创建用于文本分类的训练流水线

使用 create_training_pipeline 方法创建用于文本分类的训练流水线。

深入探索

如需查看包含此代码示例的详细文档，请参阅以下内容：

• 训练文本分类模型

代码示例

Java

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Java 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Java API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.DeployedModelRef;
import com.google.cloud.aiplatform.v1.EnvVar;
import com.google.cloud.aiplatform.v1.FilterSplit;
import com.google.cloud.aiplatform.v1.FractionSplit;
import com.google.cloud.aiplatform.v1.InputDataConfig;
import com.google.cloud.aiplatform.v1.LocationName;
import com.google.cloud.aiplatform.v1.Model;
import com.google.cloud.aiplatform.v1.Model.ExportFormat;
import com.google.cloud.aiplatform.v1.ModelContainerSpec;
import com.google.cloud.aiplatform.v1.PipelineServiceClient;
import com.google.cloud.aiplatform.v1.PipelineServiceSettings;
import com.google.cloud.aiplatform.v1.Port;
import com.google.cloud.aiplatform.v1.PredefinedSplit;
import com.google.cloud.aiplatform.v1.PredictSchemata;
import com.google.cloud.aiplatform.v1.TimestampSplit;
import com.google.cloud.aiplatform.v1.TrainingPipeline;
import com.google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTextClassificationInputs;
import com.google.rpc.Status;
import java.io.IOException;

public class CreateTrainingPipelineTextClassificationSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String trainingPipelineDisplayName = "YOUR_TRAINING_PIPELINE_DISPLAY_NAME";
    String project = "YOUR_PROJECT_ID";
    String datasetId = "YOUR_DATASET_ID";
    String modelDisplayName = "YOUR_MODEL_DISPLAY_NAME";

    createTrainingPipelineTextClassificationSample(
        project, trainingPipelineDisplayName, datasetId, modelDisplayName);
  }

  static void createTrainingPipelineTextClassificationSample(
      String project, String trainingPipelineDisplayName, String datasetId, String modelDisplayName)
      throws IOException {
    PipelineServiceSettings pipelineServiceSettings =
        PipelineServiceSettings.newBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PipelineServiceClient pipelineServiceClient =
        PipelineServiceClient.create(pipelineServiceSettings)) {
      String location = "us-central1";
      String trainingTaskDefinition =
          "gs://google-cloud-aiplatform/schema/trainingjob/definition/"
              + "automl_text_classification_1.0.0.yaml";

      LocationName locationName = LocationName.of(project, location);

      AutoMlTextClassificationInputs trainingTaskInputs =
          AutoMlTextClassificationInputs.newBuilder().setMultiLabel(false).build();

      InputDataConfig trainingInputDataConfig =
          InputDataConfig.newBuilder().setDatasetId(datasetId).build();
      Model model = Model.newBuilder().setDisplayName(modelDisplayName).build();
      TrainingPipeline trainingPipeline =
          TrainingPipeline.newBuilder()
              .setDisplayName(trainingPipelineDisplayName)
              .setTrainingTaskDefinition(trainingTaskDefinition)
              .setTrainingTaskInputs(ValueConverter.toValue(trainingTaskInputs))
              .setInputDataConfig(trainingInputDataConfig)
              .setModelToUpload(model)
              .build();

      TrainingPipeline trainingPipelineResponse =
          pipelineServiceClient.createTrainingPipeline(locationName, trainingPipeline);

      System.out.println("Create Training Pipeline Text Classification Response");
      System.out.format("\tName: %s\n", trainingPipelineResponse.getName());
      System.out.format("\tDisplay Name: %s\n", trainingPipelineResponse.getDisplayName());

      System.out.format(
          "\tTraining Task Definition %s\n", trainingPipelineResponse.getTrainingTaskDefinition());
      System.out.format(
          "\tTraining Task Inputs: %s\n", trainingPipelineResponse.getTrainingTaskInputs());
      System.out.format(
          "\tTraining Task Metadata: %s\n", trainingPipelineResponse.getTrainingTaskMetadata());
      System.out.format("State: %s\n", trainingPipelineResponse.getState());

