8000 [MRG] remove warnings in univariate feature selection by larsmans · Pull Request #2369 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG] remove warnings in univariate feature selection #2369

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
Aug 19, 2013
Merged

[MRG] remove warnings in univariate feature selection #2369

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
11 changes: 11 additions & 0 deletions sklearn/feature_selection/tests/test_feature_select.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -481,6 +481,17 @@ def test_tied_pvalues():
assert_not_in(9998, Xt)


def test_tied_scores():
"""Test for stable sorting in k-best with tied scores."""
X_train = np.array([[0, 0, 0], [1, 1, 1]])
y_train = [0, 1]

for n_features in [1, 2, 3]:
sel = SelectKBest(chi2, k=n_features).fit(X_train, y_train)
X_test = sel.transform([0, 1, 2])
assert_array_equal(X_test[0], np.arange(3)[-n_features:])


def test_nans():
"""Assert that SelectKBest and SelectPercentile can handle NaNs."""
# First feature has zero variance to confuse f_classif (ANOVA) and
Expand Down
14 changes: 5 additions & 9 deletions sklearn/feature_selection/univariate_selection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,10 +299,6 @@ def fit(self, X, y):
self.scores_, self.pvalues_ = self.score_func(X, y)
self.scores_ = np.asarray(self.scores_)
self.pvalues_ = np.asarray(self.pvalues_)
if len(np.unique(self.pvalues_)) < len(self.pvalues_):
warn("Duplicate p-values. Result may depend on feature ordering."
"There are probably duplicate features, or you used a "
"classification score for a regression task.")
return self


Expand All @@ -315,10 +311,6 @@ def fit(self, X, y):
self.scores_, self.pvalues_ = self.score_func(X, y)
self.scores_ = np.asarray(self.scores_)
self.pvalues_ = np.asarray(self.pvalues_)
if len(np.unique(self.scores_)) < len(self.scores_):
warn("Duplicate scores. Result may depend on feature ordering."
"There are probably duplicate features, or you used a "
"classification score for a regression task.")
return self


Expand Down Expand Up @@ -428,7 +420,11 @@ def _get_support_mask(self):
# from argsort, which we transform to a mask, which we probably
# transform back to indices later.
mask = np.zeros(scores.shape, dtype=bool)
mask[np.argsort(scores)[-k:]] = 1

# Request a stable sort. Mergesort takes more memory (~40MB per
# megafeature on x86-64), but blows heapsort out of the water in
# terms of speed.
mask[np.argsort(scores, kind="mergesort")[-k:]] = 1
return mask


Expand Down
0