Skip to content

CLN Fixes PendingDeprecationWarning in CountVectorizer #19299

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
Jan 30, 2021
Merged

CLN Fixes PendingDeprecationWarning in CountVectorizer #19299

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
31198d8
CLN Fixes PendingDeprecationWarning in CountVectorizer
thomasjpfan Jan 29, 2021
0d12239
ENH Uses check_array
thomasjpfan Jan 29, 2021
4924ab4
Improve coverage of inverse_transform on non-CSR input
ogrisel Jan 30, 2021
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
18 changes: 15 additions & 3 deletions sklearn/feature_extraction/tests/test_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -773,18 +773,30 @@ def test_vectorizer_inverse_transform(Vectorizer):
vectorizer = Vectorizer()
transformed_data = vectorizer.fit_transform(data)
inversed_data = vectorizer.inverse_transform(transformed_data)
assert isinstance(inversed_data, list)

analyze = vectorizer.build_analyzer()
for doc, inversed_terms in zip(data, inversed_data):
terms = np.sort(np.unique(analyze(doc)))
inversed_terms = np.sort(np.unique(inversed_terms))
assert_array_equal(terms, inversed_terms)

# Test that inverse_transform also works with numpy arrays
transformed_data = transformed_data.toarray()
inversed_data2 = vectorizer.inverse_transform(transformed_data)
assert sparse.issparse(transformed_data)
assert transformed_data.format == "csr"

# Test that inverse_transform also works with numpy arrays and
# scipy
transformed_data2 = transformed_data.toarray()
inversed_data2 = vectorizer.inverse_transform(transformed_data2)
for terms, terms2 in zip(inversed_data, inversed_data2):
assert_array_equal(np.sort(terms), np.sort(terms2))

# Check that inverse_transform also works on non CSR sparse data:
transformed_data3 = transformed_data.tocsc()
inversed_data3 = vectorizer.inverse_transform(transformed_data3)
for terms, terms3 in zip(inversed_data, inversed_data3):
assert_array_equal(np.sort(terms), np.sort(terms3))


def test_count_vectorizer_pipeline_grid_selection():
# raw documents
Expand Down
18 changes: 8 additions & 10 deletions sklearn/feature_extraction/text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1270,22 +1270,20 @@ def inverse_transform(self, X):
List of arrays of terms.
"""
self._check_vocabulary()

if sp.issparse(X):
# We need CSR format for fast row manipulations.
X = X.tocsr()
else:
# We need to convert X to a matrix, so that the indexing
# returns 2D objects
X = np.asmatrix(X)
# We need CSR format for fast row manipulations.
X = check_array(X, accept_sparse='csr')
n_samples = X.shape[0]

terms = np.array(list(self.vocabulary_.keys()))
indices = np.array(list(self.vocabulary_.values()))
inverse_vocabulary = terms[np.argsort(indices)]

return [inverse_vocabulary[X[i, :].nonzero()[1]].ravel()
for i in range(n_samples)]
if sp.issparse(X):
return [inverse_vocabulary[X[i, :].nonzero()[1]].ravel()
for i in range(n_samples)]
else:
return [inverse_vocabulary[np.flatnonzero(X[i, :])].ravel()
for i in range(n_samples)]

def get_feature_names(self):
"""Array mapping from feature integer indices to feature name.
Expand Down