Skip to content

CLN Clean up logic in validate_data and cast_to_ndarray #26300

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 3 commits into from
May 4, 2023
Merged

CLN Clean up logic in validate_data and cast_to_ndarray #26300

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8de37e1
CLN Clean up logic in validate_data and cast_to_ndarray
thomasjpfan Apr 29, 2023
8607ad1
TST Adds unit test for coverage
thomasjpfan May 2, 2023
6fce04b
TST Add test for no input
thomasjpfan May 3, 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
24 changes: 14 additions & 10 deletions sklearn/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -548,7 +548,7 @@ def _validate_data(

cast_to_ndarray : bool, default=True
Cast `X` and `y` to ndarray with checks in `check_params`. If
`False`, `X` and `y` are unchanged and only `feature_names` and
`False`, `X` and `y` are unchanged and only `feature_names_in_` and
`n_features_in_` are checked.

**check_params : kwargs
Expand Down Expand Up @@ -576,21 +576,25 @@ def _validate_data(
no_val_X = isinstance(X, str) and X == "no_validation"
no_val_y = y is None or isinstance(y, str) and y == "no_validation"

if no_val_X and no_val_y:
raise ValueError("Validation should be done on X, y or both.")
Copy link
Member

Choose a reason for hiding this comment

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

probably a dummy test for this wouldn't hurt.

Copy link
Member Author

Choose a reason for hiding this comment

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

Yea, makes sense. I updated the test to check this code path.


default_check_params = {"estimator": self}
check_params = {**default_check_params, **check_params}

if no_val_X and no_val_y:
raise ValueError("Validation should be done on X, y or both.")
if not cast_to_ndarray:
if not no_val_X and no_val_y:
out = X
elif no_val_X and not no_val_y:
out = y
else:
out = X, y
elif not no_val_X and no_val_y:
if cast_to_ndarray:
X = check_array(X, input_name="X", **check_params)
out = X
out = check_array(X, input_name="X", **check_params)
elif no_val_X and not no_val_y:
if cast_to_ndarray:
y = _check_y(y, **check_params) if cast_to_ndarray else y
out = y
out = _check_y(y, **check_params)
else:
if validate_separately and cast_to_ndarray:
if validate_separately:
# We need this because some estimators validate X and y
# separately, and in general, separately calling check_array()
# on X and y isn't equivalent to just calling check_X_y()
Expand Down
41 changes: 41 additions & 0 deletions sklearn/tests/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -719,6 +719,47 @@ def transform(self, X):
trans.transform(df_mixed)


def test_validate_data_cast_to_ndarray():
"""Check cast_to_ndarray option of _validate_data."""

pd = pytest.importorskip("pandas")
iris = datasets.load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.Series(iris.target)

class NoOpTransformer(TransformerMixin, BaseEstimator):
pass

no_op = NoOpTransformer()
X_np_out = no_op._validate_data(df, cast_to_ndarray=True)
assert isinstance(X_np_out, np.ndarray)
assert_allclose(X_np_out, df.to_numpy())

X_df_out = no_op._validate_data(df, cast_to_ndarray=False)
assert X_df_out is df

y_np_out = no_op._validate_data(y=y, cast_to_ndarray=True)
assert isinstance(y_np_out, np.ndarray)
assert_allclose(y_np_out, y.to_numpy())

y_series_out = no_op._validate_data(y=y, cast_to_ndarray=False)
assert y_series_out is y

X_np_out, y_np_out = no_op._validate_data(df, y, cast_to_ndarray=True)
assert isinstance(X_np_out, np.ndarray)
assert_allclose(X_np_out, df.to_numpy())
assert isinstance(y_np_out, np.ndarray)
assert_allclose(y_np_out, y.to_numpy())

X_df_out, y_series_out = no_op._validate_data(df, y, cast_to_ndarray=False)
assert X_df_out is df
assert y_series_out is y

msg = "Validation should be done on X, y or both."
with pytest.raises(ValueError, match=msg):
no_op._validate_data()


def test_clone_keeps_output_config():
"""Check that clone keeps the set_output config."""

Expand Down