ML workflow to train and deploy a scikit-learn model.
-    - Create custom pipeline components that generate artifacts and metadata.
-    - Compare Vertex AI Pipelines runs.
-    - Trace the lineage for pipeline-generated artifacts.
-    - Query your pipeline run metadata.
-```
 
-[Get started with Vertex AI Model Evaluation](get_started_with_model_evaluation.ipynb)
+- Building KFP lightweight Python function components.
+- Assembling and compiling KFP components into a pipeline.
+- Executing a KFP pipeline using Vertex AI Pipelines.
+- Loading component and pipeline definitions from a source code repository.
+- Building sequential, parallel, multiple output components.
+- Building control flow into pipelines.
+
+[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`.
 
-```
 The steps performed include:
-- Evaluate an `AutoML` model.
-    - Train an `AutoML` image classification model.
-    - Retrieve the default evaluation metrics from training.
-    - Do a batch evaluation for a custom evaluation slice.
-- Evaluate a BigQuery ML model.
-    - Train a `BigQuery ML` tabular classification model.
-    - Retrieve the default evaluation metrics from training.
-    - Do a batch evaluation for a custom evaluation slice.
-- Evaluate a custom model.
-    - Do a batch evaluation for a custom evaluation slice.
-    - Add an evaluation to the `Model Registry` for the `Model` resource.
-- Evaluate an `AutoML` model.
-    - Train an `AutoML` image classification model.
-    - Retrieve the default evaluation metrics from training.
-    - Do a batch evaluation for a custom evaluation slice.
-- Evaluate a BigQuery ML model.
-    - Train a `BigQuery ML` tabular classification model.
-    - Retrieve the default evaluation metrics from training.
-    - Do a batch evaluation for a custom evaluation slice.
-- Evaluate a custom model.
-    - Do a batch evaluation for a custom evaluation slice.
-    - Add an evaluation to the `Model Registry` for the `Model` resource.
-```
+
+- Construct a pipeline for:
+    - Training a Vertex AI custom trained model.
+    - Test the serving binary with a batch prediction job.
+    - Deploying a Vertex AI custom trained model.
+- Execute a Vertex AI pipeline.
+- Construct a pipeline for:
+     - Construct a custom training component.
+     - Convert custom training component to CustomTrainingJobOp.
+     - Training a Vertex AI custom trained model using the converted component.
+    - Deploying a Vertex AI custom trained model.
+- Execute a Vertex AI pipeline.
+
+[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. 
+
+
+The steps performed include:
+
+- `DataprocPySparkBatchOp` for running PySpark batch workloads.
+- `DataprocSparkBatchOp` for running Spark batch workloads.
+- `DataprocSparkSqlBatchOp` for running Spark SQL batch workloads.
+- `DataprocSparkRBatchOp` for running SparkR batch workloads.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Hyperparameter tune/train a custom model.
+    - Retrieve the tuned hyperparameter values and metrics to optimize.
+    - If the metrics exceed a specified threshold.
+      - Get the location of the model artifacts for the best tuned model.
+      - Upload the model artifacts to a `Vertex AI Model` resource.
+- Execute a Vertex AI pipeline.
+
+[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:
+
+    - The training job and artifacts are trackable.
+    - Set machine resources, such as machine-type, cpu/gpu, memory, disk, etc.
+
+The steps performed in this tutorial include:
+
+- Create a custom component with a self-contained training job.
+- Execute pipeline using component-level settings for machine resources
+- 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](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`.
+
+The steps performed include:
+
+- Create a TFX e2e pipeline.
+- Execute the pipeline locally.
+- Execute the pipeline on Google Cloud using `Vertex AI Training`
+- Execute the pipeline using `Vertex AI Pipelines`.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training BigQuery ML model.
+    - Evaluating the BigQuery ML model.
+    - Exporting the BigQuery ML model.
+    - Importing the BigQuery ML model to a Vertex AI model.
+    - Deploy the Vertex AI model.
+- Execute a Vertex AI pipeline.
+- Make a prediction with the deployed Vertex AI model.
+
+[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.
+
+The steps performed include:
+
+- Define training specification.
+    - Dataset specification
+    - Hyperparameter overide specification
+    - machine specifications
+- Construct tabular workflow pipeline.
+- Compile and execute pipeline.
+- View evaluation metrics artifact.
+- Export AutoML model as an OSS TF model.
+- Create `Endpoint` resource.
+- Deploy exported OSS TF model.
+- Make a prediction.
+
+[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.
+
+The steps performed include:
+
+- Creating a BigQuery and Vertex AI training dataset.
+- Training a BigQuery ML and AutoML model.
+- Extracting evaluation metrics from the BigQueryML and AutoML models.
+- Selecting the best trained model.
+- Deploying the best trained model.
+- Testing the deployed model infrastructure.
+
+[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`.
+
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training a Vertex AI AutoML trained model.
+    - Test the serving binary with a batch prediction job.
+    - Deploying a Vertex AI AutoML trained model.
+- Execute a Vertex AI pipeline.
+
+
+[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.
+
+The steps performed include:
+
+- Build and execute a pipeline component for creating a Vertex AI Tabular Dataset from a BigQuery table.
+- Build and execute a pipeline component for generating TFDV statistics and schema from a Vertex AI Tabular Dataset.
+- Execute a Vertex AI pipeline.
+
 ### E2E Stage Example
 
