Merge branch 'main' into autlogging

* Reduced notebook boilerplate

* Fixed lint issues

* Added unique suffix note

* Added unique string processor and moved tests to own folder

* Fixed broken link

* Added message about updating links

* Fixed typo

* Added missing import

* Added back useful instructions

* Addressed comments

* Removed matching engine

* Fixed comments

.cloud-build/cleanup/cleanup-requirements.txt

@@ -1 +1,2 @@
+ratemate
 google-cloud-aiplatform

.cloud-build/cleanup/cleanup.py

@@ -1,45 +1,49 @@
 from typing import List
+from ratemate import RateLimit
 from resource_cleanup_manager import (
-	ResourceCleanupManager,
-	DatasetResourceCleanupManager,
-	EndpointResourceCleanupManager,
-	ModelResourceCleanupManager,
+    DatasetResourceCleanupManager,
+    ModelResourceCleanupManager,
+    EndpointResourceCleanupManager,
+    ResourceCleanupManager,
 )
 
+rate_limit = RateLimit(max_count=25, per=60, greedy=False)
+
 
 def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: bool):
-	for manager in managers:
-		type_name = manager.type_name
+    for manager in managers:
+        type_name = manager.type_name
 
-		print(f"Fetching {type_name}'s...")
-		resources = manager.list()
-		print(f"Found {len(resources)} {type_name}'s")
-		for resource in resources:
-			if not manager.is_deletable(resource):
-				continue
+        print(f"Fetching {type_name}'s...")
+        resources = manager.list()
+        print(f"Found {len(resources)} {type_name}'s")
+        for resource in resources:
+            try:
+                if not manager.is_deletable(resource):
+                    continue
 
-			if is_dry_run:
-				resource_name = manager.resource_name(resource)
-				print(f"Will delete '{type_name}': {resource_name}")
-			else:
-				try:
-					manager.delete(resource)
-				except Exception as exception:
-					print(exception)
+                if is_dry_run:
+                    resource_name = manager.resource_name(resource)
+                    print(f"Will delete '{type_name}': {resource_name}")
+                else:
+                    rate_limit.wait()  # wait before deleting
+                    manager.delete(resource)
+            except Exception as exception:
+                print(exception)
 
-		print("")
+        print("")
 
 
 is_dry_run = False
 
 if is_dry_run:
-	print("Starting cleanup in dry run mode...")
+    print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
 managers = [
-	DatasetResourceCleanupManager(),
-	EndpointResourceCleanupManager(),
-	ModelResourceCleanupManager(),
+    DatasetResourceCleanupManager(),
+    EndpointResourceCleanupManager(),
+    ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
 ]
 
 run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,8 +1,9 @@
 import abc
+from typing import Any, Type
+
 from google.cloud import aiplatform
-from typing import Any
-from proto.datetime_helpers import DatetimeWithNanoseconds
 from google.cloud.aiplatform import base
+from proto.datetime_helpers import DatetimeWithNanoseconds
 
 # If a resource was updated within this number of seconds, do not delete.
 RESOURCE_UPDATE_BUFFER_IN_SECONDS = 60 * 60 * 8
@@ -40,7 +41,7 @@ class ResourceCleanupManager(abc.ABC):
         # Check that it wasn't created too recently, to prevent race conditions
         if time_difference <= RESOURCE_UPDATE_BUFFER_IN_SECONDS:
             print(
-                f"Skipping '{resource}' due update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
+                f"Skipping '{resource}' due to update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
             )
             return False
 
@@ -50,7 +51,7 @@ class ResourceCleanupManager(abc.ABC):
 class VertexAIResourceCleanupManager(ResourceCleanupManager):
     @property
     @abc.abstractmethod
-    def vertex_ai_resource(self) -> base.VertexAiResourceNounWithFutureManager:
+    def vertex_ai_resource(self) -> Type[base.VertexAiResourceNounWithFutureManager]:
         pass
 
     @property
@@ -60,7 +61,9 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def list(self) -> Any:
         return self.vertex_ai_resource.list()
 
-    def resource_name(self, resource: Any) -> str:
+    def resource_name(
+        self, resource: Type[base.VertexAiResourceNounWithFutureManager]
+    ) -> str:
         return resource.display_name
 
     def delete(self, resource):
@@ -74,12 +77,33 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
 
 class DatasetResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.datasets._Dataset
+    dataset_types = [
+        aiplatform.ImageDataset,
+        aiplatform.TabularDataset,
+        aiplatform.TextDataset,
+        aiplatform.TimeSeriesDataset,
+        aiplatform.VideoDataset,
+    ]
+
+    def list(self) -> Any:
+        return [
+            dataset
+            for dataset_type in self.dataset_types
+            for dataset in dataset_type.list()
+        ]
 
 
 class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Endpoint
 
     def delete(self, resource):
+        # TODO: Remove this once https://github.com/googleapis/python-aiplatform/issues/1441 is fixed
+        resource._sync_gca_resource()
+        for deployed_model_id in [
+            models.id for models in resource._gca_resource.deployed_models
+        ]:
+            resource._undeploy(deployed_model_id=deployed_model_id)
+
         resource.delete(force=True)
 
 

.cloud-build/execute_changed_notebooks_cli.py

@@ -17,6 +17,7 @@
 
 import argparse
 import pathlib
+
 import execute_changed_notebooks_helper
 
 
@@ -61,6 +62,18 @@ parser.add_argument(
     help="The GCP region. This is used to inject a variable value into the notebook before running.",
     required=True,
 )
+parser.add_argument(
+    "--variable_service_account",
+    type=str,
+    help="A service account. This is used to inject a variable value into the notebook before running. This is not the account that will run the notebook.",
+    required=True,
+)
+parser.add_argument(
+    "--variable_vpc_network",
+    type=str,
+    help="The full VPC network name. See https://cloud.google.com/compute/docs/networks-and-firewalls#networks. Format is projects/{project}/global/networks/{network}, where {project} is a project number, as in '12345', and {network} is network name. See <https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert> for details. This is used to inject a variable value into the notebook before running.",
+    required=False,
+)
 parser.add_argument(
     "--staging_bucket",
     type=str,
@@ -73,6 +86,13 @@ parser.add_argument(
     help="The GCP directory for storing executed notebooks.",
     required=True,
 )
+parser.add_argument(
+    "--timeout",
+    type=int,
+    help="Timeout in seconds",
+    default=86400,
+    required=False,
+)
 parser.add_argument(
     "--private_pool_id",
     type=str,
@@ -100,8 +120,11 @@ execute_changed_notebooks_helper.process_and_execute_notebooks(
     container_uri=args.container_uri,
     staging_bucket=args.staging_bucket,
     artifacts_bucket=args.artifacts_bucket,
+    should_parallelize=args.should_parallelize,
+    timeout=args.timeout,
     variable_project_id=args.variable_project_id,
     variable_region=args.variable_region,
-    private_pool_id=args.private_pool_id if not "default" else None,
-    should_parallelize=args.should_parallelize,
+    variable_service_account=args.variable_service_account,
+    variable_vpc_network=args.variable_vpc_network,
+    private_pool_id=args.private_pool_id,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,18 +17,28 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import json
+import git
+import operator
 import os
 import pathlib
-import nbformat
 import re
 import subprocess
+import utils
 from typing import List, Optional
-from tabulate import tabulate
-import operator
+from utils import util
 
+import execute_notebook_helper
 import execute_notebook_remote
-from utils import util, NotebookProcessors
+import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
+from ratemate import RateLimit
+from tabulate import tabulate
+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:
@@ -60,13 +70,23 @@ class NotebookExecutionResult:
     log_url: str
     output_uri: str
     build_id: str
+    logs_bucket: str
     error_message: Optional[str]
 
+    @property
+    def output_uri_web(self) -> Optional[str]:
+        if self.output_uri.startswith("gs://"):
+            return f"https://storage.googleapis.com/{self.output_uri[5:]}"
+        else:
+            return None
+
 
 def _process_notebook(
     notebook_path: str,
     variable_project_id: str,
     variable_region: str,
+    variable_service_account: str,
+    variable_vpc_network: Optional[str],
 ):
     # Read notebook
     with open(notebook_path) as f:
@@ -78,8 +98,11 @@ def _process_notebook(
         replacement_map={
             "PROJECT_ID": variable_project_id,
             "REGION": variable_region,
+            "SERVICE_ACCOUNT": variable_service_account,
+            "VPC_NETWORK": variable_vpc_network,
         },
     )
+    unique_strings_preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
 
     # Use no-execute preprocessor
     (
@@ -93,6 +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)
@@ -103,18 +155,33 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
+rate_limit = RateLimit(max_count=50, per=60, greedy=True)
+
+
 def process_and_execute_notebook(
     container_uri: str,
     staging_bucket: str,
     artifacts_bucket: str,
     variable_project_id: str,
     variable_region: str,
+    variable_service_account: str,
+    variable_vpc_network: Optional[str],
     private_pool_id: Optional[str],
+    deadline: datetime.datetime,
     notebook: str,
     should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
+    rate_limit.wait()  # wait before creating the task
+
     print(f"Running notebook: {notebook}")
 
+    # Handle empty strings
+    if not variable_vpc_network:
+        variable_vpc_network = None
+
+    if not private_pool_id:
+        private_pool_id = None
+
     # Create paths
     notebook_output_uri = "/".join([artifacts_bucket, pathlib.Path(notebook).name])
 
@@ -128,6 +195,7 @@ def process_and_execute_notebook(
         output_uri=notebook_output_uri,
         log_url="",
         build_id="",
+        logs_bucket="",
         error_message=None,
     )
 
@@ -135,29 +203,45 @@ 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,
             variable_project_id=variable_project_id,
             variable_region=variable_region,
+            variable_service_account=variable_service_account,
+            variable_vpc_network=variable_vpc_network,
         )
 
         # Upload the pre-processed code to a GCS bucket
         code_archive_uri = util.archive_code_and_upload(staging_bucket=staging_bucket)
 
+        # Calculate timeout in seconds
+        timeout_in_seconds = max(
+            int((deadline - datetime.datetime.now()).total_seconds()), 1
+        )
+
         operation = execute_notebook_remote.execute_notebook_remote(
             code_archive_uri=code_archive_uri,
             notebook_uri=notebook,
             notebook_output_uri=notebook_output_uri,
             container_uri=container_uri,
             tag=tag,
-            region=variable_region,
             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()
@@ -215,20 +299,40 @@ def get_changed_notebooks(
 
     # Find notebooks
     notebooks = []
+
+    # Instantiate GitPython objects
+    repo = git.Repo(os.getcwd())
+    index = repo.index
+
     if base_branch:
-        print(f"Looking for notebooks that changed from branch: {base_branch}")
-        notebooks = subprocess.check_output(
-            ["git", "diff", "--name-only", f"origin/{base_branch}..."] + test_paths
-        )
+        # Get the point at which this branch branches off from main
+        branching_commits = repo.merge_base("HEAD", f"origin/{base_branch}")
+
+        if len(branching_commits) > 0:
+            branching_commit = branching_commits[0]
+            print(f"Looking for notebooks that changed from branch: {branching_commit}")
+
+            notebooks = [
+                diff.b_path
+                for diff in index.diff(branching_commit, paths=test_paths)
+                if diff.b_path is not None
+            ]
+        else:
+            notebooks = []
     else:
         print(f"Looking for all notebooks.")
-        notebooks = subprocess.check_output(["git", "ls-files"] + test_paths)
+        notebooks_str = subprocess.check_output(["git", "ls-files"] + test_paths)
+        notebooks = notebooks_str.decode("utf-8").split("\n")
 
-    notebooks = notebooks.decode("utf-8").split("\n")
     notebooks = [notebook for notebook in notebooks if notebook.endswith(".ipynb")]
     notebooks = [notebook for notebook in notebooks if len(notebook) > 0]
     notebooks = [notebook for notebook in notebooks if pathlib.Path(notebook).exists()]
 
+    if len(notebooks) > 0:
+        print(f"Found {len(notebooks)} notebooks:")
+        for notebook in notebooks:
+            print(f"\t{notebook}")
+
     return notebooks
 
 
@@ -237,10 +341,13 @@ def process_and_execute_notebooks(
     container_uri: str,
     staging_bucket: str,
     artifacts_bucket: str,
+    should_parallelize: bool,
+    timeout: int,
     variable_project_id: str,
     variable_region: str,
-    private_pool_id: Optional[str],
-    should_parallelize: bool,
+    variable_service_account: str,
+    variable_vpc_network: Optional[str] = None,
+    private_pool_id: Optional[str] = None,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -267,17 +374,27 @@ def process_and_execute_notebooks(
             Required. The value for REGION to inject into notebooks.
         should_parallelize (bool):
             Required. Should run notebooks in parallel using a thread pool as opposed to in sequence.
+        timeout (str):
+            Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
     """
-    notebook_execution_results: List[NotebookExecutionResult] = []
 
-    if len(notebooks) > 0:
+    # Calculate deadline
+    deadline = datetime.datetime.now() + datetime.timedelta(
+        seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
+    )
+
+    if len(notebooks) >= 1:
+        notebook_execution_results: List[NotebookExecutionResult] = []
+
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
 
         if should_parallelize and len(notebooks) > 1:
             print(
                 "Running notebooks in parallel, so no logs will be displayed. Please wait..."
             )
-            with concurrent.futures.ThreadPoolExecutor(max_workers=None) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
+                print(f"Max workers: {executor._max_workers}")
+
                 notebook_execution_results = list(
                     executor.map(
                         functools.partial(
@@ -287,7 +404,10 @@ def process_and_execute_notebooks(
                             artifacts_bucket,
                             variable_project_id,
                             variable_region,
+                            variable_service_account,
+                            variable_vpc_network,
                             private_pool_id,
+                            deadline,
                         ),
                         notebooks,
                     )
@@ -300,48 +420,88 @@ def process_and_execute_notebooks(
                     artifacts_bucket=artifacts_bucket,
                     variable_project_id=variable_project_id,
                     variable_region=variable_region,
+                    variable_service_account=variable_service_account,
+                    variable_vpc_network=variable_vpc_network,
                     private_pool_id=private_pool_id,
+                    deadline=deadline,
                     notebook=notebook,
                 )
                 for notebook in notebooks
             ]
+
+        print("\n=== RESULTS ===\n")
+
+        results_sorted = sorted(
+            notebook_execution_results,
+            key=lambda result: result.is_pass,
+            reverse=True,
+        )
+
+        # Print results
+        print(
+            tabulate(
+                [
+                    [
+                        result.name,
+                        "PASSED" if result.is_pass else "FAILED",
+                        format_timedelta(result.duration),
+                        result.log_url,
+                        result.output_uri,
+                        result.output_uri_web,
+                        result.logs_bucket,
+                    ]
+                    for result in results_sorted
+                ],
+                headers=[
+                    "build_tag",
+                    "status",
+                    "duration",
+                    "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(
+            operator.add,
+            [datetime.timedelta(seconds=0)]
+            + [result.duration for result in results_sorted],
+        )
+
+        print(
+            f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}"
+        )
+
+        # 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")
     else:
         print("No notebooks modified in this pull request.")
-
-    print("\n=== RESULTS ===\n")
-
-    results_sorted = sorted(
-        notebook_execution_results,
-        key=lambda result: result.is_pass,
-        reverse=True,
-    )
-
-    # Print results
-    print(
-        tabulate(
-            [
-                [
-                    result.name,
-                    "PASSED" if result.is_pass else "FAILED",
-                    format_timedelta(result.duration),
-                    result.log_url,
-                ]
-                for result in results_sorted
-            ],
-            headers=["build_tag", "status", "duration", "log_url"],
-        )
-    )
-
-    print("\n=== END RESULTS===\n")
-
-    total_notebook_duration = functools.reduce(
-        operator.add,
-        [datetime.timedelta(seconds=0)]
-        + [result.duration for result in results_sorted],
-    )
-
-    print(f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}")
-
-    # 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")

.cloud-build/execute_notebook_cli.py

@@ -16,6 +16,7 @@
 """A CLI to download (optional) and run a single notebook locally"""
 
 import argparse
+
 import execute_notebook_helper
 
 parser = argparse.ArgumentParser(description="Run a single notebook locally.")

