Load data from a CSV file on Cloud Storage to a clustered table.

## Explore further


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

- [Create clustered tables](https://docs.cloud.google.com/bigquery/docs/creating-clustered-tables)

## Code sample

### Go


Before trying this sample, follow the Go setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Go API
reference documentation](https://godoc.org/cloud.google.com/go/bigquery).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    import (
    	"context"
    	"fmt"

    	"cloud.google.com/go/bigquery"
    )

    // importClusteredTable demonstrates creating a table from a load job and defining partitioning and clustering
    // properties.
    func importClusteredTable(projectID, destDatasetID, destTableID string) error {
    	// projectID := "my-project-id"
    	// datasetID := "mydataset"
    	// tableID := "mytable"
    	ctx := context.Background()
    	client, err := bigquery.NewClient(ctx, projectID)
    	if err != nil {
    		return fmt.Errorf("bigquery.NewClient: %w", err)
    	}
    	defer client.Close()

    	gcsRef := bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_GCSReference_NewGCSReference("gs://cloud-samples-data/bigquery/sample-transactions/transactions.csv")
    	gcsRef.SkipLeadingRows = 1
    	gcsRef.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Schema = bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Schema{
    		{Name: "timestamp", Type: bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_StringFieldType_BytesFieldType_IntegerFieldType_FloatFieldType_BooleanFieldType_TimestampFieldType_RecordFieldType_DateFieldType_TimeFieldType_DateTimeFieldType_NumericFieldType_GeographyFieldType_BigNumericFieldType_IntervalFieldType_JSONFieldType_RangeFieldType},
    		{Name: "origin", Type: bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_StringFieldType_BytesFieldType_IntegerFieldType_FloatFieldType_BooleanFieldType_TimestampFieldType_RecordFieldType_DateFieldType_TimeFieldType_DateTimeFieldType_NumericFieldType_GeographyFieldType_BigNumericFieldType_IntervalFieldType_JSONFieldType_RangeFieldType},
    		{Name: "destination", Type: bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_StringFieldType_BytesFieldType_IntegerFieldType_FloatFieldType_BooleanFieldType_TimestampFieldType_RecordFieldType_DateFieldType_TimeFieldType_DateTimeFieldType_NumericFieldType_GeographyFieldType_BigNumericFieldType_IntervalFieldType_JSONFieldType_RangeFieldType},
    		{Name: "amount", Type: bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_StringFieldType_BytesFieldType_IntegerFieldType_FloatFieldType_BooleanFieldType_TimestampFieldType_RecordFieldType_DateFieldType_TimeFieldType_DateTimeFieldType_NumericFieldType_GeographyFieldType_BigNumericFieldType_IntervalFieldType_JSONFieldType_RangeFieldType},
    	}
    	loader := client.Dataset(destDatasetID).Table(destTableID).https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Table_LoaderFrom(gcsRef)
    	loader.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_TimePartitioning = &bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_TimePartitioning{
    		Field: "timestamp",
    	}
    	loader.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Clustering = &bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Clustering{
    		Fields: []string{"origin", "destination"},
    	}
    	loader.WriteDisposition = bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_WriteAppend_WriteTruncate_WriteTruncateData_WriteEmpty

    	job, err := loader.Run(ctx)
    	if err != nil {
    		return err
    	}
    	status, err := job.Wait(ctx)
    	if err != nil {
    		return err
    	}

    	if status.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_JobStatus_Err() != nil {
    		return fmt.Errorf("job completed with error: %w", status.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_JobStatus_Err())
    	}
    	return nil
    }

### Java


Before trying this sample, follow the Java setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Java API
reference documentation](https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/overview).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryException.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryOptions.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Clustering.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.JobInfo.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TimePartitioning.html;
    import com.google.common.collect.ImmutableList;
    import java.util.List;