 Stage 4: Evaluation

notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 4 : formalization: get started with Vertex AI ML Metadata\n",
+        "# E2E ML on GCP: MLOps stage 4 : formalization: get started with Vertex ML Metadata\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -62,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 4 : formalization: get started with Vertex AI ML Metadata."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 4 : formalization: get started with Vertex ML Metadata."
       ]
     },
     {
@@ -73,11 +73,11 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Vertex AI ML Metadata`.\n",
+        "In this tutorial, you learn how to use `Vertex ML Metadata`.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
-        "- `Vertex AI ML Metadata`\n",
+        "- `Vertex ML Metadata`\n",
         "- `Vertex AI Pipelines`\n",
         "\n",
         "The steps performed include:\n",
@@ -657,7 +657,7 @@
       "source": [
         "## Introduction to Vertex AI Metadata\n",
         "\n",
-        "The `Vertex AI ML Metadata` service provides you with the ability to record, and subsequently search and analyze, the artifacts and corresponding metadata produced by your ML workflows. For example, during experimentation one might desire to record the location of the model artifacts, as artifacts, and the training hyperparameters and evaluation metrics as the corresponding metadata.\n",
+        "The `Vertex ML Metadata` service provides you with the ability to record, and subsequently search and analyze, the artifacts and corresponding metadata produced by your ML workflows. For example, during experimentation one might desire to record the location of the model artifacts, as artifacts, and the training hyperparameters and evaluation metrics as the corresponding metadata.\n",
         "\n",
         "The service supports recording ML metadata both manually and automatically, with the later occurring when you use Vertex AI Pipelines.\n",
         "\n",
@@ -675,9 +675,9 @@
         "\n",
         "### ML artifact lineage\n",
         "\n",
-        "Vertex AI ML Metadata provides the ability to understand changes in the performance of your machine ML system, and analyze the metadata produced by your ML workflow and the lineage of its artifacts. An artifact's lineage includes all the factors that contributed to its creation, as well as artifacts and metadata that descend from this artifact.\n",
+        "Vertex ML Metadata provides the ability to understand changes in the performance of your machine ML system, and analyze the metadata produced by your ML workflow and the lineage of its artifacts. An artifact's lineage includes all the factors that contributed to its creation, as well as artifacts and metadata that descend from this artifact.\n",
         "\n",
-        "Learn more about [Introduction to Vertex AI ML Metadata ](https://cloud.google.com/vertex-ai/docs/ml-metadata/introduction)"
+        "Learn more about [Introduction to Vertex ML Metadata ](https://cloud.google.com/vertex-ai/docs/ml-metadata/introduction)"
       ]
     },
     {

notebooks/community/ml_ops/stage5/README.md

@@ -25,10 +25,12 @@ The fifth stage in MLOps is deployment to production of the blessed model, which
 ### Get Started
 
 
-[Get started with Vertex AI Endpoints](get_started_with_vertex_endpoints.ipynb)
+[Get started with Vertex AI Endpoints](community/ml_ops/stage5/get_started_with_vertex_endpoints.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Endpoint` resources.
 
-```
 The steps performed include:
+
 - Creating an `Endpoint` resource.
 - List all `Endpoint` resources.
 - List `Endpoint` resources by query filter.
@@ -43,39 +45,13 @@ The steps performed include:
 - Delete an `Endpoint` resource.
 - In pipeline: Create an `Endpoint` resource and deploy an existing `Model` resource to the `Endpoint` resource.
 - In pipeline: Deploy an existing `Model` resource to an existing `Endpoint` resource.
-```
 
-[Get started with configuring autoscaling for Vertex AI Endpoint deployment](get_started_with_autoscaling.ipynb)
+[Get started with Vertex AI Endpoint and shared VM](community/ml_ops/stage5/get_started_with_vertex_endpoint_and_shared_vm.ipynb)
+
+In this tutorial, you learn how to use deployment resource pools for deploying models. A deployment resouce pool provides one with the ability to co-host more than one model on the same (shared) VM.
 
-```
 The steps performed include:
-- Download a pretrained image classification model from TensorFlow Hub.
-- Upload the pretrained model as a `Model` resource.
-- Create an `Endpoint` resource.
-- Deploy `Model` resource for no-scaling (single node).
-- Deploy `Model` resource for manual scaling.
-- Deploy `Model` resource for auto-scaling.
-- Fine-tune scaling thresholds for CPU utilization.
-- Fine-tune scaling thresholds for GPU utilization.
-- Deploy mix of CPU and GPU model instances with auto-scaling to an `Endpoint` resource.
-```
 
-[Get started with Vertex AI Private Endpoints](get_started_with_vertex_private_endpoints.ipynb)
-
-```
-The steps performed include:
-- Creating a `Private Endpoint` resource.
-- Configure a VPC peering connection.
-- Configuring the serving binary of a `Model` resource for deployment to a `Private Endpoint` resource.
-- Deploying a `Model` resource to a `Private Endpoint` resource.
-- Send a prediction request to a `Private Endpoint`
-
-```
-
-[Get started with Vertex AI Endpoint and shared VM](get_started_with_vertex_endpoint_and_shared_vm.ipynb)
-
-```
-The steps performed include:
 - Upload a pre-trained image classification model as a `Model` resource (model A).
 - Upload a pre-trained text sentence encoder model as a `Model` resource (model B).
 - Create a shared VM deployment resource pool.
@@ -85,4 +61,36 @@ The steps performed include:
 - Deploy second model (model B) to second `Endpoint` resource using deployment resource pool.
 - Make a prediction request with first deployed model (model A).
 - Make a prediction request with second deployed model (model B).
-```
+
+[Get started with configuring autoscaling for Vertex AI Endpoint deployment](community/ml_ops/stage5/get_started_with_autoscaling.ipynb)
+
+In this tutorial, you learn how to use fine-tune control auto-scaling configuration when deploying a `Model` resource to an `Endpoint` resource.
+
+The steps performed include:
+
+- Download a pretrained image classification model from TensorFlow Hub.
+- Upload the pretrained model as a `Model` resource.
+- Create an `Endpoint` resource.
+- Deploy `Model` resource for no-scaling (single node).
+- Deploy `Model` resource for manual scaling.
+- Deploy `Model` resource for auto-scaling.
+- Fine-tune scaling thresholds for CPU utilization.
+- Fine-tune scaling thresholds for GPU utilization.
+- Deploy mix of CPU and GPU model instances with auto-scaling to an `Endpoint` resource.
+
+[Get started with Vertex AI Private Endpoints](community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Private Endpoint` resources.
+
+The steps performed include:
+
+- Creating a `Private Endpoint` resource.
+- Configure a VPC peering connection.
+- Configuring the serving binary of a `Model` resource for deployment to a `Private Endpoint` resource.
+- Deploying a `Model` resource to a `Private Endpoint` resource.
+- Send a prediction request to a `Private Endpoint`
+- Enable two additional APIs: Service Networking and Cloud DNS.
+- Add Compute Admin Network role to your (default) service account.
+- Issue two gcloud commands to setup the VPC peering for your service account.
+- There is *currently* no SDK support yet, so private endpoint is created with GAPIC client and has an extra argument for the peering network.
+- To send a request, you can't use SDK/GAPIC since they do a HTTP internet request. Instead, you use curl to send a peer-to-peer request.

notebooks/community/ml_ops/stage6/README.md

@@ -30,48 +30,232 @@ This stage may be done entirely by MLOps. We recommend:
 ### Get Started
 
 
-[Get started with TensorFlow serving functions with Vertex AI Prediction](get_started_with_tf_serving_function.ipynb)
+[Get started with Vertex AI Batch Prediction for AutoML image models](community/ml_ops/stage6/get_started_with_automl_image_model_batch.ipynb)
+
+In this tutorial, you create an AutoML image classification model from a Python script, and then do a batch prediction using the Vertex AI SDK. 
 
