def test_list_metafeatures(self):
mf_list = Metafeatures.list_metafeatures()
mf_list_copy = [mf for mf in mf_list]
mf_list.clear()
if Metafeatures.list_metafeatures() != mf_list_copy:
mf_list.extend(mf_list_copy)
self.fail('Metafeature list has been mutated')
def test_numeric_targets(self):
""" Test Metafeatures().compute() with numeric targets
"""
test_failures = {}
test_name = inspect.stack()[0][3]
for dataset_filename, dataset in self.datasets.items():
metafeatures = Metafeatures()
column_types = dataset["column_types"].copy()
column_types[dataset["Y"].name] = consts.NUMERIC
computed_mfs = metafeatures.compute(
X=dataset["X"],
Y=pd.Series(np.random.rand(dataset["Y"].shape[0]),
name=dataset["Y"].name),
seed=CORRECTNESS_SEED,
column_types=column_types)
known_mfs = dataset["known_metafeatures"]
target_dependent_metafeatures = Metafeatures.list_metafeatures(
consts.MetafeatureGroup.TARGET_DEPENDENT.value)
for mf_name in target_dependent_metafeatures:
known_mfs[mf_name] = {
consts.VALUE_KEY: consts.NUMERIC_TARGETS,
consts.COMPUTE_TIME_KEY: 0.
}
required_checks = [(self._check_correctness,
[computed_mfs, known_mfs, dataset_filename]),
(self._check_compare_metafeature_lists,
[computed_mfs, known_mfs, dataset_filename])]
test_failures.update(self._perform_checks(required_checks))
self._report_test_failures(test_failures, test_name)
def test_exclude_metafeature_groups(self):
SUBSET_LENGTH = 3
test_failures = {}
test_name = inspect.stack()[0][3]
for dataset_filename, dataset in self.datasets.items():
groups = random.sample(
[group.value for group in consts.MetafeatureGroup],
SUBSET_LENGTH)
computed_mfs = Metafeatures().compute(
X=dataset["X"],
Y=dataset["Y"],
column_types=dataset["column_types"],
seed=CORRECTNESS_SEED,
exclude_groups=groups,
)
known_metafeatures = dataset["known_metafeatures"]
required_checks = [
(self._check_correctness,
[computed_mfs, known_metafeatures, dataset_filename])
]
test_failures.update(self._perform_checks(required_checks))
metafeature_ids = set(
mf_id for group in groups
for mf_id in Metafeatures.list_metafeatures(group))
if any(mf_id in computed_mfs.keys() for mf_id in metafeature_ids):
self.fail('Metafeatures computed an excluded metafeature')
self._report_test_failures(test_failures, test_name)
def get_list_metafeatures(list_X, list_y, type_metafeatures):
metafeatures = Metafeatures()
list_dataset_metafeatures = []
for X, y in tqdm(zip(list_X, list_Y), total=7084):
mfs = metafeatures.compute(
pd.DataFrame(X),
Y=pd.Series(y, dtype="category"),
metafeature_ids=metafeatures.list_metafeatures(
group=type_metafeatures),
exclude=None,
seed=0,
#verbose=True,
timeout=60,
# return_times=True,
)
list_dataset_metafeatures.append(
pd.DataFrame(mfs).reset_index(drop=True))
df_metafeatures = pd.concat(list_dataset_metafeatures).fillna(0)
df_metafeatures["index"] = list_files
df_metafeatures.set_index("index", inplace=True)
return df_metafeatures
