Skip to content

fix: fix value_counts column label for normalize=True #245

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
merged 6 commits into from
Dec 6, 2023
Merged

fix: fix value_counts column label for normalize=True #245

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f4a0607
fix: fix value_counts column label for normalize=True
TrevorBergeron Nov 30, 2023
74f63bc
amend series value_counts test
TrevorBergeron Nov 30, 2023
5561feb
fix another value_counts test
TrevorBergeron Dec 1, 2023
60f69d7
Merge branch 'main' into proportion
TrevorBergeron Dec 4, 2023
9404a67
Merge branch 'main' into proportion
TrevorBergeron Dec 5, 2023
7ac3109
Merge branch 'main' into proportion
TrevorBergeron Dec 6, 2023
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion bigframes/core/block_transforms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,7 +353,9 @@ def value_counts(
)
]
)
return block.select_column(count_id).with_column_labels(["count"])
return block.select_column(count_id).with_column_labels(
["proportion" if normalize else "count"]
)


def pct_change(block: blocks.Block, periods: int = 1) -> blocks.Block:
Expand Down
6 changes: 2 additions & 4 deletions tests/system/small/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3453,6 +3453,8 @@ def test_df_to_orc(scalars_df_index, scalars_pandas_df_index):
],
)
def test_df_value_counts(scalars_dfs, subset, normalize, ascending, dropna):
if pd.__version__.startswith("1."):
pytest.skip("pandas 1.x produces different column labels.")
scalars_df, scalars_pandas_df = scalars_dfs

bf_result = (
Expand All @@ -3464,10 +3466,6 @@ def test_df_value_counts(scalars_dfs, subset, normalize, ascending, dropna):
subset, normalize=normalize, ascending=ascending, dropna=dropna
)

# Older pandas version may not have these values, bigframes tries to emulate 2.0+
Copy link
Contributor

Choose a reason for hiding this comment

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

Let's remove this from test_series as well https://github.com/search?q=repo%3Agoogleapis%2Fpython-bigquery-dataframes%20%22Older%20pandas%20version%20may%20not%20have%20these%20values%22&type=code
Copy link
Contributor Author

Choose a reason for hiding this comment

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

done
Copy link
Contributor

Choose a reason for hiding this comment

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

Thanks, just one one more test test_value_counts_w_cut in test_series.py
Copy link
Contributor Author

Choose a reason for hiding this comment

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

done
pd_result.name = "count"
pd_result.index.names = bf_result.index.names

pd.testing.assert_series_equal(
bf_result, pd_result, check_dtype=False, check_index_type=False
)
Expand Down
11 changes: 4 additions & 7 deletions tests/system/small/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1940,23 +1940,23 @@ def test_cummax_int(scalars_df_index, scalars_pandas_df_index):


def test_value_counts(scalars_dfs):
if pd.__version__.startswith("1."):
pytest.skip("pandas 1.x produces different column labels.")
scalars_df, scalars_pandas_df = scalars_dfs
col_name = "int64_too"

bf_result = scalars_df[col_name].value_counts().to_pandas()
pd_result = scalars_pandas_df[col_name].value_counts()

# Older pandas version may not have these values, bigframes tries to emulate 2.0+
pd_result.name = "count"
pd_result.index.name = col_name

pd.testing.assert_series_equal(
bf_result,
pd_result,
)


def test_value_counts_w_cut(scalars_dfs):
if pd.__version__.startswith("1."):
pytest.skip("value_counts results different in pandas 1.x.")
scalars_df, scalars_pandas_df = scalars_dfs
col_name = "int64_col"

Expand All @@ -1965,9 +1965,6 @@ def test_value_counts_w_cut(scalars_dfs):

bf_result = bf_cut.value_counts().to_pandas()
pd_result = pd_cut.value_counts()
# Older pandas version may not have these values, bigframes tries to emulate 2.0+
pd_result.name = "count"
pd_result.index.name = col_name
pd_result.index = pd_result.index.astype(pd.Int64Dtype())

pd.testing.assert_series_equal(
Expand Down