当前位置: 首页>>代码示例>>Python>>正文


Python bigquery.QueryJobConfig方法代码示例

本文整理汇总了Python中google.cloud.bigquery.QueryJobConfig方法的典型用法代码示例。如果您正苦于以下问题:Python bigquery.QueryJobConfig方法的具体用法?Python bigquery.QueryJobConfig怎么用?Python bigquery.QueryJobConfig使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在google.cloud.bigquery的用法示例。


在下文中一共展示了bigquery.QueryJobConfig方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: test_client_library_legacy_query

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def test_client_library_legacy_query():
    # [START bigquery_migration_client_library_query_legacy]
    from google.cloud import bigquery

    client = bigquery.Client()
    sql = """
        SELECT name
        FROM [bigquery-public-data:usa_names.usa_1910_current]
        WHERE state = 'TX'
        LIMIT 100
    """
    query_config = bigquery.QueryJobConfig(use_legacy_sql=True)

    df = client.query(sql, job_config=query_config).to_dataframe()
    # [END bigquery_migration_client_library_query_legacy]
    assert len(df) > 0 
开发者ID:GoogleCloudPlatform,项目名称:python-docs-samples,代码行数:18,代码来源:samples_test.py

示例2: test_client_library_query_with_parameters

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def test_client_library_query_with_parameters():
    # [START bigquery_migration_client_library_query_parameters]
    from google.cloud import bigquery

    client = bigquery.Client()
    sql = """
        SELECT name
        FROM `bigquery-public-data.usa_names.usa_1910_current`
        WHERE state = @state
        LIMIT @limit
    """
    query_config = bigquery.QueryJobConfig(
        query_parameters=[
            bigquery.ScalarQueryParameter('state', 'STRING', 'TX'),
            bigquery.ScalarQueryParameter('limit', 'INTEGER', 100)
        ]
    )

    df = client.query(sql, job_config=query_config).to_dataframe()
    # [END bigquery_migration_client_library_query_parameters]
    assert len(df) > 0 
开发者ID:GoogleCloudPlatform,项目名称:python-docs-samples,代码行数:23,代码来源:samples_test.py

示例3: client_query_legacy_sql

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def client_query_legacy_sql():

    # [START bigquery_query_legacy]
    from google.cloud import bigquery

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

    query = (
        "SELECT name FROM [bigquery-public-data:usa_names.usa_1910_2013] "
        'WHERE state = "TX" '
        "LIMIT 100"
    )

    # Set use_legacy_sql to True to use legacy SQL syntax.
    job_config = bigquery.QueryJobConfig(use_legacy_sql=True)

    # Start the query, passing in the extra configuration.
    query_job = client.query(query, job_config=job_config)  # Make an API request.

    print("The query data:")
    for row in query_job:
        print(row)
    # [END bigquery_query_legacy] 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:26,代码来源:client_query_legacy_sql.py

示例4: query_no_cache

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def query_no_cache():

    # [START bigquery_query_no_cache]
    from google.cloud import bigquery

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

    job_config = bigquery.QueryJobConfig(use_query_cache=False)
    sql = """
        SELECT corpus
        FROM `bigquery-public-data.samples.shakespeare`
        GROUP BY corpus;
    """
    query_job = client.query(sql, job_config=job_config)  # Make an API request.

    for row in query_job:
        print(row)
    # [END bigquery_query_no_cache] 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:21,代码来源:query_no_cache.py

示例5: client_query_dry_run

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def client_query_dry_run():

    # [START bigquery_query_dry_run]
    from google.cloud import bigquery

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

    job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)

    # Start the query, passing in the extra configuration.
    query_job = client.query(
        (
            "SELECT name, COUNT(*) as name_count "
            "FROM `bigquery-public-data.usa_names.usa_1910_2013` "
            "WHERE state = 'WA' "
            "GROUP BY name"
        ),
        job_config=job_config,
    )  # Make an API request.

    # A dry run query completes immediately.
    print("This query will process {} bytes.".format(query_job.total_bytes_processed))
    # [END bigquery_query_dry_run]
    return query_job 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:27,代码来源:client_query_dry_run.py

示例6: client_query_destination_table

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def client_query_destination_table(table_id):

    # [START bigquery_query_destination_table]
    from google.cloud import bigquery

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

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

    job_config = bigquery.QueryJobConfig(destination=table_id)

    sql = """
        SELECT corpus
        FROM `bigquery-public-data.samples.shakespeare`
        GROUP BY corpus;
    """

    # Start the query, passing in the extra configuration.
    query_job = client.query(sql, job_config=job_config)  # Make an API request.
    query_job.result()  # Wait for the job to complete.

