Skip to content

Commit

Permalink
Fix lint
Browse files Browse the repository at this point in the history
  • Loading branch information
@pvk-developer
pvk-developer committed Sep 17, 2024
1 parent e94a4bf commit dae1d47
Show file tree
Hide file tree
Showing 6 changed files with 41 additions and 50 deletions.
1 change: 1 addition & 0 deletions pyproject.toml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -185,6 +185,7 @@ exclude = [
".tox",
".git",
"__pycache__",
"*.ipynb",
".ipynb_checkpoints",
"tasks.py",
]
Expand Down
2 changes: 1 addition & 1 deletion tests/_external/gdrive_utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ def get_latest_file(folder_id):
drive_query = drive.ListFile({
'q': f"'{folder_id}' in parents and trashed=False",
'orderBy': 'modifiedDate desc',
'maxResults': 1
'maxResults': 1,
})
file_list = drive_query.GetList()
if len(file_list) > 0:
Expand Down
4 changes: 1 addition & 3 deletions tests/_external/slack_utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -34,9 +34,7 @@ def post_slack_message(channel, text):
response = client.chat_postMessage(channel=channel, text=text)
if not response['ok']:
error = response.get('error', 'unknown_error')
msg = (
f'{error} occured trying to post message to {channel}'
)
msg = f'{error} occured trying to post message to {channel}'
raise RuntimeError(msg)

return response
62 changes: 30 additions & 32 deletions tests/benchmark/pyarrow_dtypes.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -44,77 +44,75 @@
'pa.utf8': pd.Series(['A', 'B', None, 'C'], dtype=pd.ArrowDtype(pa.utf8()))
}),
'pa.binary': pd.DataFrame({
'pa.binary': pd.Series([
b'binary1', b'binary2', None, b'binary3'], dtype=pd.ArrowDtype(pa.binary()))
'pa.binary': pd.Series(
[b'binary1', b'binary2', None, b'binary3'], dtype=pd.ArrowDtype(pa.binary())
)
}),
'pa.large_binary': pd.DataFrame({
'pa.large_binary': pd.Series([
b'large_binary1',
b'large_binary2',
None,
b'large_binary3'
], dtype=pd.ArrowDtype(pa.large_binary()))
'pa.large_binary': pd.Series(
[b'large_binary1', b'large_binary2', None, b'large_binary3'],
dtype=pd.ArrowDtype(pa.large_binary()),
)
}),
'pa.large_string': pd.DataFrame({
'pa.large_string': pd.Series(['A', 'B', None, 'C'], dtype=pd.ArrowDtype(pa.large_string()))
}),
'pa.date32': pd.DataFrame({
'pa.date32': pd.Series(
[pd.Timestamp('2023-01-01'), pd.Timestamp('2024-01-01'), None],
dtype=pd.ArrowDtype(pa.date32())
dtype=pd.ArrowDtype(pa.date32()),
)
}),
'pa.date64': pd.DataFrame({
'pa.date64': pd.Series(
[pd.Timestamp('2023-01-01'), pd.Timestamp('2024-01-01'), None],
dtype=pd.ArrowDtype(pa.date64())
dtype=pd.ArrowDtype(pa.date64()),
)
}),
'pa.timestamp': pd.DataFrame({
'pa.timestamp': pd.Series(
[
pd.Timestamp('2023-01-01T00:00:00'),
pd.Timestamp('2024-01-01T00:00:00'),
None
],
dtype=pd.ArrowDtype(pa.timestamp('ms'))
[pd.Timestamp('2023-01-01T00:00:00'), pd.Timestamp('2024-01-01T00:00:00'), None],
dtype=pd.ArrowDtype(pa.timestamp('ms')),
)
}),
'pa.duration': pd.DataFrame({
'pa.duration': pd.Series(
[pd.Timedelta(days=1), pd.Timedelta(hours=2), None],
dtype=pd.ArrowDtype(pa.duration('s'))
dtype=pd.ArrowDtype(pa.duration('s')),
)
}),
'pa.time32': pd.DataFrame({
'pa.time32': pd.Series([
pd.Timestamp('2023-01-01T01:00:00').time(),
pd.Timestamp('2023-01-01T02:00:00').time(),
None
], dtype=pd.ArrowDtype(pa.time32('s'))
'pa.time32': pd.Series(
[
pd.Timestamp('2023-01-01T01:00:00').time(),
pd.Timestamp('2023-01-01T02:00:00').time(),
None,
],
dtype=pd.ArrowDtype(pa.time32('s')),
)
}),
'pa.time64': pd.DataFrame({
'pa.time64': pd.Series([
pd.Timestamp('2023-01-01T01:00:00').time(),
pd.Timestamp('2023-01-01T02:00:00').time(),
None
], dtype=pd.ArrowDtype(pa.time64('ns')))
'pa.time64': pd.Series(
[
pd.Timestamp('2023-01-01T01:00:00').time(),
pd.Timestamp('2023-01-01T02:00:00').time(),
None,
],
dtype=pd.ArrowDtype(pa.time64('ns')),
)
}),
'pa.binary_view': pd.DataFrame({
'pa.binary_view': pd.Series(
[b'view1', b'view2', None, b'view3'], dtype=pd.ArrowDtype(pa.binary())
)
}),
'pa.string_view': pd.DataFrame({
'pa.string_view': pd.Series(
['A', 'B', None, 'C'], dtype=pd.ArrowDtype(pa.string())
)
'pa.string_view': pd.Series(['A', 'B', None, 'C'], dtype=pd.ArrowDtype(pa.string()))
}),
'pa.decimal128': pd.DataFrame({
'pa.decimal128': pd.Series(
[decimal.Decimal('123.45'), decimal.Decimal('678.90'), None],
dtype=pd.ArrowDtype(pa.decimal128(precision=10, scale=2))
dtype=pd.ArrowDtype(pa.decimal128(precision=10, scale=2)),
)
})
}),
}
8 changes: 3 additions & 5 deletions tests/benchmark/supported_dtypes_benchmark.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,6 @@
'pd.timedelta64': 'datetime',
'pd.Period': 'datetime',
'pd.Complex': 'numerical',

