def test_predefined_split():
cv = PredefinedSplit(np.array(list(range(4)) * 5))
cv2 = PredefinedSplit(np.array(list(range(5)) * 4))
assert tokenize(cv) == tokenize(cv)
assert tokenize(cv) != tokenize(cv2)
sol = cv.get_n_splits(np_X, np_y, np_groups)
assert compute_n_splits(cv, np_X, np_y, np_groups) == sol
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == sol
def test_predefined_split():
cv = PredefinedSplit(np.array(list(range(4)) * 5))
cv2 = PredefinedSplit(np.array(list(range(5)) * 4))
assert tokenize(cv) == tokenize(cv)
assert tokenize(cv) != tokenize(cv2)
sol = cv.get_n_splits(np_X, np_y, np_groups)
assert compute_n_splits(cv, np_X, np_y, np_groups) == sol
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == sol
def test_old_style_cv():
cv1 = _CVIterableWrapper([np.array([True, False, True, False] * 5),
np.array([False, True, False, True] * 5)])
cv2 = _CVIterableWrapper([np.array([True, False, True, False] * 5),
np.array([False, True, True, True] * 5)])
assert tokenize(cv1) == tokenize(cv1)
assert tokenize(cv1) != tokenize(cv2)
sol = cv1.get_n_splits(np_X, np_y, np_groups)
assert compute_n_splits(cv1, np_X, np_y, np_groups) == sol
with assert_dask_compute(False):
assert compute_n_splits(cv1, da_X, da_y, da_groups) == sol
def test_shuffle_split(cls):
assert (tokenize(cls(n_splits=3, random_state=0)) == tokenize(
cls(n_splits=3, random_state=0)))
assert (tokenize(cls(n_splits=3, random_state=0)) != tokenize(
cls(n_splits=3, random_state=2)))
assert (tokenize(cls(n_splits=3, random_state=0)) != tokenize(
cls(n_splits=4, random_state=0)))
cv = cls(n_splits=3)
assert compute_n_splits(cv, np_X, np_y, np_groups) == 3
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == 3
def test_shuffle_split(cls):
assert (tokenize(cls(n_splits=3, random_state=0)) ==
tokenize(cls(n_splits=3, random_state=0)))
assert (tokenize(cls(n_splits=3, random_state=0)) !=
tokenize(cls(n_splits=3, random_state=2)))
assert (tokenize(cls(n_splits=3, random_state=0)) !=
tokenize(cls(n_splits=4, random_state=0)))
cv = cls(n_splits=3)
assert compute_n_splits(cv, np_X, np_y, np_groups) == 3
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == 3
def test_leave_group_out(cvs):
tokens = []
for cv in cvs:
assert tokenize(cv) == tokenize(cv)
tokens.append(cv)
assert len(set(tokens)) == len(tokens)
cv = cvs[0]
sol = cv.get_n_splits(np_X, np_y, np_groups)
assert compute_n_splits(cv, np_X, np_y, np_groups) == sol
with assert_dask_compute(True):
assert compute_n_splits(cv, da_X, da_y, da_groups) == sol
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, np_groups) == sol
def test_leave_group_out(cvs):
tokens = []
for cv in cvs:
assert tokenize(cv) == tokenize(cv)
tokens.append(cv)
assert len(set(tokens)) == len(tokens)
cv = cvs[0]
sol = cv.get_n_splits(np_X, np_y, np_groups)
assert compute_n_splits(cv, np_X, np_y, np_groups) == sol
with assert_dask_compute(True):
assert compute_n_splits(cv, da_X, da_y, da_groups) == sol
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, np_groups) == sol
def test_kfolds(cls, has_shuffle):
assert tokenize(cls()) == tokenize(cls())
assert tokenize(cls(n_splits=3)) != tokenize(cls(n_splits=4))
if has_shuffle:
assert (tokenize(cls(shuffle=True, random_state=0)) == tokenize(
cls(shuffle=True, random_state=0)))
rs = np.random.RandomState(42)
assert (tokenize(cls(shuffle=True, random_state=rs)) == tokenize(
cls(shuffle=True, random_state=rs)))
assert (tokenize(cls(shuffle=True, random_state=0)) != tokenize(
cls(shuffle=True, random_state=2)))
assert (tokenize(cls(shuffle=False, random_state=0)) == tokenize(
cls(shuffle=False, random_state=2)))
cv = cls(n_splits=3)
assert compute_n_splits(cv, np_X, np_y, np_groups) == 3
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == 3
def test_kfolds(cls, has_shuffle):
assert tokenize(cls()) == tokenize(cls())
assert tokenize(cls(n_splits=3)) != tokenize(cls(n_splits=4))
if has_shuffle:
assert (tokenize(cls(shuffle=True, random_state=0)) ==
tokenize(cls(shuffle=True, random_state=0)))
rs = np.random.RandomState(42)
assert (tokenize(cls(shuffle=True, random_state=rs)) ==
tokenize(cls(shuffle=True, random_state=rs)))
assert (tokenize(cls(shuffle=True, random_state=0)) !=
tokenize(cls(shuffle=True, random_state=2)))
assert (tokenize(cls(shuffle=False, random_state=0)) ==
tokenize(cls(shuffle=False, random_state=2)))
cv = cls(n_splits=3)
assert compute_n_splits(cv, np_X, np_y, np_groups) == 3
with assert_dask_compute(False):
assert compute_n_splits(cv, da_X, da_y, da_groups) == 3
