def _run_weka(name: str, extra_args: List[str], dataset: Bunch,
log_results: Callable, cache_dir: str):
logger.info('weka: prepare dataset')
arffgz_path = _get_local_path(
_DATA_FILE.format(dataset.details['file_id']), # maybe != ds_id
data_home=cache_dir + '/openml/')
with tempfile.TemporaryDirectory() as tmpdirname:
# link to a file named '*.arff.gz', otherwise weka doesn't
# recognize it's gzipped
arffgz_linked = (tmpdirname + '/' + os.path.basename(arffgz_path) +
'.arff.gz')
os.symlink(arffgz_path, arffgz_linked)
# get target column
target_column_ids = [
int(feature['index'])
for feature in _get_data_features(dataset.details['id'],
data_home=cache_dir)
if feature['is_target'] == 'true'
]
if len(target_column_ids) != 1:
logger.warning(
"identified {} target columns [{}], using only {}".format(
len(target_column_ids),
','.join(map(str,
target_column_ids)), target_column_ids[0]))
logger.info('run weka.' + name)
_cmd = WEKA_CMD + [
name,
'-t',
arffgz_linked, # "train" ARFF file
'-c',
str(target_column_ids[0] + 1),
# todo: hardcode metrics
] + extra_args
logger.debug(_cmd)
weka_process = subprocess.run(_cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
universal_newlines=True)
logger.info('weka.{} returned with {}'.format(name,
weka_process.returncode))
if weka_process.stdout:
weka_stdout_logger.debug(weka_process.stdout)
if weka_process.stderr:
weka_stderr_logger.debug(weka_process.stderr)
weka_out: str = weka_process.stdout
if WEKA_REGEX.FULL_MODEL.search(weka_out): # if has successful run
runtime_single, runtime_cv, jrip_n_rules, metrics = \
_process_weka_output(weka_out)
log_results(algorithm='weka.' + name,
runtime_single=runtime_single,
runtime_cv=runtime_cv,
n_rules=jrip_n_rules,
metrics=metrics)
else:
logger.warning('weka.{}: no successful output found')
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_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_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
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