      System.out.format("\tCreate Time: %s\n", trainingPipelineResponse.getCreateTime());
      System.out.format("\tStartTime %s\n", trainingPipelineResponse.getStartTime());
      System.out.format("\tEnd Time: %s\n", trainingPipelineResponse.getEndTime());
      System.out.format("\tUpdate Time: %s\n", trainingPipelineResponse.getUpdateTime());
      System.out.format("\tLabels: %s\n", trainingPipelineResponse.getLabelsMap());

      InputDataConfig inputDataConfig = trainingPipelineResponse.getInputDataConfig();
      System.out.println("\tInput Data Config");
      System.out.format("\t\tDataset Id: %s", inputDataConfig.getDatasetId());
      System.out.format("\t\tAnnotations Filter: %s\n", inputDataConfig.getAnnotationsFilter());

      FractionSplit fractionSplit = inputDataConfig.getFractionSplit();
      System.out.println("\t\tFraction Split");
      System.out.format("\t\t\tTraining Fraction: %s\n", fractionSplit.getTrainingFraction());
      System.out.format("\t\t\tValidation Fraction: %s\n", fractionSplit.getValidationFraction());
      System.out.format("\t\t\tTest Fraction: %s\n", fractionSplit.getTestFraction());

      FilterSplit filterSplit = inputDataConfig.getFilterSplit();
      System.out.println("\t\tFilter Split");
      System.out.format("\t\t\tTraining Filter: %s\n", filterSplit.getTrainingFilter());
      System.out.format("\t\t\tValidation Filter: %s\n", filterSplit.getValidationFilter());
      System.out.format("\t\t\tTest Filter: %s\n", filterSplit.getTestFilter());

      PredefinedSplit predefinedSplit = inputDataConfig.getPredefinedSplit();
      System.out.println("\t\tPredefined Split");
      System.out.format("\t\t\tKey: %s\n", predefinedSplit.getKey());

      TimestampSplit timestampSplit = inputDataConfig.getTimestampSplit();
      System.out.println("\t\tTimestamp Split");
      System.out.format("\t\t\tTraining Fraction: %s\n", timestampSplit.getTrainingFraction());
      System.out.format("\t\t\tValidation Fraction: %s\n", timestampSplit.getValidationFraction());
      System.out.format("\t\t\tTest Fraction: %s\n", timestampSplit.getTestFraction());
      System.out.format("\t\t\tKey: %s\n", timestampSplit.getKey());

      Model modelResponse = trainingPipelineResponse.getModelToUpload();
      System.out.println("\tModel To Upload");
      System.out.format("\t\tName: %s\n", modelResponse.getName());
      System.out.format("\t\tDisplay Name: %s\n", modelResponse.getDisplayName());
      System.out.format("\t\tDescription: %s\n", modelResponse.getDescription());

      System.out.format("\t\tMetadata Schema Uri: %s\n", modelResponse.getMetadataSchemaUri());
      System.out.format("\t\tMetadata: %s\n", modelResponse.getMetadata());
      System.out.format("\t\tTraining Pipeline: %s\n", modelResponse.getTrainingPipeline());
      System.out.format("\t\tArtifact Uri: %s\n", modelResponse.getArtifactUri());

      System.out.format(
          "\t\tSupported Deployment Resources Types: %s\n",
          modelResponse.getSupportedDeploymentResourcesTypesList());
      System.out.format(
          "\t\tSupported Input Storage Formats: %s\n",
          modelResponse.getSupportedInputStorageFormatsList());
      System.out.format(
          "\t\tSupported Output Storage Formats: %s\n",
          modelResponse.getSupportedOutputStorageFormatsList());

      System.out.format("\t\tCreate Time: %s\n", modelResponse.getCreateTime());
      System.out.format("\t\tUpdate Time: %s\n", modelResponse.getUpdateTime());
      System.out.format("\t\tLabels: %sn\n", modelResponse.getLabelsMap());

      PredictSchemata predictSchemata = modelResponse.getPredictSchemata();
      System.out.println("\t\tPredict Schemata");
      System.out.format("\t\t\tInstance Schema Uri: %s\n", predictSchemata.getInstanceSchemaUri());
      System.out.format(
          "\t\t\tParameters Schema Uri: %s\n", predictSchemata.getParametersSchemaUri());
      System.out.format(
          "\t\t\tPrediction Schema Uri: %s\n", predictSchemata.getPredictionSchemaUri());

      for (ExportFormat exportFormat : modelResponse.getSupportedExportFormatsList()) {
        System.out.println("\t\tSupported Export Format");
        System.out.format("\t\t\tId: %s\n", exportFormat.getId());
      }

