此旧版 AutoML Tables 已弃用，2024 年 3 月 31 日之后将不再在 Google Cloud 上提供。旧版 AutoML Tables 的所有功能和新功能均在 Vertex AI 平台上提供。请参阅迁移到 Vertex AI，了解如何迁移资源。

管理数据集

本页面介绍如何删除和获取与数据集相关的信息。

如需了解如何创建数据集并将数据导入其中，请参阅创建数据集并导入数据。

准备工作

您必须先按照准备工作所述设置项目，然后才能使用 AutoML Tables。

列出数据集

一个项目可以包含许多数据集。本部分介绍如何检索项目的可用数据集列表。

控制台

要使用 AutoML Tables 界面查看可用数据集列表，请点击左侧导航菜单顶部的数据集链接，然后选择区域。

REST

要列出数据集，请使用 datasets.list 方法。

在使用任何请求数据之前，请先进行以下替换：

endpoint：全球位置为 automl.googleapis.com，欧盟地区为 eu-automl.googleapis.com。
project-id：您的 Google Cloud 项目 ID。
location：资源的位置：全球位置为 us-central1，欧盟位置为 eu。

HTTP 方法和网址：

GET https://endpoint/v1beta1/projects/project-id/locations/location/datasets

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X GET \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: project-id" \
    "https://endpoint/v1beta1/projects/project-id/locations/location/datasets"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://endpoint/v1beta1/projects/project-id/locations/location/datasets" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
      "name": "projects/29434381/locations/us-central1/datasets/TBL75559",
      "displayName": "test_dataset",
      "createTime": "2019-03-21T00:50:20.660378Z",
      "updateTime": "2019-08-23T19:32:52.025469Z",
      "etag": "AB3BwFoV4USmhM3pT8c6Y5AIA6n51dAmSuObc=",
      "exampleCount": 94356,
      "tablesDatasetMetadata": {
        "primaryTableSpecId": "16930321664",
        "targetColumnSpecId": "46579780096",
        "areStatsFresh": true,
        "targetColumnCorrelations": {
          "6788648672679690240": {
            "cramersV": 0.16511808788616378
          },
          "87292427152392192": {
            "cramersV": 0.20327159375043746
          },
          "2393135436366086144": {
            "cramersV": 0.15513206308654948
          },
          "9094491681893384192": {
            "cramersV": 0.021499396246101456
          },
          "7004821454793474048": {
            "cramersV": 0.030097587339321379
          }
        },
        "statsUpdateTime": "2019-08-16T01:43:38.583Z",
        "tablesDatasetType": "BASIC"
      }
    },
...

Java

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

import com.google.cloud.automl.v1beta1.AutoMlClient;
import com.google.cloud.automl.v1beta1.Dataset;
import com.google.cloud.automl.v1beta1.ListDatasetsRequest;
import com.google.cloud.automl.v1beta1.LocationName;
import java.io.IOException;

class ListDatasets {

  static void listDatasets() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    listDatasets(projectId);
  }

  // List the datasets
  static void listDatasets(String projectId) throws IOException {
    // 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");
      ListDatasetsRequest request =
          ListDatasetsRequest.newBuilder().setParent(projectLocation.toString()).build();

      // List all the datasets available in the region by applying filter.
      System.out.println("List of datasets:");
      for (Dataset dataset : client.listDatasets(request).iterateAll()) {
        // Display the dataset information
        System.out.format("%nDataset name: %s%n", dataset.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 = dataset.getName().split("/");
        String retrievedDatasetId = names[names.length - 1];
        System.out.format("Dataset id: %s%n", retrievedDatasetId);
        System.out.format("Dataset display name: %s%n", dataset.getDisplayName());
        System.out.println("Dataset create time:");
        System.out.format("\tseconds: %s%n", dataset.getCreateTime().getSeconds());
        System.out.format("\tnanos: %s%n", dataset.getCreateTime().getNanos());

