def test_random_state():
X = generate_df_from_array(np.random.normal(size=10))
random_state = 1234
for n_intervals in [0.5, 10, 'sqrt', 'random', 'log']:
trans = RandomIntervalSegmenter(n_intervals=n_intervals, random_state=random_state)
first_Xt = trans.fit_transform(X)
for _ in range(N_ITER):
trans = RandomIntervalSegmenter(n_intervals=n_intervals, random_state=random_state)
Xt = trans.fit_transform(X)
np.testing.assert_array_equal(tabularize(first_Xt).values, tabularize(Xt).values)
def test_different_implementations():
random_seed = 1233
X_train, y_train = load_gunpoint(return_X_y=True)
# Compare with chained transformations.
tran1 = RandomIntervalSegmenter(n_intervals='sqrt',
random_state=random_seed)
tran2 = RowwiseTransformer(
FunctionTransformer(func=np.mean, validate=False))
A = tran2.fit_transform(tran1.fit_transform(X_train))
tran = RandomIntervalFeatureExtractor(n_intervals='sqrt',
features=[np.mean],
random_state=random_seed)
B = tran.fit_transform(X_train)
np.testing.assert_array_equal(A, B)
def test_output_format_dim(len_series, n_instances, n_intervals):
X = generate_df_from_array(np.ones(len_series), n_rows=n_instances, n_cols=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(len_series * 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(len_series)))
elif n_intervals == 'log':
assert Xt.shape[1] == np.maximum(1, int(np.log(len_series)))