def test_disable_repeats_when_disabled_shuffle(self):
data = {
"X":
pd.DataFrame(np.array([[0, 0], [0, 1], [1, 0], [1, 1]]),
columns=["a", "b"]),
"y":
pd.DataFrame(np.array([0, 0, 1, 1]), columns=["target"]),
}
X_path = os.path.join(self._results_path, "X.data")
y_path = os.path.join(self._results_path, "y.data")
dump_data(X_path, data["X"])
dump_data(y_path, data["y"])
params = {
"shuffle": False,
"stratify": False,
"k_folds": 2,
"repeats": 10,
"results_path": self._results_path,
"X_path": X_path,
"y_path": y_path,
"random_seed": 1,
}
vl = KFoldValidator(params)
self.assertEqual(params["k_folds"], vl.get_n_splits())
self.assertEqual(1, vl.get_repeats())
class ValidationStep:
def __init__(self, params):
# kfold is default validation technique
self.validation_type = params.get("validation_type", "kfold")
if self.validation_type == "kfold":
self.validator = KFoldValidator(params)
else:
raise Exception("Other validation types are not implemented yet!")
"""
elif self.validation_type == "split":
self.validator = SplitValidator(params, data)
elif self.validation_type == "with_dataset":
self.validator = WithDatasetValidator(params, data)
else:
msg = "Unknown validation type: {0}".format(self.validation_type)
raise ValidationStepException(msg)
"""
def get_split(self, k):
return self.validator.get_split(k)
def split(self):
return self.validator.split()
def get_n_splits(self):
return self.validator.get_n_splits()
def test_repeats(self):
data = {
"X":
pd.DataFrame(np.array([[0, 0], [0, 1], [1, 0], [1, 1]]),
columns=["a", "b"]),
"y":
pd.DataFrame(np.array([0, 0, 1, 1]), columns=["target"]),
}
X_path = os.path.join(self._results_path, "X.data")
y_path = os.path.join(self._results_path, "y.data")
dump_data(X_path, data["X"])
dump_data(y_path, data["y"])
params = {
"shuffle": True,
"stratify": False,
"k_folds": 2,
"repeats": 10,
"results_path": self._results_path,
"X_path": X_path,
"y_path": y_path,
"random_seed": 1,
}
vl = KFoldValidator(params)
self.assertEqual(params["k_folds"], vl.get_n_splits())
self.assertEqual(params["repeats"], vl.get_repeats())
for repeat in range(vl.get_repeats()):
for k_fold in range(vl.get_n_splits()):
train, validation = vl.get_split(k_fold, repeat)
X_train, y_train = train.get("X"), train.get("y")
X_validation, y_validation = validation.get(
"X"), validation.get("y")
self.assertEqual(X_train.shape[0], 2)
self.assertEqual(y_train.shape[0], 2)
self.assertEqual(X_validation.shape[0], 2)
self.assertEqual(y_validation.shape[0], 2)
def test_missing_target_values(self):
data = {
"train": {
"X":
pd.DataFrame(
np.array([[1, 0], [2, 1], [3, 0], [4, 1], [5, 1], [6, 1]]),
columns=["a", "b"],
),
"y":
pd.DataFrame(np.array(["a", "b", "a", "b", np.nan, np.nan]),
columns=["target"]),
}
}
X_train_path = os.path.join(self._results_path, "X_train.parquet")
y_train_path = os.path.join(self._results_path, "y_train.parquet")
data["train"]["X"].to_parquet(X_train_path, index=False)
data["train"]["y"].to_parquet(y_train_path, index=False)
params = {
"shuffle": True,
"stratify": True,
"k_folds": 2,
"results_path": self._results_path,
"X_train_path": X_train_path,
"y_train_path": y_train_path,
}
vl = KFoldValidator(params)
self.assertEqual(params["k_folds"], vl.get_n_splits())
for k_fold in range(vl.get_n_splits()):
train, validation = vl.get_split(k_fold)
X_train, y_train = train.get("X"), train.get("y")
X_validation, y_validation = validation.get("X"), validation.get(
"y")
self.assertEqual(X_train.shape[0], 2)
self.assertEqual(y_train.shape[0], 2)
self.assertEqual(X_validation.shape[0], 2)
self.assertEqual(y_validation.shape[0], 2)
def test_create(self):
data = {
"train": {
"X":
pd.DataFrame(np.array([[0, 0], [0, 1], [1, 0], [1, 1]]),
columns=["a", "b"]),
"y":
pd.DataFrame(np.array([0, 0, 1, 1]), columns=["target"]),
}
}
X_train_path = os.path.join(self._results_path, "X_train.parquet")
y_train_path = os.path.join(self._results_path, "y_train.parquet")
data["train"]["X"].to_parquet(X_train_path, index=False)
data["train"]["y"].to_parquet(y_train_path, index=False)
params = {
"shuffle": False,
"stratify": False,
"k_folds": 2,
"results_path": self._results_path,
"X_train_path": X_train_path,
"y_train_path": y_train_path,
}
vl = KFoldValidator(params)
self.assertEqual(params["k_folds"], vl.get_n_splits())
# for train, validation in vl.split():
for k_fold in range(vl.get_n_splits()):
train, validation = vl.get_split(k_fold)
X_train, y_train = train.get("X"), train.get("y")
X_validation, y_validation = validation.get("X"), validation.get(
"y")
self.assertEqual(X_train.shape[0], 2)
self.assertEqual(y_train.shape[0], 2)
self.assertEqual(X_validation.shape[0], 2)
self.assertEqual(y_validation.shape[0], 2)
def test_create_with_target_as_labels(self):
data = {
"train": {
"X": pd.DataFrame(np.array([[0, 0], [0, 1], [1, 0], [1, 1]])),
"y": pd.DataFrame(np.array(["a", "b", "a", "b"])),
}
}
params = {"shuffle": True, "stratify": True, "k_folds": 2}
vl = KFoldValidator(params, data)
self.assertEqual(params["k_folds"], vl.get_n_splits())
for train, validation in vl.split():
X_train, y_train = train.get("X"), train.get("y")
X_validation, y_validation = validation.get("X"), validation.get("y")
self.assertEqual(X_train.shape[0], 2)
self.assertEqual(y_train.shape[0], 2)
self.assertEqual(X_validation.shape[0], 2)
self.assertEqual(y_validation.shape[0], 2)
def test_missing_target_values(self):
# rows with missing target will be distributed equaly among folds
data = {
"train": {
"X": pd.DataFrame(
np.array([[1, 0], [2, 1], [3, 0], [4, 1], [5, 1], [6, 1]])
),
"y": pd.DataFrame(np.array(["a", "b", "a", "b", np.nan, np.nan])),
}
}
params = {"shuffle": True, "stratify": True, "k_folds": 2}
vl = KFoldValidator(params, data)
self.assertEqual(params["k_folds"], vl.get_n_splits())
for train, validation in vl.split():
X_train, y_train = train.get("X"), train.get("y")
X_validation, y_validation = validation.get("X"), validation.get("y")
self.assertEqual(X_train.shape[0], 3)
self.assertEqual(y_train.shape[0], 3)
self.assertEqual(X_validation.shape[0], 3)
self.assertEqual(y_validation.shape[0], 3)