Skip to content

fix!: rename cosine_similarity to paired_cosine_distances #393

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 1 commit into from
Feb 26, 2024
Merged

fix!: rename cosine_similarity to paired_cosine_distances #393

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 5 additions & 3 deletions bigframes/ml/metrics/pairwise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,15 +20,17 @@
import third_party.bigframes_vendored.sklearn.metrics.pairwise as vendored_metrics_pairwise


def cosine_similarity(
def paired_cosine_distances(
X: Union[bpd.DataFrame, bpd.Series], Y: Union[bpd.DataFrame, bpd.Series]
) -> bpd.DataFrame:
X, Y = utils.convert_to_dataframe(X, Y)
if len(X.columns) != 1 or len(Y.columns) != 1:
raise ValueError("Inputs X and Y can only contain 1 column.")

base_bqml = core.BaseBqml(session=X._session)
return base_bqml.distance(X, Y, type="COSINE", name="cosine_similarity")
return base_bqml.distance(X, Y, type="COSINE", name="cosine_distance")


cosine_similarity.__doc__ = inspect.getdoc(vendored_metrics_pairwise.cosine_similarity)
paired_cosine_distances.__doc__ = inspect.getdoc(
vendored_metrics_pairwise.paired_cosine_distances
)
6 changes: 3 additions & 3 deletions tests/system/small/ml/test_metrics_pairwise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,15 +19,15 @@
import bigframes.pandas as bpd


def test_cosine_similarity():
def test_paired_cosine_distances():
x_col = [np.array([4.1, 0.5, 1.0])]
y_col = [np.array([3.0, 0.0, 2.5])]
X = bpd.read_pandas(pd.DataFrame({"X": x_col}))
Y = bpd.read_pandas(pd.DataFrame({"Y": y_col}))

result = metrics.pairwise.cosine_similarity(X, Y)
result = metrics.pairwise.paired_cosine_distances(X, Y)
expected_pd_df = pd.DataFrame(
{"X": x_col, "Y": y_col, "cosine_similarity": [0.108199]}
{"X": x_col, "Y": y_col, "cosine_distance": [0.108199]}
)

pd.testing.assert_frame_equal(
Expand Down
11 changes: 3 additions & 8 deletions third_party/bigframes_vendored/sklearn/metrics/pairwise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,8 @@
import bigframes.pandas as bpd


def cosine_similarity(X, Y) -> bpd.DataFrame:
"""Compute cosine similarity between samples in X and Y.

Cosine similarity, or the cosine kernel, computes similarity as the
normalized dot product of X and Y:

K(X, Y) = <X, Y> / (||X||*||Y||)
def paired_cosine_distances(X, Y) -> bpd.DataFrame:
"""Compute the paired cosine distances between X and Y.

Args:
X (Series or single column DataFrame of array of numeric type):
Expand All @@ -26,6 +21,6 @@ def cosine_similarity(X, Y) -> bpd.DataFrame:
Input data. X and Y are mapped by indexes, must have the same index.

Returns:
bigframes.dataframe.DataFrame: DataFrame with columns of X, Y and cosine_similarity
bigframes.dataframe.DataFrame: DataFrame with columns of X, Y and cosine_distance
"""
raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)