From 432b758569e62dade9cadf19cf072dbf52fac350 Mon Sep 17 00:00:00 2001 From: "Thomas J. Fan" Date: Fri, 1 Oct 2021 10:50:23 -0400 Subject: [PATCH 1/5] FIX Do not use deprecated API in fetch_20newsgroups_vectorized --- sklearn/datasets/_twenty_newsgroups.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sklearn/datasets/_twenty_newsgroups.py b/sklearn/datasets/_twenty_newsgroups.py index 7fe17cbcb0a7a..24046367c69c6 100644 --- a/sklearn/datasets/_twenty_newsgroups.py +++ b/sklearn/datasets/_twenty_newsgroups.py @@ -479,7 +479,7 @@ def fetch_20newsgroups_vectorized( vectorizer = CountVectorizer(dtype=np.int16) X_train = vectorizer.fit_transform(data_train.data).tocsr() X_test = vectorizer.transform(data_test.data).tocsr() - feature_names = vectorizer.get_feature_names() + feature_names = vectorizer.get_feature_names_out() joblib.dump((X_train, X_test, feature_names), target_file, compress=9) From 619edc95d21c66fa6a55f14e61a486b805d6d6b8 Mon Sep 17 00:00:00 2001 From: "Thomas J. Fan" Date: Fri, 1 Oct 2021 10:50:48 -0400 Subject: [PATCH 2/5] BLD [scipy-dev] From 2f985f9b13147880957aa08416fdbe95d846022a Mon Sep 17 00:00:00 2001 From: "Thomas J. Fan" Date: Fri, 1 Oct 2021 13:43:56 -0400 Subject: [PATCH 3/5] TST Be explicit about fill value [scipy-dev] --- sklearn/utils/tests/test_validation.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py index 2cbbaac35a31b..f72d0ae65ae67 100644 --- a/sklearn/utils/tests/test_validation.py +++ b/sklearn/utils/tests/test_validation.py @@ -1456,8 +1456,8 @@ def test_check_pandas_sparse_valid(ntype1, ntype2, expected_subtype): pd = pytest.importorskip("pandas", minversion="0.25.0") df = pd.DataFrame( { - "col1": pd.arrays.SparseArray([0, 1, 0], dtype=ntype1), - "col2": pd.arrays.SparseArray([1, 0, 1], dtype=ntype2), + "col1": pd.arrays.SparseArray([0, 1, 0], dtype=ntype1, fill_value=0), + "col2": pd.arrays.SparseArray([1, 0, 1], dtype=ntype2, fill_value=0), } ) arr = check_array(df, accept_sparse=["csr", "csc"]) From 81613ffe513eef50dd7188e51a4fa95db7329821 Mon Sep 17 00:00:00 2001 From: "Thomas J. Fan" Date: Fri, 1 Oct 2021 16:31:43 -0400 Subject: [PATCH 4/5] TST Fixes tests for fill value --- sklearn/utils/tests/test_validation.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py index f72d0ae65ae67..167118fb4ff8f 100644 --- a/sklearn/utils/tests/test_validation.py +++ b/sklearn/utils/tests/test_validation.py @@ -1414,8 +1414,8 @@ def test_check_pandas_sparse_invalid(ntype1, ntype2): pd = pytest.importorskip("pandas", minversion="0.25.0") df = pd.DataFrame( { - "col1": pd.arrays.SparseArray([0, 1, 0], dtype=ntype1), - "col2": pd.arrays.SparseArray([1, 0, 1], dtype=ntype2), + "col1": pd.arrays.SparseArray([0, 1, 0], dtype=ntype1, fill_value=0), + "col2": pd.arrays.SparseArray([1, 0, 1], dtype=ntype2, fill_value=0), } ) From abe92ea64b0d17c1fb33dfba405864ebc282a6ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lo=C3=AFc=20Est=C3=A8ve?= Date: Mon, 4 Oct 2021 14:40:47 +0200 Subject: [PATCH 5/5] [scipy-dev] trigger nightly build