Export a dataset (beta)

Exports a dataset from the given Google Cloud project.

Explore further

For detailed documentation that includes this code sample, see the following:

• Exporting labeled data

Code sample

Java

To learn how to install and use the client library for Data Labeling Service, see Data Labeling Service client libraries. For more information, see the Data Labeling Service Java API reference documentation.

To authenticate to Data Labeling Service, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.datalabeling.v1beta1.DataLabelingServiceClient;
import com.google.cloud.datalabeling.v1beta1.DataLabelingServiceSettings;
import com.google.cloud.datalabeling.v1beta1.ExportDataOperationMetadata;
import com.google.cloud.datalabeling.v1beta1.ExportDataOperationResponse;
import com.google.cloud.datalabeling.v1beta1.ExportDataRequest;
import com.google.cloud.datalabeling.v1beta1.GcsDestination;
import com.google.cloud.datalabeling.v1beta1.LabelStats;
import com.google.cloud.datalabeling.v1beta1.OutputConfig;
import java.io.IOException;
import java.util.Map.Entry;
import java.util.Set;
import java.util.concurrent.ExecutionException;

class ExportData {

  // Export data from an annotated dataset.
  static void exportData(String datasetName, String annotatedDatasetName, String gcsOutputUri)
      throws IOException {
    // String datasetName = DataLabelingServiceClient.formatDatasetName(
    //     "YOUR_PROJECT_ID", "YOUR_DATASETS_UUID");
    // String annotatedDatasetName = DataLabelingServiceClient.formatAnnotatedDatasetName(
    //     "YOUR_PROJECT_ID",
    //     "YOUR_DATASET_UUID",
    //     "YOUR_ANNOTATED_DATASET_UUID");
    // String gcsOutputUri = "gs://YOUR_BUCKET_ID/export_path";


    DataLabelingServiceSettings settings =
        DataLabelingServiceSettings.newBuilder()
            .build();
    try (DataLabelingServiceClient dataLabelingServiceClient =
        DataLabelingServiceClient.create(settings)) {
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUri(gcsOutputUri).setMimeType("text/csv").build();

      OutputConfig outputConfig =
          OutputConfig.newBuilder().setGcsDestination(gcsDestination).build();

      ExportDataRequest exportDataRequest =
          ExportDataRequest.newBuilder()
              .setName(datasetName)
              .setOutputConfig(outputConfig)
              .setAnnotatedDataset(annotatedDatasetName)
              .build();

      OperationFuture<ExportDataOperationResponse, ExportDataOperationMetadata> operation =
          dataLabelingServiceClient.exportDataAsync(exportDataRequest);

      ExportDataOperationResponse response = operation.get();

      System.out.format("Exported item count: %d\n", response.getExportCount());
      LabelStats labelStats = response.getLabelStats();
      Set<Entry<String, Long>> entries = labelStats.getExampleCountMap().entrySet();
      for (Entry<String, Long> entry : entries) {
        System.out.format("\tLabel: %s\n", entry.getKey());
        System.out.format("\tCount: %d\n\n", entry.getValue());
      }
    } catch (IOException | InterruptedException | ExecutionException e) {
      e.printStackTrace();
    }
  }
}

Python

To learn how to install and use the client library for Data Labeling Service, see Data Labeling Service client libraries. For more information, see the Data Labeling Service Python API reference documentation.

To authenticate to Data Labeling Service, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

def export_data(dataset_resource_name, annotated_dataset_resource_name, export_gcs_uri):
    """Exports a dataset from the given Google Cloud project."""
    from google.cloud import datalabeling_v1beta1 as datalabeling

    client = datalabeling.DataLabelingServiceClient()

    gcs_destination = datalabeling.GcsDestination(
        output_uri=export_gcs_uri, mime_type="text/csv"
    )

    output_config = datalabeling.OutputConfig(gcs_destination=gcs_destination)

    response = client.export_data(
        request={
            "name": dataset_resource_name,
            "annotated_dataset": annotated_dataset_resource_name,
            "output_config": output_config,
        }
    )

    print(f"Dataset ID: {response.result().dataset}\n")
    print("Output config:")
    print("\tGcs destination:")
    print(
        "\t\tOutput URI: {}\n".format(
            response.result().output_config.gcs_destination.output_uri
        )
    )

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.