8000 BUG Corrects tag in TfidfTransformer by thomasjpfan · Pull Request #20919 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

BUG Corrects tag in TfidfTransformer #20919

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
Sep 3, 2021
Merged

BUG Corrects tag in TfidfTransformer #20919

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
64c7e11
BUG Corrects tag in TfidfTransformer
thomasjpfan Sep 2, 2021
0f6ac9e
CLN Slightly better code
thomasjpfan Sep 2, 2021
4b34318
ENH Do not accept large sparse for 32bit platforms
thomasjpfan Sep 3, 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
9 changes: 7 additions & 2 deletions sklearn/feature_extraction/text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1559,7 +1559,12 @@ def fit(self, X, y=None):
self : object
Fitted transformer.
"""
X = self._validate_data(X, accept_sparse=("csr", "csc"))
# large sparse data is not supported for 32bit platforms because
# _document_frequency uses np.bincount which works on arrays of
# dtype NPY_INTP which is int32 for 32bit platforms. See #20923
X = self._validate_data(
X, accept_sparse=("csr", "csc"), accept_large_sparse=not _IS_32BIT
)
if not sp.issparse(X):
X = sp.csr_matrix(X)
dtype = X.dtype if X.dtype in FLOAT_DTYPES else np.float64
Expand Down Expand Up @@ -1648,7 +1653,7 @@ def idf_(self, value):
)

def _more_tags(self):
return {"X_types": "sparse"}
return {"X_types": ["2darray", "sparse"]}


class TfidfVectorizer(CountVectorizer):
Expand Down
16 changes: 16 additions & 0 deletions sklearn/tests/test_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
from sklearn.pipeline import make_pipeline

from sklearn.utils import IS_PYPY
from sklearn.utils._tags import _DEFAULT_TAGS, _safe_tags
from sklearn.utils._testing import (
SkipTest,
set_random_state,
Expand Down Expand Up @@ -308,6 +309,21 @@ def test_search_cv(estimator, check, request):
check(estimator)


@pytest.mark.parametrize(
"estimator", _tested_estimators(), ids=_get_check_estimator_ids
)
def test_valid_tag_types(estimator):
"""Check that estimator tags are valid."""
tags = _safe_tags(estimator)

for name, tag in tags.items():
correct_tags = type(_DEFAULT_TAGS[name])
if name == "_xfail_checks":
# _xfail_checks can be a dictionary
correct_tags = (correct_tags, dict)
assert isinstance(tag, correct_tags)


@pytest.mark.parametrize(
"estimator", _tested_estimators(), ids=_get_check_estimator_ids
)
Expand Down
0