        System.out.format("Tables dataset metadata: %s%n", dataset.getTablesDatasetMetadata());

      }
    }
  }
}

Node.js

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

const automl = require('@google-cloud/automl');
const util = require('util');
const client = new automl.v1beta1.AutoMlClient();

/**
 * Demonstrates using the AutoML client to list all datasets.
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const projectId = '[PROJECT_ID]' e.g., "my-gcloud-project";
// const computeRegion = '[REGION_NAME]' e.g., "us-central1";
// const filter = '[FILTER_EXPRESSIONS]' e.g., "tablesDatasetMetadata:*";

// A resource that represents Google Cloud Platform location.
const projectLocation = client.locationPath(projectId, computeRegion);

// List all the datasets available in the region by applying filter.
client
  .listDatasets({parent: projectLocation, filter: filter})
  .then(responses => {
    const dataset = responses[0];

    // Display the dataset information.
    console.log('List of datasets:');
    for (let i = 0; i < dataset.length; i++) {
      const tablesDatasetMetadata = dataset[i].tablesDatasetMetadata;

      console.log(`Dataset name: ${dataset[i].name}`);
      console.log(`Dataset Id: ${dataset[i].name.split('/').pop(-1)}`);
      console.log(`Dataset display name: ${dataset[i].displayName}`);
      console.log(`Dataset example count: ${dataset[i].exampleCount}`);
      console.log('Tables dataset metadata:');
      console.log(
        `\tTarget column correlations: ${util.inspect(
          tablesDatasetMetadata.targetColumnCorrelations,
          false,
          null
        )}`
      );
      console.log(
        `\tPrimary table spec Id: ${tablesDatasetMetadata.primaryTableSpecId}`
      );
      console.log(
        `\tTarget column spec Id: ${tablesDatasetMetadata.targetColumnSpecId}`
      );
      console.log(
        `\tWeight column spec Id: ${tablesDatasetMetadata.weightColumnSpecId}`
      );
      console.log(
        `\tMl use column spec Id: ${tablesDatasetMetadata.mlUseColumnSpecId}`
      );
    }
  })
  .catch(err => {
    console.error(err);
  });

Python

AutoML Tables 的客户端库包含其他 Python 方法，这些方法使用 AutoML Tables API 进行简化。这些方法按名称而不是 ID 来引用数据集和模型。您的数据集和模型的名称必须是唯一的。如需了解详情，请参阅客户端参考。

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

# TODO(developer): Uncomment and set the following variables
# project_id = 'PROJECT_ID_HERE'
# compute_region = 'COMPUTE_REGION_HERE'
# filter = 'filter expression here'

from google.cloud import automl_v1beta1 as automl

client = automl.TablesClient(project=project_id, region=compute_region)

# List all the datasets available in the region by applying filter.
response = client.list_datasets(filter=filter)

print("List of datasets:")
for dataset in response:
    # Display the dataset information.
    print(f"Dataset name: {dataset.name}")
    print("Dataset id: {}".format(dataset.name.split("/")[-1]))
    print(f"Dataset display name: {dataset.display_name}")
    metadata = dataset.tables_dataset_metadata
    print(
        "Dataset primary table spec id: {}".format(metadata.primary_table_spec_id)
    )
    print(
        "Dataset target column spec id: {}".format(metadata.target_column_spec_id)
    )
    print(
        "Dataset target column spec id: {}".format(metadata.target_column_spec_id)
    )
    print(
        "Dataset weight column spec id: {}".format(metadata.weight_column_spec_id)
    )
    print(
        "Dataset ml use column spec id: {}".format(metadata.ml_use_column_spec_id)
    )
    print(f"Dataset example count: {dataset.example_count}")
    print(f"Dataset create time: {dataset.create_time}")
    print("\n")