    print("Query results loaded to the table {}".format(table_id))
    # [END bigquery_query_destination_table] 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:27,代码来源:client_query_destination_table.py

示例7: create_job

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def create_job():

    # [START bigquery_create_job]
    from google.cloud import bigquery

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

    query_job = client.query(
        "SELECT country_name from `bigquery-public-data.utility_us.country_code_iso`",
        # Explicitly force job execution to be routed to a specific processing
        # location.
        location="US",
        # Specify a job configuration to set optional job resource properties.
        job_config=bigquery.QueryJobConfig(
            labels={"example-label": "example-value"}, maximum_bytes_billed=1000000
        ),
        # The client libraries automatically generate a job ID. Override the
        # generated ID with either the job_id_prefix or job_id parameters.
        job_id_prefix="code_sample_",
    )  # Make an API request.

    print("Started job: {}".format(query_job.job_id))
    # [END bigquery_create_job]
    return query_job 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:27,代码来源:create_job.py

示例8: test_query_w_legacy_sql_types

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def test_query_w_legacy_sql_types(self):
        naive = datetime.datetime(2016, 12, 5, 12, 41, 9)
        stamp = "%s %s" % (naive.date().isoformat(), naive.time().isoformat())
        zoned = naive.replace(tzinfo=UTC)
        examples = [
            {"sql": "SELECT 1", "expected": 1},
            {"sql": "SELECT 1.3", "expected": 1.3},
            {"sql": "SELECT TRUE", "expected": True},
            {"sql": 'SELECT "ABC"', "expected": "ABC"},
            {"sql": 'SELECT CAST("foo" AS BYTES)', "expected": b"foo"},
            {"sql": 'SELECT CAST("%s" AS TIMESTAMP)' % (stamp,), "expected": zoned},
        ]
        for example in examples:
            job_config = bigquery.QueryJobConfig()
            job_config.use_legacy_sql = True
            rows = list(Config.CLIENT.query(example["sql"], job_config=job_config))
            self.assertEqual(len(rows), 1)
            self.assertEqual(len(rows[0]), 1)
            self.assertEqual(rows[0][0], example["expected"]) 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:21,代码来源:system.py

示例9: test_querying_data_w_timeout

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def test_querying_data_w_timeout(self):
        job_config = bigquery.QueryJobConfig()
        job_config.use_query_cache = False

        query_job = Config.CLIENT.query(
            """
            SELECT name, SUM(number) AS total_people
            FROM `bigquery-public-data.usa_names.usa_1910_current`
            GROUP BY name
            """,
            location="US",
            job_config=job_config,
        )

        # Specify a very tight deadline to demonstrate that the timeout
        # actually has effect.
        with self.assertRaises(requests.exceptions.Timeout):
            query_job.done(timeout=0.1)

        # Now wait for the result using a more realistic deadline.
        query_job.result(timeout=30)
        self.assertTrue(query_job.done(timeout=30)) 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:24,代码来源:system.py

示例10: default_query_job_config

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def default_query_job_config(self):
        """google.cloud.bigquery.job.QueryJobConfig: Default job
        configuration for queries.

        The context's :class:`~google.cloud.bigquery.job.QueryJobConfig` is
        used for queries. Some properties can be overridden with arguments to
        the magics.

        Example:
            Manually setting the default value for ``maximum_bytes_billed``
            to 100 MB:

            >>> from google.cloud.bigquery import magics
            >>> magics.context.default_query_job_config.maximum_bytes_billed = 100000000
        """
        return self._default_query_job_config 
开发者ID:googleapis,项目名称:python-bigquery,代码行数:18,代码来源:magics.py

示例11: execute_transformation_query

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def execute_transformation_query(bq_client):
    """Executes transformation query to a new destination table.
    Args:
        bq_client: Object representing a reference to a BigQuery Client
    """
    dataset_ref = bq_client.get_dataset(bigquery.DatasetReference(
        project=config.config_vars['billing_project_id'],
        dataset_id=config.config_vars['output_dataset_id']))
    table_ref = dataset_ref.table(config.config_vars['output_table_name'])
    job_config = bigquery.QueryJobConfig()
    job_config.destination = table_ref
    job_config.write_disposition = bigquery.WriteDisposition().WRITE_TRUNCATE
    job_config.time_partitioning = bigquery.TimePartitioning(
        field='usage_start_time',
        expiration_ms=None)
    sql = file_to_string(config.config_vars['sql_file_path'])
    sql = sql.format(**config.config_vars)
    logging.info('Attempting query on all dates...')
    # Execute Query
    query_job = bq_client.query(
        sql,
        job_config=job_config)

    query_job.result()  # Waits for the query to finish
    logging.info('Transformation query complete. All partitions are updated.') 
开发者ID:GoogleCloudPlatform,项目名称:professional-services,代码行数:27,代码来源:main.py

