CLN EnvironmentError, IOError, WindowsError → OSError (scikit-learn#2…

…6466)

doc/install.rst

@@ -323,7 +323,7 @@ size limit of Windows if Python is installed in a nested location such as the
  Collecting scikit-learn
  ...
  Installing collected packages: scikit-learn
- ERROR: Could not install packages due to an EnvironmentError: [Errno 2] No such file or directory: 'C:\\Users\\username\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python37\\site-packages\\sklearn\\datasets\\tests\\data\\openml\\292\\api-v1-json-data-list-data_name-australian-limit-2-data_version-1-status-deactivated.json.gz'
+ ERROR: Could not install packages due to an OSError: [Errno 2] No such file or directory: 'C:\\Users\\username\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python37\\site-packages\\sklearn\\datasets\\tests\\data\\openml\\292\\api-v1-json-data-list-data_name-australian-limit-2-data_version-1-status-deactivated.json.gz'
 
 In this case it is possible to lift that limit in the Windows registry by
 using the ``regedit`` tool:

doc/whats_new/v1.3.rst

@@ -659,6 +659,13 @@ Changelog
  accepts sparse metrics.
  :pr:`19664` by :user:`Kaushik Amar Das <cozek>`.
 
+Miscellaneous
+.............
+
+- |Enhancement| Replace obsolete exceptions EnvironmentError, IOError and
+ WindowsError.
+ :pr:`26466` by :user:`Dimitri Papadopoulos ORfanos <DimitriPapadopoulos>`.
+
 Code and Documentation Contributors
 -----------------------------------
 

sklearn/conftest.py

@@ -87,7 +87,7 @@ def wrapped(*args, **kwargs):
  kwargs["download_if_missing"] = download_if_missing
  try:
  return f(*args, **kwargs)
- except IOError as e:
+ except OSError 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")

sklearn/datasets/_base.py

@@ -1377,7 +1377,7 @@ def _fetch_remote(remote, dirname=None):
  urlretrieve(remote.url, file_path)
  checksum = _sha256(file_path)
  if remote.checksum != checksum:
- raise IOError(
+ raise OSError(
  "{} has an SHA256 checksum ({}) "
  "differing from expected ({}), "
  "file may be corrupted.".format(file_path, checksum, remote.checksum)

sklearn/datasets/_california_housing.py

@@ -80,7 +80,7 @@ def fetch_california_housing(
  all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False
@@ -138,7 +138,7 @@ def fetch_california_housing(
  filepath = _pkl_filepath(data_home, "cal_housing.pkz")
  if not exists(filepath):
  if not download_if_missing:
- raise IOError("Data not found and `download_if_missing` is False")
+ raise OSError("Data not found and `download_if_missing` is False")
 
  logger.info(
  "Downloading Cal. housing from {} to {}".format(ARCHIVE.url, data_home)

sklearn/datasets/_covtype.py

@@ -101,7 +101,7 @@ def fetch_covtype(
  all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  random_state : int, RandomState instance or None, default=None
@@ -184,7 +184,7 @@ def fetch_covtype(
  os.rename(targets_tmp_path, targets_path)
 
  elif not available and not download_if_missing:
- raise IOError("Data not found and `download_if_missing` is False")
+ raise OSError("Data not found and `download_if_missing` is False")
  try:
  X, y
  except NameError:

sklearn/datasets/_kddcup99.py

@@ -110,7 +110,7 @@ def fetch_kddcup99(
  Whether to load only 10 percent of the data.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False
@@ -252,7 +252,7 @@ def _fetch_brute_kddcup99(data_home=None, download_if_missing=True, percent10=Tr
  all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  percent10 : bool, default=True
@@ -345,7 +345,7 @@ def _fetch_brute_kddcup99(data_home=None, download_if_missing=True, percent10=Tr
  X = joblib.load(samples_path)
  y = joblib.load(targets_path)
  except Exception as e:
- raise IOError(
+ raise OSError(
  "The cache for fetch_kddcup99 is invalid, please delete "
  f"{str(kddcup_dir)} and run the fetch_kddcup99 again"
  ) from e
@@ -379,7 +379,7 @@ def _fetch_brute_kddcup99(data_home=None, download_if_missing=True, percent10=Tr
  joblib.dump(X, samples_path, compress=0)
  joblib.dump(y, targets_path, compress=0)
  else:
- raise IOError("Data not found and `download_if_missing` is False")
+ raise OSError("Data not found and `download_if_missing` is False")
 
  return Bunch(
  data=X,

sklearn/datasets/_lfw.py

@@ -88,7 +88,7 @@ def _check_fetch_lfw(data_home=None, funneled=True, download_if_missing=True):
  logger.info("Downloading LFW metadata: %s", target.url)
  _fetch_remote(target, dirname=lfw_home)
  else:
- raise IOError("%s is missing" % target_filepath)
+ raise OSError("%s is missing" % target_filepath)
 
  if funneled:
  data_folder_path = join(lfw_home, "lfw_funneled")
@@ -104,7 +104,7 @@ def _check_fetch_lfw(data_home=None, funneled=True, download_if_missing=True):
  logger.info("Downloading LFW data (~200MB): %s", archive.url)
  _fetch_remote(archive, dirname=lfw_home)
  else:
- raise IOError("%s is missing" % archive_path)
+ raise OSError("%s is missing" % archive_path)
 
