def test_open_openml_url_cache(monkeypatch, gzip_response, tmpdir):
data_id = 61
_monkey_patch_webbased_functions(monkeypatch, data_id, gzip_response)
openml_path = sklearn.datasets._openml._DATA_FILE.format(data_id)
cache_directory = str(tmpdir.mkdir('scikit_learn_data'))
# first fill the cache
response1 = _open_openml_url(openml_path, cache_directory)
# assert file exists
location = _get_local_path(openml_path, cache_directory)
assert os.path.isfile(location)
# redownload, to utilize cache
response2 = _open_openml_url(openml_path, cache_directory)
assert response1.read() == response2.read()
def test_open_openml_url_unlinks_local_path(monkeypatch, gzip_response, tmpdir,
write_to_disk):
data_id = 61
openml_path = sklearn.datasets._openml._DATA_FILE.format(data_id)
cache_directory = str(tmpdir.mkdir('scikit_learn_data'))
location = _get_local_path(openml_path, cache_directory)
def _mock_urlopen(request):
if write_to_disk:
with open(location, "w") as f:
f.write("")
raise ValueError("Invalid request")
monkeypatch.setattr(sklearn.datasets._openml, 'urlopen', _mock_urlopen)
with pytest.raises(ValueError, match="Invalid request"):
_open_openml_url(openml_path, cache_directory)
assert not os.path.exists(location)
def test_retry_with_clean_cache(tmpdir):
data_id = 61
openml_path = sklearn.datasets._openml._DATA_FILE.format(data_id)
cache_directory = str(tmpdir.mkdir('scikit_learn_data'))
location = _get_local_path(openml_path, cache_directory)
os.makedirs(os.path.dirname(location))
with open(location, 'w') as f:
f.write("")
@_retry_with_clean_cache(openml_path, cache_directory)
def _load_data():
# The first call will raise an error since location exists
if os.path.exists(location):
raise Exception("File exist!")
return 1
warn_msg = "Invalid cache, redownloading file"
with pytest.warns(RuntimeWarning, match=warn_msg):
result = _load_data()
assert result == 1
