클러스터링된 테이블 만들기 및 사용

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

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

schema = [
    bigquery.SchemaField("full_name", "STRING"),
    bigquery.SchemaField("city", "STRING"),
    bigquery.SchemaField("zipcode", "INTEGER"),
]

table = bigquery.Table(table_id, schema=schema)
table.clustering_fields = ["city", "zipcode"]
table = client.create_table(table)  # Make an API request.
print(
    "Created clustered table {}.{}.{}".format(
        table.project, table.dataset_id, table.table_id
    )
)

import (
	"context"
	"fmt"
	"time"

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

// createTableClustered demonstrates creating a BigQuery table with advanced properties like
// partitioning and clustering features.
func createTableClustered(projectID, datasetID, tableID string) error {
	// projectID := "my-project-id"
	// datasetID := "mydatasetid"
	// tableID := "mytableid"
	ctx := context.Background()

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

	sampleSchema := bigquery.Schema{
		{Name: "timestamp", Type: bigquery.TimestampFieldType},
		{Name: "origin", Type: bigquery.StringFieldType},
		{Name: "destination", Type: bigquery.StringFieldType},
		{Name: "amount", Type: bigquery.NumericFieldType},
	}
	metaData := &bigquery.TableMetadata{
		Schema: sampleSchema,
		TimePartitioning: &bigquery.TimePartitioning{
			Field:      "timestamp",
			Expiration: 90 * 24 * time.Hour,
		},
		Clustering: &bigquery.Clustering{
			Fields: []string{"origin", "destination"},
		},
	}
	tableRef := client.Dataset(datasetID).Table(tableID)
	if err := tableRef.Create(ctx, metaData); err != nil {
		return err
	}
	return nil
}

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.Clustering;
import com.google.cloud.bigquery.Field;
import com.google.cloud.bigquery.Schema;
import com.google.cloud.bigquery.StandardSQLTypeName;
import com.google.cloud.bigquery.StandardTableDefinition;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TableInfo;
import com.google.cloud.bigquery.TimePartitioning;
import com.google.common.collect.ImmutableList;

public class CreateClusteredTable {
  public static void runCreateClusteredTable() {
    // TODO(developer): Replace these variables before running the sample.
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    createClusteredTable(datasetName, tableName);
  }

  public static void createClusteredTable(String datasetName, String tableName) {
    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.
      BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();

      TableId tableId = TableId.of(datasetName, tableName);

      TimePartitioning partitioning = TimePartitioning.of(TimePartitioning.Type.DAY);

      Schema schema =
          Schema.of(
              Field.of("name", StandardSQLTypeName.STRING),
              Field.of("post_abbr", StandardSQLTypeName.STRING),
              Field.of("date", StandardSQLTypeName.DATE));

      Clustering clustering =
          Clustering.newBuilder().setFields(ImmutableList.of("name", "post_abbr")).build();

      StandardTableDefinition tableDefinition =
          StandardTableDefinition.newBuilder()
              .setSchema(schema)
              .setTimePartitioning(partitioning)
              .setClustering(clustering)
              .build();
      TableInfo tableInfo = TableInfo.newBuilder(tableId, tableDefinition).build();

      bigquery.create(tableInfo);
      System.out.println("Clustered table created successfully");
    } catch (BigQueryException e) {
      System.out.println("Clustered table was not created. \n" + e.toString());
    }
  }
}

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: %v", err)
	}
	defer client.Close()

	gcsRef := bigquery.NewGCSReference("gs://cloud-samples-data/bigquery/sample-transactions/transactions.csv")
	gcsRef.SkipLeadingRows = 1
	gcsRef.Schema = bigquery.Schema{
		{Name: "timestamp", Type: bigquery.TimestampFieldType},
		{Name: "origin", Type: bigquery.StringFieldType},
		{Name: "destination", Type: bigquery.StringFieldType},
		{Name: "amount", Type: bigquery.NumericFieldType},
	}
	loader := client.Dataset(destDatasetID).Table(destTableID).LoaderFrom(gcsRef)
	loader.TimePartitioning = &bigquery.TimePartitioning{
		Field: "timestamp",
	}
	loader.Clustering = &bigquery.Clustering{
		Fields: []string{"origin", "destination"},
	}
	loader.WriteDisposition = bigquery.WriteEmpty

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

	if status.Err() != nil {
		return fmt.Errorf("job completed with error: %v", status.Err())
	}
	return nil
}

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.Clustering;
import com.google.cloud.bigquery.Field;
import com.google.cloud.bigquery.FormatOptions;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.LoadJobConfiguration;
import com.google.cloud.bigquery.Schema;
import com.google.cloud.bigquery.StandardSQLTypeName;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TimePartitioning;
import com.google.common.collect.ImmutableList;

public class LoadTableClustered {

  public static void runLoadTableClustered() throws Exception {
    // 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";
    loadTableClustered(datasetName, tableName, sourceUri);
  }

  public static void loadTableClustered(String datasetName, String tableName, String sourceUri)
      throws Exception {
    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.
      BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();

      TableId tableId = TableId.of(datasetName, tableName);

      Schema schema =
          Schema.of(
              Field.of("name", StandardSQLTypeName.STRING),
              Field.of("post_abbr", StandardSQLTypeName.STRING),
              Field.of("date", StandardSQLTypeName.DATE));

      TimePartitioning partitioning = TimePartitioning.of(TimePartitioning.Type.DAY);

      Clustering clustering =
          Clustering.newBuilder().setFields(ImmutableList.of("name", "post_abbr")).build();

      LoadJobConfiguration loadJobConfig =
          LoadJobConfiguration.builder(tableId, sourceUri)
              .setFormatOptions(FormatOptions.csv())
              .setSchema(schema)
              .setTimePartitioning(partitioning)
              .setClustering(clustering)
              .build();

      Job loadJob = bigquery.create(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.
      Job completedJob = loadJob.waitFor();

      // Check for errors
      if (completedJob == null) {
        throw new Exception("Job not executed since it no longer exists.");
      } else if (completedJob.getStatus().getError() != null) {
        // You can also look at queryJob.getStatus().getExecutionErrors() for all
        // errors, not just the latest one.
        throw new Exception(
            "BigQuery was unable to load into the table due to an error: \n"
                + loadJob.getStatus().getError());
      }
      System.out.println("Data successfully loaded into clustered table during load job");
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Data not loaded into clustered table during load job \n" + e.toString());
    }
  }
}

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

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

job_config = bigquery.LoadJobConfig(
    skip_leading_rows=1,
    source_format=bigquery.SourceFormat.CSV,
    schema=[
        bigquery.SchemaField("timestamp", bigquery.SqlTypeNames.TIMESTAMP),
        bigquery.SchemaField("origin", bigquery.SqlTypeNames.STRING),
        bigquery.SchemaField("destination", bigquery.SqlTypeNames.STRING),
        bigquery.SchemaField("amount", bigquery.SqlTypeNames.NUMERIC),
    ],
    time_partitioning=bigquery.TimePartitioning(field="timestamp"),
    clustering_fields=["origin", "destination"],
)

job = client.load_table_from_uri(
    ["gs://cloud-samples-data/bigquery/sample-transactions/transactions.csv"],
    table_id,
    job_config=job_config,
)

job.result()  # Waits for the job to complete.

table = client.get_table(table_id)  # Make an API request.
print(
    "Loaded {} rows and {} columns to {}".format(
        table.num_rows, len(table.schema), table_id
    )
)