Skip to content

feat: Implement operator @ for DataFrame.dot #139

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
Oct 30, 2023
Merged

feat: Implement operator @ for DataFrame.dot #139

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
e8b8c9a
feat: Implement operator `@` for `DataFrame.dot`
shobsi Oct 24, 2023
b03dd21
Merge branch 'main' into shobs-df-dot-dunder
shobsi Oct 25, 2023
a26de35
Merge branch 'main' into shobs-df-dot-dunder
shobsi Oct 26, 2023
94d275b
Merge branch 'main' into shobs-df-dot-dunder
shobsi Oct 26, 2023
ff81876
Merge branch 'main' into shobs-df-dot-dunder
shobsi Oct 27, 2023
6ad7648
Merge branch 'main' into shobs-df-dot-dunder
shobsi Oct 30, 2023
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: 2 additions & 0 deletions bigframes/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2707,3 +2707,5 @@ def get_right_id(id):
result = result[other.name].rename()

return result

__matmul__ = dot
33 changes: 33 additions & 0 deletions tests/system/small/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3264,6 +3264,23 @@ def test_df_dot(
)


def test_df_dot_operator(
matrix_2by3_df, matrix_2by3_pandas_df, matrix_3by4_df, matrix_3by4_pandas_df
):
bf_result = (matrix_2by3_df @ matrix_3by4_df).to_pandas()
pd_result = matrix_2by3_pandas_df @ matrix_3by4_pandas_df

# Patch pandas dtypes for testing parity
# Pandas result is object instead of Int64 (nullable) dtype.
for name in pd_result.columns:
pd_result[name] = pd_result[name].astype(pd.Int64Dtype())

pd.testing.assert_frame_equal(
bf_result,
pd_result,
)


def test_df_dot_series(
matrix_2by3_df, matrix_2by3_pandas_df, matrix_3by4_df, matrix_3by4_pandas_df
):
Expand All @@ -3278,3 +3295,19 @@ def test_df_dot_series(
bf_result,
pd_result,
)


def test_df_dot_operator_series(
matrix_2by3_df, matrix_2by3_pandas_df, matrix_3by4_df, matrix_3by4_pandas_df
):
bf_result = (matrix_2by3_df @ matrix_3by4_df["x"]).to_pandas()
pd_result = matrix_2by3_pandas_df @ matrix_3by4_pandas_df["x"]

# Patch pandas dtypes for testing parity
# Pandas result is object instead of Int64 (nullable) dtype.
pd_result = pd_result.astype(pd.Int64Dtype())

pd.testing.assert_series_equal(
bf_result,
pd_result,
)
16 changes: 16 additions & 0 deletions tests/system/small/test_multiindex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -998,13 +998,19 @@ def test_df_multi_index_dot_not_supported():
with pytest.raises(NotImplementedError, match="Multi-index input is not supported"):
bf1.dot(bf2)

with pytest.raises(NotImplementedError, match="Multi-index input is not supported"):
bf1 @ bf2

# right multi-index
right_index = pandas.MultiIndex.from_tuples([("a", "aa"), ("a", "ab"), ("b", "bb")])
bf1 = bpd.DataFrame(left_matrix)
bf2 = bpd.DataFrame(right_matrix, index=right_index)
with pytest.raises(NotImplementedError, match="Multi-index input is not supported"):
bf1.dot(bf2)

with pytest.raises(NotImplementedError, match="Multi-index input is not supported"):
bf1 @ bf2


def test_column_multi_index_dot_not_supported():
left_matrix = [[1, 2, 3], [2, 5, 7]]
Expand All @@ -1022,10 +1028,20 @@ def test_column_multi_index_dot_not_supported():
):
bf1.dot(bf2)

with pytest.raises(
NotImplementedError, match="Multi-level column input is not supported"
):
bf1 @ bf2

# right multi-columns
bf1 = bpd.DataFrame(left_matrix)
bf2 = bpd.DataFrame(right_matrix, columns=multi_level_columns)
with pytest.raises(
NotImplementedError, match="Multi-level column input is not supported"
):
bf1.dot(bf2)

with pytest.raises(
NotImplementedError, match="Multi-level column input is not supported"
):
bf1 @ bf2