-```
 The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` image classification model.
+- Make a batch prediction with JSONL input.
+
+[Get started with Vertex AI Matching Engine and Swivel builtin algorithm](community/ml_ops/stage6/get_started_with_matching_engine_swivel.ipynb)
+
+In this notebook, you learn how to train custom embeddings using Vertex AI Pipelines and subsequently train and deploy a matching engine index using the embeddings.
+
+The steps performed include:
+
+1. Train the `Swivel` algorithm to generate embeddings (encoder) for the dataset.
+2. Make example predictions (embeddings) from then trained encoder.
+3. Generate embeddings using the trained `Swivel` builtin algorithm.
+4. Store embeddings to format supported by `Matching Engine`.
+5. Create a `Matching Engine Index` for the embeddings.
+6. Deploy the `Matching Engine Index` to a `Index Endpoint`.
+7. Make a matching engine prediction request.
+
+[Get started with Vertex AI Matching Engine](community/ml_ops/stage6/get_started_with_matching_engine.ipynb)
+
+In this notebook, you learn how to create Approximate Nearest Neighbor (ANN) Index, query against indexes. 
+
+The steps performed include:
+
+- Create ANN Index.
+- Create an IndexEndpoint with VPC Network
+- Deploy ANN Index
+- Perform online query
+- Deploy brute force Index.
+- Perform calibration between ANN and brute force index.
+
+[Get started with Vertex AI Matching Engine and Two Towers builtin algorithm](community/ml_ops/stage6/get_started_with_matching_engine_twotowers.ipynb)
+
+
+In this notebook, you learn how to use the `Two-Tower` builtin algorithms for generating embeddings for a dataset, for use with generating an `Matching Engine Index`, with the `Vertex AI Matching Engine` service.
+
+The steps performed include:
+
+1. Train the `Two-Tower` algorithm to generate embeddings (encoder) for the dataset.
+2. Hyperparameter tune the trained `Two-Tower` encoder.
+3. Make example predictions (embeddings) from then trained encoder.
+4. Generate embeddings using the trained `Two-Tower` builtin algorithm.
+5. Store embeddings to format supported by `Matching Engine`.
+6. Create a `Matching Engine Index` for the embeddings.
+7. Deploy the `Matching Engine Index` to a `Index Endpoint`.
+8. Make a matching engine prediction request.
+
+[Get started with Vertex AI Batch Prediction for custom tabular models](community/ml_ops/stage6/get_started_with_custom_tabular_model_batch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Batch Prediction`  with a custom tabular model.
+
+The steps performed include:
+
+- Upload a pretrained tabular model as a `Vertex AI Model` resource.
+- Make batch prediction to the `Model` resource, in JSONL format.
+- Make batch prediction to the `Model` resource, in CSV format.
+- Make batch prediction to the `Model` resource, in BigQuery format.
+
+[Get started with Optimized TensorFlow Enterprise container with Vertex AI Prediction / text models](community/ml_ops/stage6/get_started_with_optimized_tfe_bert.ipynb)
+
+In this tutorial, you learn how to use `TensorFlow Enterprise Optimized` container for TensorFlow models deployed to a `Vertex AI Endpoint` resource.
+
+The steps performed include:
+
+- Download a pretrained BERT model from TensorFlow Hub.
+- Fine-tune (transfer learning) the BERT model as a binary classifier.
+- Upload the TensorFlow Hub model as a `Vertex AI Model` resource, with standard TensorFlow serving container.
+- Upload the TensorFlow Hub model as a `Vertex AI Model` resource, with TensorFlow Enterprise Optimized container
+- Create two `Endpoint` resources.
+- Deploying both `Model` resources to separate `Endpoint` resources.
+- Make the same online prediction requests to both `Model` resource instances deployed to the `Endpoint` resources.
+- Compare the prediction accuracy between the two deployed `Model` resources.
+- Configuring container settings for fine-tune control of optimizations.
+- Create a `Private Endpoint` resource.
+- Deploy the `Model` resoure with then `TensorFlow Enterprise Optimized` to the `Private Endpoint` resource.
+- Make an online prediction request to the `Private Endpoint` resource.
+
+[Get started with Vertex AI Batch Prediction and Explainable AI for AutoML tabular models](community/ml_ops/stage6/get_started_with_automl_tabular_model_batch.ipynb)
+
+In this tutorial, you create an AutoML tabular binary classification model from a Python script, and then do a batch prediction with Explainable AI using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` tabular model.
+- Make a batch prediction with CSV input.
+- Make a batch prediction with JSONL objects input.
+- Make a batch prediction with JSONL list input.
+- Make a batch prediction with BigQuery table input.
+- Make a batch prediction with explanations.
+
+[Get started with re-importing AutoML tabular models](community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.ipynb)
+
+In this tutorial, you learn how to use `AutoML Tabular` for re-importing exported model artifacts as a `Model` resource. This is useful for example, if one wants to move the exported model across projects.
+
+The steps performed include:
+
+- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.
+- Create an `Endpoint` resource.
+- Deploy the `Model` resource to the `Endpoint` resource.
+- Make a prediction.
+
+[Get started with Vertex AI Batch Prediction for AutoML text models](community/ml_ops/stage6/get_started_with_automl_text_model_batch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Batch Prediction`  with a `AutoML` text model.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` model.
+- Make a batch prediction with JSONL input
+
+[Get started with Vertex AI Prediction for AutoML text models](community/ml_ops/stage6/get_started_with_automl_text_model_online.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Prediction`  with a `AutoML` text model.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` model.
+- Deploy the model to an `Endpoint` resource.
+- Make an online prediction.
+
+[Get started with TensorFlow serving functions with Vertex AI Raw Prediction](community/ml_ops/stage6/get_started_with_raw_predict.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Raw Prediction` on a `Vertex AI Endpoint` resource.
+
+The steps performed include:
+
+- Download a pretrained tabular classification model artifacts for a TensorFlow 1.x estimator.
+- Upload the TensorFlow estimator model as a `Vertex AI Model` resource.
+- Creating an `Endpoint` resource.
+- Deploying the `Model` resource to an `Endpoint` resource.
+- Make an online raw prediction to the `Model` resource instance deployed to the `Endpoint` resource.
+
+[Get started with TensorFlow serving functions with Vertex AI Prediction](community/ml_ops/stage6/get_started_with_tf_serving_function.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Prediction` on a `Vertex AI Endpoint` resource with a serving function.
+
+The steps performed include:
+
 - Download a pretrained image classification model from TensorFlow Hub.
 - Create a serving function to receive compressed image data, and output decomopressed preprocessed data for the model input.
 - Upload the TensorFlow Hub model and serving function as a `Vertex AI Model` resource.
 - Creating an `Endpoint` resource.
 - Deploying the `Model` resource to an `Endpoint` resource.
 - Make an online prediction to the `Model` resource instance deployed to the `Endpoint` resource.
-```
 
