def test_random_state():
N_ITER = 10
X = generate_df_from_array(np.random.normal(size=20))
random_state = 1234
trans = RandomIntervalFeatureExtractor(n_intervals='random',
random_state=random_state)
first_Xt = trans.fit_transform(X)
for _ in range(N_ITER):
trans = RandomIntervalFeatureExtractor(n_intervals='random',
random_state=random_state)
Xt = trans.fit_transform(X)
assert first_Xt.equals(Xt)
def test_different_pipelines():
random_seed = 1233
X_train, y_train = load_gunpoint(return_X_y=True)
steps = [
('segment', RandomIntervalSegmenter(n_intervals='sqrt')),
('transform',
FeatureUnion([
('mean',
RowwiseTransformer(
FunctionTransformer(func=np.mean, validate=False))),
('std',
RowwiseTransformer(
FunctionTransformer(func=np.std, validate=False))),
('slope',
RowwiseTransformer(
FunctionTransformer(func=time_series_slope,
validate=False))),
])),
]
pipe = Pipeline(steps, random_state=random_seed)
a = pipe.fit_transform(X_train)
tran = RandomIntervalFeatureExtractor(
n_intervals='sqrt',
features=[np.mean, np.std, time_series_slope],
random_state=random_seed)
b = tran.fit_transform(X_train)
np.testing.assert_array_equal(a, b)
np.testing.assert_array_equal(pipe.steps[0][1].intervals_, tran.intervals_)
def test_output_format_dim(n_instances, len_series, n_intervals, features):
X = generate_df_from_array(np.ones(len_series),
n_rows=n_instances,
n_cols=1)
n_rows, n_cols = X.shape
trans = RandomIntervalFeatureExtractor(n_intervals=n_intervals,
features=features)
Xt = trans.fit_transform(X)
assert isinstance(Xt, pd.DataFrame)
assert Xt.shape[0] == n_rows
assert np.array_equal(Xt.values, np.ones(Xt.shape))
def test_results(n_instances, len_series, n_intervals):
x = np.random.normal(size=len_series)
X = generate_df_from_array(x, n_rows=n_instances, n_cols=1)
trans = RandomIntervalFeatureExtractor(
n_intervals=n_intervals, features=[np.mean, np.std, time_series_slope])
Xt = trans.fit_transform(X)
# Check results
for s, e in trans.intervals_:
assert np.all(Xt.filter(like=f'_{s}_{e}_mean') == np.mean(x[s:e]))
assert np.all(Xt.filter(like=f'_{s}_{e}_std') == np.std(x[s:e]))
assert np.all(
Xt.filter(like=f'_{s}_{e}_time_series_slope') == time_series_slope(
x[s:e]))
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)