def test_different_implementations():
random_state = 1233
X_train, y_train = make_classification_problem()
# Compare with chained transformations.
tran1 = RandomIntervalSegmenter(n_intervals=1, random_state=random_state)
tran2 = SeriesToPrimitivesRowTransformer(FunctionTransformer(
func=np.mean, validate=False),
check_transformer=False)
A = tran2.fit_transform(tran1.fit_transform(X_train))
tran = RandomIntervalFeatureExtractor(n_intervals=1,
features=[np.mean],
random_state=random_state)
B = tran.fit_transform(X_train)
np.testing.assert_array_almost_equal(A, B)
def test_output_format_dim(n_timepoints, n_instances, n_intervals):
X = _make_nested_from_array(
np.ones(n_timepoints), n_instances=n_instances, n_columns=1
)
trans = RandomIntervalSegmenter(n_intervals=n_intervals)
Xt = trans.fit_transform(X)
# Check number of rows and output type.
assert isinstance(Xt, pd.DataFrame)
assert Xt.shape[0] == X.shape[0]
# Check number of generated intervals/columns.
if n_intervals != "random":
if np.issubdtype(type(n_intervals), np.floating):
assert Xt.shape[1] == np.maximum(1, int(n_timepoints * n_intervals))
elif np.issubdtype(type(n_intervals), np.integer):
assert Xt.shape[1] == n_intervals
elif n_intervals == "sqrt":
assert Xt.shape[1] == np.maximum(1, int(np.sqrt(n_timepoints)))
elif n_intervals == "log":
assert Xt.shape[1] == np.maximum(1, int(np.log(n_timepoints)))