Thanks to visit codestin.com
Credit goes to github.com

Skip to content

ENH better error message in HGBRT with feature names #25092

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 4 commits into from
Dec 2, 2022
Merged

ENH better error message in HGBRT with feature names #25092

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e4d9ae8
ENH better error message in HGBRT with feature names
ogrisel Dec 1, 2022
8460622
Merge branch 'main' into improve-hgbrt-error-msg-with-feature-names
jeremiedbb Dec 2, 2022
26f1e5d
less duplicated code
jeremiedbb Dec 2, 2022
4b921bb
cln
jeremiedbb Dec 2, 2022
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
15 changes: 9 additions & 6 deletions sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,18 +270,21 @@ def _check_categories(self, X):
if missing.any():
categories = categories[~missing]

if hasattr(self, "feature_names_in_"):
feature_name = f"'{self.feature_names_in_[f_idx]}'"
else:
feature_name = f"at index {f_idx}"

if categories.size > self.max_bins:
raise ValueError(
f"Categorical feature at index {f_idx} is "
"expected to have a "
f"cardinality <= {self.max_bins}"
f"Categorical feature {feature_name} is expected to "
f"have a cardinality <= {self.max_bins}"
)

if (categories >= self.max_bins).any():
raise ValueError(
f"Categorical feature at index {f_idx} is "
"expected to be encoded with "
f"values < {self.max_bins}"
f"Categorical feature {feature_name} is expected to "
f"be encoded with values < {self.max_bins}"
)
else:
categories = None
Expand Down
22 changes: 17 additions & 5 deletions sklearn/ensemble/_hist_gradient_boosting/tests/test_gradient_boosting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1141,20 +1141,32 @@ def test_categorical_spec_no_categories(Est, categorical_features, as_array):
@pytest.mark.parametrize(
"Est", (HistGradientBoostingClassifier, HistGradientBoostingRegressor)
)
def test_categorical_bad_encoding_errors(Est):
@pytest.mark.parametrize(
"use_pandas, feature_name", [(False, "at index 0"), (True, "'f0'")]
)
def test_categorical_bad_encoding_errors(Est, use_pandas, feature_name):
# Test errors when categories are encoded incorrectly

gb = Est(categorical_features=[True], max_bins=2)

X = np.array([[0, 1, 2]]).T
if use_pandas:
pd = pytest.importorskip("pandas")
X = pd.DataFrame({"f0": [0, 1, 2]})
else:
X = np.array([[0, 1, 2]]).T
y = np.arange(3)
msg = "Categorical feature at index 0 is expected to have a cardinality <= 2"
msg = f"Categorical feature {feature_name} is expected to have a cardinality <= 2"
with pytest.raises(ValueError, match=msg):
gb.fit(X, y)

X = np.array([[0, 2]]).T
if use_pandas:
X = pd.DataFrame({"f0": [0, 2]})
else:
X = np.array([[0, 2]]).T
y = np.arange(2)
msg = "Categorical feature at index 0 is expected to be encoded with values < 2"
msg = (
f"Categorical feature {feature_name} is expected to be encoded with values < 2"
)
with pytest.raises(ValueError, match=msg):
gb.fit(X, y)

Expand Down