创建用于提取文本实体的数据集

创建用于提取文本实体的数据集。

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：

代码示例

Go

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Go API 参考文档。

如需向 AutoML Natural Language 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 (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// languageEntityExtractionCreateDataset creates a dataset for text entity extraction.
func languageEntityExtractionCreateDataset(w io.Writer, projectID string, location string, datasetName string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// datasetName := "dataset_display_name"

	ctx := context.Background()
	client, err := automl.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer client.Close()

	req := &automlpb.CreateDatasetRequest{
		Parent: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		Dataset: &automlpb.Dataset{
			DisplayName: datasetName,
			DatasetMetadata: &automlpb.Dataset_TextExtractionDatasetMetadata{
				TextExtractionDatasetMetadata: &automlpb.TextExtractionDatasetMetadata{},
			},
		},
	}

	op, err := client.CreateDataset(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateDataset: %w", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	dataset, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	fmt.Fprintf(w, "Dataset name: %v\n", dataset.GetName())

	return nil
}

Java

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Java API 参考文档。

如需向 AutoML Natural Language 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.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1.AutoMlClient;
import com.google.cloud.automl.v1.Dataset;
import com.google.cloud.automl.v1.LocationName;
import com.google.cloud.automl.v1.OperationMetadata;
import com.google.cloud.automl.v1.TextExtractionDatasetMetadata;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class LanguageEntityExtractionCreateDataset {

  static void createDataset() throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String displayName = "YOUR_DATASET_NAME";
    createDataset(projectId, displayName);
  }

  // Create a dataset
  static void createDataset(String projectId, String displayName)
      throws IOException, ExecutionException, InterruptedException {
    // 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 (AutoMlClient client = AutoMlClient.create()) {
      // A resource that represents Google Cloud Platform location.
      LocationName projectLocation = LocationName.of(projectId, "us-central1");

      TextExtractionDatasetMetadata metadata = TextExtractionDatasetMetadata.newBuilder().build();
      Dataset dataset =
          Dataset.newBuilder()
              .setDisplayName(displayName)
              .setTextExtractionDatasetMetadata(metadata)
              .build();
      OperationFuture<Dataset, OperationMetadata> future =
          client.createDatasetAsync(projectLocation, dataset);

      Dataset createdDataset = future.get();

      // Display the dataset information.
      System.out.format("Dataset name: %s\n", createdDataset.getName());
      // To get the dataset id, you have to parse it out of the `name` field. As dataset Ids are
      // required for other methods.
      // Name Form: `projects/{project_id}/locations/{location_id}/datasets/{dataset_id}`
      String[] names = createdDataset.getName().split("/");
      String datasetId = names[names.length - 1];
      System.out.format("Dataset id: %s\n", datasetId);
    }
  }
}

Node.js

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Node.js API 参考文档。

如需向 AutoML Natural Language 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.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const displayName = 'YOUR_DISPLAY_NAME';

// Imports the Google Cloud AutoML library
const {AutoMlClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new AutoMlClient();

async function createDataset() {
  // Construct request
  const request = {
    parent: client.locationPath(projectId, location),
    dataset: {
      displayName: displayName,
      textExtractionDatasetMetadata: {},
    },
  };

  // Create dataset
  const [operation] = await client.createDataset(request);

  // Wait for operation to complete.
  const [response] = await operation.promise();

  console.log(`Dataset name: ${response.name}`);
  console.log(`
    Dataset id: ${
      response.name
        .split('/')
        [response.name.split('/').length - 1].split('\n')[0]
    }`);
}

createDataset();

Python

如需了解如何安装和使用 AutoML Natural Language 的客户端库，请参阅 AutoML Natural Language 客户端库。 如需了解详情，请参阅 AutoML Natural Language Python API 参考文档。

如需向 AutoML Natural Language 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 automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# display_name = "YOUR_DATASET_NAME"

client = automl.AutoMlClient()

# A resource that represents Google Cloud Platform location.
project_location = f"projects/{project_id}/locations/us-central1"
metadata = automl.TextExtractionDatasetMetadata()
dataset = automl.Dataset(
    display_name=display_name, text_extraction_dataset_metadata=metadata
)

# Create a dataset with the dataset metadata in the region.
response = client.create_dataset(parent=project_location, dataset=dataset)

created_dataset = response.result()

# Display the dataset information
print(f"Dataset name: {created_dataset.name}")
print("Dataset id: {}".format(created_dataset.name.split("/")[-1]))

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。