Obtener predicciones por lotes con entrada de BigQuery

Crea un trabajo de predicción por lotes con una tabla de BigQuery como entrada.

Páginas de documentación que incluyen esta muestra de código

Para ver la muestra de código usada en contexto, consulta la siguiente documentación:

Muestra de código

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1beta1.BatchPredictInputConfig;
import com.google.cloud.automl.v1beta1.BatchPredictOutputConfig;
import com.google.cloud.automl.v1beta1.BatchPredictRequest;
import com.google.cloud.automl.v1beta1.BatchPredictResult;
import com.google.cloud.automl.v1beta1.BigQueryDestination;
import com.google.cloud.automl.v1beta1.BigQuerySource;
import com.google.cloud.automl.v1beta1.ModelName;
import com.google.cloud.automl.v1beta1.OperationMetadata;
import com.google.cloud.automl.v1beta1.PredictionServiceClient;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class TablesBatchPredictBigQuery {

  static void batchPredict() throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String inputUri = "bq://YOUR_PROJECT_ID.bqDatasetID.bqTableId";
    String outputUri = "bq://YOUR_PROJECT_ID";
    batchPredict(projectId, modelId, inputUri, outputUri);
  }

  static void batchPredict(String projectId, String modelId, String inputUri, String outputUri)
      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 (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // Configure the source of the file from BigQuery
      BigQuerySource bigQuerySource = BigQuerySource.newBuilder().setInputUri(inputUri).build();
      BatchPredictInputConfig inputConfig =
          BatchPredictInputConfig.newBuilder().setBigquerySource(bigQuerySource).build();

      // Configure where to store the output in BigQuery
      BigQueryDestination bigQueryDestination =
          BigQueryDestination.newBuilder().setOutputUri(outputUri).build();
      BatchPredictOutputConfig outputConfig =
          BatchPredictOutputConfig.newBuilder().setBigqueryDestination(bigQueryDestination).build();

      // Build the request that will be sent to the API
      BatchPredictRequest request =
          BatchPredictRequest.newBuilder()
              .setName(name.toString())
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      // Start an asynchronous request
      OperationFuture<BatchPredictResult, OperationMetadata> future =
          client.batchPredictAsync(request);

      System.out.println("Waiting for operation to complete...");
      BatchPredictResult response = future.get();
      System.out.println("Batch Prediction results saved to BigQuery.");
    }
  }
}

Node.js


/**
 * Demonstrates using the AutoML client to request prediction from
 * automl tables using bigQuery.
 * 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 modelId = '[MODEL_ID]' e.g., "TBL4704590352927948800";
// const inputUri = '[BIGQUERY_PATH]'
// e.g., "bq://<project_id>.<dataset_id>.<table_id>",
// `The Big Query URI containing the inputs`;
// const outputUri = '[BIGQUERY_PATH]' e.g., "bq://<project_id>",
// `The destination Big Query URI for storing outputs`;

const automl = require('@google-cloud/automl');

// Create client for prediction service.
const automlClient = new automl.v1beta1.PredictionServiceClient();

// Get the full path of the model.
const modelFullId = automlClient.modelPath(projectId, computeRegion, modelId);

async function batchPredict() {
  // Construct request
  // Get the Big Query input URI.
  const inputConfig = {
    bigquerySource: {
      inputUri: inputUri,
    },
  };

  // Get the Big Query output URI.
  const outputConfig = {
    bigqueryDestination: {
      outputUri: outputUri,
    },
  };

  const [, operation] = await automlClient.batchPredict({
    name: modelFullId,
    inputConfig: inputConfig,
    outputConfig: outputConfig,
  });

  // Get the latest state of long-running operation.
  console.log(`Operation name: ${operation.name}`);
}

batchPredict();

Python

# TODO(developer): Uncomment and set the following variables
# project_id = 'PROJECT_ID_HERE'
# compute_region = 'COMPUTE_REGION_HERE'
# model_display_name = 'MODEL_DISPLAY_NAME_HERE'
# bq_input_uri = 'bq://my-project.my-dataset.my-table'
# bq_output_uri = 'bq://my-project'
# params = {}

from google.cloud import automl_v1beta1 as automl

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

# Query model
response = client.batch_predict(bigquery_input_uri=bq_input_uri,
                                bigquery_output_uri=bq_output_uri,
                                model_display_name=model_display_name,
                                params=params)
print("Making batch prediction... ")
# `response` is a async operation descriptor,
# you can register a callback for the operation to complete via `add_done_callback`:
# def callback(operation_future):
#   result = operation_future.result()
# response.add_done_callback(callback)
#
# or block the thread polling for the operation's results:
response.result()
# AutoML puts predictions in a newly generated dataset with a name by a mask "prediction_" + model_id + "_" + timestamp
# here's how to get the dataset name:
dataset_name = response.metadata.batch_predict_details.output_info.bigquery_output_dataset

print("Batch prediction complete.\nResults are in '{}' dataset.\n{}".format(
    dataset_name, response.metadata))

¿Qué sigue?

Para buscar y filtrar muestras de código para otros productos de Google Cloud, consulta el navegador de muestra de Google Cloud.