This documentation is for AutoML Natural Language, which is different from Vertex AI. If you are using Vertex AI, see the Vertex AI documentation.

Get a dataset for text entity extraction

Get a dataset for text entity extraction.

Code sample

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// getDataset gets a dataset.
func getDataset(w io.Writer, projectID string, location string, datasetID string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// datasetID := "TRL123456789..."

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

	req := &automlpb.GetDatasetRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/datasets/%s", projectID, location, datasetID),
	}

	dataset, err := client.GetDataset(ctx, req)
	if err != nil {
		return fmt.Errorf("DeleteDataset: %v", err)
	}

	fmt.Fprintf(w, "Dataset name: %v\n", dataset.GetName())
	fmt.Fprintf(w, "Dataset display name: %v\n", dataset.GetDisplayName())
	fmt.Fprintf(w, "Dataset create time:\n")
	fmt.Fprintf(w, "\tseconds: %v\n", dataset.GetCreateTime().GetSeconds())
	fmt.Fprintf(w, "\tnanos: %v\n", dataset.GetCreateTime().GetNanos())

	// Language entity extraction
	if metadata := dataset.GetTextExtractionDatasetMetadata(); metadata != nil {
		fmt.Fprintf(w, "Text extraction dataset metadata: %v\n", metadata)
	}

	return nil
}

Java

import com.google.cloud.automl.v1.AutoMlClient;
import com.google.cloud.automl.v1.Dataset;
import com.google.cloud.automl.v1.DatasetName;
import java.io.IOException;

class GetDataset {

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

  // Get a dataset
  static void getDataset(String projectId, String datasetId) 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()) {
      // Get the complete path of the dataset.
      DatasetName datasetFullId = DatasetName.of(projectId, "us-central1", datasetId);
      Dataset dataset = client.getDataset(datasetFullId);

      // Display the dataset information
      System.out.format("Dataset 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(
          "Text extraction dataset metadata: %s\n", dataset.getTextExtractionDatasetMetadata());
    }
  }
}

Python

from google.cloud import automl

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

client = automl.AutoMlClient()
# Get the full path of the dataset
dataset_full_id = client.dataset_path(project_id, "us-central1", dataset_id)
dataset = client.get_dataset(name=dataset_full_id)

# Display the dataset information
print("Dataset name: {}".format(dataset.name))
print("Dataset id: {}".format(dataset.name.split("/")[-1]))
print("Dataset display name: {}".format(dataset.display_name))
print("Dataset create time: {}".format(dataset.create_time))
print(
    "Text extraction dataset metadata: {}".format(
        dataset.text_extraction_dataset_metadata
    )
)

What's next

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