def test_sw_first_window_size(train_size, window_size, horizon, expected):
'''
check that the window size is correct in the sliding
window method - this tests the first fold.
'''
train = np.arange(train_size)
cv = ms.sliding_window(train, window_size=window_size, horizon=horizon)
train_cv, _ = next(cv)
assert expected == len(train_cv)
def test_sw_test_length(train_size, horizon, expected):
'''
test the length of test is correct in the sliding window
generator
'''
train = np.arange(train_size)
cv = ms.sliding_window(train, window_size=1, horizon=horizon)
_, test_cv = next(cv)
assert expected == len(test_cv)
def test_sw_number_of_folds(train_size, window_size, horizon, step, expected):
'''
check that the number of folds returned from sliding window
is as expected
'''
train = np.arange(train_size)
cv = ms.sliding_window(train,
window_size=window_size,
horizon=horizon,
step=step)
actual = 0
# number of folds found
for _, _ in cv:
actual += 1
assert expected == actual
def test_sw_number_of_folds_pd(train_size, window_size, horizon, step,
expected):
'''
check that the number of folds returned from rolling origin
is as expected when data source is a PANDAS.DATAFRAME
'''
train = pd.DataFrame(np.arange(train_size))
cv = ms.sliding_window(train,
window_size=window_size,
horizon=horizon,
step=step)
actual = 0
# number of folds found
for _, _ in cv:
actual += 1
assert expected == actual