  import tarfile
 
@@ -297,7 +297,7 @@ def fetch_lfw_people(
  correlation from the background.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False
@@ -500,7 +500,7 @@ def fetch_lfw_pairs(
  correlation from the background.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  Returns

sklearn/datasets/_olivetti_faces.py

@@ -83,7 +83,7 @@ def fetch_olivetti_faces(
  See :term:`Glossary <random_state>`.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False
@@ -121,7 +121,7 @@ def fetch_olivetti_faces(
  filepath = _pkl_filepath(data_home, "olivetti.pkz")
  if not exists(filepath):
  if not download_if_missing:
- raise IOError("Data not found and `download_if_missing` is False")
+ raise OSError("Data not found and `download_if_missing` is False")
 
  print("downloading Olivetti faces from %s to %s" % (FACES.url, data_home))
  mat_path = _fetch_remote(FACES, dirname=data_home)

sklearn/datasets/_rcv1.py

@@ -126,7 +126,7 @@ def fetch_rcv1(
  This follows the official LYRL2004 chronological split.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  random_state : int, RandomState instance or None, default=None

sklearn/datasets/_species_distributions.py

@@ -151,7 +151,7 @@ def fetch_species_distributions(*, data_home=None, download_if_missing=True):
  all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
  download_if_missing : bool, default=True
- If False, raise a IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  Returns
@@ -228,7 +228,7 @@ def fetch_species_distributions(*, data_home=None, download_if_missing=True):
 
  if not exists(archive_path):
  if not download_if_missing:
- raise IOError("Data not found and `download_if_missing` is False")
+ raise OSError("Data not found and `download_if_missing` is False")
  logger.info("Downloading species data from %s to %s" % (SAMPLES.url, data_home))
  samples_path = _fetch_remote(SAMPLES, dirname=data_home)
  with np.load(samples_path) as X: # samples.zip is a valid npz

sklearn/datasets/_twenty_newsgroups.py

@@ -226,7 +226,7 @@ def fetch_20newsgroups(
  correct.
 
  download_if_missing : bool, default=True
- If False, raise an IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False
@@ -283,7 +283,7 @@ def fetch_20newsgroups(
  target_dir=twenty_home, cache_path=cache_path
  )
  else:
- raise IOError("20Newsgroups dataset not found")
+ raise OSError("20Newsgroups dataset not found")
 
  if subset in ("train", "test"):
  data = cache[subset]
@@ -413,7 +413,7 @@ def fetch_20newsgroups_vectorized(
  all scikit-learn data is stored in '~/scikit_learn_data' subfolders.
 
  download_if_missing : bool, default=True
- If False, raise an IOError if the data is not locally available
+ If False, raise an OSError if the data is not locally available
  instead of trying to download the data from the source site.
 
  return_X_y : bool, default=False

sklearn/datasets/tests/test_kddcup99.py

@@ -82,5 +82,5 @@ def test_corrupted_file_error_message(fetch_kddcup99_fxt, tmp_path):
  f"delete {str(kddcup99_dir)} and run the fetch_kddcup99 again"
  )
 
- with pytest.raises(IOError, match=msg):
+ with pytest.raises(OSError, match=msg):
  fetch_kddcup99_fxt(data_home=str(tmp_path))

sklearn/datasets/tests/test_lfw.py

@@ -109,7 +109,7 @@ def teardown_module():
 
 
 def test_load_empty_lfw_people():
- with pytest.raises(IOError):
+ with pytest.raises(OSError):
  fetch_lfw_people(data_home=SCIKIT_LEARN_EMPTY_DATA, download_if_missing=False)
 
 
@@ -181,7 +181,7 @@ def test_load_fake_lfw_people_too_restrictive():
 
 
 def test_load_empty_lfw_pairs():
- with pytest.raises(IOError):
+ with pytest.raises(OSError):
  fetch_lfw_pairs(data_home=SCIKIT_LEARN_EMPTY_DATA, download_if_missing=False)
 
 

sklearn/datasets/tests/test_svmlight_format.py

@@ -249,7 +249,7 @@ def test_not_a_filename():
 
 
 def test_invalid_filename():
- with pytest.raises(IOError):
+ with pytest.raises(OSError):
  load_svmlight_file("trou pic nic douille")
 
 

sklearn/model_selection/tests/test_validation.py

@@ -79,12 +79,6 @@
 from sklearn.model_selection import GridSearchCV
 
 
-try:
- WindowsError # type: ignore
-except NameError:
- WindowsError = None
-
-
 class MockImprovingEstimator(BaseEstimator):
  """Dummy classifier to test the learning curve"""
 
@@ -2064,7 +2058,7 @@ def test_score_memmap():
  try:
  os.unlink(tf.name)
  break
- except WindowsError:
+ except OSError:
  sleep(1.0)
 
 

sklearn/utils/_testing.py

@@ -33,12 +33,6 @@
 import unittest
 from unittest import TestCase
 
-# WindowsError only exist on Windows
-try:
- WindowsError # type: ignore
-except NameError:
- WindowsError = None
-
 from numpy.testing import assert_allclose as np_assert_allclose
 from numpy.testing import assert_almost_equal
 from numpy.testing import assert_approx_equal
@@ -453,7 +447,7 @@ def _delete_folder(folder_path, warn=False):
  # This can fail under windows,
  # but will succeed when called by atexit
  shutil.rmtree(folder_path)
- except WindowsError:
+ except OSError:
  if warn:
  warnings.warn("Could not delete temporary folder %s" % folder_path)