删除数据集

删除数据集会将数据集从您的项目中永久移除。此操作不会删除根据该数据集创建的任何模型。如果想要删除模型，则必须明确删除它们。

控制台

在 AutoML Tables 界面中，点击左侧导航菜单顶部的数据集链接，然后选择区域以显示可用数据集的列表。
点击要删除的行最右侧的“更多操作”菜单，然后选择删除数据集。
在确认对话框中点击确认。

REST

要删除数据集，请使用 datasets.delete 方法。

在使用任何请求数据之前，请先进行以下替换：

endpoint：全球位置为 automl.googleapis.com，欧盟地区为 eu-automl.googleapis.com。
project-id：您的 Google Cloud 项目 ID。
location：资源的位置：全球位置为 us-central1，欧盟位置为 eu。
dataset-id：要删除的数据集的 ID。例如，TBL6543。

HTTP 方法和网址：

DELETE https://endpoint/v1beta1/projects/project-id/locations/location/datasets/dataset-id

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: project-id" \
    "https://endpoint/v1beta1/projects/project-id/locations/location/datasets/dataset-id"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "project-id" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://endpoint/v1beta1/projects/project-id/locations/location/datasets/dataset-id" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/29452381/locations/us-central1/operations/TBL6543",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
    "createTime": "2019-12-26T17:19:50.684850Z",
    "updateTime": "2019-12-26T17:19:50.684850Z",
    "deleteDetails": {},
    "worksOn": [
      "projects/29452381/locations/us-central1/datasets/TBL6543"
    ],
    "state": "DONE"
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.protobuf.Empty"
  }
}

删除数据集是一项长时间运行的操作。您可以轮询操作状态或等待操作返回。了解详情。

Java

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

import com.google.cloud.automl.v1beta1.AutoMlClient;
import com.google.cloud.automl.v1beta1.DatasetName;
import com.google.protobuf.Empty;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class DeleteDataset {

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

  // Delete a dataset
  static void deleteDataset(String projectId, String datasetId)
      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()) {
      // Get the full path of the dataset.
      DatasetName datasetFullId = DatasetName.of(projectId, "us-central1", datasetId);
      Empty response = client.deleteDatasetAsync(datasetFullId).get();
      System.out.format("Dataset deleted. %s%n", response);
    }
  }
}

Node.js

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

const automl = require('@google-cloud/automl');
const client = new automl.v1beta1.AutoMlClient();

/**
 * Demonstrates using the AutoML client to delete a dataset.
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const projectId = '[PROJECT_ID]' e.g., "my-gcloud-project";
// const computeRegion = '[REGION_NAME]' e.g., "us-central1";
// const datasetId = '[DATASET_ID]' e.g., "TBL2246891593778855936";

// Get the full path of the dataset.
const datasetFullId = client.datasetPath(projectId, computeRegion, datasetId);

// Delete a dataset.
client
  .deleteDataset({name: datasetFullId})
  .then(responses => {
    const operation = responses[0];
    return operation.promise();
  })
  .then(responses => {
    // The final result of the operation.
    const operationDetails = responses[2];

    // Get the dataset delete details.
    console.log('Dataset delete details:');
    console.log('\tOperation details:');
    console.log(`\t\tName: ${operationDetails.name}`);
    console.log(`\t\tDone: ${operationDetails.done}`);
  })
  .catch(err => {
    console.error(err);
  });

Python

如果资源位于欧盟区域，您必须明确设置端点。了解详情。

# TODO(developer): Uncomment and set the following variables
# project_id = 'PROJECT_ID_HERE'
# compute_region = 'COMPUTE_REGION_HERE'
# dataset_display_name = 'DATASET_DISPLAY_NAME_HERE

from google.cloud import automl_v1beta1 as automl

client = automl.TablesClient(project=project_id, region=compute_region)

# Delete a dataset.
response = client.delete_dataset(dataset_display_name=dataset_display_name)

# synchronous check of operation status.
print(f"Dataset deleted. {response.result()}")

后续步骤

创建模型。
详细了解数据类型。