    // Sample to load clustered table.
    public class LoadTableClustered {

      public static void main(String[] args) {
        // TODO(developer): Replace these variables before running the sample.
        String datasetName = "MY_DATASET_NAME";
        String tableName = "MY_TABLE_NAME";
        String sourceUri = "/path/to/file.csv";
        https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html schema =
            https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html.of(
                https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html.of("name", https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html.STRING),
                https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html.of("post_abbr", https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html.STRING),
                https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html.of("date", https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html.DATE));
        loadTableClustered(
            datasetName, tableName, sourceUri, schema, ImmutableList.of("name", "post_abbr"));
      }

      public static void loadTableClustered(
          String datasetName,
          String tableName,
          String sourceUri,
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html schema,
          List<String> clusteringFields) {
        try {
          // Initialize client that will be used to send requests. This client only needs to be created
          // once, and can be reused for multiple requests.
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html bigquery = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryOptions.html.getDefaultInstance().getService();

          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html tableId = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html.of(datasetName, tableName);

          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TimePartitioning.html partitioning = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TimePartitioning.html.of(https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TimePartitioning.html.Type.DAY);
          // Clustering fields will be consisted of fields mentioned in the schema.
          // BigQuery supports clustering for both partitioned and non-partitioned tables.
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Clustering.html clustering = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Clustering.html.newBuilder().setFields(clusteringFields).build();

          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html loadJobConfig =
              https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html.builder(tableId, sourceUri)
                  .setFormatOptions(https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html#com_google_cloud_bigquery_FormatOptions_csv__())
                  .setSchema(schema)
                  .setTimePartitioning(partitioning)
                  .setClustering(clustering)
                  .build();

          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html loadJob = bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html#com_google_cloud_bigquery_BigQuery_create_com_google_cloud_bigquery_DatasetInfo_com_google_cloud_bigquery_BigQuery_DatasetOption____(JobInfo.newBuilder(loadJobConfig).build());

          // Load data from a GCS parquet file into the table
          // Blocks until this load table job completes its execution, either failing or succeeding.
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html job = loadJob.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html#com_google_cloud_bigquery_Job_waitFor_com_google_cloud_bigquery_BigQueryRetryConfig_com_google_cloud_RetryOption____();

          // Check for errors
          if (job.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html#com_google_cloud_bigquery_Job_isDone__() && job.getStatus().getError() == null) {
            System.out.println("Data successfully loaded into clustered table during load job");
          } else {
            System.out.println(
                "BigQuery was unable to load into the table due to an error:"
                    + job.getStatus().getError());
          }
        } catch (https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryException.html | InterruptedException e) {
          System.out.println("Data not loaded into clustered table during load job \n" + e.toString());
        }
      }
    }

### Python


Before trying this sample, follow the Python setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Python API
reference documentation](https://docs.cloud.google.com/python/docs/reference/bigquery/latest).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    from google.cloud import https://docs.cloud.google.com/python/docs/reference/bigquery/latest

    # Construct a BigQuery client object.
    client = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html()

    # TODO(developer): Set table_id to the ID of the table to create.
    # table_id = "your-project.your_dataset.your_table_name"

    job_config = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.LoadJobConfig.html(
        skip_leading_rows=1,
        source_format=https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SourceFormat.html.CSV,
        schema=[
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("timestamp", https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SqlTypeNames.html.TIMESTAMP),
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("origin", https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SqlTypeNames.html.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.DecimalTargetType.html#google_cloud_bigquery_enums_DecimalTargetType_STRING),
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("destination", https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SqlTypeNames.html.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.DecimalTargetType.html#google_cloud_bigquery_enums_DecimalTargetType_STRING),
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("amount", https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SqlTypeNames.html.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.DecimalTargetType.html#google_cloud_bigquery_enums_DecimalTargetType_NUMERIC),
        ],
        time_partitioning=https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.TimePartitioning.html(field="timestamp"),
        clustering_fields=["origin", "destination"],
    )

    job = client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_load_table_from_uri(
        ["gs://cloud-samples-data/bigquery/sample-transactions/transactions.csv"],
        table_id,
        job_config=job_config,
    )

    https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.html.result()  # Waits for the job to complete.

    table = client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_get_table(table_id)  # Make an API request.
    print(
        "Loaded {} rows and {} columns to {}".format(
            table.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html#google_cloud_bigquery_table_Table_num_rows, len(table.schema), table_id
        )
    )

## What's next


To search and filter code samples for other Google Cloud products, see the
[Google Cloud sample browser](https://docs.cloud.google.com/docs/samples?product=bigquery).