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())
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)