.cloud-build/execute_notebook_helper.py

@@ -15,17 +15,20 @@
 
 """Methods to run a notebook locally"""
 
-import sys
-import os
 import errno
-import papermill as pm
+import os
 import shutil
+import sys
 
-from utils import util
+import papermill as pm
 from google.cloud.aiplatform import utils
+from utils import util
 
 # This script is used to execute a notebook and write out the output notebook.
 
+# This is used to force papermill to use this kernel to run the notebook instead of any defined inside the notebook itself
+DEFAULT_KERNEL_NAME = "python3"
+
 
 def execute_notebook(
     notebook_source: str,
@@ -50,6 +53,17 @@ def execute_notebook(
 
     execution_exception = None
 
+    print("\n=== DOWNLOAD EXECUTED NOTEBOOK ===\n")
+    print(f"Please debug the executed notebook by downloading the executed notebook:")
+
+    print("Option 1. Using gsutil. Run the following command in your terminal.")
+    print(f'\tgsutil cp "{output_file_or_uri}" .')
+
+    print("Option 2. Using this link.")
+    print(f"\thttps://storage.googleapis.com/{output_file_or_uri[5:]}")
+
+    print("\n======\n")
+
     # Execute notebook
     try:
         # Execute notebook
@@ -58,6 +72,7 @@ def execute_notebook(
             output_path=notebook_source,
             progress_bar=should_log_output,
             request_save_on_cell_execute=should_log_output,
+            kernel_name=DEFAULT_KERNEL_NAME,
             log_output=should_log_output,
             stdout_file=sys.stdout if should_log_output else None,
             stderr_file=sys.stderr if should_log_output else None,
@@ -71,10 +86,6 @@ def execute_notebook(
             util.upload_file(notebook_source, remote_file_path=output_file_or_uri)
 
             print("\n=== EXECUTION FINISHED ===\n")
-            print(
-                f"Please debug the executed notebook by downloading: {output_file_or_uri}"
-            )
-            print("\n======\n")
         else:
             # Create directories if they don't exist
             if not os.path.exists(os.path.dirname(output_file_or_uri)):

.cloud-build/execute_notebook_remote.py

@@ -16,22 +16,18 @@
 """Methods to run a notebook on Google Cloud Build"""
 
 from re import sub
+from typing import Optional
+
+import google.auth
+import yaml
+from google.api_core import client_options, operation
+from google.cloud.aiplatform import utils
+from google.cloud.devtools import cloudbuild_v1
+from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
 from google.protobuf import duration_pb2
 from yaml.loader import FullLoader
 
-import google.auth
-from google.cloud.devtools import cloudbuild_v1
-from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
-
-from typing import Optional
-import yaml
-
-from google.cloud.aiplatform import utils
-from google.api_core import operation, client_options
-
-
 CLOUD_BUILD_FILEPATH = ".cloud-build/notebook-execution-test-cloudbuild-single.yaml"
-TIMEOUT_IN_SECONDS = 86400
 SERVICE_BASE_PATH = "cloudbuild.googleapis.com"
 
 
@@ -40,30 +36,38 @@ def execute_notebook_remote(
     notebook_uri: str,
     notebook_output_uri: str,
     container_uri: str,
-    region: str,
     private_pool_id: Optional[str],
+    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
+
     cloudbuild_config = yaml.load(open(CLOUD_BUILD_FILEPATH), Loader=FullLoader)
 
     substitutions = {
         "_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
-    if private_pool_id:
-        substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
-        build.options = cloudbuild_config["options"]
+    if private_pool_id and private_pool_region:
+        # substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
+        build.options = cloudbuild_config.get("options")
+        build.options.pool = {"name": private_pool_id}
 
         # Switch to the regional endpoint of the pool
         options = client_options.ClientOptions(
-            api_endpoint=f"{region}-{SERVICE_BASE_PATH}"
+            api_endpoint=f"{private_pool_region}-{SERVICE_BASE_PATH}"
         )
 
     # Authorize the client with Google defaults
@@ -85,8 +89,8 @@ def execute_notebook_remote(
 
     build.steps = cloudbuild_config["steps"]
     build.substitutions = substitutions
-    build.timeout = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
-    build.queue_ttl = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
+    build.timeout = duration_pb2.Duration(seconds=timeout_in_seconds)
+    build.queue_ttl = duration_pb2.Duration(seconds=timeout_in_seconds)
 
     if tag:
         build.tags = [tag]

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

@@ -4,28 +4,35 @@ steps:
     entrypoint: /bin/sh
     args:
     - -c
-    - 'gcloud config list'
+    - 'gcloud config list --quiet'
   # Check the Python version
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 .cloud-build/CheckPythonVersion.py'
+    - ${_PYTHON_VERSION} .cloud-build/CheckPythonVersion.py -q
+  # Create a virtual environment
+  - name: ${_PYTHON_IMAGE}
+    entrypoint: /bin/sh
+    args:
+    - -c
+    - ${_PYTHON_VERSION} -m venv workspace/env
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 -m pip install -U pip && python3 -m pip install -U --user -r .cloud-build/requirements.txt'
+    - . workspace/env/bin/activate &&
+      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: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 -m pip install -U pip && python3 -m pip freeze && python3 .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"'
+    - |
+      . workspace/env/bin/activate &&
+      python .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"
     env:
     - 'IS_TESTING=1'
 timeout: 86400s
-options:
-  pool:
-    name: ${_PRIVATE_POOL_NAME}

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

@@ -4,35 +4,42 @@ steps:
     entrypoint: /bin/sh
     args:
     - -c
-    - 'gcloud config list'
+    - gcloud config list --quiet
   # Check the Python version
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 .cloud-build/CheckPythonVersion.py'
-  # Fetch base branch if required
+    - python3 .cloud-build/CheckPythonVersion.py -q
+  # Fetch full repo for diff purposes
+  - name: gcr.io/cloud-builders/git
+    args: [fetch, --unshallow, --quiet]
+  # Create a virtual environment
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'if [ -n "${_BASE_BRANCH}" ]; then git fetch origin "${_BASE_BRANCH}":refs/remotes/origin/"${_BASE_BRANCH}"; else echo "Skipping fetch."; fi'
+    - python3 -m venv workspace/env
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 -m pip install -U pip && python3 -m pip install -U --user -r .cloud-build/requirements.txt'
+    - . workspace/env/bin/activate &&
+      python3 -m pip -q install -U pip &&
+      python3 -m pip -q install -U -r .cloud-build/requirements.txt
   # Install Python dependencies and run testing script
   # TODO: Only pass in private_pool_id if it is set
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - 'python3 -m pip install -U pip && python3 -m pip freeze && python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi`'
+    - |
+      . workspace/env/bin/activate &&
+      python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} --variable_service_account ${_GCP_SERVICE_ACCOUNT} --variable_vpc_network "${_GPC_VPC_NETWORK_NAME}" `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi`
     env:
     - 'IS_TESTING=1'
 timeout: 86400s
 options:
   pool:
-    name: ${_PRIVATE_POOL_NAME}
+    name: ${_PRIVATE_POOL_NAME}

.cloud-build/requirements.txt

@@ -9,4 +9,5 @@ tabulate
 google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
-gcloud
+ratemate
+GitPython

.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/matching_engine/intro-swivel.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/custom/custom-tabular-bq-managed-dataset.ipynb
+.cloud-build/tests/python_version_test.ipynb

.cloud-build/test_single_notebook_vm.txt

@@ -0,0 +1 @@
+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

@@ -13,8 +13,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nbconvert.preprocessors import Preprocessor
 from typing import Dict
+import random
+import string
+
+from nbconvert.preprocessors import Preprocessor
+
 from . import UpdateNotebookVariables as update_notebook_variables
 
 
@@ -60,4 +64,31 @@ class UpdateVariablesPreprocessor(Preprocessor):
 
             executable_cells.append(cell)
         notebook.cells = executable_cells
-        return notebook, resources
+        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

@@ -35,47 +35,8 @@ Variables in conditionals can also be replaced:
 
 def get_updated_value(content: str, variable_name: str, variable_value: str) -> str:
     return re.sub(
-        rf"({variable_name}.*?=.*?[\",\'])\[.+?\]([\",\'].*?)",
-        rf"\1{variable_value}\2",
+        rf"({variable_name}.*? = .*?[\",\'])\[.+?\]([\",\'].*?)",
+        rf"\g<1>{variable_value}\g<2>",
         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"}'

.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

@@ -1,13 +1,13 @@
-from datetime import datetime
-from typing import Optional
-from google.cloud import storage
-from google.cloud.aiplatform import utils
-from google.auth import credentials as auth_credentials
 import os
-
 import subprocess
 import tarfile
 import uuid
+from datetime import datetime
+from typing import Optional, Union
+
+from google.auth import credentials as auth_credentials
+from google.cloud import storage
+from google.cloud.aiplatform import utils
 
 
 def download_file(bucket_name: str, blob_name: str, destination_file: str) -> str:
@@ -57,4 +57,35 @@ def archive_code_and_upload(staging_bucket: str):
 
     print(f"Uploaded source code archive to {source_archived_file_gcs}")
 
-    return 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/PULL_REQUEST_TEMPLATE.md

@@ -1,18 +1,28 @@
-If you are opening a PR for `Official Notebooks` under the [notebooks/official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder, follow this mandatory checklist:
+**REQUIRED:** Add a summary of your PR here, typically including why the change is needed and what was changed. Include any design alternatives for discussion purposes.
+
+<br>
+--- YOUR PR SUMMARY GOES HERE ---
+<br><br><br>
+
+**REQUIRED:** Fill out the below checklists or remove if irrelevant
+1. If you are opening a PR for `Official Notebooks` under the [notebooks/official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder, follow this mandatory checklist:
 - [ ] Use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.
 - [ ] Follow the style and grammar rules outlined in the above notebook template.
 - [ ] Verify the notebook runs successfully in Colab since the automated tests cannot guarantee this even when it passes.
-- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 - [ ] You have consulted with a tech writer to see if tech writer review is necessary. If so, the notebook has been reviewed by a tech writer, and they have approved it.
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under `# Official Notebooks` section, pointing to the author or the author's team.
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/CODEOWNERS) file under the `Official Notebooks` section, pointing to the author or the author's team.
 - [ ] The Jupyter notebook cleans up any artifacts it has created (datasets, ML models, endpoints, etc) so as not to eat up unnecessary resources.
 
+<br>
 
-If you are opening a PR for `Community Notebooks` under the [notebooks/community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder:
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Notebooks` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+2. If you are opening a PR for `Community Notebooks` under the [notebooks/community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder:
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/CODEOWNERS) file under the `Community Notebooks` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 
-If you are opening a PR for `Community Content` under the [community-content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/community-content) folder:
+<br>
+
+3. If you are opening a PR for `Community Content` under the [community-content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/community-content) folder:
 - [ ] Make sure your main `Content Directory Name` is descriptive, informative, and includes some of the key products and attributes of your content, so that it is differentiable from other content
-- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Content` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/community-content/CODEOWNERS) file under the `Community Content` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).