-[Get started with FastAPI with Vertex AI Prediction](get_started_with_fastapi.ipynb)
+[Get started with Vertex Explainable AI using custom deployment container](community/ml_ops/stage6/get_started_with_xai_and_custom_server.ipynb)
+
+In this tutorial, you learn to build a custom container to serve a PyTorch model on `Vertex AI Endpoint`. 
 
-```
 The steps performed include:
+
+- Locally train a Pytorch tabular classifier.
+- Locally test the trained model.
+- Build a HTTP server using FastAPI.
+- Create a custom serving container with the trained model and FastAPI server.
+- Locally test the custom serving container.
+- Push the custom serving container to the Artifact Registry.
+- Upload the custom serving container as a `Model` resource.
+- Deploy the `Model` resource to an `Endpoint` resource.
+- Make a prediction request to the deployed custom serving container.
+- Make an explanation request to the deployed custom serving container.
+
+[Get started with Vertex AI Online Prediction for AutoML image models](community/ml_ops/stage6/get_started_with_automl_image_model_online.ipynb)
+
+In this tutorial, you create an AutoML image classification model from a Python script, and then do an online prediction using the Vertex AI SDK. 
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` image classification model.
+- Make an online prediction.
+
+[Get started with FastAPI with Vertex AI Prediction](community/ml_ops/stage6/get_started_with_fastapi.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Prediction` on a `Vertex AI Endpoint` with a custom serving binary using `FastAPI`.
+
+The steps performed include:
+
 - Download a pretrained image classification model from TensorFlow Hub.
 - Create a serving function to receive compressed image data, and output decomopressed preprocessed data for the model input.
 - Upload the TensorFlow Hub model and serving function as a `Vertex AI Model` resource.
 - Creating an `Endpoint` resource.
 - Deploying the `Model` resource to an `Endpoint` resource with `FastAPI` custom serving binary.
 - Make an online prediction to the `Model` resource instance deployed to the `Endpoint` resource.
-```
 
-[Get started with Nvidia Triton server](get_started_with_nvidia_triton_serving.ipynb)
+[Get started with Vertex AI Online Prediction for AutoML tabular models](community/ml_ops/stage6/get_started_with_automl_tabular_model_online.ipynb)
 
-```
-The steps performed in this tutorial include:
-- Download the model artifacts from TensorFlow Hub.
-- Create Triton serving configuration file for the model.
-- Construct a custom container, with Triton serving image, for model deployment.
-- Upload the model as a `Vertex AI Model` resource.
-- Deploy the `Vertex AI Model` resource to a `Vertex AI Endpoint` resource.
-- Make a prediction request
-- Undeploy the `Model` resource and delete the `Endpoint`
+In this tutorial, you create an AutoML tabular binary classification model from a Python script, and then do an online prediction using the Vertex AI SDK. 
 
-```
-
-[Get started with Custom Prediction Routine (CPR)](get_started_with_cpr.ipynb)
-
-```
 The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` tabular model.
+- Deploy the model to an `Endpoint` resource.
+- Make an online prediction.
+- Make an online prediction with explanations.
+
+[Get started with TensorFlow Serving with Vertex AI Prediction](community/ml_ops/stage6/get_started_with_tf_serving.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Prediction` on a `Vertex AI Endpoint` resource with `TensorFlow Serving` serving binary.
+
+The steps performed include:
+
+- Download a pretrained image classification model from TensorFlow Hub.
+- Create a serving function to receive compressed image data, and output decomopressed preprocessed data for the model input.
+- Upload the TensorFlow Hub model and serving function as a `Vertex AI Model` resource.
+- Creating an `Endpoint` resource.
+- Deploying the `Model` resource to an `Endpoint` resource with `TensorFlow Serving` serving binary.
+- Make an online prediction to the `Model` resource instance deployed to the `Endpoint` resource.
+- Make a batch prediction to the `Model` resource instance.
+
+[Get started with Custom Prediction Routine (CPR)](community/ml_ops/stage6/get_started_with_cpr.ipynb)
+
+In this tutorial, you learn how to use Custom Prediction Routine (CPR) for `Vertex AI Predictions`.
+
+The steps performed include:
+
 - Write a custom data preprocessor.
 - Train the model.
 - Build a custom scikit-learn serving container with custom data preprocessing using the Custom Prediction Routine model server.
@@ -93,115 +277,50 @@ The steps performed include:
     - Test the model serving container locally.
     - Upload and deploy the model serving container to Vertex AI Endpoint.
     - Make a prediction request.
-```
 
-[Get started with re-importing AutoML tabular models](get_started_automl_tabular_exported_deploy.ipynb)
+[Get started with Vertex AI Batch Prediction for custom text models](community/ml_ops/stage6/get_started_with_custom_text_model_batch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Batch Prediction`  with a custom text model.
 
