def test_set_feature_union_steps():
mult2 = Mult(2)
mult2.get_feature_names = lambda: ['x2']
mult3 = Mult(3)
mult3.get_feature_names = lambda: ['x3']
mult5 = Mult(5)
mult5.get_feature_names = lambda: ['x5']
ft = FeatureUnion([('m2', mult2), ('m3', mult3)])
assert_array_equal([[2, 3]], ft.transform(np.asarray([[1]])))
assert ['m2__x2', 'm3__x3'] == ft.get_feature_names()
# Directly setting attr
ft.transformer_list = [('m5', mult5)]
assert_array_equal([[5]], ft.transform(np.asarray([[1]])))
assert ['m5__x5'] == ft.get_feature_names()
# Using set_params
ft.set_params(transformer_list=[('mock', mult3)])
assert_array_equal([[3]], ft.transform(np.asarray([[1]])))
assert ['mock__x3'] == ft.get_feature_names()
# Using set_params to replace single step
ft.set_params(mock=mult5)
assert_array_equal([[5]], ft.transform(np.asarray([[1]])))
assert ['mock__x5'] == ft.get_feature_names()
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_feature_names():
word_vect = CountVectorizer(analyzer="word")
char_vect = CountVectorizer(analyzer="char_wb", ngram_range=(3, 3))
ft = FeatureUnion([("chars", char_vect), ("words", word_vect)])
ft.fit(JUNK_FOOD_DOCS)
feature_names = ft.get_feature_names()
for feat in feature_names:
assert "chars__" in feat or "words__" in feat
assert len(feature_names) == 35
ft = FeatureUnion([("tr1", Transf())]).fit([[1]])
assert_raise_message(
AttributeError, 'Transformer tr1 (type Transf) does not provide '
'get_feature_names', ft.get_feature_names)