.github/workflows/ci.yaml

@@ -7,7 +7,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'      
     - name: Fetch pull request branch
       uses: actions/checkout@v3
       with:

.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/requirements.txt

@@ -2,8 +2,9 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==22.1.0
-pyupgrade==2.31.1
+black==22.6.0
+pyupgrade==2.34.0
 isort==5.10.1
 flake8==4.0.1
-nbqa==1.3.1
+nbqa==1.4.0
+

.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
@@ -68,7 +78,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
 
             if [ "$is_test" = true ]; then
                 echo "Running nbfmt..."
-                python3 -m tensorflow_docs.tools.nbfmt --remove_outputs --test "$notebook"
+                python3 -m tensorflow_docs.tools.nbfmt --test "$notebook"
                 NBFMT_RTN=$?
                 # echo "Running black..."
                 # python3 -m nbqa black "$notebook" --check
@@ -93,7 +103,7 @@ if [ ${#notebooks[@]} -gt 0 ]; then
                 python3 -m nbqa isort "$notebook"
                 ISORT_RTN=$?
                 echo "Running nbfmt..."
-                python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
+                python3 -m tensorflow_docs.tools.nbfmt "$notebook"
                 NBFMT_RTN=$?
                 echo "Running flake8..."
                 python3 -m nbqa flake8 "$notebook" --show-source --extend-ignore=W391,E501,F821,E402,F404,W503,E203,E722,W293,W291

CONTRIBUTING.md

@@ -48,8 +48,8 @@ then you will need to manually address them before submitting your PR.
 nbqa black "$notebook"
 nbqa pyupgrade "$notebook"
 nbqa isort "$notebook"
-python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 nbqa flake8 "$notebook" --extend-ignore=W391,E501,F821,E402,F404,W503,E203,E722,W293,W291
+python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 ```
 
 ## Code Reviews

community-content/CODEOWNERS

@@ -1,5 +1,9 @@
 *  @vertex-ai-samples-contributors  @GoogleCloudPlatform/cloudml-samples-owners
 /tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk	@yinghsienwu
+/pytorch_pre_built_images_deployment @googleapis/vertex-prediction-team
 /pytorch_text_classification_using_vertex_sdk_and_gcloud  @RajeshThallam
 /pytorch_text_classification_using_vertex_sdk_and_gcloud		@RajeshThallam @ultrons
 /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/.dockerignore

@@ -0,0 +1,5 @@
+testdata/*
+build.py
+test.py
+state_dict.pth
+config.json

community-content/cpr-examples/timm_serving/.gitignore

@@ -0,0 +1,6 @@
+cpr_model_server.py
+entrypoint.py
+state_dict.pth
+config.json
+**/__pycache__
+!testdata/**

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

@@ -0,0 +1,110 @@
+# CPR Example: PyTorch Image Models (timm)
+
+## About CPR
+
+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
+
+This code is a self-contained example of a custom model server project built using CPR.
+
+As is, you can use it to serve the ViT-Small image classification model from Ross Wightman's [`timm`](https://github.com/rwightman/pytorch-image-models) library of image model implementations in PyTorch. Both CPU and GPU are supported.
+
+You can also consider using the code here as a template for your own CPR project if you want to use a different model from `timm`, a different PyTorch model, or an entirely different framework.
+
+### Requirements
+
+In order to use this example, you'll need Docker and Python 3 installed on your system.
+
+To get started, first create a virtual environment in an empty directory:
+```sh
+mkdir cpr-example
+python3 -m venv cpr-example
+cd cpr-example && source bin/activate
+``` 
+
+Then, clone the [vertex-ai-samples repo](https://github.com/GoogleCloudPlatform/vertex-ai-samples) in that directory:
+```sh
+git clone https://github.com/GoogleCloudPlatform/vertex-ai-samples.git
+cd vertex-ai-samples/community-content/cpr-examples/timm_serving
+```
+
+Finally, install the Python modules required to build and run the model server:
+```sh
+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.
+
+- `load(artifacts_dir)`: The predictor's `load` method is called when the server starts up in order to set up the predictor, usually by loading model weights and any artifacts needed for preprocessing and postprocessing. In this example, we initialize the saved model from the `state_dict.pth` file located inside the `artifacts_dir` folder and create the preprocessing transform from the model config.
+
+- `preprocess`, `predict`, `postprocess`: These methods are applied in sequence to the deserialized JSON data from each request. 
+    - `preprocess` decodes images from base64 and apply cropping, scaling and normalizing transforms. 
+    - `predict` runs the ViT-Small model on the preprocessed images and returns class scores.
+    - `postprocess` finds the top five classes and packs the class names, probabilities, and indices in a serializable result.
+
+### Building the container
+
+To build the model server locally, run the build command:
+```sh
+python build.py build
+```
+
+You can edit configuration values such as the model server's base image, the name and tag assigned to the image, and the path where model weights are stored locally.
+
+When you run the build command, model weights are downloaded and the model server container is built.
+
+### Running local tests
+
+`test.py` contains a suite of unit tests for the predictor as well as end-to-end tests for the model server. 
+
+To run the tests:
+```sh
+python test.py
+```
+
+All of the test images are public domain.
+- [Cat](https://commons.wikimedia.org/wiki/File:Stray_cat_on_wall.jpg)
+- [Airplane](https://commons.wikimedia.org/wiki/File:Airplanes_jets.jpg)
+- The infamous [mandrill](https://commons.wikimedia.org/wiki/File:Wikipedia-sipi-image-db-mandrill-4.2.03.png)
+
+### Deploying to Vertex AI
+
+Before uploading or deploying the container, you'll need to modify `config.py` to set appropriate values for: 
+- `project_id`: Your GCP project id.
+- `region`: Region where the model will be uploaded and deployed.
+- `repository`: [Artifact Registry repository](https://cloud.google.com/artifact-registry/docs/repositories/create-repos) in your project where the container image will be uploaded. 
+- `artifacts_gcs_dir`: Folder in a [Google Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) where the model weights will be uploaded.
+
+Once this is done, first upload the model:
+```sh
+python build.py upload
+```
+
+Then deploy it:
+```sh
+python build.py deploy
+```
+
+If you run the deploy command again, it will create a new endpoint. If you want to undeploy the model, you can do so using the Vertex AI dashboard on the Google Cloud console, or use `gcloud ai endpoints undeploy` from the command line.
+
+After deploying successfully, you can run `python build.py probe` to send a sample request to the deployed model. 

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

@@ -0,0 +1,117 @@
+# Copyright 2022 Google LLC
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     https://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Build the model server container."""
+import json
+import logging
+import os
+import pathlib
+from typing import Sequence
+
+from absl import app
+from absl import logging
+from config import CPRConfig
+from google.cloud import aiplatform
+from google.cloud.aiplatform import prediction as cpr
+import smart_open
+import timm
+from timm_serving import predictor
+import torch
+
+
+def build_container(config: CPRConfig, tag: str) -> cpr.LocalModel:
+    """Build the model server container.
+
+    Args:
+      tag: Output image tag.
+
+    Returns:
+      LocalModel exposing the built model server.
+    """
+    return cpr.LocalModel.build_cpr_model(
+        src_dir=os.path.join(os.getcwd()),
+        output_image_uri=tag,
+        base_image=config.base_image,
+        predictor=predictor.TimmPredictor,
+        requirements_path=os.path.join(os.getcwd(), "requirements.txt"),
+    )
+
+
+def save_model_artifact(destination: str) -> None:
+    """Save a copy of the model state dict."""
+    model = timm.create_model(predictor.TimmPredictor.TIMM_MODEL_NAME, pretrained=True)
+    dest_file = os.path.join(destination, predictor.TimmPredictor.WEIGHTS_FILE)
+    with smart_open.open(dest_file, "wb") as f:
+        torch.save(model, f)
+    logging.info("Saved model to %s", dest_file)
+    logging.info("%s parameters", sum(p.numel() for p in model.parameters()))
+
+
+def upload_model(config: CPRConfig) -> aiplatform.Model:
+    """Tag and upload the model server."""
+    ar_tag = (
+        f"{config.region}-docker.pkg.dev/{config.project_id}"
+        f"/{config.repository}/{config.image}"
+    )
+    local_model = build_container(config, tag=ar_tag)
+    aiplatform.init(project=config.project_id, location=config.region)
+    local_model.push_image()
+    aip_model = aiplatform.Model.upload(
+        local_model=local_model,
+        display_name=predictor.TimmPredictor.TIMM_MODEL_NAME,
+        artifact_uri=config.artifact_gcs_dir,
+    )
+    config.model_name = aip_model.resource_name
+    config.save()
+    return aip_model
+
+
+def deploy_model(config: CPRConfig) -> aiplatform.Endpoint:
+    """Deploy the model server to a Vertex Prediction endpoint."""
+    aiplatform.init(project=config.project_id, location=config.region)
+    aip_model = aiplatform.Model(model_name=config.model_name)
+    endpoint = aip_model.deploy(machine_type=config.machine_type)
+    config.endpoint_name = endpoint.resource_name
+    config.save()
+    return endpoint
+
+
+def probe_prediction(config: CPRConfig, request_path: str) -> None:
+    """Send a sample prediction request to the Vertex Prediction endpoint."""
+    aiplatform.init(project=config.project_id, location=config.region)
+    aip_endpoint = aiplatform.Endpoint(endpoint_name=config.endpoint_name)
+    with open(request_path) as f:
+        logging.info(aip_endpoint.predict(**json.load(f)))
+
+
+def main(argv: Sequence[str]):
+    config = CPRConfig()
+    if pathlib.Path(config.config_file).exists():
+        config.load()
+
+    actions = set(argv[1:])
+    if "build" in actions:
+        build_container(config, config.image)
+        save_model_artifact(config.artifact_local_dir)
+    if "upload" in actions:
+        save_model_artifact(config.artifact_gcs_dir)
+        upload_model(config)
+    if "deploy" in actions:
+        deploy_model(config)
+    if "probe" in actions:
+        probe_prediction(config, request_path="sample_request.json")
+
+
+if __name__ == "__main__":
+    app.run(main)

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

@@ -0,0 +1,76 @@
+# Copyright 2022 Google LLC
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     https://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import dataclasses
+import json
+
+
+@dataclasses.dataclass
+class CPRConfig(object):
+    """Configure the build process by editing the default values here.
+
+    config_file: File path used to save values in this config. (Some
+      values, such as the model name, are generated at build time and
+      depended on by future steps, so saving it allows this script to
+      deploy the model without re-uploading it, for example.)
+
+    base_image: Base Docker image on top of which the model server will
+      be built. By default, a Debian-based Python 3 image without GPU
+      support will be used.
+
+    image: Name and tag assigned to the built model server image.
+
+    artifact_local_dir: Local directory where a copy of the pretrained model weights
+      will be saved.
+
+    region: Google Cloud Region where the model will be uploaded during the
+      build process.
+
+    project_id: Google Cloud project ID.
+
+    repository: Name of the Artifact Registry repository where the container
+      will be uploaded.
+
+    artifact_gcs_dir: Location on GCS where a copy of the pretrained model
+      weights will be uploaded.
+
+    model_name: Full resource path of the uploaded model. This is a write-only
+      field, the value is generated by Vertex AI when the model is uploaded.
+
+    endpoint_name: Full resource path of the created endpoint. This is a
+      write-only field, the value is generated by Vertex AI when the model is
+      deployed to an endpoint.
+
+    machine_type: Machine type to use when deploying the model.
+    """
+
+    config_file: str = "config.json"
+    base_image: str = "python:3.10-bullseye"
+    image: str = "timm_predictor:latest"
+    artifact_local_dir: str = ""
+    region: str = "us-central1"
+    project_id: str = "<your project ID here>"
+    repository: str = "cpr-images"
+    artifact_gcs_dir: str = "gs://<your bucket ID here>/timm-vit224/"
+    model_name: str = ""
+    endpoint_name: str = ""
+    machine_type: str = "n1-standard-2"
+
+    def save(self):
+        with open(self.config_file, "w") as f:
+            json.dump(dataclasses.asdict(self), f, indent=2)
+
+    def load(self):
+        with open(self.config_file) as f:
+            self.__init__(**json.load(f))

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

@@ -0,0 +1,8 @@
+absl-py==1.1.0
+fastapi==0.75.2
+uvicorn==0.18.2
+timm==0.5.4
+smart_open==6.0.0
+
+google-cloud-storage>=1.26.0,<2.0.0dev
+google-cloud-aiplatform[prediction]>=1.16.0

