Skip to content

fix: use pandas function to check for NaN #750

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

Merged
plamut merged 4 commits into from
Jul 12, 2021
Merged

fix: use pandas function to check for NaN #750

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ebdc683
fix: use pandas function to check for NaN
LinuxChristian Jun 28, 2021
f86d103
tests: Skip tests if pandas below required version
LinuxChristian Jul 12, 2021
659e9f7
tests: compare expected and actual directly as lists
LinuxChristian Jul 12, 2021
dc0529b
Fix pytest.mark.skipif spelling
plamut Jul 12, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion google/cloud/bigquery/_pandas_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -780,7 +780,7 @@ def dataframe_to_json_generator(dataframe):
output = {}
for column, value in zip(dataframe.columns, row):
# Omit NaN values.
if value != value:
if pandas.isna(value):
continue
output[column] = value
yield output
41 changes: 41 additions & 0 deletions tests/unit/test__pandas_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
import operator
import queue
import warnings
import pkg_resources

import mock

Expand Down Expand Up @@ -47,6 +48,14 @@
except ImportError: # pragma: NO COVER
bigquery_storage = None

PANDAS_MINIUM_VERSION = pkg_resources.parse_version("1.0.0")

if pandas is not None:
PANDAS_INSTALLED_VERSION = pkg_resources.get_distribution("pandas").parsed_version
else:
# Set to less than MIN version.
PANDAS_INSTALLED_VERSION = pkg_resources.parse_version("0.0.0")


skip_if_no_bignumeric = pytest.mark.skipif(
not _BIGNUMERIC_SUPPORT, reason="BIGNUMERIC support requires pyarrow>=3.0.0",
Expand Down Expand Up @@ -734,6 +743,38 @@ def test_list_columns_and_indexes_with_named_index_same_as_column_name(
assert columns_and_indexes == expected


@pytest.mark.skipIf(
pandas is None or PANDAS_INSTALLED_VERSION < PANDAS_MINIUM_VERSION,
reason="Requires `pandas version >= 1.0.0` which introduces pandas.NA",
Copy link
Contributor

@plamut plamut Jul 12, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Neat to also include the reason why a minimum version is needed. 👍

)
def test_dataframe_to_json_generator(module_under_test):
utcnow = datetime.datetime.utcnow()
df_data = collections.OrderedDict(
[
("a_series", [pandas.NA, 2, 3, 4]),
("b_series", [0.1, float("NaN"), 0.3, 0.4]),
("c_series", ["a", "b", pandas.NA, "d"]),
("d_series", [utcnow, utcnow, utcnow, pandas.NaT]),
("e_series", [True, False, True, None]),
]
)
dataframe = pandas.DataFrame(
df_data, index=pandas.Index([4, 5, 6, 7], name="a_index")
)

dataframe = dataframe.astype({"a_series": pandas.Int64Dtype()})

rows = module_under_test.dataframe_to_json_generator(dataframe)
expected = [
{"b_series": 0.1, "c_series": "a", "d_series": utcnow, "e_series": True},
{"a_series": 2, "c_series": "b", "d_series": utcnow, "e_series": False},
{"a_series": 3, "b_series": 0.3, "d_series": utcnow, "e_series": True},
{"a_series": 4, "b_series": 0.4, "c_series": "d"},
]
for row, expect in zip(rows, expected):
assert row == expect


@pytest.mark.skipif(pandas is None, reason="Requires `pandas`")
def test_list_columns_and_indexes_with_named_index(module_under_test):
df_data = collections.OrderedDict(
Expand Down