def _test_download_file(self, mocker, type):
staging_path = "gs://temp/"
staging_file_name = "temp_0"
dst_path = "/tmp/myfile.csv"
table_id = "project_id.dataset_id.table_id"
table_dldr = TableDownloader()
mock_blob = _Blob()
mocker.patch.object(mock_blob, "download_to_filename")
table_dldr._bq = _Mock_BQ_Client()
mocker.patch.object(table_dldr._bq,
"extract_table",
return_value=_Job())
table_dldr._gcs = _Mock_GCS_Client()
mocker.patch.object(table_dldr._gcs,
"get_bucket",
return_value=_Bucket(mock_blob))
table_dldr.download_table_as_file(table_id,
dst_path,
staging_location=staging_path,
file_type=type)
exp_staging_path = os.path.join(staging_path, staging_file_name)
assert len(table_dldr._bq.extract_table.call_args_list) == 1
args, kwargs = table_dldr._bq.extract_table.call_args_list[0]
assert args[0].full_table_id == Table.from_string(
table_id).full_table_id
assert args[1] == exp_staging_path
assert kwargs["job_config"].destination_format == str(type)
mock_blob.download_to_filename.assert_called_once_with(dst_path)
def test_download_table_as_df(self, mocker):
self._stop_time(mocker)
mocked_gcs_to_df = mocker.patch("feast.sdk.utils.bq_util.gcs_to_df",
return_value=None)
staging_path = "gs://temp/"
staging_file_name = "temp_0"
table_id = "project_id.dataset_id.table_id"
table_dldr = TableDownloader()
exp_staging_path = os.path.join(staging_path, staging_file_name)
table_dldr._bq = _Mock_BQ_Client()
mocker.patch.object(table_dldr._bq,
"extract_table",
return_value=_Job())
table_dldr.download_table_as_df(table_id,
staging_location=staging_path)
assert len(table_dldr._bq.extract_table.call_args_list) == 1
args, kwargs = table_dldr._bq.extract_table.call_args_list[0]
assert args[0].full_table_id == Table.from_string(
table_id).full_table_id
assert args[1] == exp_staging_path
assert kwargs["job_config"].destination_format == "CSV"
mocked_gcs_to_df.assert_called_once_with(exp_staging_path)
def download_table_as_df(self, full_table_id, staging_location):
"""
Download a BigQuery table as Pandas Dataframe
Args:
full_table_id (src) : fully qualified BigQuery table id
staging_location: url to staging_location (currently
support a folder in GCS)
Returns: pandas.DataFrame: dataframe of the training dataset
"""
if not is_gs_path(staging_location):
raise ValueError("staging_uri must be a directory in GCS")
temp_file_name = "temp_{}".format(int(round(time.time() * 1000)))
staging_file_path = os.path.join(staging_location, temp_file_name)
job_config = ExtractJobConfig()
job_config.destination_format = DestinationFormat.CSV
job = self.bq.extract_table(Table.from_string(full_table_id),
staging_file_path,
job_config=job_config)
# await completion
job.result()
return gcs_to_df(staging_file_path)
def download_table_as_file(self, full_table_id, dest, staging_location,
file_type):
"""
Download a bigquery table as file
Args:
full_table_id (str): fully qualified BigQuery table id
dest (str): destination filename
staging_location (str): url to staging_location (currently
support a folder in GCS)
file_type (feast.sdk.resources.feature_set.FileType): (default:
FileType.CSV) exported file format
Returns: (str) path to the downloaded file
"""
if not is_gs_path(staging_location):
raise ValueError("staging_uri must be a directory in GCS")
temp_file_name = "temp_{}".format(int(round(time.time() * 1000)))
staging_file_path = os.path.join(staging_location, temp_file_name)
job_config = ExtractJobConfig()
job_config.destination_format = file_type
src_table = Table.from_string(full_table_id)
job = self.bq.extract_table(src_table,
staging_file_path,
job_config=job_config)
# await completion
job.result()
bucket_name, blob_name = split_gs_path(staging_file_path)
bucket = self.gcs.get_bucket(bucket_name)
blob = bucket.blob(blob_name)
blob.download_to_filename(dest)
return dest
def _test_download_file(self, mocker, type):
mocked_gcs_folder_to_file = mocker.patch(
"feast.sdk.utils.bq_util.gcs_folder_to_file", return_value=None)
staging_path = "gs://temp"
temp_folder = "temp_0"
full_table_id = "project_id.dataset_id.table_id"
dst_path = "/tmp/myfile.csv"
exp_staging_folder = os.path.join(staging_path, temp_folder)
exp_staging_path = os.path.join(exp_staging_folder, "shard_*")
table_dldr = TableDownloader()
table_dldr._bqclient = _Mock_BQ_Client()
mocker.patch.object(table_dldr._bqclient,
"extract_table",
return_value=_Job())
table_dldr.download_table_as_file(full_table_id,
dst_path,
staging_location=staging_path,
file_type=type)
assert len(table_dldr._bqclient.extract_table.call_args_list) == 1
args, kwargs = table_dldr._bqclient.extract_table.call_args_list[0]
assert args[0].full_table_id == Table.from_string(
full_table_id).full_table_id
assert args[1] == exp_staging_path
assert kwargs["job_config"].destination_format == str(type)
mocked_gcs_folder_to_file.assert_called_once_with(
exp_staging_folder, dst_path)
def download_table_as_file(self,
full_table_id,
dest,
file_type,
staging_location=None):
"""
Download a bigquery table as file
Args:
full_table_id (str): fully qualified BigQuery table id
dest (str): destination filename
file_type (feast.sdk.resources.feature_set.FileType): (default:
FileType.CSV) exported file format
staging_location (str, optional): url to staging_location (currently
support a folder in GCS)
Returns: (str) path to the downloaded file
"""
if not staging_location:
df = self.download_table_as_df(full_table_id)
if file_type == FileType.CSV:
df.to_csv(dest, index=False)
elif file_type == FileType.JSON:
df.to_json(dest, index=False)
else:
raise ValueError(
"Only FileType: CSV and JSON are supported for download_table_as_file without staging location"
)
return dest
if not is_gs_path(staging_location):
raise ValueError("staging_uri must be a directory in GCS")
temp_file_name = "temp_{}".format(int(round(time.time() * 1000)))
staging_file_path = os.path.join(staging_location, temp_file_name)
job_config = ExtractJobConfig()
job_config.destination_format = file_type
src_table = Table.from_string(full_table_id)
job = self.bqclient.extract_table(src_table,
staging_file_path,
job_config=job_config)
# await completion
job.result()
bucket_name, blob_name = split_gs_path(staging_file_path)
bucket = self.storageclient.get_bucket(bucket_name)
blob = bucket.blob(blob_name)
blob.download_to_filename(dest)
return dest
def __extract_table_to_shard_folder(self, full_table_id,
staging_location, file_type):
shard_folder = os.path.join(staging_location,
'temp_%d' % int(round(time.time() * 1000)))
staging_file_path = os.path.join(shard_folder, "shard_*")
job_config = ExtractJobConfig()
job_config.destination_format = file_type
job = self.bqclient.extract_table(
Table.from_string(full_table_id),
staging_file_path,
job_config=job_config
)
# await completion
job.result()
return shard_folder
