From 025f619d4208415ee964005401b22bc05ad65232 Mon Sep 17 00:00:00 2001 From: Julien Jerphanion Date: Tue, 28 Sep 2021 11:00:09 +0200 Subject: [PATCH 1/2] TST Handle Connection error in test_load_boston_alternative Currently a ConnectionResetError can make test fail if there is a problem with downloading the dataset. This marks the test as xfail in this case. --- sklearn/datasets/tests/test_base.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py index 3e27a6119554e..586ea67a688bb 100644 --- a/sklearn/datasets/tests/test_base.py +++ b/sklearn/datasets/tests/test_base.py @@ -341,7 +341,10 @@ def test_load_boston_alternative(): boston_sklearn = load_boston() data_url = "http://lib.stat.cmu.edu/datasets/boston" - raw_df = pd.read_csv(data_url, sep=r"\s+", skiprows=22, header=None) + try: + raw_df = pd.read_csv(data_url, sep=r"\s+", skiprows=22, header=None) + except ConnectionResetError: + pytest.xfail("The dataset can't be downloaded (Connection reset by peer).") data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]]) target = raw_df.values[1::2, 2] From e7fb4208717496078b7a61e7041fc269002b08d1 Mon Sep 17 00:00:00 2001 From: Julien Jerphanion Date: Tue, 28 Sep 2021 11:10:58 +0200 Subject: [PATCH 2/2] Handle more connection errors --- sklearn/datasets/tests/test_base.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py index 586ea67a688bb..e8840a4d8829f 100644 --- a/sklearn/datasets/tests/test_base.py +++ b/sklearn/datasets/tests/test_base.py @@ -343,8 +343,8 @@ def test_load_boston_alternative(): data_url = "http://lib.stat.cmu.edu/datasets/boston" try: raw_df = pd.read_csv(data_url, sep=r"\s+", skiprows=22, header=None) - except ConnectionResetError: - pytest.xfail("The dataset can't be downloaded (Connection reset by peer).") + except ConnectionError as e: + pytest.xfail(f"The dataset can't be downloaded. Got exception: {e}") data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]]) target = raw_df.values[1::2, 2]