示例12: testPartitionsAndUsageDates

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def testPartitionsAndUsageDates(self):
        """Tests that the # of partitions is equal to the # of usage_start_times."""
        bq_client = bigquery.Client()
        job_config = bigquery.QueryJobConfig()
        usage_query = """
            SELECT COUNT(DISTINCT(DATE(usage_start_time))) AS cnt
            FROM `{billing_project_id}.{output_dataset_id}.{output_table_name}`
            """
        usage_query = usage_query.format(**config.config_vars)
        query_job = bq_client.query(usage_query, job_config=job_config)
        for row in query_job.result():
            output_result = row.cnt

        partition_query = """
            SELECT COUNT(DISTINCT(partition_id)) AS cnt
            FROM [{billing_project_id}.{output_dataset_id}.{output_table_name}$__PARTITIONS_SUMMARY__]
            """
        partition_query = partition_query.format(**config.config_vars)
        job_config = bigquery.QueryJobConfig()
        job_config.use_legacy_sql = True
        query_job = bq_client.query(partition_query, job_config=job_config)
        for row in query_job.result():
            partition_result = row.cnt
        assert output_result == partition_result 
开发者ID:GoogleCloudPlatform,项目名称:professional-services,代码行数:26,代码来源:main_test.py

示例13: get_max_ingest_timestamp

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def get_max_ingest_timestamp(self):
        """Gets the max timestamp that was set during the latest merge.

        Returns:
            latest_merge as a timestamp in string format.
        """
        get_last_max_ts_config = bigquery.QueryJobConfig()
        get_last_max_ts_config.use_legacy_sql = False
        get_last_max_timestamp_query = self.bq_client.query(
            query='SELECT max(ingestTimestamp) as max_ingest_timestamp '
            'FROM `{0:s}.{1:s}.{2:s}`'.format(self.project_id, self.dataset_id,
                                              self.temp_updates_table_id),
            job_config=get_last_max_ts_config,
            location='US')
        get_last_max_timestamp_query.result()
        results = list(get_last_max_timestamp_query)
        max_ingest_timestamp = results[0]['max_ingest_timestamp']
        if not max_ingest_timestamp:
            max_ingest_timestamp = INITIAL_TIMESTAMP

        return max_ingest_timestamp.strftime('%Y-%m-%d %H:%M:%S.%f %Z') 
开发者ID:GoogleCloudPlatform,项目名称:professional-services,代码行数:23,代码来源:user_info_updater.py

示例14: merge_updates

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def merge_updates(self, merge_updates_query):
        """Merges rows from the temp table into the final table.

        Args:
            merge_updates_query(str): Query for merging updates from the temp
                updates table to the final table.

        """

        logging.info('{0:s} Merging updates from {1:s} into {2:s}.'.format(
            str(datetime.datetime.now()), self.temp_updates_table_id,
            self.final_table_id))

        merge_updates_job_config = bigquery.QueryJobConfig()
        merge_updates_job_config.use_legacy_sql = False

        merge_updates_query_job = self.bq_client.query(
            query=merge_updates_query,
            location='US',
            job_config=merge_updates_job_config)
        merge_updates_query_job.result()
        logging.info('{0:s} Successfully merged updates into {1:s}.'.format(
            str(datetime.datetime.now()), self.final_table_id)) 
开发者ID:GoogleCloudPlatform,项目名称:professional-services,代码行数:25,代码来源:user_info_updater.py

示例15: get_table

# 需要导入模块: from google.cloud import bigquery [as 别名]
# 或者: from google.cloud.bigquery import QueryJobConfig [as 别名]
def get_table(view):
    """Helper for determining what table underlies a user-facing view, since the Storage API can't read views."""
    bq = bigquery.Client()
    view = view.replace(":", ".")
    # partition filter is required, so try a couple options
    for partition_column in ["DATE(submission_timestamp)", "submission_date"]:
        try:
            job = bq.query(
                f"SELECT * FROM `{view}` WHERE {partition_column} = CURRENT_DATE",
                bigquery.QueryJobConfig(dry_run=True),
            )
            break
        except Exception:
            continue
    else:
        raise ValueError("could not determine partition column")
    assert len(job.referenced_tables) == 1, "View combines multiple tables"
    table = job.referenced_tables[0]
    return f"{table.project}:{table.dataset_id}.{table.table_id}" 
开发者ID:mozilla,项目名称:telemetry-airflow,代码行数:21,代码来源:taar_similarity.py


注:本文中的google.cloud.bigquery.QueryJobConfig方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。