Create a dataset

Demonstrates how to create a dataset.

Explore further

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

• Creating datasets and importing data

Code sample

Java

View on GitHub Feedback

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

class TablesCreateDataset {

  public static void main(String[] args) throws IOException {
    // 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 {
    // 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");
      TablesDatasetMetadata metadata = TablesDatasetMetadata.newBuilder().build();
      Dataset dataset =
          Dataset.newBuilder()
              .setDisplayName(displayName)
              .setTablesDatasetMetadata(metadata)
              .build();

      Dataset createdDataset = client.createDataset(projectLocation, dataset);

      // 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

View on GitHub Feedback

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

/**
 * Demonstrates using the AutoML client to create 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 datasetName = '[DATASET_NAME]' e.g., “myDataset”;

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

// Set dataset name and metadata.
const myDataset = {
  displayName: datasetName,
  tablesDatasetMetadata: {},
};

// Create a dataset with the dataset metadata in the region.
client
  .createDataset({parent: projectLocation, dataset: myDataset})
  .then(responses => {
    const dataset = responses[0];
    // Display the dataset information.
    console.log(`Dataset name: ${dataset.name}`);
    console.log(`Dataset Id: ${dataset.name.split('/').pop(-1)}`);
    console.log(`Dataset display name: ${dataset.displayName}`);
    console.log(`Dataset example count: ${dataset.exampleCount}`);
    console.log(
      `Tables dataset metadata: ${util.inspect(
        dataset.tablesDatasetMetadata,
        false,
        null
      )}`
    );
  })
  .catch(err => {
    console.error(err);
  });

Python

View on GitHub Feedback

# 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)

# Create a dataset with the given display name
dataset = client.create_dataset(dataset_display_name)

# 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 metadata:")
print("\t{}".format(dataset.tables_dataset_metadata))
print("Dataset example count: {}".format(dataset.example_count))
print("Dataset create time: {}".format(dataset.create_time))

What's next

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