# NumPy
'np.int8': 'numerical',
'np.int16': 'numerical',
Expand All @@ -118,7 +117,6 @@
'np.bool': 'categorical',
'np.string': 'categorical',
'np.unicode': 'categorical',

# PyArrow
'pa.int8': 'numerical',
'pa.int16': 'numerical',
Expand Down Expand Up @@ -294,7 +292,7 @@ def test_fit_and_sample_synthesizer(dtype, data):
save_results_to_json({
'dtype': dtype,
'SYNTHESIZER_FIT': fit_result,
'SYNTHESIZER_SAMPLE': sample_result
'SYNTHESIZER_SAMPLE': sample_result,
})
fit_assertion_message = f"{dtype} is no longer supported by 'SYNTHESIZER_FIT'."
if fit_result is False:
Expand Down Expand Up @@ -475,7 +473,7 @@ def test_fit_and_sample_single_column_constraints(constraint_name, constraint, d
save_results_to_json({
'dtype': dtype,
f'{constraint_name}_FIT': fit_result,
f'{constraint_name}_SAMPLE': sample_result
f'{constraint_name}_SAMPLE': sample_result,
})
if fit_result is False:
fit_assertion_message = f"{dtype} is no longer supported by '{constraint_name}_FIT''."
Expand Down Expand Up @@ -553,7 +551,7 @@ def test_fit_and_sample_multi_column_constraints(constraint_name, constraint, dt
save_results_to_json({
'dtype': dtype,
f'{constraint_name}_FIT': fit_result,
f'{constraint_name}_SAMPLE': sample_result
f'{constraint_name}_SAMPLE': sample_result,
})
if fit_result is False:
assert fit_result == previous_fit_result, f"{dtype} failed during '{constraint_name}_FIT'."
Expand Down
14 changes: 5 additions & 9 deletions tests/benchmark/utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ def _get_output_filename():

def compare_previous_result_with_current(args):
"""Compare the previous result with the current and post a message on slack."""
output_filename = output_filename or TEMPRESULTS
output_filename = TEMPRESULTS
current_results = _load_temp_results(output_filename)
output_filename = _get_output_filename()
csv_output = Path(f'results/{PYTHON_VERSION}.csv')
Expand Down Expand Up @@ -127,19 +127,15 @@ def _get_parser():
action.required = True

# Compare with previous results
compare = action.add_parser(
'compare',
help='Compare previous results to the current one.'
)
compare = action.add_parser('compare', help='Compare previous results to the current one.')
compare.set_defaults(action=compare_previous_result_with_current)

# Command Line package creation
upload = action.add_parser(
'upload',
help='Upload a new spreadsheet with the results.'
)
upload = action.add_parser('upload', help='Upload a new spreadsheet with the results.')

upload.set_defaults(action=store_results_in_gdrive)
return parser


if __name__ == '__main__':
parser = _get_parser()
Expand Down

0 comments on commit dae1d47

Please sign in to comment.