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

@@ -0,0 +1,255 @@
+"""Test the timm_serving predictor."""
+import base64
+import json
+import logging
+import os
+import pickle
+from typing import List, Dict
+
+from absl import flags
+from absl import logging
+from absl.testing import absltest
+from config import CPRConfig
+import fastapi
+from google.cloud import aiplatform
+from google.cloud.aiplatform import prediction as cpr
+import PIL
+from timm_serving import predictor
+import torch
+
+VIT_SMALL_PARAMS = 22878952
+
+
+def b64_encode_file(path: str) -> str:
+    """Encode a file's contents as base64.
+
+    Args:
+      path: Path to the file.
+
+    Returns:
+      Base64-encoded contents of the file.
+    """
+    with open(path, "rb") as f:
+        return str(base64.b64encode(f.read()), encoding="utf-8")
+
+
+def make_instance_dict(
+    image_paths: List[str], base64_encodings: List[str]
+) -> Dict[str, List[str]]:
+    """Generate a dictionary similar to a parsed prediction server request.
+
+    Args:
+      image_paths: Paths to image files to include.
+      base64_encodings: Pre-encoded base64 strings.
+
+    Returns:
+      Dictionary of instances in the format accepted by the preprocessor.
+    """
+    instances = [s for s in base64_encodings]
+    for path in image_paths:
+        instances.append(b64_encode_file(path))
+    return {"instances": instances}
+
+
+def count_parameters(model: torch.nn.Module):
+    """Count the parameters in a Pytorch model.
+
+    Args:
+      model: Pytorch model (nn.Module).
+
+    Returns:
+      Number of parameters in the model.
+
+    """
+    return sum(p.numel() for p in model.parameters())
+
+
+class PredictorUnitTests(absltest.TestCase):
+    """Unit tests for timm_serving.predictor."""
+
+    def setUp(self):
+        super().setUp()
+        self.config = CPRConfig()
+        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):
+        self.predictor.load(self.config.artifact_local_dir)
+        self.assertEqual(count_parameters(self.predictor._model), VIT_SMALL_PARAMS)
+
+    def test_load_bad_path(self):
+        with self.assertRaises(FileNotFoundError):
+            self.predictor.load("testdata/")
+        with self.assertRaisesRegex(ValueError, "not a directory"):
+            self.predictor.load("blah")
+
+    def test_load_bad_data(self):
+        with self.assertRaises(pickle.UnpicklingError):
+            self.predictor.load("testdata/bad_model_1")
+        with self.assertRaisesRegex(RuntimeError, "Invalid magic number"):
+            self.predictor.load("testdata/bad_model_2")
+
+    def test_preprocess_ok(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        instance_dict = make_instance_dict(
+            base64_encodings=[],
+            image_paths=[
+                "testdata/airplane.jpg",
+                "testdata/mandrill.tiff",
+                "testdata/mandrill.tiff",
+                "testdata/cat_alpha.png",
+            ],
+        )
+        result = self.predictor.preprocess(instance_dict)
+        self.assertEqual(result.size(), torch.Size([4, 3, 224, 224]))
+        self.assertEqual(result.dtype, torch.float32)
+
+    def test_preprocess_no_instances(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        with self.assertRaises(fastapi.HTTPException) as ctx:
+            self.predictor.preprocess({})
+        self.assertEqual(ctx.exception.status_code, 400)
+        self.assertRegex(ctx.exception.detail, 'must contain "instances"')
+
+    def test_preprocess_wrong_shape_instances(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        instance_dict = {"instances": [[b64_encode_file("testdata/mandrill.tiff")]]}
+        with self.assertRaises(fastapi.HTTPException) as ctx:
+            self.predictor.preprocess(instance_dict)
+        self.assertEqual(ctx.exception.status_code, 400)
+        self.assertRegex(ctx.exception.detail, "not 'list'")
+
+    def test_preprocess_bad_base64(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        instance_dict = make_instance_dict(base64_encodings=["!@#$"], image_paths=[])
+        with self.assertRaises(fastapi.HTTPException) as ctx:
+            self.predictor.preprocess(instance_dict)
+        self.assertEqual(ctx.exception.status_code, 400)
+        self.assertRegex(ctx.exception.detail, "[Bb]ase64")
+
+    def test_preprocess_not_image_data(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        instance_dict = make_instance_dict(
+            base64_encodings=[], image_paths=["testdata/bad.jpg"]
+        )
+        with self.assertRaises(fastapi.HTTPException) as ctx:
+            self.predictor.preprocess(instance_dict)
+        self.assertEqual(ctx.exception.status_code, 400)
+        self.assertRegex(ctx.exception.detail, "image file")
+
+    def test_predict_ok(self):
+        self.predictor.load(self.config.artifact_local_dir)
+        inputs = torch.zeros(size=[2, 3, 224, 224], dtype=torch.float32)
+        if torch.cuda.device_count() > 0:
+            inputs = inputs.cuda()
+        result = self.predictor.predict(inputs)
+        self.assertEqual(result.size(), torch.Size([2, 1000]))
+        self.assertEqual(result.dtype, torch.float32)
+
+    def test_postprocess_ok(self):
+        class_probs = torch.zeros(size=[2, 1000])
+        class_probs[0, 0] = 1
+        class_probs[1, 123] = 1
+        result = self.predictor.postprocess(class_probs)
+        predictions = result["predictions"]
+        self.assertLen(predictions[0]["class_names"], 5)
+        self.assertLen(predictions[0]["indices"], 5)
+        self.assertLen(predictions[0]["probabilities"], 5)
+        self.assertLen(predictions[1]["class_names"], 5)
+        self.assertLen(predictions[1]["indices"], 5)
+        self.assertLen(predictions[1]["probabilities"], 5)
+        self.assertContainsSubsequence(predictions[0]["class_names"][0], "tench")
+        self.assertContainsSubsequence(
+            predictions[1]["class_names"][0], "spiny lobster"
+        )
+
+
+class ServerEndToEndTests(absltest.TestCase):
+    """End-to-end tests for the model server, using LocalEndpoint."""
+
+    def setUp(self):
+        super().setUp()
+        self.config = CPRConfig()
+        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
+            )
+        )
+
+        self.local_endpoint = self.local_model.deploy_to_local_endpoint(
+            artifact_uri=self.config.artifact_local_dir or os.getcwd()
+        )
+        self.local_endpoint.serve()
+
+    def tearDown(self):
+        self.local_endpoint.stop()
+        super().tearDown()
+
+    def test_e2e_healthcheck_ok(self):
+        health_check_response = self.local_endpoint.run_health_check()
+        self.assertEqual(health_check_response.status_code, 200)
+        self.assertEqual(health_check_response.content, b"{}")
+
+    def test_e2e_predict_ok(self):
+        predict_request = json.dumps(
+            make_instance_dict(
+                base64_encodings=[],
+                image_paths=[
+                    "testdata/mandrill.tiff",
+                ],
+            )
+        )
+        response = self.local_endpoint.predict(
+            request=predict_request, headers={"Content-Type": "application/json"}
+        )
+        logging.info(response.content)
+        self.assertEqual(response.status_code, 200)
+        predictions = response.json()["predictions"]
+        self.assertContainsSubsequence(predictions[0]["class_names"][0], "baboon")
+
+    def test_e2e_predict_bad_json_returns_400(self):
+        predict_request = "blah"
+        response = self.local_endpoint.predict(
+            request=predict_request, headers={"Content-Type": "application/json"}
+        )
+        logging.info(response.content)
+        self.assertEqual(response.status_code, 400)
+
+    def test_e2e_predict_no_instances_returns_400(self):
+        predict_request = json.dumps({})
+        response = self.local_endpoint.predict(
+            request=predict_request, headers={"Content-Type": "application/json"}
+        )
+        logging.info(response.content)
+        self.assertEqual(response.status_code, 400)
+
+    def test_e2e_predict_bad_base64_returns_400(self):
+        predict_request = json.dumps(
+            make_instance_dict(base64_encodings=["blah"], image_paths=[])
+        )
+        response = self.local_endpoint.predict(
+            request=predict_request, headers={"Content-Type": "application/json"}
+        )
+        logging.info(response.content)
+        self.assertEqual(response.status_code, 400)
+
+    def test_e2e_predict_bad_image_returns_400(self):
+        predict_request = json.dumps(
+            make_instance_dict(base64_encodings=[], image_paths=["testdata/bad.jpg"])
+        )
+        response = self.local_endpoint.predict(
+            request=predict_request, headers={"Content-Type": "application/json"}
+        )
+        logging.info(response.content)
+        self.assertEqual(response.status_code, 400)
+
+
+if __name__ == "__main__":
+    absltest.main()

community-content/cpr-examples/timm_serving/testdata/bad.jpg

@@ -0,0 +1 @@
+some non-image data

community-content/cpr-examples/timm_serving/testdata/bad.txt

@@ -0,0 +1 @@
+some non-image data

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

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

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

@@ -0,0 +1,178 @@
+# Copyright 2022 Google LLC
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+#     https://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Adapts a pretrained TIMM image classification model to the CPR framework.
+
+Documentation for the TIMM (Torch IMage Models) library is here:
+  https://rwightman.github.io/pytorch-image-models/
+
+Its source can also be found here:
+  https://github.com/rwightman/pytorch-image-models
+"""
+
+import base64
+import binascii
+import io
+import os
+from typing import Dict, List, Union
+
+from fastapi import HTTPException
+from google.cloud.aiplatform import prediction as cpr
+from pathlib import Path
+import PIL
+import smart_open
+import timm
+import torch
+import torch.nn.functional as F
+
+with open(Path(__file__).parent.absolute().joinpath("imagenet.txt")) as f:
+    IMAGENET_CLASSES = f.read().splitlines()
+
+
+class TimmPredictor(cpr.predictor.Predictor):
+    """Predictor class for image models based on TIMM."""
+
+    TIMM_MODEL_NAME = os.getenv("TIMM_MODEL_NAME", default="vit_small_patch32_224")
+    WEIGHTS_FILE = "state_dict.pth"
+    NUM_TOP_CLASSES_TO_RETURN = 5
+
+    def __init__(self):
+        self._cuda = torch.cuda.device_count() > 0
+
+    def load(self, artifacts_uri: str = ""):
+        """Initializes the model and preprocessing transforms.
+
+        Args:
+          artifacts_uri: Directory where state dict is stored. Can be a
+          GCS URI or local path.
+        """
+        if artifacts_uri:
+            artifact_path = os.path.join(artifacts_uri)
+            if not (os.path.isdir(artifact_path) or artifact_path.startswith("gs://")):
+                raise ValueError("Provided artifact_uri is not a directory.")
+        else:
+            artifact_path = os.getcwd()
+
+        artifact_path = os.path.join(artifact_path, self.WEIGHTS_FILE)
+        with smart_open.open(artifact_path, "rb") as f:
+            self._model = torch.load(f)
+
+        if self._cuda:
+            self._model.cuda()
+
+        config = timm.data.resolve_data_config(model=self.TIMM_MODEL_NAME, args=[])
+        self._transform = timm.data.create_transform(
+            is_training=False, use_prefetcher=False, **config
+        )
+
+    def preprocess(self, request_dict: Dict[str, List[str]]) -> torch.Tensor:
+        """Performs preprocessing.
+
+        By default, the server expects a request body consisting of a valid JSON
+        object. This will be parsed by the handler before it's evaluated by the
+        preprocess method.
+
+        Args:
+          request_dict: Parsed request body. We expect that the input consists of
+            a list of base64-encoded image files under the "instances" key. (Any
+            image format that PIL.image.open can handle is okay.)
+
+        Returns:
+          torch.Tensor containing the preprocessed images as a batch. If GPU is
+          available, the result tensor will be stored on GPU.
+        """
+
+        if "instances" not in request_dict:
+            raise HTTPException(
+                status_code=400,
+                detail='Request must contain "instances" as a top-level key.',
+            )
+
+        tensors = []
+
+        for (i, image) in enumerate(request_dict["instances"]):
+            # We use Base64 encoding to handle image data.
+            # This is probably the best we can do while still using JSON input.
+            # Overriding the input format requires building a custom Handler.
+            try:
+                image_bytes = base64.b64decode(image, validate=True)
+            except (binascii.Error, TypeError) as e:
+                raise HTTPException(
+                    status_code=400,
+                    detail=f"Base64 decoding of the input image at index {i} failed:"
+                    f" {str(e)}",
+                )
+
+            try:
+                pil_image = PIL.Image.open(io.BytesIO(image_bytes)).convert("RGB")
+            except PIL.UnidentifiedImageError:
+                raise HTTPException(
+                    status_code=400,
+                    detail=f"The input image at index {i} could not be identified as an"
+                    " image file.",
+                )
+
+            tensors.append(self._transform(pil_image))
+
+        with torch.inference_mode():
+            result = torch.stack(tensors)
+            if self._cuda:
+                result = result.cuda()
+        return result
+
+    def predict(self, instances: torch.Tensor) -> torch.Tensor:
+        """Performs prediction.
+
+        Args:
+          instances: torch.Tensor with type torch.float32 and shape
+            [?, 3, 224, 224], containing the pre-processed input images.
+
+        Returns:
+          Vector of scores with type torch.float32 and shape [?, 1000],
+            representing the model's estimate of the likelihood that the
+            input belongs to the Imagenet class with that index.
+        """
+        with torch.inference_mode():
+            class_scores = self._model(instances)
+        return class_scores
+
+    def postprocess(
+        self, class_scores: torch.Tensor
+    ) -> Dict[str, List[Dict[str, Union[str, int, float]]]]:
+        """Translate the model output into a classification result.
+
+        Args:
+          class_scores: torch.Tensor with type torch.float32 and shape
+            [?, 1000], containing the scores assigned to each class by
+            the model.
+
+        Returns:
+          Dictionary containing the list of classification results. Each
+            classification result contains the probabilities, class names, and
+            class indices of the classes with the top class scores as reported by
+            the model.
+        """
+        class_probs = F.softmax(class_scores, dim=1)
+        top_k = class_probs.topk(self.NUM_TOP_CLASSES_TO_RETURN)
+        top_k_values = top_k.values.numpy().tolist()
+        top_k_indices = top_k.indices.numpy().tolist()
+        predictions = [
+            dict(
+                probabilities=values,
+                indices=indices,
+                class_names=[IMAGENET_CLASSES[int(class_num)] for class_num in indices],
+            )
+            for (values, indices) in zip(top_k_values, top_k_indices)
+        ]
+        return {"predictions": predictions}

community-content/pluto_on_workbench/README.md

@@ -0,0 +1,52 @@
+# Overview
+*Pluto* is a programming environment for Julia, designed to be interactive and helpful. It provides a familiar notebook interface but it is not a Jupyter notebook. The biggest difference is that Pluto notebooks are reactive, changing a variable or function in one cell causes the cells that depend on that variable or function to be reevaluated. Pluto also provides useful interaction mechanisms that allow users to dynamically interact with the notebooks computation state.
+
+The JuliaCon 2020 presentation: [Interactive notebooks ~ Pluto.jl]() provides a good introduction to Pluto. The source is at [fonsp/Pluto.jl]()
+
+# Install Pluto
+
+## Create a Vertex AI JupyterLab Instance
+
+1. From the [GCP console](https://console.cloud.google.com) "hamburger menu"
+
+   select Vertex AI > Workbench
+2. Click NEW NOTEBOOK
+   
+   * Choose Python 3 if you won't be using a GPU
+   * Choose Python 3 (CUDA Toolkit xx.y) if you do want use a GPU
+3. Give the notebook an appropriate name
+4. Edit Notebook properties if you have special requirements otherwise accept the defaults and click CREATE
+5. When the notebook instance is ready click OPEN JUPYTERLAB
+
+## Configure JupyterLab
+
+1. Open a terminal by clicking the Terminal icon.
+1. Install the plutoserver
+pip3 install git+https://github.com/fonsp/pluto-on-jupyterlab.git
+1. In a browser go to [julialang.org/downloads](https://julialang.org/downloads/)
+1. In the Current stable release right click on the `Generic Linux on x86 / 64-bit (glibc)` link
+Select copy link address
+1. Back in the terminal switch to root via
+sudo -i
+1. Download the release to /opt and install julia in /usr/local/bin
+    ```bash
+    cd /opt
+    wget <paste the release link address>
+    tar xf <name of the downloaded tar file>
+    ln -s /opt/<julia-x.y.z>/bin/julia /usr/local/bin
+    ^d
+    ```
+1. Add the Pluto package to Julia
+   ```bash
+    julia
+    julia> ]add Pluto
+    julia> bksp
+    julia> using Pluto
+    julia> ^d
+    ```
+1. From the JupyterLab menu bar select File > Shut Down
+
+# Start Pluto
+1. Click OPEN JUPYTERLAB in the Workbench
+1. In the Notebook section of the Launcher click Pluto.jl
+1. The welcome to Pluto.jl screen should appear

