建立表格預測訓練管道

使用 create_training_pipeline 方法，為表格預測建立訓練管道。

程式碼範例

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Vertex AI 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Vertex AI Python API 參考文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

from google.cloud import aiplatform
from google.protobuf import json_format
from google.protobuf.struct_pb2 import Value


def create_training_pipeline_tabular_forecasting_sample(
    project: str,
    display_name: str,
    dataset_id: str,
    model_display_name: str,
    target_column: str,
    time_series_identifier_column: str,
    time_column: str,
    time_series_attribute_columns: str,
    unavailable_at_forecast: str,
    available_at_forecast: str,
    forecast_horizon: int,
    location: str = "us-central1",
    api_endpoint: str = "us-central1-aiplatform.googleapis.com",
):
    # The AI Platform services require regional API endpoints.
    client_options = {"api_endpoint": api_endpoint}
    # Initialize client that will be used to create and send requests.
    # This client only needs to be created once, and can be reused for multiple requests.
    client = aiplatform.gapic.PipelineServiceClient(client_options=client_options)
    # set the columns used for training and their data types
    transformations = [
        {"auto": {"column_name": "date"}},
        {"auto": {"column_name": "state_name"}},
        {"auto": {"column_name": "county_fips_code"}},
        {"auto": {"column_name": "confirmed_cases"}},
        {"auto": {"column_name": "deaths"}},
    ]

    data_granularity = {"unit": "day", "quantity": 1}

    # the inputs should be formatted according to the training_task_definition yaml file
    training_task_inputs_dict = {
        # required inputs
        "targetColumn": target_column,
        "timeSeriesIdentifierColumn": time_series_identifier_column,
        "timeColumn": time_column,
        "transformations": transformations,
        "dataGranularity": data_granularity,
        "optimizationObjective": "minimize-rmse",
        "trainBudgetMilliNodeHours": 8000,
        "timeSeriesAttributeColumns": time_series_attribute_columns,
        "unavailableAtForecast": unavailable_at_forecast,
        "availableAtForecast": available_at_forecast,
        "forecastHorizon": forecast_horizon,
    }

    training_task_inputs = json_format.ParseDict(training_task_inputs_dict, Value())

    training_pipeline = {
        "display_name": display_name,
        "training_task_definition": "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_forecasting_1.0.0.yaml",
        "training_task_inputs": training_task_inputs,
        "input_data_config": {
            "dataset_id": dataset_id,
            "fraction_split": {
                "training_fraction": 0.8,
                "validation_fraction": 0.1,
                "test_fraction": 0.1,
            },
        },
        "model_to_upload": {"display_name": model_display_name},
    }
    parent = f"projects/{project}/locations/{location}"
    response = client.create_training_pipeline(
        parent=parent, training_pipeline=training_pipeline
    )
    print("response:", response)

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 瀏覽器範例。