Create a model

Stay organized with collections Save and categorize content based on your preferences.

Demonstrates using AutoML Tables to create a model.

Explore further

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

Code sample

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1beta1.AutoMlClient;
import com.google.cloud.automl.v1beta1.ColumnSpec;
import com.google.cloud.automl.v1beta1.ColumnSpecName;
import com.google.cloud.automl.v1beta1.LocationName;
import com.google.cloud.automl.v1beta1.Model;
import com.google.cloud.automl.v1beta1.OperationMetadata;
import com.google.cloud.automl.v1beta1.TablesModelMetadata;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class TablesCreateModel {

  public static void main(String[] args)
      throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String datasetId = "YOUR_DATASET_ID";
    String tableSpecId = "YOUR_TABLE_SPEC_ID";
    String columnSpecId = "YOUR_COLUMN_SPEC_ID";
    String displayName = "YOUR_DATASET_NAME";
    createModel(projectId, datasetId, tableSpecId, columnSpecId, displayName);
  }

  // Create a model
  static void createModel(
      String projectId,
      String datasetId,
      String tableSpecId,
      String columnSpecId,
      String displayName)
      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()) {
      // A resource that represents Google Cloud Platform location.
      LocationName projectLocation = LocationName.of(projectId, "us-central1");

      // Get the complete path of the column.
      ColumnSpecName columnSpecName =
          ColumnSpecName.of(projectId, "us-central1", datasetId, tableSpecId, columnSpecId);

      // Build the get column spec.
      ColumnSpec targetColumnSpec =
          ColumnSpec.newBuilder().setName(columnSpecName.toString()).build();

      // Set model metadata.
      TablesModelMetadata metadata =
          TablesModelMetadata.newBuilder()
              .setTargetColumnSpec(targetColumnSpec)
              .setTrainBudgetMilliNodeHours(24000)
              .build();

      Model model =
          Model.newBuilder()
              .setDisplayName(displayName)
              .setDatasetId(datasetId)
              .setTablesModelMetadata(metadata)
              .build();

      // Create a model with the model metadata in the region.
      OperationFuture<Model, OperationMetadata> future =
          client.createModelAsync(projectLocation, model);
      // OperationFuture.get() will block until the model is created, which may take several hours.
      // You can use OperationFuture.getInitialFuture to get a future representing the initial
      // response to the request, which contains information while the operation is in progress.
      System.out.format("Training operation name: %s%n", future.getInitialFuture().get().getName());
      System.out.println("Training started...");
    }
  }
}

Node.js

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

/**
 * Demonstrates using the AutoML client to create a model.
 * 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";
// const tableId = '[TABLE_ID]' e.g., "1991013247762825216";
// const columnId = '[COLUMN_ID]' e.g., "773141392279994368";
// const modelName = '[MODEL_NAME]' e.g., "testModel";
// const trainBudget = '[TRAIN_BUDGET]' e.g., "1000",
// `Train budget in milli node hours`;

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

// Get the full path of the column.
const columnSpecId = client.columnSpecPath(
  projectId,
  computeRegion,
  datasetId,
  tableId,
  columnId
);

// Set target column to train the model.
const targetColumnSpec = {name: columnSpecId};

// Set tables model metadata.
const tablesModelMetadata = {
  targetColumnSpec: targetColumnSpec,
  trainBudgetMilliNodeHours: trainBudget,
};

// Set datasetId, model name and model metadata for the dataset.
const myModel = {
  datasetId: datasetId,
  displayName: modelName,
  tablesModelMetadata: tablesModelMetadata,
};

// Create a model with the model metadata in the region.
client
  .createModel({parent: projectLocation, model: myModel})
  .then(responses => {
    const initialApiResponse = responses[1];
    console.log(`Training operation name: ${initialApiResponse.name}`);
    console.log('Training started...');
  })
  .catch(err => {
    console.error(err);
  });

Python

# 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'
# model_display_name = 'MODEL_DISPLAY_NAME_HERE'
# train_budget_milli_node_hours = 'TRAIN_BUDGET_MILLI_NODE_HOURS_HERE'
# include_column_spec_names = 'INCLUDE_COLUMN_SPEC_NAMES_HERE'
#    or None if unspecified
# exclude_column_spec_names = 'EXCLUDE_COLUMN_SPEC_NAMES_HERE'
#    or None if unspecified

from google.cloud import automl_v1beta1 as automl

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

# Create a model with the model metadata in the region.
response = client.create_model(
    model_display_name,
    train_budget_milli_node_hours=train_budget_milli_node_hours,
    dataset_display_name=dataset_display_name,
    include_column_spec_names=include_column_spec_names,
    exclude_column_spec_names=exclude_column_spec_names,
)

print("Training model...")
print("Training operation name: {}".format(response.operation.name))
print("Training completed: {}".format(response.result()))

What's next

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