def test_feature_union_weights():
# test feature union with transformer weights
X = iris.data
y = iris.target
pca = PCA(n_components=2, svd_solver='randomized', random_state=0)
select = SelectKBest(k=1)
# test using fit followed by transform
fs = FeatureUnion([("pca", pca), ("select", select)],
transformer_weights={"pca": 10})
fs.fit(X, y)
X_transformed = fs.transform(X)
# test using fit_transform
fs = FeatureUnion([("pca", pca), ("select", select)],
transformer_weights={"pca": 10})
X_fit_transformed = fs.fit_transform(X, y)
# test it works with transformers missing fit_transform
fs = FeatureUnion([("mock", Transf()), ("pca", pca), ("select", select)],
transformer_weights={"mock": 10})
X_fit_transformed_wo_method = fs.fit_transform(X, y)
# check against expected result
# We use a different pca object to control the random_state stream
assert_array_almost_equal(X_transformed[:, :-1], 10 * pca.fit_transform(X))
assert_array_equal(X_transformed[:, -1],
select.fit_transform(X, y).ravel())
assert_array_almost_equal(X_fit_transformed[:, :-1],
10 * pca.fit_transform(X))
assert_array_equal(X_fit_transformed[:, -1],
select.fit_transform(X, y).ravel())
assert X_fit_transformed_wo_method.shape == (X.shape[0], 7)
def test_feature_union_warns_with_none():
msg = (r"Using None as a transformer is deprecated in version 0\.22 and "
r"will be removed in version 0\.24\. Please use 'drop' instead\.")
with pytest.warns(FutureWarning, match=msg):
union = FeatureUnion([('multi1', None), ('multi2', Mult())])
X = [[1, 2, 3], [4, 5, 6]]
with pytest.warns(FutureWarning, match=msg):
union.fit_transform(X)
def test_feature_union():
# basic sanity check for feature union
X = iris.data
X -= X.mean(axis=0)
y = iris.target
svd = TruncatedSVD(n_components=2, random_state=0)
select = SelectKBest(k=1)
fs = FeatureUnion([("svd", svd), ("select", select)])
fs.fit(X, y)
X_transformed = fs.transform(X)
assert X_transformed.shape == (X.shape[0], 3)
# check if it does the expected thing
assert_array_almost_equal(X_transformed[:, :-1], svd.fit_transform(X))
assert_array_equal(X_transformed[:, -1],
select.fit_transform(X, y).ravel())
# test if it also works for sparse input
# We use a different svd object to control the random_state stream
fs = FeatureUnion([("svd", svd), ("select", select)])
X_sp = sparse.csr_matrix(X)
X_sp_transformed = fs.fit_transform(X_sp, y)
assert_array_almost_equal(X_transformed, X_sp_transformed.toarray())
# Test clone
fs2 = assert_no_warnings(clone, fs)
assert fs.transformer_list[0][1] is not fs2.transformer_list[0][1]
# test setting parameters
fs.set_params(select__k=2)
assert fs.fit_transform(X, y).shape == (X.shape[0], 4)
# test it works with transformers missing fit_transform
fs = FeatureUnion([("mock", Transf()), ("svd", svd), ("select", select)])
X_transformed = fs.fit_transform(X, y)
assert X_transformed.shape == (X.shape[0], 8)
# test error if some elements do not support transform
assert_raises_regex(
TypeError, 'All estimators should implement fit and '
'transform.*\\bNoTrans\\b', FeatureUnion,
[("transform", Transf()), ("no_transform", NoTrans())])
# test that init accepts tuples
fs = FeatureUnion((("svd", svd), ("select", select)))
fs.fit(X, y)
def test_feature_union_fit_params():
# Regression test for issue: #15117
class Dummy(TransformerMixin, BaseEstimator):
def fit(self, X, y=None, **fit_params):
if fit_params != {'a': 0}:
raise ValueError
return self
def transform(self, X, y=None):
return X
X, y = iris.data, iris.target
t = FeatureUnion([('dummy0', Dummy()), ('dummy1', Dummy())])
with pytest.raises(ValueError):
t.fit(X, y)
with pytest.raises(ValueError):
t.fit_transform(X, y)
t.fit(X, y, a=0)
t.fit_transform(X, y, a=0)
def test_set_feature_union_step_drop(drop):
mult2 = Mult(2)
mult2.get_feature_names = lambda: ['x2']
mult3 = Mult(3)
mult3.get_feature_names = lambda: ['x3']
X = np.asarray([[1]])
ft = FeatureUnion([('m2', mult2), ('m3', mult3)])
assert_array_equal([[2, 3]], ft.fit(X).transform(X))
assert_array_equal([[2, 3]], ft.fit_transform(X))
assert ['m2__x2', 'm3__x3'] == ft.get_feature_names()
with pytest.warns(None) as record:
ft.set_params(m2=drop)
assert_array_equal([[3]], ft.fit(X).transform(X))
assert_array_equal([[3]], ft.fit_transform(X))
assert ['m3__x3'] == ft.get_feature_names()
assert record if drop is None else not record
with pytest.warns(None) as record:
ft.set_params(m3=drop)
assert_array_equal([[]], ft.fit(X).transform(X))
assert_array_equal([[]], ft.fit_transform(X))
assert [] == ft.get_feature_names()
assert record if drop is None else not record
with pytest.warns(None) as record:
# check we can change back
ft.set_params(m3=mult3)
assert_array_equal([[3]], ft.fit(X).transform(X))
assert record if drop is None else not record
with pytest.warns(None) as record:
# Check 'drop' step at construction time
ft = FeatureUnion([('m2', drop), ('m3', mult3)])
assert_array_equal([[3]], ft.fit(X).transform(X))
assert_array_equal([[3]], ft.fit_transform(X))
assert ['m3__x3'] == ft.get_feature_names()
assert record if drop is None else not record
def test_feature_union_parallel():
# test that n_jobs work for FeatureUnion
X = JUNK_FOOD_DOCS
fs = FeatureUnion([
("words", CountVectorizer(analyzer='word')),
("chars", CountVectorizer(analyzer='char')),
])
fs_parallel = FeatureUnion([
("words", CountVectorizer(analyzer='word')),
("chars", CountVectorizer(analyzer='char')),
],
n_jobs=2)
fs_parallel2 = FeatureUnion([
("words", CountVectorizer(analyzer='word')),
("chars", CountVectorizer(analyzer='char')),
],
n_jobs=2)
fs.fit(X)
X_transformed = fs.transform(X)
assert X_transformed.shape[0] == len(X)
fs_parallel.fit(X)
X_transformed_parallel = fs_parallel.transform(X)
assert X_transformed.shape == X_transformed_parallel.shape
assert_array_equal(X_transformed.toarray(),
X_transformed_parallel.toarray())
# fit_transform should behave the same
X_transformed_parallel2 = fs_parallel2.fit_transform(X)
assert_array_equal(X_transformed.toarray(),
X_transformed_parallel2.toarray())
# transformers should stay fit after fit_transform
X_transformed_parallel2 = fs_parallel2.transform(X)
assert_array_equal(X_transformed.toarray(),
X_transformed_parallel2.toarray())