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb

@@ -1,474 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a6b56b1c7b76"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2021 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# 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": "c414a395a19b"
-      },
-      "source": [
-        "# PyTorch Image Classification Multi-Node Distributed Data Parallel Training on CPU using Vertex Training with Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b98238e32cf7"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_gloo_vertex_training_with_custom_container.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",
-        "</table>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "03d216c7f7b1"
-      },
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c5ac73516218"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"YOUR PROJECT ID\"\n",
-        "BUCKET_NAME = \"gs://YOUR BUCKET NAME\"\n",
-        "REGION = \"YOUR REGION\"\n",
-        "SERVICE_ACCOUNT = \"YOUR SERVICE ACCOUNT\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b5ae674177e"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "19a9b3bdd553"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = \"pt-img-cls-multi-node-ddp-cust-cont\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "57bf6f8b4361"
-      },
-      "source": [
-        "## Local Training"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e5d8a3443da0"
-      },
-      "outputs": [],
-      "source": [
-        "! ls trainer"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "07f79309472d"
-      },
-      "outputs": [],
-      "source": [
-        "! cat trainer/requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e16cd8bb7483"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r trainer/requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b8a210718c4"
-      },
-      "outputs": [],
-      "source": [
-        "! cat trainer/task.py"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c0c6e7dfb3c6"
-      },
-      "outputs": [],
-      "source": [
-        "%run trainer/task.py --epochs 5 --no-cuda --local-mode"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "31dfdeede587"
-      },
-      "outputs": [],
-      "source": [
-        "! ls ./tmp"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "48d56ec621cc"
-      },
-      "outputs": [],
-      "source": [
-        "! rm -rf ./tmp"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8f3ea1210749"
-      },
-      "source": [
-        "## Vertex Training using Vertex SDK and Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "93002a20a2a6"
-      },
-      "source": [
-        "### Build Custom Container"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4130ce43fd08"
-      },
-      "outputs": [],
-      "source": [
-        "hostname = \"gcr.io\"\n",
-        "image_name = content_name\n",
-        "tag = \"latest\"\n",
-        "\n",
-        "custom_container_image_uri = f\"{hostname}/{PROJECT_ID}/{image_name}:{tag}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2f1fc5b05240"
-      },
-      "outputs": [],
-      "source": [
-        "! cd trainer && docker build -t $custom_container_image_uri -f Dockerfile ."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b4f274f499ac"
-      },
-      "outputs": [],
-      "source": [
-        "! docker run --rm $custom_container_image_uri --epochs 5 --no-cuda --local-mode"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ee1a0a06d0b4"
-      },
-      "outputs": [],
-      "source": [
-        "! docker push $custom_container_image_uri"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cb763be12fc9"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud container images list --repository $hostname/$PROJECT_ID"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "10c8cc6b3334"
-      },
-      "source": [
-        "### Initialize Vertex SDK"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "1a12348169fa"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "42e981cefe41"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(\n",
-        "    project=PROJECT_ID,\n",
-        "    staging_bucket=BUCKET_NAME,\n",
-        "    location=REGION,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "73c92c9298e9"
-      },
-      "source": [
-        "### Create a Vertex Tensorboard Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bde509558cd5"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = content_name + \"-cpu\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6d7908c0083c"
-      },
-      "outputs": [],
-      "source": [
-        "tensorboard = aiplatform.Tensorboard.create(\n",
-        "    display_name=content_name,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a1f0a4f54037"
-      },
-      "source": [
-        "#### Option: Use a Previously Created Vertex Tensorboard Instance\n",
-        "\n",
-        "```\n",
-        "tensorboard_name = \"Your Tensorboard Resource Name or Tensorboard ID\"\n",
-        "tensorboard = aiplatform.Tensorboard(tensorboard_name=tensorboard_name)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a4cac84e04ac"
-      },
-      "source": [
-        "### Run a Vertex SDK CustomContainerTrainingJob"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f92e8fdd44ee"
-      },
-      "outputs": [],
-      "source": [
-        "display_name = content_name\n",
-        "gcs_output_uri_prefix = f\"{BUCKET_NAME}/{display_name}\"\n",
-        "\n",
-        "replica_count = 4\n",
-        "machine_type = \"n1-standard-4\"\n",
-        "\n",
-        "args = [\n",
-        "    \"--backend\",\n",
-        "    \"gloo\",\n",
-        "    \"--no-cuda\",\n",
-        "    \"--batch-size\",\n",
-        "    \"128\",\n",
-        "    \"--epochs\",\n",
-        "    \"25\",\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ae4c57df7e07"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job = aiplatform.CustomContainerTrainingJob(\n",
-        "    display_name=display_name,\n",
-        "    container_uri=custom_container_image_uri,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "35cf3ecdf0df"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job.run(\n",
-        "    args=args,\n",
-        "    base_output_dir=gcs_output_uri_prefix,\n",
-        "    replica_count=replica_count,\n",
-        "    machine_type=machine_type,\n",
-        "    tensorboard=tensorboard.resource_name,\n",
-        "    service_account=SERVICE_ACCOUNT,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "49d10dded73b"
-      },
-      "outputs": [],
-      "source": [
-        "print(f\"Custom Training Job Name: {custom_container_training_job.resource_name}\")\n",
-        "print(f\"GCS Output URI Prefix: {gcs_output_uri_prefix}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "78398f52807b"
-      },
-      "source": [
-        "### Training Output Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fc74422de1d1"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls $gcs_output_uri_prefix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5e99a6a05b10"
-      },
-      "source": [
-        "## Clean Up Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b0c1b3f7466b"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil rm -rf $gcs_output_uri_prefix"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb

@@ -1,347 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a6b56b1c7b76"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2021 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# 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": "20a5ea0081d0"
-      },
-      "source": [
-        "# PyTorch Image Classification Multi-Node Distributed Data Parallel Training on GPU using Vertex Training with Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8752d4a255fb"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_nccl_vertex_training_with_custom_container.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",
-        "</table>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "03d216c7f7b1"
-      },
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c5ac73516218"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"YOUR PROJECT ID\"\n",
-        "BUCKET_NAME = \"gs://YOUR BUCKET NAME\"\n",
-        "REGION = \"YOUR REGION\"\n",
-        "SERVICE_ACCOUNT = \"YOUR SERVICE ACCOUNT\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b5ae674177e"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "19a9b3bdd553"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = \"pt-img-cls-multi-node-ddp-cust-cont\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5307fe28b633"
-      },
-      "source": [
-        "## Vertex Training using Vertex SDK and Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "46cb58c7fbf9"
-      },
-      "source": [
-        "### Built Custom Container"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "97e66e9f9bab"
-      },
-      "outputs": [],
-      "source": [
-        "hostname = \"gcr.io\"\n",
-        "image_name = content_name\n",
-        "tag = \"latest\"\n",
-        "\n",
-        "custom_container_image_uri = f\"{hostname}/{PROJECT_ID}/{image_name}:{tag}\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ae9b29c4773f"
-      },
-      "source": [
-        "### Initialize Vertex SDK"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "dc1e84d5dec2"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6964be27b98e"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(\n",
-        "    project=PROJECT_ID,\n",
-        "    staging_bucket=BUCKET_NAME,\n",
-        "    location=REGION,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "594a91f438f2"
-      },
-      "source": [
-        "### Create a Vertex Tensorboard Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "93134273261e"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = content_name + \"-gpu\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c2bd82dbcd9b"
-      },
-      "outputs": [],
-      "source": [
-        "tensorboard = aiplatform.Tensorboard.create(\n",
-        "    display_name=content_name,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ebc593c6472e"
-      },
-      "source": [
-        "#### Option: Use a Previously Created Vertex Tensorboard Instance\n",
-        "\n",
-        "```\n",
-        "tensorboard_name = \"Your Tensorboard Resource Name or Tensorboard ID\"\n",
-        "tensorboard = aiplatform.Tensorboard(tensorboard_name=tensorboard_name)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0769e8e34c2f"
-      },
-      "source": [
-        "### Run a Vertex SDK CustomContainerTrainingJob"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "023f33ece826"
-      },
-      "outputs": [],
-      "source": [
-        "display_name = content_name\n",
-        "gcs_output_uri_prefix = f\"{BUCKET_NAME}/{display_name}\"\n",
-        "\n",
-        "replica_count = 1\n",
-        "machine_type = \"n1-standard-4\"\n",
-        "accelerator_count = 4\n",
-        "accelerator_type = \"NVIDIA_TESLA_K80\"\n",
-        "\n",
-        "args = [\n",
-        "    \"--backend\",\n",
-        "    \"nccl\",\n",
-        "    \"--batch-size\",\n",
-        "    \"128\",\n",
-        "    \"--epochs\",\n",
-        "    \"25\",\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d4b599e726ef"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job = aiplatform.CustomContainerTrainingJob(\n",
-        "    display_name=display_name,\n",
-        "    container_uri=custom_container_image_uri,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "81321e3bdf7f"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job.run(\n",
-        "    args=args,\n",
-        "    base_output_dir=gcs_output_uri_prefix,\n",
-        "    replica_count=replica_count,\n",
-        "    machine_type=machine_type,\n",
-        "    accelerator_count=accelerator_count,\n",
-        "    accelerator_type=accelerator_type,\n",
-        "    tensorboard=tensorboard.resource_name,\n",
-        "    service_account=SERVICE_ACCOUNT,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "5100712c2c4c"
-      },
-      "outputs": [],
-      "source": [
-        "print(f\"Custom Training Job Name: {custom_container_training_job.resource_name}\")\n",
-        "print(f\"GCS Output URI Prefix: {gcs_output_uri_prefix}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f9b77676e5a6"
-      },
-      "source": [
-        "### Training Output Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0e171ce95ace"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls $gcs_output_uri_prefix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cf1b74a12b87"
-      },
-      "source": [
-        "## Clean Up Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a0b15089c341"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil rm -rf $gcs_output_uri_prefix"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

community-content/pytorch_pre_built_images_deployment/README.md

@@ -0,0 +1,30 @@
+# PyTorch Deployment on Google Cloud: Text Classification
+
+**This is an Experimental release**, covered by the Pre-GA Offerings Terms of your Google Cloud Platform [Terms of Service](https://cloud.google.com/terms).
+
+Experiments are focused on validating a prototype and are not guaranteed to be released. They are not intended for production use or covered by any SLA, support obligation, or deprecation policy and might be subject to backward-incompatible changes.
+
+**Kindly drop us a note before you run any scale tests.**
+
+**Do not hesitate to contact vertexai-prediction-preview-feedback@google.com if you have any questions or run into any issues.**
+
+The projects need to be added to the allowlist in order to deploy PyTorch models using Vertex AI Prediction pre-built PyTorch images. If you are interested in the feature, please send an email to vertexai-prediction-preview-feedback@google.com to provide your project numbers OR project ids.
+
+## Overview
+
+In the PyTorch on Google Cloud series of blog posts, we aim to share how to deploy PyTorch models at scale on [Vertex AI](https://cloud.google.com/vertex-ai).
+
+This tutorial on text classification shows how to deploy a PyTorch based text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/start/client-libraries#python) using Vertex SDK and [`gcloud ai`](https://cloud.google.com/sdk/gcloud/reference/beta/ai).
+
+## Notebooks
+
+| <h4>Notebook</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [pytorch-text-classification-vertex-ai-deploy.ipynb](./pytorch-text-classification-vertex-ai-deploy.ipynb) | Notebook to show deploying a PyTorch model on Vertex AI |
+
+## Folders
+
+
+| <h4>Folder Name</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [`predictor`](./predictor) | Folder with custom prediction handler to deploy a PyTorch model to Vertex Prediction. In the [notebook](./pytorch-text-classification-vertex-ai-deploy.ipynb), this folder is used for deploying a PyTorch model on Vertex AI using Vertex Prediction pre-built PyTorch images |

community-content/pytorch_pre_built_images_deployment/predictor/custom_handler.py

@@ -0,0 +1,91 @@
+
+import os
+import json
+import logging
+
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from ts.torch_handler.base_handler import BaseHandler
+
+logger = logging.getLogger(__name__)
+
+
+class TransformersClassifierHandler(BaseHandler):
+    """
+    The handler takes an input string and returns the classification text 
+    based on the serialized transformers checkpoint.
+    """
+    def __init__(self):
+        super(TransformersClassifierHandler, self).__init__()
+        self.initialized = False
+
+    def initialize(self, ctx):
+        """ Loads the model.pt file and initialized the model object.
+        Instantiates Tokenizer for preprocessor to use
+        Loads labels to name mapping file for post-processing inference response
+        """
+        self.manifest = ctx.manifest
+
+        properties = ctx.system_properties
+        model_dir = properties.get("model_dir")
+        self.device = torch.device("cuda:" + str(properties.get("gpu_id")) if torch.cuda.is_available() else "cpu")
+
+        # Read model serialize/pt file
+        serialized_file = self.manifest["model"]["serializedFile"]
+        model_pt_path = os.path.join(model_dir, serialized_file)
+        if not os.path.isfile(model_pt_path):
+            raise RuntimeError("Missing the model.pt or pytorch_model.bin file")
+        
+        # Load model
+        self.model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+        self.model.to(self.device)
+        self.model.eval()
+        logger.debug('Transformer model from path {0} loaded successfully'.format(model_dir))
+        
+        # Ensure to use the same tokenizer used during training
+        self.tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+
+        # Read the mapping file, index to object name
+        mapping_file_path = os.path.join(model_dir, "index_to_name.json")
+
+        if os.path.isfile(mapping_file_path):
+            with open(mapping_file_path) as f:
+                self.mapping = json.load(f)
+        else:
+            logger.warning('Missing the index_to_name.json file. Inference output will default.')
+            self.mapping = {"0": "Negative",  "1": "Positive"}
+
+        self.initialized = True
+
+    def preprocess(self, data):
+        """ Preprocessing input request by tokenizing
+            Extend with your own preprocessing steps as needed
+        """
+        text = data[0].get("data")
+        if text is None:
+            text = data[0].get("body")
+        sentences = text.decode('utf-8')
+        logger.info("Received text: '%s'", sentences)
+
+        # Tokenize the texts
+        tokenizer_args = ((sentences,))
+        inputs = self.tokenizer(*tokenizer_args,
+                                padding='max_length',
+                                max_length=128,
+                                truncation=True,
+                                return_tensors = "pt")
+        return inputs
+
+    def inference(self, inputs):
+        """ Predict the class of a text using a trained transformer model.
+        """
+        prediction = self.model(inputs['input_ids'].to(self.device))[0].argmax().item()
+
+        if self.mapping:
+            prediction = self.mapping[str(prediction)]
+
+        logger.info("Model predicted: '%s'", prediction)
+        return [prediction]
+
+    def postprocess(self, inference_output):
+        return inference_output

community-content/pytorch_pre_built_images_deployment/predictor/index_to_name.json

