Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

perf: add size parameter for load table from dataframe and json methods #280

Merged
merged 8 commits into from Oct 14, 2020
Merged

perf: add size parameter for load table from dataframe and json methods #280

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
4158bcb
feat: add size parameter for load from dataframe and json
HemangChothani Sep 29, 2020
321d977
pref: calculate length of encoded string
HemangChothani Sep 30, 2020
1b36189
pref: resolve conflict
HemangChothani Oct 5, 2020
c0d08c0
Merge branch 'master' of https://github.com/googleapis/python-bigquer…
HemangChothani Oct 5, 2020
147db35
Merge branch 'master' of https://github.com/googleapis/python-bigquer…
HemangChothani Oct 7, 2020
b5e6a89
fix: conflict resolved
HemangChothani Oct 13, 2020
50c3c44
Merge branch 'master' of https://github.com/googleapis/python-bigquer…
HemangChothani Oct 13, 2020
017c732
Merge branch 'master' of https://github.com/googleapis/python-bigquer…
HemangChothani Oct 14, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
7 changes: 5 additions & 2 deletions google/cloud/bigquery/client.py
View file
Open in desktop
Expand Up @@ -2237,11 +2237,13 @@ def load_table_from_dataframe(
dataframe.to_parquet(tmppath, compression=parquet_compression)

with open(tmppath, "rb") as parquet_file:
file_size = os.path.getsize(tmppath)
return self.load_table_from_file(
parquet_file,
destination,
num_retries=num_retries,
rewind=True,
size=file_size,
job_id=job_id,
job_id_prefix=job_id_prefix,
location=location,
Expand Down Expand Up @@ -2343,11 +2345,12 @@ def load_table_from_json(
destination = _table_arg_to_table_ref(destination, default_project=self.project)

data_str = u"\n".join(json.dumps(item) for item in json_rows)
data_file = io.BytesIO(data_str.encode())

encoded_str = data_str.encode()
data_file = io.BytesIO(encoded_str)
return self.load_table_from_file(
data_file,
destination,
size=len(encoded_str),
num_retries=num_retries,
job_id=job_id,
job_id_prefix=job_id_prefix,
Expand Down
15 changes: 15 additions & 0 deletions tests/unit/test_client.py
View file
Open in desktop
Expand Up @@ -7482,6 +7482,7 @@ def test_load_table_from_dataframe(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=None,
Expand Down Expand Up @@ -7525,6 +7526,7 @@ def test_load_table_from_dataframe_w_client_location(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7577,6 +7579,7 @@ def test_load_table_from_dataframe_w_custom_job_config_wihtout_source_format(sel
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7631,6 +7634,7 @@ def test_load_table_from_dataframe_w_custom_job_config_w_source_format(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7723,6 +7727,7 @@ def test_load_table_from_dataframe_w_automatic_schema(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7782,6 +7787,7 @@ def test_load_table_from_dataframe_w_index_and_auto_schema(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7827,6 +7833,7 @@ def test_load_table_from_dataframe_unknown_table(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=None,
Expand Down Expand Up @@ -7867,6 +7874,7 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7913,6 +7921,7 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype_automatic_schema(se
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -7973,6 +7982,7 @@ def test_load_table_from_dataframe_struct_fields(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -8046,6 +8056,7 @@ def test_load_table_from_dataframe_w_partial_schema(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -8139,6 +8150,7 @@ def test_load_table_from_dataframe_w_partial_schema_missing_types(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -8251,6 +8263,7 @@ def test_load_table_from_dataframe_w_nulls(self):
self.TABLE_REF,
num_retries=_DEFAULT_NUM_RETRIES,
rewind=True,
size=mock.ANY,
job_id=mock.ANY,
job_id_prefix=None,
location=self.LOCATION,
Expand Down Expand Up @@ -8302,6 +8315,7 @@ def test_load_table_from_json_basic_use(self):
client,
mock.ANY,
self.TABLE_REF,
size=mock.ANY,
num_retries=_DEFAULT_NUM_RETRIES,
job_id=mock.ANY,
job_id_prefix=None,
Expand Down Expand Up @@ -8353,6 +8367,7 @@ def test_load_table_from_json_non_default_args(self):
client,
mock.ANY,
self.TABLE_REF,
size=mock.ANY,
num_retries=_DEFAULT_NUM_RETRIES,
job_id=mock.ANY,
job_id_prefix=None,
Expand Down