8000 ENH Better error for corrupted files in fetch_kddcup99 by thomasjpfan · Pull Request #19669 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]

Skip to content

ENH Better error for corrupted files in fetch_kddcup99 #19669

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.

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 2 commits into from
Mar 18, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 3 additions & 0 deletions doc/whats_new/v1.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,9 @@ Changelog
`Thomas Fan`_ and :user:`Amanda Dsouza <amy12xx>` and
:user:`EL-ATEIF Sara <elateifsara>`.

- |Enhancement| :func:`datasets.fetch_kddcup99` raises a better message
when the cached file is invalid. :pr:`19669` `Thomas Fan`_.

:mod:`sklearn.decomposition`
............................

Expand Down
7 changes: 5 additions & 2 deletions sklearn/conftest.py
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,11 @@ def wrapped(*args, **kwargs):
kwargs['download_if_missing'] = download_if_missing
try:
return f(*args, **kwargs)
except IOError:
pytest.skip("test is enabled when SKLEARN_SKIP_NETWORK_TESTS=0")
except IOError as e:
if str(e) != "Data not found and `download_if_missing` is False":
raise
pytest.skip("test is enabled when "
"SKLEARN_SKIP_NETWORK_TESTS=0")
return pytest.fixture(lambda: wrapped)


Expand Down
23 changes: 13 additions & 10 deletions sklearn/datasets/_kddcup99.py
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,17 @@ def _fetch_brute_kddcup99(data_home=None,
column_names = [c[0] for c in dt]
target_names = column_names[-1]
feature_names = column_names[:-1]
if download_if_missing and not available:

if available:
try:
X = joblib.load(samples_path)
y = joblib.load(targets_path)
except Exception as e:
raise IOError(
"The cache for fetch_kddcup99 is invalid, please delete "
f"{str(kddcup_dir)} and run the fetch_kddcup99 again") from e

elif download_if_missing:
_mkdirp(kddcup_dir)
logger.info("Downloading %s" % archive.url)
_fetch_remote(archive, dirname=kddcup_dir)
Expand Down Expand Up @@ -343,15 +353,8 @@ def _fetch_brute_kddcup99(data_home=None,

joblib.dump(X, samples_path, compress=0)
joblib.dump(y, targets_path, compress=0)
elif not available:
if not download_if_missing:
raise IOError("Data not found and `download_if_missing` is False")

try:
X, y
except NameError:
X = joblib.load(samples_path)
y 8000 = joblib.load(targets_path)
else:
raise IOError("Data not found and `download_if_missing` is False")

return Bunch(
data=X,
Expand Down
16 changes: 16 additions & 0 deletions sklearn/datasets/tests/test_kddcup99.py
Original file line number Diff line number Diff line change
Expand Up @@ -58,3 +58,19 @@ def test_fetch_kddcup99_shuffle(fetch_kddcup99_fxt):

def test_pandas_dependency_message(fetch_kddcup99_fxt, hide_available_pandas):
check_pandas_dependency_message(fetch_kddcup99_fxt)


def test_corrupted_file_error_message(fetch_kddcup99_fxt, tmp_path):
"""Check that a nice error message is raised when cache is corrupted."""
kddcup99_dir = tmp_path / "kddcup99_10-py3"
kddcup99_dir.mkdir()
samples_path = kddcup99_dir / "samples"

with samples_path.open("wb") as f:
f.write(b"THIS IS CORRUPTED")

msg = (f"The cache for fetch_kddcup99 is invalid, please "
f"delete {str(kddcup99_dir)} and run the fetch_kddcup99 again")

with pytest.raises(IOError, match=msg):
fetch_kddcup99_fxt(data_home=str(tmp_path))
0