@@ -0,0 +1,5 @@
+
+{
+    "0": "Negative", 
+    "1": "Positive"
+}

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/pytorch-text-classification-vertex-ai-train-tune-deploy.ipynb

@@ -658,8 +658,8 @@
       },
       "outputs": [],
       "source": [
-        "datasets = load_dataset(\"imdb\")\n",
-        "datasets"
+        "dataset = load_dataset(\"imdb\")\n",
+        "dataset"
       ]
     },
     {
@@ -668,7 +668,7 @@
         "id": "RzfPtOMoIrIu"
       },
       "source": [
-        "The `datasets` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
+        "The `dataset` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
       ]
     },
     {
@@ -681,12 +681,12 @@
       "source": [
         "print(\n",
         "    \"Total # of rows in training dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"train\"].shape[0], datasets[\"train\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"train\"].shape[0], dataset[\"train\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")\n",
         "print(\n",
         "    \"Total # of rows in test dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"test\"].shape[0], datasets[\"test\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"test\"].shape[0], dataset[\"test\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")"
       ]
@@ -708,7 +708,7 @@
       },
       "outputs": [],
       "source": [
-        "datasets[\"train\"][0]"
+        "dataset[\"train\"][0]"
       ]
     },
     {
@@ -728,7 +728,7 @@
       },
       "outputs": [],
       "source": [
-        "label_list = datasets[\"train\"].unique(\"label\")\n",
+        "label_list = dataset[\"train\"].unique(\"label\")\n",
         "label_list"
       ]
     },
@@ -779,7 +779,7 @@
       },
       "outputs": [],
       "source": [
-        "show_random_elements(datasets[\"train\"])"
+        "show_random_elements(dataset[\"train\"])"
       ]
     },
     {
@@ -883,7 +883,7 @@
       },
       "outputs": [],
       "source": [
-        "example = datasets[\"train\"][4]\n",
+        "example = dataset[\"train\"][4]\n",
         "print(example)"
       ]
     },
@@ -920,7 +920,7 @@
       "source": [
         "# Dataset loading repeated here to make this cell idempotent\n",
         "# Since we are over-writing datasets variable\n",
-        "datasets = load_dataset(\"imdb\")\n",
+        "dataset = load_dataset(\"imdb\")\n",
         "\n",
         "# Mapping labels to ids\n",
         "# NOTE: We can extract this automatically but the `Unique` method of the datasets\n",
@@ -948,7 +948,7 @@
         "\n",
         "\n",
         "# apply preprocessing function to input examples\n",
-        "datasets = datasets.map(preprocess_function, batched=True, load_from_cache_file=True)"
+        "dataset = dataset.map(preprocess_function, batched=True, load_from_cache_file=True)"
       ]
     },
     {
@@ -1091,8 +1091,8 @@
         "trainer = Trainer(\n",
         "    model,\n",
         "    args,\n",
-        "    train_dataset=datasets[\"train\"],\n",
-        "    eval_dataset=datasets[\"test\"],\n",
+        "    train_dataset=dataset[\"train\"],\n",
+        "    eval_dataset=dataset[\"test\"],\n",
         "    data_collator=default_data_collator,\n",
         "    tokenizer=tokenizer,\n",
         "    compute_metrics=compute_metrics,\n",

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/logger/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-bigquery==2.20.0
-tensorflow==2.5.3
+tensorflow==2.7.2
 pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/prediction_container/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-pubsub==2.5.0
 pillow==9.0.1
 tf-agents==0.8.0
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/simulator/requirements.txt

@@ -1,5 +1,5 @@
 dataclasses==0.6
 google-cloud-aiplatform==1.8.1
-tensorflow==2.5.3
+tensorflow==2.7.2
 pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/step_by_step_sdk_tf_agents_bandits_movie_recommendation/step_by_step_sdk_tf_agents_bandits_movie_recommendation.ipynb

@@ -706,8 +706,8 @@
         "    else:\n",
         "        data_spec = training_data_spec_transformation_fn(\n",
         "            agent.policy.trajectory_spec)\n",
-        "        replay_buffer = trainer.get_replay_buffer(data_spec, environment.batch_size,\n",
-        "                                                  steps_per_loop)\n",
+        "    replay_buffer = trainer.get_replay_buffer(data_spec, environment.batch_size,\n",
+        "                                              steps_per_loop)\n",
         "\n",
         "    # `step_metric` records the number of individual rounds of bandit interaction;\n",
         "    # that is, (number of trajectories) * batch_size.\n",

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

notebooks/README.md

@@ -1,5 +1,5 @@
-The [official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder contains notebooks organized by Google Cloud product.
+The [official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder contains notebooks organized by Google Cloud product. These are tested weekly and maintained by Google.
 
-The [community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder contains notebooks that aren't officially supported by Google.
+The [community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder contains notebooks that may be created by Google or external contributors. They are not necessary maintained.
 
 Contributions to the repo should use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.

notebooks/community/CODEOWNERS

@@ -5,17 +5,33 @@
 
 /sdk/sdk_* @andrewferlitsch
 /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/
+/bigquery_ml/ @polong
 /sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
 /pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb @brianchunkang
+/explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
 /matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
 /matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
+/matching_engine/stream_update_for_matching_engine.ipynb @peterping666
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu
+/prediction @googleapis/vertex-prediction-team
 /vertex_endpoints/tf_hub_obj_detection/deploy_tfhub_object_detection_on_vertex_endpoints.ipynb @entrpn
 /vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
+/vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
+/notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
+/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/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/feature_store/gapic-feature-store.ipynb

@@ -171,7 +171,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip install {USER_FLAG} --upgrade git+https://github.com/googleapis/python-aiplatform.git@v1.6.0"
+        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform"
       ]
     },
     {
@@ -266,7 +266,7 @@
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output=!gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
         "    PROJECT_ID = shell_output[0]\n",
         "    print(\"Project ID: \", PROJECT_ID)"
       ]
@@ -292,6 +292,37 @@
         "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d9f118b92c74"
+      },
+      "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": "3ee72715c0fd"
+      },
+      "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": {
@@ -478,7 +509,6 @@
         "from google.cloud.aiplatform_v1.types import \\\n",
         "    featurestore_service as featurestore_service_pb2\n",
         "from google.cloud.aiplatform_v1.types import io as io_pb2\n",
-        "from google.protobuf.duration_pb2 import Duration\n",
         "\n",
         "# Create admin_client for CRUD and data_client for reading feature values.\n",
         "admin_client = FeaturestoreServiceClient(client_options={\"api_endpoint\": API_ENDPOINT})\n",
@@ -542,30 +572,23 @@
       },
       "outputs": [],
       "source": [
-        "FEATURESTORE_ID = \"movie_prediction\"\n",
-        "create_lro = admin_client.create_featurestore(\n",
-        "    featurestore_service_pb2.CreateFeaturestoreRequest(\n",
-        "        parent=BASE_RESOURCE_PATH,\n",
-        "        featurestore_id=FEATURESTORE_ID,\n",
-        "        featurestore=featurestore_pb2.Featurestore(\n",
-        "            online_serving_config=featurestore_pb2.Featurestore.OnlineServingConfig(\n",
-        "                fixed_node_count=1\n",
+        "FEATURESTORE_ID = f\"movie_prediction_{UUID}\"\n",
+        "try:\n",
+        "    create_lro = admin_client.create_featurestore(\n",
+        "        featurestore_service_pb2.CreateFeaturestoreRequest(\n",
+        "            parent=BASE_RESOURCE_PATH,\n",
+        "            featurestore_id=FEATURESTORE_ID,\n",
+        "            featurestore=featurestore_pb2.Featurestore(\n",
+        "                online_serving_config=featurestore_pb2.Featurestore.OnlineServingConfig(\n",
+        "                    fixed_node_count=1\n",
+        "                ),\n",
         "            ),\n",
-        "        ),\n",
+        "        )\n",
         "    )\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "57V8eVcB5VFZ"
-      },
-      "outputs": [],
-      "source": [
-        "# Wait for LRO to finish and get the LRO result.\n",
-        "print(create_lro.result())"
+        "    # Wait for LRO to finish and get the LRO result.\n",
+        "    print(create_lro.result())\n",
+        "except Exception as e:\n",
+        "    print(e)"
       ]
     },
     {
@@ -574,7 +597,7 @@
         "id": "ag8pCQ7rNjVf"
       },
       "source": [
-        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
+        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
       ]
     },
     {
@@ -590,6 +613,41 @@
         ")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "018ab19d934f"
+      },
+      "source": [
+        "Auto scaling is available in v1 since v1.11. Below is the example for the `CreateFeaturestoreRequest` with auto-scaling, use it with `aiplatform_v1.FeaturestoreServiceClient` to create Featurestore:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aea39718b5d3"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore as v1_featurestore_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
+        "\n",
+        "create_featurestore_request = v1_featurestore_service_pb2.CreateFeaturestoreRequest(\n",
+        "    parent=BASE_RESOURCE_PATH,\n",
+        "    featurestore_id=FEATURESTORE_ID,\n",
+        "    featurestore=v1_featurestore_pb2.Featurestore(\n",
+        "        online_serving_config=v1_featurestore_pb2.Featurestore.OnlineServingConfig(\n",
+        "            scaling=v1_featurestore_pb2.Featurestore.OnlineServingConfig.Scaling(\n",
+        "                min_node_count=1, max_node_count=5\n",
+        "            )\n",
+        "        ),\n",
+        "    ),\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -607,18 +665,20 @@
       },
       "outputs": [],
       "source": [
-        "users_entity_type_lro = admin_client.create_entity_type(\n",
-        "    featurestore_service_pb2.CreateEntityTypeRequest(\n",
-        "        parent=admin_client.featurestore_path(PROJECT_ID, REGION, FEATURESTORE_ID),\n",
-        "        entity_type_id=\"users\",\n",
-        "        entity_type=entity_type_pb2.EntityType(\n",
-        "            description=\"Users entity\",\n",
-        "        ),\n",
+        "try:\n",
+        "    users_entity_type_lro = admin_client.create_entity_type(\n",
+        "        featurestore_service_pb2.CreateEntityTypeRequest(\n",
+        "            parent=admin_client.featurestore_path(PROJECT_ID, REGION, FEATURESTORE_ID),\n",
+        "            entity_type_id=\"users\",\n",
+        "            entity_type=entity_type_pb2.EntityType(\n",
+        "                description=\"Users entity\",\n",
+        "            ),\n",
+        "        )\n",
         "    )\n",
-        ")\n",
-        "\n",
-        "# Similarly, wait for EntityType creation operation.\n",
-        "print(users_entity_type_lro.result())"
+        "    # Similarly, wait for EntityType creation operation.\n",
+        "    print(users_entity_type_lro.result())\n",
+        "except Exception as e:\n",
+        "    print(e)"
       ]
     },
     {
@@ -630,16 +690,73 @@
       "outputs": [],
       "source": [
         "# Create movies entity type without a monitoring configuration.\n",
-        "movies_entity_type_lro = admin_client.create_entity_type(\n",
-        "    featurestore_service_pb2.CreateEntityTypeRequest(\n",
-        "        parent=admin_client.featurestore_path(PROJECT_ID, REGION, FEATURESTORE_ID),\n",
-        "        entity_type_id=\"movies\",\n",
-        "        entity_type=entity_type_pb2.EntityType(description=\"Movies entity\"),\n",
+        "try:\n",
+        "    movies_entity_type_lro = admin_client.create_entity_type(\n",
+        "        featurestore_service_pb2.CreateEntityTypeRequest(\n",
+        "            parent=admin_client.featurestore_path(PROJECT_ID, REGION, FEATURESTORE_ID),\n",
+        "            entity_type_id=\"movies\",\n",
+        "            entity_type=entity_type_pb2.EntityType(description=\"Movies entity\"),\n",
+        "        )\n",
         "    )\n",
+        "\n",
+        "    # Similarly, wait for EntityType creation operation.\n",
+        "    print(movies_entity_type_lro.result())\n",
+        "except Exception as e:\n",
+        "    print(e)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dPkT7KDuEvWv"
+      },
+      "source": [
+        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1 Python. Import feature analysis is only available through SDK for now."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9kiqrBN6E28r"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
+        "\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
+        "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
-        "# Similarly, wait for EntityType creation operation.\n",
-        "print(movies_entity_type_lro.result())"
+        "# Enable import feature analysis for users entity type.\n",
+        "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
+        "            name=admin_client.entity_type_path(\n",
+        "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
+        "            ),\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                import_features_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(\n",
+        "                    anomaly_detection_baseline=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline.LATEST_STATS,\n",
+        "                    state=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State.ENABLED,\n",
+        "                ),\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "            ),\n",
+        "        ),\n",
+        "    )\n",
+        ")"
       ]
     },
     {
@@ -648,8 +765,7 @@
         "id": "85b1f59fbf6d"
       },
       "source": [
-        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1beta1 Python. The easiest way to set this for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1beta1 SDK.\n",
-        "\n",
+        "The easiest way to set up snapshot analysis for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1 SDK.\n",
         "\n",
         "You can view monitoring statistics on [console UI](https://console.cloud.google.com/vertex-ai/features)."
       ]
@@ -662,30 +778,36 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1 import \\\n",
-        "    FeaturestoreServiceClient as v1beta1_FeaturestoreServiceClient\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    entity_type as v1beta1_entity_type_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_monitoring as v1beta1_featurestore_monitoring_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "v1beta1_admin_client = v1beta1_FeaturestoreServiceClient(\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
-        "# Enable monitoring for users entity type.\n",
+        "# Enable snapshot analysis for users entity type.\n",
         "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
-        "v1beta1_admin_client.update_entity_type(\n",
-        "    v1beta1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
-        "        entity_type=v1beta1_entity_type_pb2.EntityType(\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
         "            name=admin_client.entity_type_path(\n",
         "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "            ),\n",
-        "            monitoring_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
-        "                snapshot_analysis=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
-        "                    monitoring_interval=Duration(seconds=86400),  # 1 day\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                snapshot_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
+        "                    monitoring_interval_days=1,  # 1 day\n",
+        "                    staleness_days=30,\n",
+        "                ),\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
         "        ),\n",
@@ -711,32 +833,40 @@
       "outputs": [],
       "source": [
         "# Create features for the 'users' entity.\n",
-        "admin_client.batch_create_features(\n",
-        "    parent=admin_client.entity_type_path(PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"),\n",
-        "    requests=[\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.INT64,\n",
-        "                description=\"User age\",\n",
-        "            ),\n",
-        "            feature_id=\"age\",\n",
+        "try:\n",
+        "    admin_client.batch_create_features(\n",
+        "        parent=admin_client.entity_type_path(\n",
+        "            PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "        ),\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.STRING,\n",
-        "                description=\"User gender\",\n",
+        "        requests=[\n",
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.INT64,\n",
+        "                    description=\"User age\",\n",
+        "                    disable_monitoring=False,\n",
+        "                ),\n",
+        "                feature_id=\"age\",\n",
         "            ),\n",
-        "            feature_id=\"gender\",\n",
-        "        ),\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.STRING_ARRAY,\n",
-        "                description=\"An array of genres that this user liked\",\n",
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.STRING,\n",
+        "                    description=\"User gender\",\n",
+        "                    # Default is False. If True, Feature 'gender' monitoring analysis is disabled.\n",
+        "                    disable_monitoring=True,\n",
+        "                ),\n",
+        "                feature_id=\"gender\",\n",
         "            ),\n",
-        "            feature_id=\"liked_genres\",\n",
-        "        ),\n",
-        "    ],\n",
-        ").result()"
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.STRING_ARRAY,\n",
+        "                    description=\"An array of genres that this user liked\",\n",
+        "                ),\n",
+        "                feature_id=\"liked_genres\",\n",
+        "            ),\n",
+        "        ],\n",
+        "    ).result()\n",
+        "except Exception as e:\n",
+        "    print(e)"
       ]
     },
     {
@@ -748,32 +878,37 @@
       "outputs": [],
       "source": [
         "# Create features for movies type.\n",
-        "admin_client.batch_create_features(\n",
-        "    parent=admin_client.entity_type_path(PROJECT_ID, REGION, FEATURESTORE_ID, \"movies\"),\n",
-        "    requests=[\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.STRING,\n",
-        "                description=\"The title of the movie\",\n",
-        "            ),\n",
-        "            feature_id=\"title\",\n",
+        "try:\n",
+        "    admin_client.batch_create_features(\n",
+        "        parent=admin_client.entity_type_path(\n",
+        "            PROJECT_ID, REGION, FEATURESTORE_ID, \"movies\"\n",
         "        ),\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.STRING,\n",
-        "                description=\"The genres of the movie\",\n",
+        "        requests=[\n",
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.STRING,\n",
+        "                    description=\"The title of the movie\",\n",
+        "                ),\n",
+        "                feature_id=\"title\",\n",
         "            ),\n",
-        "            feature_id=\"genres\",\n",
-        "        ),\n",
-        "        featurestore_service_pb2.CreateFeatureRequest(\n",
-        "            feature=feature_pb2.Feature(\n",
-        "                value_type=feature_pb2.Feature.ValueType.DOUBLE,\n",
-        "                description=\"The average rating for the movie, range is [1.0-5.0]\",\n",
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.STRING,\n",
+        "                    description=\"The genres of the movie\",\n",
+        "                ),\n",
+        "                feature_id=\"genres\",\n",
         "            ),\n",
-        "            feature_id=\"average_rating\",\n",
-        "        ),\n",
-        "    ],\n",
-        ").result()"
+        "            featurestore_service_pb2.CreateFeatureRequest(\n",
+        "                feature=feature_pb2.Feature(\n",
+        "                    value_type=feature_pb2.Feature.ValueType.DOUBLE,\n",
+        "                    description=\"The average rating for the movie, range is [1.0-5.0]\",\n",
+        "                ),\n",
+        "                feature_id=\"average_rating\",\n",
+        "            ),\n",
+        "        ],\n",
+        "    ).result()\n",
+        "except Exception as e:\n",
+        "    print(e)"
       ]
     },
     {
@@ -784,8 +919,8 @@
       "source": [
         "## Search created features\n",
         "\n",
-        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
-        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
+        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
+        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
         "and entity types in a given location (such as `us-central1`). This can help you discover features that were created by someone else.\n",
         "\n",
         "You can query based on feature properties including feature ID, entity type ID,\n",
@@ -987,6 +1122,8 @@
         "    ],\n",
         "    feature_time_field=\"update_time\",\n",
         "    worker_count=1,\n",
+        "    # Default is False. If True, the import feature analysis won't happen for this specific operation.\n",
+        "    disable_ingestion_analysis=False,\n",
         ")"
       ]
     },
@@ -1097,7 +1234,7 @@
       },
       "source": [
         "The\n",
-        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#featurestoreonlineservingservice)\n",
+        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#featurestoreonlineservingservice)\n",
         "lets you serve feature values for small batches of entities. It's designed for latency-sensitive service, such as online model prediction. For example, for a movie service, you might want to quickly shows movies that the current user would most likely watch by using online predictions."
       ]
     },
@@ -1395,9 +1532,7 @@
   ],
   "metadata": {
     "colab": {
-      "collapsed_sections": [
-        "ze4-nDLfK4pw"
-      ],
+      "collapsed_sections": [],
       "name": "gapic-feature-store.ipynb",
       "toc_visible": true
     },

