def get_pandas_df(self, bql, parameters=None):
"""
Returns a Pandas DataFrame for the results produced by a BigQuery
query. The DbApiHook method must be overridden because Pandas
doesn't support PEP 249 connections, except for SQLite. See:
https://github.com/pydata/pandas/blob/master/pandas/io/sql.py#L447
https://github.com/pydata/pandas/issues/6900
:param bql: The BigQuery SQL to execute.
:type bql: string
"""
service = self.get_service()
project = self._get_field('project')
connector = BigQueryPandasConnector(project, service)
schema, pages = connector.run_query(bql)
dataframe_list = []
while len(pages) > 0:
page = pages.pop()
dataframe_list.append(gbq_parse_data(schema, page))
if len(dataframe_list) > 0:
return concat(dataframe_list, ignore_index=True)
else:
return gbq_parse_data(schema, [])
def get_pandas_df(self, bql, parameters=None, dialect='legacy'):
"""
Returns a Pandas DataFrame for the results produced by a BigQuery
query. The DbApiHook method must be overridden because Pandas
doesn't support PEP 249 connections, except for SQLite. See:
https://github.com/pydata/pandas/blob/master/pandas/io/sql.py#L447
https://github.com/pydata/pandas/issues/6900
:param bql: The BigQuery SQL to execute.
:type bql: string
:param parameters: The parameters to render the SQL query with (not used, leave to override superclass method)
:type parameters: mapping or iterable
:param dialect: Dialect of BigQuery SQL – legacy SQL or standard SQL
:type dialect: string in {'legacy', 'standard'}, default 'legacy'
"""
service = self.get_service()
project = self._get_field('project')
connector = BigQueryPandasConnector(project, service, dialect=dialect)
schema, pages = connector.run_query(bql)
dataframe_list = []
while len(pages) > 0:
page = pages.pop()
dataframe_list.append(gbq_parse_data(schema, page))
if len(dataframe_list) > 0:
return concat(dataframe_list, ignore_index=True)
else:
return gbq_parse_data(schema, [])
def get_pandas_df(self, bql, parameters=None, dialect='legacy'):
"""
Returns a Pandas DataFrame for the results produced by a BigQuery
query. The DbApiHook method must be overridden because Pandas
doesn't support PEP 249 connections, except for SQLite. See:
https://github.com/pydata/pandas/blob/master/pandas/io/sql.py#L447
https://github.com/pydata/pandas/issues/6900
:param bql: The BigQuery SQL to execute.
:type bql: string
:param parameters: The parameters to render the SQL query with (not
used, leave to override superclass method)
:type parameters: mapping or iterable
:param dialect: Dialect of BigQuery SQL – legacy SQL or standard SQL
:type dialect: string in {'legacy', 'standard'}, default 'legacy'
"""
service = self.get_service()
project = self._get_field('project')
connector = BigQueryPandasConnector(project, service, dialect=dialect)
schema, pages = connector.run_query(bql)
dataframe_list = []
while len(pages) > 0:
page = pages.pop()
dataframe_list.append(gbq_parse_data(schema, page))
if len(dataframe_list) > 0:
return concat(dataframe_list, ignore_index=True)
else:
return gbq_parse_data(schema, [])
