Import data

Imports data to the given Google Cloud project and dataset.

Explore further

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

• Creating datasets

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.DataType;
import com.google.cloud.datalabeling.v1beta1.GcsSource;
import com.google.cloud.datalabeling.v1beta1.ImportDataOperationMetadata;
import com.google.cloud.datalabeling.v1beta1.ImportDataOperationResponse;
import com.google.cloud.datalabeling.v1beta1.ImportDataRequest;
import com.google.cloud.datalabeling.v1beta1.InputConfig;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class ImportData {

  // Import data to an existing dataset.
  static void importData(String datasetName, String gcsSourceUri) throws IOException {
    // String datasetName = DataLabelingServiceClient.formatDatasetName(
    //     "YOUR_PROJECT_ID", "YOUR_DATASETS_UUID");
    // String gcsSourceUri = "gs://YOUR_BUCKET_ID/path_to_data";


    DataLabelingServiceSettings settings =
        DataLabelingServiceSettings.newBuilder()
            .build();
    try (DataLabelingServiceClient dataLabelingServiceClient =
        DataLabelingServiceClient.create(settings)) {
      GcsSource gcsSource =
          GcsSource.newBuilder().setInputUri(gcsSourceUri).setMimeType("text/csv").build();

      InputConfig inputConfig =
          InputConfig.newBuilder()
              .setDataType(DataType.IMAGE) // DataTypes: AUDIO, IMAGE, VIDEO, TEXT
              .setGcsSource(gcsSource)
              .build();

      ImportDataRequest importDataRequest =
          ImportDataRequest.newBuilder().setName(datasetName).setInputConfig(inputConfig).build();

      OperationFuture<ImportDataOperationResponse, ImportDataOperationMetadata> operation =
          dataLabelingServiceClient.importDataAsync(importDataRequest);

      ImportDataOperationResponse response = operation.get();

      System.out.format("Imported items: %d\n", response.getImportCount());
    } 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 import_data(dataset_resource_name, data_type, input_gcs_uri):
    """Imports data to the given Google Cloud project and dataset."""
    from google.cloud import datalabeling_v1beta1 as datalabeling

    client = datalabeling.DataLabelingServiceClient()

    gcs_source = datalabeling.GcsSource(input_uri=input_gcs_uri, mime_type="text/csv")

    csv_input_config = datalabeling.InputConfig(
        data_type=data_type, gcs_source=gcs_source
    )

    response = client.import_data(
        request={"name": dataset_resource_name, "input_config": csv_input_config}
    )

    result = response.result()

    # The format of resource name:
    # project_id/{project_id}/datasets/{dataset_id}
    print(f"Dataset resource name: {result.dataset}\n")

    return result

What's next

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