notebooks/community/managed_notebooks/pricing_optimization/pricing-optimization.ipynb

@@ -1,823 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d1cc1c1fa076"
-      },
-      "source": [
-        "# Pricing Optimization \n",
-        "## Table of contents\n",
-        "* [Overview](#section-1)\n",
-        "* [Dataset](#section-2)\n",
-        "* [Objective](#section-3)\n",
-        "* [Costs](#section-4)\n",
-        "* [Create a BigQuery dataset](#section-5)\n",
-        "* [Load the dataset from Cloud Storage](#section-6)\n",
-        "* [Data analysis](#section-7)\n",
-        "* [Preprocess the data for training](#section-8)\n",
-        "* [Train the model using BigQuery ML](#section-9)\n",
-        "* [Generate forecasts from the model](#section-10)\n",
-        "* [Interpret the results to choose the best price](#section-11)\n",
-        "* [Clean up](#section-12)\n",
-        "\n",
-        "## Overview\n",
-        "<a name=\"section-1\"></a>\n",
-        "\n",
-        "This notebook demonstrates analysis of pricing optimization on [CDM Pricing Data](https://github.com/trifacta/trifacta-google-cloud/tree/main/design-pattern-pricing-optimization) and automating the workflow using Vertex AI Workbench managed notebooks.\n",
-        "\n",
-        "*Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the Python (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
-        "\n",
-        "## Dataset\n",
-        "<a name=\"section-2\"></a>\n",
-        "\n",
-        "The dataset used in this notebook is a part of the [CDM Pricing dataset](https://github.com/trifacta/trifacta-google-cloud/blob/main/design-pattern-pricing-optimization/CDM_Pricing_large_table.csv), which consists of product sales information on specified dates.\n",
-        "\n",
-        "## Objective\n",
-        "<a name=\"section-3\"></a>\n",
-        "\n",
-        "The objective of this notebook is to build a pricing optimization model using Vertex AI. The following steps have been followed:  \n",
-        "\n",
-        "- Load the required dataset from a Cloud Storage bucket.\n",
-        "- Analyze the fields present in the dataset.\n",
-        "- Process the data to build a model.\n",
-        "- Build a BigQuery ML forecast model on the processed data.\n",
-        "- Get forecasted values from the BigQuery ML model.\n",
-        "- Interpret the forecasts to identify the best prices.\n",
-        "- Clean up.\n",
-        "\n",
-        "## Costs\n",
-        "<a name=\"section-4\"></a>\n",
-        "\n",
-        "This tutorial uses the following billable components of Google Cloud:\n",
-        "\n",
-        "- Vertex AI\n",
-        "- BigQuery\n",
-        "- Cloud Storage\n",
-        "\n",
-        "\n",
-        "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/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.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5ed1f5e85640"
-      },
-      "source": [
-        "## Before you begin\n",
-        "\n",
-        "### 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": "c3f30148b66d"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "750bf2883c2d"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3c6db1ca88b9"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2a1c270c7d34"
-      },
-      "source": [
-        "### Import the required libraries and define constants\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "acc6fac1fa55"
-      },
-      "outputs": [],
-      "source": [
-        "import matplotlib.pyplot as plt\n",
-        "import pandas as pd\n",
-        "import seaborn as sns\n",
-        "from google.cloud import bigquery\n",
-        "from google.cloud.bigquery import Client"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a06006dff8f9"
-      },
-      "outputs": [],
-      "source": [
-        "DATASET = \"[your-bigquery-dataset-id]\"  # set the BigQuery dataset-id\n",
-        "TRAINING_DATA_TABLE = \"[your-bigquery-table-id-to-store-the-training-data]\"  # set the BigQuery table-id to store the training data"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "016c3d47cc69"
-      },
-      "source": [
-        "## Create a BigQuery dataset\n",
-        "<a name=\"section-5\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "12ccd8d7956e"
-      },
-      "source": [
-        "#@bigquery\n",
-        "-- create a dataset in BigQuery\n",
-        "\n",
-        "CREATE SCHEMA pricing_optimization\n",
-        "OPTIONS(\n",
-        "  location=\"us\"\n",
-        "  )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c106b978a79b"
-      },
-      "source": [
-        "## Load the dataset from Cloud Storage\n",
-        "<a name=\"section-6\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8aeae9da9796"
-      },
-      "outputs": [],
-      "source": [
-        "DATA_LOCATION = \"gs://cloud-samples-data/ai-platform-unified/datasets/tabular/cdm_pricing_large_table.csv\"\n",
-        "df = pd.read_csv(DATA_LOCATION)\n",
-        "print(df.shape)\n",
-        "df.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "7b98d5f09842"
-      },
-      "source": [
-        "You will build a forecast model on this data and thus determine the best price for a product. For this type of model, you will not be using many fields: only the sales and price related ones. For the current execrcise, focus on the following fields:\n",
-        "\n",
-        "- `Product_ID`\n",
-        "- `Customer_Hierarchy`\n",
-        "- `Fiscal_Date`\n",
-        "- `List_Price_Converged`\n",
-        "- `Invoiced_quantity_in_Pieces`\n",
-        "- `Net_Sales`\n",
-        "\n",
-        "## Data Analysis\n",
-        "<a name=\"section-7\"></a>\n",
-        "\n",
-        "First, explore the data and distributions.\n",
-        "\n",
-        "Select the required columns from the dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "af4b41c5eb1f"
-      },
-      "outputs": [],
-      "source": [
-        "id_col = \"Product_ID\"\n",
-        "date_col = \"Fiscal_Date\"\n",
-        "categ_cols = [\"Customer_Hierarchy\"]\n",
-        "num_cols = [\"List_Price_Converged\", \"Invoiced_quantity_in_Pieces\", \"Net_Sales\"]\n",
-        "\n",
-        "df = df[[id_col, date_col] + categ_cols + num_cols].copy()\n",
-        "df.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3d780043ee5b"
-      },
-      "source": [
-        "Check the column types and null values in the dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f54c445a1288"
-      },
-      "outputs": [],
-      "source": [
-        "df.info()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd817b414c4d"
-      },
-      "source": [
-        "This data description reveals that there are no null values in the data. Also, the field `Fiscal_Date` which is a date field is loaded as an object type. \n",
-        "\n",
-        "Change the type of the date field to datetime."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b160fac085c8"
-      },
-      "outputs": [],
-      "source": [
-        "df[\"Fiscal_Date\"] = pd.to_datetime(df[\"Fiscal_Date\"], infer_datetime_format=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fb4778578064"
-      },
-      "source": [
-        "Plot the distributions for the categorical fields."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "dd0467cd57c3"
-      },
-      "outputs": [],
-      "source": [
-        "for i in categ_cols:\n",
-        "    df[i].value_counts(normalize=True).plot(kind=\"bar\")\n",
-        "    plt.title(i)\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "145deed255e0"
-      },
-      "source": [
-        "Plot the distributions for the numerical fields."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f934137c6d82"
-      },
-      "outputs": [],
-      "source": [
-        "for i in num_cols:\n",
-        "    _, ax = plt.subplots(1, 2, figsize=(10, 4))\n",
-        "    df[i].plot(kind=\"box\", ax=ax[0])\n",
-        "    df[i].plot(kind=\"hist\", ax=ax[1])\n",
-        "    ax[0].set_title(i + \"-Boxplot\")\n",
-        "    ax[1].set_title(i + \"-Histogram\")\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f9b9c2e58380"
-      },
-      "source": [
-        "Check the maximum date and minimum date in Fiscal_Date column."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2a10aa689f9d"
-      },
-      "outputs": [],
-      "source": [
-        "print(df[\"Fiscal_Date\"].max())\n",
-        "print(df[\"Fiscal_Date\"].min())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4834f63e2e59"
-      },
-      "source": [
-        "Check the product distribution across each category."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4664877f5304"
-      },
-      "outputs": [],
-      "source": [
-        "grp_cols = [\"Customer_Hierarchy\", \"Product_ID\"]\n",
-        "grp_df = df[grp_cols].groupby(by=grp_cols).count().reset_index()\n",
-        "grp_df.groupby(\"Customer_Hierarchy\").nunique()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "01ed02b9c8fd"
-      },
-      "source": [
-        "Check the percentage changes in the orders based on the percentage changes in the price."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b2c428cb135"
-      },
-      "outputs": [],
-      "source": [
-        "# aggregate the data\n",
-        "df_aggr = (\n",
-        "    df.groupby([\"Product_ID\", \"List_Price_Converged\"])\n",
-        "    .agg({\"Fiscal_Date\": min, \"Invoiced_quantity_in_Pieces\": sum, \"Net_Sales\": sum})\n",
-        "    .reset_index()\n",
-        ")\n",
-        "# rename the aggregated columns\n",
-        "df_aggr.rename(\n",
-        "    columns={\n",
-        "        \"Fiscal_Date\": \"First_price_date\",\n",
-        "        \"Invoiced_quantity_in_Pieces\": \"Total_ordered_pieces\",\n",
-        "        \"Net_Sales\": \"Total_net_sales\",\n",
-        "    },\n",
-        "    inplace=True,\n",
-        ")\n",
-        "\n",
-        "# sort values chronologically\n",
-        "df_aggr.sort_values(by=[\"Product_ID\", \"First_price_date\"], inplace=True)\n",
-        "df_aggr.reset_index(drop=True, inplace=True)\n",
-        "\n",
-        "# add columns for previous values\n",
-        "df_aggr[\"Previous_List\"] = df_aggr.groupby([\"Product_ID\"])[\n",
-        "    \"List_Price_Converged\"\n",
-        "].shift()\n",
-        "df_aggr[\"Previous_Total_ordered_pieces\"] = df_aggr.groupby([\"Product_ID\"])[\n",
-        "    \"Total_ordered_pieces\"\n",
-        "].shift()\n",
-        "\n",
-        "# average price change across sku's\n",
-        "df_aggr[\"price_change_perc\"] = (\n",
-        "    (df_aggr[\"List_Price_Converged\"] - df_aggr[\"Previous_List\"])\n",
-        "    / df_aggr[\"Previous_List\"].fillna(0)\n",
-        "    * 100\n",
-        ")\n",
-        "df_aggr[\"order_change_perc\"] = (\n",
-        "    (df_aggr[\"Total_ordered_pieces\"] - df_aggr[\"Previous_Total_ordered_pieces\"])\n",
-        "    / df_aggr[\"Previous_Total_ordered_pieces\"].fillna(0)\n",
-        "    * 100\n",
-        ")\n",
-        "\n",
-        "# plot a scatterplot to visualize the changes\n",
-        "sns.scatterplot(\n",
-        "    x=\"price_change_perc\",\n",
-        "    y=\"order_change_perc\",\n",
-        "    data=df_aggr,\n",
-        "    hue=\"Product_ID\",\n",
-        "    legend=False,\n",
-        ")\n",
-        "plt.title(\"Percentage of change in price vs order\")\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8259e916fe25"
-      },
-      "source": [
-        "For most of the products, the percentage change in orders are high where the percentage changes in the prices are low. This suggests that too much change in the prices can affect the number of orders. \n",
-        "\n",
-        "**Note**: There seem to be some outliers in the data as percentage changes greater than 800 are found. In the current exercise, do not take any manual measures to deal with outliers as you will create a BigQuery ML timeseries model that already deals with outliers.\n",