-```
 The steps performed include:
-- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.
-- Create an `Endpoint` resource.
-- Deploy the `Model` resource to the `Endpoint` resource.
-- Make a prediction.
-```
 
-[Get started with Vertex Explainable AI using custom deployment container](get_started_with_xai_and_custom_server.ipynb)
+- Download a pretrained TensorFlow RNN model.
+- Upload the pretrained model as a `Vertex AI Model` resource.
+- Make batch prediction to the `Model` resource, in JSONL format.
+
+[Get started with NVIDIA Triton server](community/ml_ops/stage6/get_started_with_nvidia_triton_serving.ipynb)
+
+In this tutorial, you deploy a container running Nvidia Triton Server with a `Vertex AI Model` resource to a `Vertex AI Endpoint` for making online predictions.
+
+The steps performed in this tutorial include:
+
+- Download the model artifacts from TensorFlow Hub.
+- Create Triton serving configuration file for the model.
+- Construct a custom container, with Triton serving image, for model deployment.
+- Upload the model as a `Vertex AI Model` resource.
+- Deploy the `Vertex AI Model` resource to a `Vertex AI Endpoint` resource.
+- Make a prediction request
+- Undeploy the `Model` resource and delete the `Endpoint`
+
+[Get started with Vertex AI Batch Prediction for custom image models](community/ml_ops/stage6/get_started_with_custom_image_model_batch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Batch Prediction`  with a custom image model.
 
-```
 The steps performed include:
-- Locally train a Pytorch tabular classifier.
-- Locally test the trained model.
-- Build a HTTP server using FastAPI.
-- Create a custom serving container with the trained model and FastAPI server.
-- Locally test the custom serving container.
-- Push the custom serving container to the Artifact Registry.
-- Upload the custom serving container as a `Model` resource.
-- Deploy the `Model` resource to an `Endpoint` resource.
-- Make a prediction request to the deployed custom serving container.
-- Make an explanation request to the deployed custom serving container.
 
-```
-
-[Get started with TensorFlow serving functions with Vertex AI Raw Prediction](get_started_with_raw_predict.ipynb)
-
-```
-The steps performed include:
-- Download a pretrained tabular classification model artifacts for a TensorFlow 1.x estimator.
-- Upload the TensorFlow estimator model as a `Vertex AI Model` resource.
-- Creating an `Endpoint` resource.
-- Deploying the `Model` resource to an `Endpoint` resource.
-- Make an online raw prediction to the `Model` resource instance deployed to the `Endpoint` resource.
-```
-
-[Get started with Vertex AI Matching Engine and Two Towers builtin algorithm](get_started_with_matching_engine_twotowers.ipynb)
-
-```
-The steps performed include:
-1. Train the `Two-Tower` algorithm to generate embeddings (encoder) for the dataset.
-2. Hyperparameter tune the trained `Two-Tower` encoder.
-3. Make example predictions (embeddings) from then trained encoder.
-4. Generate embeddings using the trained `Two-Tower` builtin algorithm.
-5. Store embeddings to format supported by `Matching Engine`.
-6. Create a `Matching Engine Index` for the embeddings.
-7. Deploy the `Matching Engine Index` to a `Index Endpoint`.
-8. Make a matching engine prediction request.
-
-```
-
-[Get started with Optimized TensorFlow Enterprise container with Vertex AI Prediction / text models](get_started_with_optimized_tfe_bert.ipynb)
-
-```
-The steps performed include:
-- Download a pretrained BERT model from TensorFlow Hub.
-- Fine-tune (transfer learning) the BERT model as a binary classifier.
-- Upload the TensorFlow Hub model as a `Vertex AI Model` resource, with standard TensorFlow serving container.
-- Upload the TensorFlow Hub model as a `Vertex AI Model` resource, with TensorFlow Enterprise Optimized container
-- Create two `Endpoint` resources.
-- Deploying both `Model` resources to separate `Endpoint` resources.
-- Make the same online prediction requests to both `Model` resource instances deployed to the `Endpoint` resources.
-- Compare the prediction accuracy between the two deployed `Model` resources.
-- Configuring container settings for fine-tune control of optimizations.
-- Create a `Private Endpoint` resource.
-- Deploy the `Model` resoure with then `TensorFlow Enterprise Optimized` to the `Private Endpoint` resource.
-- Make an online prediction request to the `Private Endpoint` resource.
-
-```
-
-[Get started with Vertex AI Matching Engine](get_started_with_matching_engine.ipynb)
-
-```
-The steps performed include:
-- Create ANN Index.
-- Create an IndexEndpoint with VPC Network
-- Deploy ANN Index
-- Perform online query
-- Deploy brute force Index.
-- Perform calibration between ANN and brute force index.
-
-```
-
-[Get started with Vertex AI Matching Engine and Swivel builtin algorithm](get_started_with_matching_engine_swivel.ipynb)
-
-```
-The steps performed include:
-1. Train the `Swivel` algorithm to generate embeddings (encoder) for the dataset.
-2. Make example predictions (embeddings) from then trained encoder.
-3. Generate embeddings using the trained `Swivel` builtin algorithm.
-4. Store embeddings to format supported by `Matching Engine`.
-5. Create a `Matching Engine Index` for the embeddings.
-6. Deploy the `Matching Engine Index` to a `Index Endpoint`.
-7. Make a matching engine prediction request.
-
-```
-
-[Get started with TensorFlow serving with Vertex AI Prediction](get_started_with_tf_serving.ipynb)
-
-```
-The steps performed include:
 - Download a pretrained image classification model from TensorFlow Hub.
+- Upload the TensorFlow Hub model as a `Vertex AI Model` resource.
+- Make batch prediction with raw (uncompressed) image data to the `Model` resource, in JSONL format.
 - Create a serving function to receive compressed image data, and output decomopressed preprocessed data for the model input.
 - Upload the TensorFlow Hub model and serving function as a `Vertex AI Model` resource.
-- Creating an `Endpoint` resource.
-- Deploying the `Model` resource to an `Endpoint` resource with `TensorFlow Serving` serving binary.
-- Make an online prediction to the `Model` resource instance deployed to the `Endpoint` resource.
-```
+- Make batch prediction with compressed image data to the `Model` resource, in File-List format.
+
+[Get started with Vertex AI Batch Prediction for AutoML video models](community/ml_ops/stage6/get_started_with_automl_video_model_batch.ipynb)
+
+In this tutorial, you learn how to use `Vertex AI Batch Prediction`  with a `AutoML` video model.
+
+The steps performed include:
+
+- Create a Vertex `Dataset` resource.
+- Train an `AutoML` model.
+- Make a batch prediction with JSONL input.