      ModelContainerSpec modelContainerSpec = modelResponse.getContainerSpec();
      System.out.println("\t\tContainer Spec");
      System.out.format("\t\t\tImage Uri: %s\n", modelContainerSpec.getImageUri());
      System.out.format("\t\t\tCommand: %s\n", modelContainerSpec.getCommandList());
      System.out.format("\t\t\tArgs: %s\n", modelContainerSpec.getArgsList());
      System.out.format("\t\t\tPredict Route: %s\n", modelContainerSpec.getPredictRoute());
      System.out.format("\t\t\tHealth Route: %s\n", modelContainerSpec.getHealthRoute());

      for (EnvVar envVar : modelContainerSpec.getEnvList()) {
        System.out.println("\t\t\tEnv");
        System.out.format("\t\t\t\tName: %s\n", envVar.getName());
        System.out.format("\t\t\t\tValue: %s\n", envVar.getValue());
      }

      for (Port port : modelContainerSpec.getPortsList()) {
        System.out.println("\t\t\tPort");
        System.out.format("\t\t\t\tContainer Port: %s\n", port.getContainerPort());
      }

      for (DeployedModelRef deployedModelRef : modelResponse.getDeployedModelsList()) {
        System.out.println("\t\tDeployed Model");
        System.out.format("\t\t\tEndpoint: %s\n", deployedModelRef.getEndpoint());
        System.out.format("\t\t\tDeployed Model Id: %s\n", deployedModelRef.getDeployedModelId());
      }

      Status status = trainingPipelineResponse.getError();
      System.out.println("\tError");
      System.out.format("\t\tCode: %s\n", status.getCode());
      System.out.format("\t\tMessage: %s\n", status.getMessage());
    }
  }
}

Node.js

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Node.js 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Node.js API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */

// const datasetId = 'YOUR_DATASET_ID';
// const modelDisplayName = 'YOUR_MODEL_DISPLAY_NAME';
// const trainingPipelineDisplayName = 'YOUR_TRAINING_PIPELINE_DISPLAY_NAME';
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');
const {definition} =
  aiplatform.protos.google.cloud.aiplatform.v1.schema.trainingjob;

// Imports the Google Cloud Pipeline Service Client library
const {PipelineServiceClient} = aiplatform.v1;

// Specifies the location of the api endpoint
const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};

// Instantiates a client
const pipelineServiceClient = new PipelineServiceClient(clientOptions);

async function createTrainingPipelineTextClassification() {
  // Configure the parent resource
  const parent = `projects/${project}/locations/${location}`;

  const trainingTaskInputObj = new definition.AutoMlTextClassificationInputs({
    multiLabel: false,
  });
  const trainingTaskInputs = trainingTaskInputObj.toValue();

  const modelToUpload = {displayName: modelDisplayName};
  const inputDataConfig = {datasetId: datasetId};
  const trainingPipeline = {
    displayName: trainingPipelineDisplayName,
    trainingTaskDefinition:
      'gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_classification_1.0.0.yaml',
    trainingTaskInputs,
    inputDataConfig,
    modelToUpload,
  };
  const request = {
    parent,
    trainingPipeline,
  };

  // Create training pipeline request
  const [response] =
    await pipelineServiceClient.createTrainingPipeline(request);

  console.log('Create training pipeline text classification response :');
  console.log(`Name : ${response.name}`);
  console.log('Raw response:');
  console.log(JSON.stringify(response, null, 2));
}
createTrainingPipelineTextClassification();

Python

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Python 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Python API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

from google.cloud import aiplatform
from google.cloud.aiplatform.gapic.schema import trainingjob


def create_training_pipeline_text_classification_sample(
    project: str,
    display_name: str,
    dataset_id: str,
    model_display_name: str,
    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)
    training_task_inputs = (
        trainingjob.definition.AutoMlTextClassificationInputs().to_value()
    )

    training_pipeline = {
        "display_name": display_name,
        "training_task_definition": "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_classification_1.0.0.yaml",
        "training_task_inputs": training_task_inputs,
        "input_data_config": {"dataset_id": dataset_id},
        "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)

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅 Google Cloud 示例浏览器。