-        "\n",
-        "## Preprocess the data for training\n",
-        "<a name=\"section-8\"></a>\n",
-        "\n",
-        "Check which `Product_ID`'s  have the maximum orders."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f5cbc7709c6a"
-      },
-      "outputs": [],
-      "source": [
-        "df_orders = df.groupby([\"Product_ID\", \"Customer_Hierarchy\"], as_index=False)[\n",
-        "    \"Invoiced_quantity_in_Pieces\"\n",
-        "].sum()\n",
-        "df_orders.loc[\n",
-        "    df_orders.groupby(\"Customer_Hierarchy\")[\"Invoiced_quantity_in_Pieces\"].idxmax()\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fd6d227e513e"
-      },
-      "source": [
-        "From the above result, you can infer the following:\n",
-        "\n",
-        "- Under the **Food** category, **SKU 62** has the maximum orders.\n",
-        "- Under the **Manufacturing** category, **SKU 17** has the maximum orders.\n",
-        "- Under the **Paper** category, **SKU 107** has the maximum orders.\n",
-        "- Under the **Publishing** category, **SKU 8** has the maximum orders.\n",
-        "- Under the **Utilities** category, **SKU 140** has the maximum orders.\n",
-        "\n",
-        "Given that there are too many ids and only a few records for most of them, consider only the above `Product_ID`s for which there are a maximum number of orders. \n",
-        "\n",
-        "**Note**: The `Invoiced_quantity_in_Pieces` field seems to be a *float* type rather than an *int* type as it should be. This could be because the data itself might be averaged in the first place."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2dbc0d64d157"
-      },
-      "source": [
-        "Check the various prices available for these `Product_ID`s."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "acc1dbd2d838"
-      },
-      "outputs": [],
-      "source": [
-        "df_type_food = df[(df[\"Product_ID\"] == \"SKU 62\") & (df[\"Customer_Hierarchy\"] == \"Food\")]\n",
-        "print(\"Food :\")\n",
-        "print(df_type_food[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_manuf = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 17\") & (df[\"Customer_Hierarchy\"] == \"Manufacturing\")\n",
-        "]\n",
-        "print(\"Manufacturing :\")\n",
-        "print(df_type_manuf[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_paper = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 107\") & (df[\"Customer_Hierarchy\"] == \"Paper\")\n",
-        "]\n",
-        "print(\"Paper :\")\n",
-        "print(df_type_paper[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_pub = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 8\") & (df[\"Customer_Hierarchy\"] == \"Publishing\")\n",
-        "]\n",
-        "print(\"Publishing :\")\n",
-        "print(df_type_pub[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_util = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 140\") & (df[\"Customer_Hierarchy\"] == \"Utilities\")\n",
-        "]\n",
-        "print(\"Utilities :\")\n",
-        "print(df_type_util[\"List_Price_Converged\"].value_counts())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f023af578c0f"
-      },
-      "source": [
-        "In the publishing category, `Product_ID` `SKU 8` and `SKU 17` are less than or equal to two different prices in the entire data and so you will exclude them and consider the rest for building the forecast model. The idea here is to train a forecast model on the timeseries data for products with different prices.\n",
-        "\n",
-        "Join the data for all the `Product_ID`s into one dataframe and remove duplicate records."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a44771cc4c20"
-      },
-      "outputs": [],
-      "source": [
-        "df_final = pd.concat([df_type_food, df_type_paper, df_type_util])\n",
-        "df_final = (\n",
-        "    df_final[\n",
-        "        [\n",
-        "            \"Product_ID\",\n",
-        "            \"Fiscal_Date\",\n",
-        "            \"Customer_Hierarchy\",\n",
-        "            \"List_Price_Converged\",\n",
-        "            \"Invoiced_quantity_in_Pieces\",\n",
-        "        ]\n",
-        "    ]\n",
-        "    .drop_duplicates()\n",
-        "    .reset_index(drop=True)\n",
-        ")\n",
-        "df_final.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "add5063df368"
-      },
-      "source": [
-        "Save the data to a BigQuery table."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fd82ba56571f"
-      },
-      "outputs": [],
-      "source": [
-        "bq_client = bigquery.Client(project=PROJECT_ID)\n",
-        "\n",
-        "job_config = bigquery.LoadJobConfig(\n",
-        "    # Specify a (partial) schema. All columns are always written to the\n",
-        "    # table. The schema is used to assist in data type definitions.\n",
-        "    schema=[\n",
-        "        bigquery.SchemaField(\"Product_ID\", bigquery.enums.SqlTypeNames.STRING),\n",
-        "        bigquery.SchemaField(\"Fiscal_Date\", bigquery.enums.SqlTypeNames.DATE),\n",
-        "        bigquery.SchemaField(\"List_Price_Converged\", bigquery.enums.SqlTypeNames.FLOAT),\n",
-        "        bigquery.SchemaField(\n",
-        "            \"Invoiced_quantity_in_Pieces\", bigquery.enums.SqlTypeNames.FLOAT\n",
-        "        ),\n",
-        "    ],\n",
-        "    # Optionally, set the write disposition. BigQuery appends loaded rows\n",
-        "    # to an existing table by default, but with WRITE_TRUNCATE write\n",
-        "    # disposition it replaces the table with the loaded data.\n",
-        "    write_disposition=\"WRITE_TRUNCATE\",\n",
-        ")\n",
-        "\n",
-        "# save the dataframe to a table in the created dataset\n",
-        "job = bq_client.load_table_from_dataframe(\n",
-        "    df_final,\n",
-        "    \"{}.{}.{}\".format(PROJECT_ID, DATASET, TRAINING_DATA_TABLE),\n",
-        "    job_config=job_config,\n",
-        ")  # Make an API request.\n",
-        "job.result()  # Wait for the job to complete."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fca77641b03b"
-      },
-      "source": [
-        "# Train the model using BigQuery ML\n",
-        "<a name=\"section-9\"></a>\n",
-        "\n",
-        "Train an [Arima-Plus](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series) model on the data using BigQuery ML."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cded27507891"
-      },
-      "source": [
-        "#@bigquery\n",
-        "create or replace model pricing_optimization.bqml_arima\n",
-        "options\n",
-        " (model_type = 'ARIMA_PLUS',\n",
-        "  time_series_timestamp_col = 'Fiscal_Date',\n",
-        "  time_series_data_col = 'Invoiced_quantity_in_Pieces',\n",
-        "  time_series_id_col = 'ID'\n",
-        " ) as\n",
-        "select\n",
-        " Fiscal_Date,\n",
-        " Concat(Product_ID,\"_\" ,Cast(List_Price_Converged as string)) as ID,\n",
-        " Invoiced_quantity_in_Pieces\n",
-        "from\n",
-        " pricing_optimization.TRAINING_DATA\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "332fd11ff32b"
-      },
-      "source": [
-        "## Generate forecasts from the model\n",
-        "<a name=\"section-10\"></a>\n",
-        "\n",
-        "Predict the sales for the next 30 days for each id and save to a dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ef926cdbf28e"
-      },
-      "outputs": [],
-      "source": [
-        "client = Client()\n",
-        "\n",
-        "query = '''\n",
-        "DECLARE HORIZON STRING DEFAULT \"30\"; #number of values to forecast\n",
-        "DECLARE CONFIDENCE_LEVEL STRING DEFAULT \"0.90\"; ## required confidence level\n",
-        "\n",
-        "EXECUTE IMMEDIATE format(\"\"\"\n",
-        "    SELECT\n",
-        "      *\n",
-        "    FROM \n",
-        "      ML.FORECAST(MODEL pricing_optimization.bqml_arima, \n",
-        "                  STRUCT(%s AS horizon, \n",
-        "                         %s AS confidence_level)\n",
-        "                 )\n",
-        "    \"\"\",HORIZON,CONFIDENCE_LEVEL)'''\n",
-        "job = client.query(query)\n",
-        "dfforecast = job.to_dataframe()\n",
-        "dfforecast.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "608c7de72dae"
-      },
-      "source": [
-        "## Interpret the results to choose the best price\n",
-        "<a name=\"section-11\"></a>\n",
-        "\n",
-        "Calculate average forecast values for the forecast duration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e1e193680400"
-      },
-      "outputs": [],
-      "source": [
-        "dfforecast_avg = (\n",
-        "    dfforecast[[\"ID\", \"forecast_value\"]].groupby(\"ID\", as_index=False).mean()\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5ce395d652a3"
-      },
-      "source": [
-        "Extract the ID and Price fields from the ID field."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "452c56fa58ed"
-      },
-      "outputs": [],
-      "source": [
-        "dfforecast_avg[\"Product_ID\"] = dfforecast_avg[\"ID\"].apply(lambda x: x.split(\"_\")[0])\n",
-        "dfforecast_avg[\"Price\"] = dfforecast_avg[\"ID\"].apply(lambda x: x.split(\"_\")[1])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3cee67f4028f"
-      },
-      "source": [
-        "Plot the average forecasted sales vs. the price of the product."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fb351c8f383d"
-      },
-      "outputs": [],
-      "source": [
-        "for i in dfforecast_avg[\"Product_ID\"].unique():\n",
-        "    dfforecast_avg[dfforecast_avg[\"Product_ID\"] == i].set_index(\"Price\").sort_values(\n",
-        "        \"forecast_value\"\n",
-        "    ).plot(kind=\"bar\")\n",
-        "    plt.title(\"Price vs. Average Sales for \" + i)\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "67ff3acc74a5"
-      },
-      "source": [
-        "Based on the plots for price vs. the average forecasted orders, it can be said that to use the maximum orders, each of the considered `Product_ID`s can follow the below prices:\n",
-        "\n",
-        "- SKU 107's price range can be from 4.44 - 4.73 units\n",
-        "- SKU 140's price can be 1.95 units\n",
-        "- SKU 62's price can be 4.23 units\n",
-        "\n",
-        "\n",
-        "## Clean Up\n",
-        "<a name=\"section-12\"></a>\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud 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. The following code deletes the entire dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d78908b8134d"
-      },
-      "outputs": [],
-      "source": [
-        "# Construct a BigQuery client object.\n",
-        "client = bigquery.Client()\n",
-        "\n",
-        "# TODO(developer): Set model_id to the ID of the model to fetch.\n",
-        "dataset_id = \"{PROJECT}.{DATASET}\".format(PROJECT=PROJECT_ID, DATASET=DATASET)\n",
-        "\n",
-        "# Use the delete_contents parameter to delete a dataset and its contents.\n",
-        "# Use the not_found_ok parameter to not receive an error if the dataset has already been deleted.\n",
-        "client.delete_dataset(\n",
-        "    dataset_id, delete_contents=True, not_found_ok=True\n",
-        ")  # Make an API request.\n",
-        "\n",
-        "print(\"Deleted dataset '{}'.\".format(dataset_id))"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "pricing-optimization.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/README.md

@@ -12,7 +12,7 @@ The purpose of this set of notebooks and markdown files is to demonstrate Google
 2. [Experimentation](stage2)
 3. [Formalization](stage3)
 4. [Evaluation](stage4)
-5. Deployment
+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.