notebooks/community/ml_ops/stage6/get_started_with_automl_image_model_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# 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",
@@ -33,19 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/ml_ops/get_started_with_automl_image_model_batch.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_image_model_batch.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/tree/main/notebooks/community/ml_ops/get_started_with_automl_image_model_batch.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_image_model_batch.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/stage6/get_started_with_automl_tabular_model_batch.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\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/stage6/get_started_with_automl_image_model_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",
         "</table>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to create image classification models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+        "This tutorial demonstrates how to use the Vertex AI SDK to create image classification models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
@@ -72,7 +73,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML image classification 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 classification 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",
@@ -244,7 +245,7 @@
         "\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",
+        "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",
@@ -252,6 +253,17 @@
         "**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,
@@ -635,7 +647,7 @@
         "dataset = aiplatform.ImageDataset.create(\n",
         "    display_name=\"Flowers\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -711,7 +723,7 @@
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline will take upto 20 minutes."
+        "The execution of the training pipeline may take upto 20 minutes."
       ]
     },
     {
@@ -743,7 +755,7 @@
         "\n",
         "Batch prediction provides the ability to do offline batch processing of large amounts of prediction requests. Resources are only provisioned during the batch process and then deprovisioned when the batch request is completed. The results are stored in Cloud Storage, in contrast to online prediction where the results are returned as a HTTP response packet.\n",
         "\n",
-        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server will convert to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
+        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server converts to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
@@ -752,7 +764,7 @@
         "\n",
         "- JSONL\n",
         "\n",
-        "The batch server accepts the following input formats for AutoML image models:\n",
+        "The batch server accepts the following output formats for AutoML image models:\n",
         "\n",
         "- JSONL\n",
         "\n",
@@ -776,7 +788,7 @@
         "\n",
         "**CSV**\n",
         "\n",
-        "The csv header in the first line will always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
+        "The csv header in the first line is always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
         "\n",
         "    col1,col2,col3\n",
         "    1,3,\"cat1\"\n",
@@ -954,7 +966,7 @@
         "- `prediction_format`: The format of the batch prediction response file: \"jsonl\", \"csv\", \"bigquery\", \"tf-record\", \"tf-record-gzip\" or \"file-list\"\n",
         "- `gcs_source`: A list of one or more batch request input files.\n",
         "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+        "- `sync`: If set to True, the call blocks while waiting for the asynchronous batch job to complete."
       ]
     },
     {

notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.ipynb

@@ -33,18 +33,18 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.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://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.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://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\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/stage6/get_started_with_automl_tabular_exported_deploy.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",
@@ -866,7 +866,7 @@
   ],
   "metadata": {
     "colab": {
-      "name": "get_started_automl_tabular_exported_deploy.ipynb",
+      "name": "get_started_with_automl_tabular_exported_deploy.ipynb",
       "toc_visible": true
     },
     "kernelspec": {

notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_model_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# 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",
@@ -29,16 +29,16 @@
         "id": "title"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 6 : Get started with Vertex AI Batch Prediction for AutoML tabular models\n",
+        "# E2E ML on GCP: MLOps stage 6 : Get started with Vertex AI Batch Prediction and Explainable AI for AutoML tabular models\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/ml_ops/get_started_with_automl_tabular_model_batch.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_model_batch.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/tree/main/notebooks/community/ml_ops/get_started_with_automl_tabular_model_batch.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_model_batch.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",
@@ -62,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex AI SDK to create tabular binary classification models and do batch prediction using a [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+        "This tutorial demonstrates how to use the Vertex AI SDK to create tabular binary classification models and do batch prediction with explainable AI using a [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
@@ -73,12 +73,13 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular binary classification 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 create an AutoML tabular binary classification model from a Python script, and then do a batch prediction with Explainable AI 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 AutoML`\n",
         "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex AI Datasets`\n",
         "- `Vertex AI Models`\n",
         "- `BigQuery`\n",
         "\n",
@@ -90,6 +91,7 @@
         "- Make a batch prediction with JSONL objects input.\n",
         "- Make a batch prediction with JSONL list input.\n",
         "- Make a batch prediction with BigQuery table input.\n",
+        "- Make a batch prediction with explanations.\n",
         "\n",
         "There is one key difference between using batch prediction and using online prediction:\n",
         "\n",
@@ -106,7 +108,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . 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 dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {
@@ -119,14 +121,11 @@
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
         "\n",
-        "* Vertex AI\n",
-        "* Cloud Storage\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\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."
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage 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."
       ]
     },
     {
@@ -250,7 +249,7 @@
         "\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",
+        "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",
@@ -258,6 +257,17 @@
         "**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,
@@ -574,7 +584,7 @@
         "id": "tutorial_start:automl"
       },
       "source": [
-        "# Tutorial\n",
+        "## AutoML Tabular model training\n",
         "\n",
         "Now you are ready to start creating your own AutoML tabular binary classification model."
       ]
@@ -743,7 +753,7 @@
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline will take upto 8 hours."
+        "The execution of the training pipeline may take upto 8 hours."
       ]
     },
     {
@@ -776,7 +786,7 @@
         "\n",
         "Batch prediction provides the ability to do offline batch processing of large amounts of prediction requests. Resources are only provisioned during the batch process and then deprovisioned when the batch request is completed. The results are stored in Cloud Storage, in contrast to online prediction where the results are returned as a HTTP response packet.\n",
         "\n",
-        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server will convert to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
+        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server converts to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
@@ -786,7 +796,9 @@
         "- CSV\n",
         "- Big Query table\n",
         "\n",
-        "The batch server accepts the following input formats for AutoML tabular models:\n",
+        "### Output format for batch prediction jobs\n",
+        "\n",
+        "The batch server accepts the following output formats for AutoML tabular models:\n",
         "\n",
         "- JSONL\n",
         "- CSV\n",
@@ -812,7 +824,7 @@
         "\n",
         "**CSV**\n",
         "\n",
-        "The csv header in the first line will always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
+        "The csv header in the first line is always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
         "\n",
         "    col1,col2,col3\n",
         "    1,3,\"cat1\"\n",
@@ -926,7 +938,7 @@
         "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
         "- `instances_format`: The format for the input instances, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
         "- `predictions_format`: The format for the output predictions, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+        "- `sync`: If set to True, the call blocks while waiting for the asynchronous batch job to complete."
       ]
     },
     {
@@ -1069,21 +1081,21 @@
         "import json\n",
         "\n",
         "INSTANCE_1 = {\n",
-        "    \"Age\": 58,\n",
+        "    \"Age\": \"58\",\n",
         "    \"Job\": \"management\",\n",
         "    \"MaritalStatus\": \"married\",\n",
         "    \"Education\": \"tertiary\",\n",
         "    \"Default\": \"no\",\n",
-        "    \"Balance\": 2143,\n",
+        "    \"Balance\": \"2143\",\n",
         "    \"Housing\": \"yes\",\n",
         "    \"Loan\": \"no\",\n",
         "    \"Contact\": \"unknown\",\n",
-        "    \"Day\": 5,\n",
+        "    \"Day\": \"5\",\n",
         "    \"Month\": \"may\",\n",
-        "    \"Duration\": 261,\n",
-        "    \"Campaign\": 1,\n",
-        "    \"PDays\": -1,\n",
-        "    \"Previous\": 0,\n",
+        "    \"Duration\": \"261\",\n",
+        "    \"Campaign\": \"1\",\n",
+        "    \"PDays\": \"-1\",\n",
+        "    \"Previous\": \"0\",\n",
         "    \"POutcome\": \"unknown\",\n",
         "}\n",
         "\n",
@@ -1107,7 +1119,7 @@
         "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
         "- `instances_format`: The format for the input instances, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
         "- `predictions_format`: The format for the output predictions, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+        "- `sync`: If set to True, the call blocks while waiting for the asynchronous batch job to complete."
       ]
     },
     {
@@ -1214,6 +1226,112 @@
         "batch_predict_job.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_explain_request:mbsdk,csv"
+      },
+      "source": [
+        "### Make the batch explanation request\n",
+        "\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",
+        "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
+        "- `instances_format`: The format for the input instances, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
+        "- `predictions_format`: The format for the output predictions, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
+        "- `generate_explanations`: Set to `True` to generate explanations.\n",
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete.\n",
+        "\n",
+        "For explanations, only 'jsonl' and 'bigquery' output formats are supported."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request:mbsdk,both_csv"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job = model.batch_predict(\n",
+        "    job_display_name=\"bank_\" + UUID,\n",
+        "    gcs_source=gcs_input_uri,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    instances_format=\"jsonl\",\n",
+        "    predictions_format=\"jsonl\",\n",
+        "    generate_explanation=True,\n",
+        "    sync=False,\n",
+        ")\n",
+        "\n",
+        "print(batch_predict_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "source": [
+        "### Wait for completion of batch prediction job\n",
+        "\n",
+        "Next, wait for the batch job to complete. Alternatively, one can set the parameter `sync` to `True` in the `batch_predict()` method to block until the batch prediction job is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.wait()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_batch_explanation:mbsdk,lbn"
+      },
+      "source": [
+        "### Get the explanations\n",
+        "\n",
+        "Next, get the explanation results from the completed batch prediction job.\n",
+        "\n",
+        "The results are written to the Cloud Storage output bucket you specified in the batch prediction request. You call the method iter_outputs() to get a list of each Cloud Storage file generated with the results. Each file contains one or more explanation requests in a JSONL format:\n",
+        "\n",
+        "- instance: The feature values sent for the prediction.\n",
+        "- prediction: The predicted value.\n",
+        "- explanation: The attributions for each feature value."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_batch_explanation:mbsdk,lbn"
+      },
+      "outputs": [],
+      "source": [
+        "import tensorflow as tf\n",
+        "\n",
+        "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
+        "\n",
+        "explanation_results = list()\n",
+        "for blob in bp_iter_outputs:\n",
+        "    if blob.name.split(\"/\")[-1].startswith(\"explanation\"):\n",
+        "        explanation_results.append(blob.name)\n",
+        "\n",
+        "tags = list()\n",
+        "for explanation_result in explanation_results:\n",
+        "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{explanation_result}\"\n",
+        "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
+        "        for line in gfile.readlines():\n",
+        "            print(line)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1622,6 +1740,72 @@
         "        pass"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "12ed21da6f1f"
+      },
+      "source": [
+        "#### Delete the batch prediction job\n",
+        "\n",
+        "You can delete your `Vertex AI Batch Prediction` job with the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "286a90d9b6e7"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "992a2d57c0fc"
+      },
+      "source": [
+        "#### Delete the model\n",
+        "\n",
+        "Next, you can delete the `Vertex AI Model` resource using the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "27f9b3beec3f"
+      },
+      "outputs": [],
+      "source": [
+        "model.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "beebda94c217"
+      },
+      "source": [
+        "#### Delete the dataset\n",
+        "\n",
+        "Next, you can delete the `Vertex AI Dataset` resource using the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9e028ffc4ada"
+      },
+      "outputs": [],
+      "source": [
+        "dataset.delete()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1645,16 +1829,6 @@
       "outputs": [],
       "source": [
         "delete_bucket = False\n",
-        "delete_model = True\n",
-        "delete_batch_job = True\n",
-        "\n",
-        "if delete_model:\n",
-        "    try:\n",
-        "        model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "if delete_batch_job:\n",
-        "    batch_prediction_job.delete()\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -rf {BUCKET_URI}"

notebooks/community/ml_ops/stage6/get_started_with_automl_text_model_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# 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",
@@ -244,7 +244,7 @@
         "\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",
+        "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",
@@ -252,6 +252,17 @@
         "**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,
@@ -731,10 +742,12 @@
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
-        "The batch server accepts the following input formats for AutoML tabular models:\n",
+        "The batch server accepts the following input formats for AutoML text models:\n",
         "\n",
         "- JSONL\n",
         "\n",
+        "### Output format for batch prediction jobs\n",
+        "\n",
         "The batch server accepts the following output formats for AutoML text models:\n",
         "\n",
         "- JSONL\n",
@@ -883,8 +896,6 @@
       "source": [
         "import json\n",
         "\n",
-        "import tensorflow as tf\n",
-        "\n",
         "gcs_test_item_1 = BUCKET_URI + \"/test1.txt\"\n",
         "with open(\"test1.txt\", \"w\") as f:\n",
         "    f.write(test_item_1 + \"\\n\")\n",
@@ -967,6 +978,17 @@
         "batch_predict_job.wait()"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "batch_request_wait:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "batch_predict_job.wait()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -994,6 +1016,10 @@
       },
       "outputs": [],
       "source": [
+        "import json\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "\n",
         "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
         "\n",
         "prediction_results = list()\n",

notebooks/community/ml_ops/stage6/get_started_with_custom_image_model_batch.ipynb

@@ -741,13 +741,16 @@
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
-        "The batch server accepts the following input formats:\n",
+        "The batch server accepts the following input formats for custom image models:\n",
         "\n",
         "- JSONL\n",
-        "- CSV\n",
-        "- TFRecords\n",
         "- File-List\n",
-        "- BigQuery table\n",
+        "\n",
+        "### Output format for batch prediction jobs\n",
+        "\n",
+        "The batch server accepts the following output formats for custom image models:\n",
+        "\n",
+        "- JSONL\n",
         "\n",
         "### Pivot format\n",
         "\n",
@@ -1306,7 +1309,6 @@
       "source": [
         "### Send the prediction request\n",
         "\n",
-        "BLAH\n",
         "\n",
         "To make a batch prediction request, call the model object's `batch_predict` method with the following parameters: \n",
         "- `instances_format`: The format of the batch prediction request file: \"jsonl\", \"csv\", \"bigquery\", \"tf-record\", \"tf-record-gzip\" or \"file-list\"\n",

notebooks/community/ml_ops/stage6/get_started_with_custom_tabular_model_batch.ipynb

@@ -110,7 +110,7 @@
         "- identity - unique player identitity numbers\n",
         "- demographic features - information about the player, such as the geographic region in which a player is located\n",
         "- behavioral features - counts of the number of times a  player has triggered certain game events, such as reaching a new level\n",
-        "- churn propensity - this is the label or target feature, it provides an estimated probability that this player will churn, i.e. stop being an active player.\n",
+        "- churn propensity - this is the label or target feature, it provides an estimated probability that this player may churn, i.e. stop being an active player.\n",
         "\n",
         "**CSV batch input example**\n",
         "\n",
@@ -574,7 +574,7 @@
         "\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."
+        "*Note*: TF releases before 2.3 for GPU support fails 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."
       ]
     },
     {
@@ -638,7 +638,7 @@
         "\n",
         "Next, set the machine type to use for prediction.\n",
         "\n",
-        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for prediction.\n",
+        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you use for for prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -712,7 +712,7 @@
         "\n",
         "Batch prediction provides the ability to do offline batch processing of large amounts of prediction requests. Resources are only provisioned during the batch process and then deprovisioned when the batch request is completed. The results are stored in Cloud Storage, in contrast to online prediction where the results are returned as a HTTP response packet.\n",
         "\n",
-        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server will convert to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
+        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server converts to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
@@ -749,7 +749,7 @@
         "\n",
         "**CSV**\n",
         "\n",
-        "The csv header in the first line will always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
+        "The csv header in the first line is always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
         "\n",
         "    col1,col2,col3\n",
         "    1,3,\"cat1\"\n",
@@ -910,7 +910,7 @@
         "- `prediction_format`: The format of the batch prediction response file: \"jsonl\", \"csv\", \"bigquery\", \"tf-record\", \"tf-record-gzip\" or \"file-list\"\n",
         "- `job_display_name`: The human readable name for the prediction job.\n",
         " - `gcs_source`: A list of one or more Cloud Storage paths to your batch prediction requests.\n",
-        "- `gcs_destination_prefix`: The Cloud Storage path that the service will write the predictions to.\n",
+        "- `gcs_destination_prefix`: The Cloud Storage path that the service writes the predictions to.\n",
         "- `model_parameters`: Additional filtering parameters for serving prediction results.\n",
         "- `machine_type`: The type of machine to use for training.\n",
         "- `accelerator_type`: The hardware accelerator type.\n",

notebooks/community/ml_ops/stage6/get_started_with_nvidia_triton_serving.ipynb

@@ -81,7 +81,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you deploy a container running Nvidia Triton Server with a `Vertex AI Model` resource to a `Vertex AI Endpoint` for making online predictions.\n",
+        "In this tutorial, you learn how to deploy a container running Nvidia Triton Server with a `Vertex AI Model` resource to a `Vertex AI Endpoint` for making online predictions.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",

notebooks/community/ml_ops/stage6/get_started_with_tf_serving_function.ipynb

@@ -1054,36 +1054,17 @@
       ]
     }
   ],
- "metadata": {
-  "colab": {
-   "collapsed_sections": [],
-   "name": "get_started_with_tf_serving_function.ipynb",
-   "toc_visible": true
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [],
+      "name": "get_started_with_tf_serving_function.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
   },
-  "environment": {
-   "kernel": "python3",
-   "name": "tf2-gpu.2-6.m91",
-   "type": "gcloud",
-   "uri": "gcr.io/deeplearning-platform-release/tf2-gpu.2-6:m91"
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
+  "nbformat": 4,
+  "nbformat_minor": 0
 }

notebooks/community/ml_ops/stage6/get_started_with_xai_and_custom_server.ipynb

@@ -85,7 +85,7 @@
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Locally train a Pytorch tabular classifier.\n",
+        "- Locally train a PyTorch tabular classifier.\n",
         "- Locally test the trained model.\n",
         "- Build a HTTP server using FastAPI.\n",
         "- Create a custom serving container with the trained model and FastAPI server.\n",