def test_make_column_transformer_remainder_transformer():
scaler = StandardScaler()
norm = Normalizer()
remainder = StandardScaler()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
remainder=remainder)
assert ct.remainder == remainder
def test_make_column_transformer_pandas():
pd = pytest.importorskip('pandas')
X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
X_df = pd.DataFrame(X_array, columns=['first', 'second'])
norm = Normalizer()
ct1 = ColumnTransformer([('norm', Normalizer(), X_df.columns)])
ct2 = make_column_transformer((norm, X_df.columns))
assert_almost_equal(ct1.fit_transform(X_df), ct2.fit_transform(X_df))
def test_make_column_transformer():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']))
names, transformers, columns = zip(*ct.transformers)
assert names == ("standardscaler", "normalizer")
assert transformers == (scaler, norm)
assert columns == ('first', ['second'])
def test_column_transformer_remainder():
X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
X_res_first = np.array([0, 1, 2]).reshape(-1, 1)
X_res_second = np.array([2, 4, 6]).reshape(-1, 1)
X_res_both = X_array
# default drop
ct = ColumnTransformer([('trans1', Trans(), [0])])
assert_array_equal(ct.fit_transform(X_array), X_res_first)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_first)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'drop'
assert_array_equal(ct.transformers_[-1][2], [1])
# specify passthrough
ct = ColumnTransformer([('trans', Trans(), [0])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_both)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_both)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [1])
# column order is not preserved (passed through added to end)
ct = ColumnTransformer([('trans1', Trans(), [1])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_both[:, ::-1])
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_both[:, ::-1])
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [0])
# passthrough when all actual transformers are skipped
ct = ColumnTransformer([('trans1', 'drop', [0])], remainder='passthrough')
assert_array_equal(ct.fit_transform(X_array), X_res_second)
assert_array_equal(ct.fit(X_array).transform(X_array), X_res_second)
assert len(ct.transformers_) == 2
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][1] == 'passthrough'
assert_array_equal(ct.transformers_[-1][2], [1])
# error on invalid arg
ct = ColumnTransformer([('trans1', Trans(), [0])], remainder=1)
assert_raise_message(
ValueError,
"remainder keyword needs to be one of \'drop\', \'passthrough\', "
"or estimator.", ct.fit, X_array)
assert_raise_message(
ValueError,
"remainder keyword needs to be one of \'drop\', \'passthrough\', "
"or estimator.", ct.fit_transform, X_array)
# check default for make_column_transformer
ct = make_column_transformer((Trans(), [0]))
assert ct.remainder == 'drop'
def test_make_column_transformer_kwargs():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
n_jobs=3,
remainder='drop',
sparse_threshold=0.5)
assert ct.transformers == make_column_transformer(
(scaler, 'first'), (norm, ['second'])).transformers
assert ct.n_jobs == 3
assert ct.remainder == 'drop'
assert ct.sparse_threshold == 0.5
# invalid keyword parameters should raise an error message
assert_raise_message(TypeError,
'Unknown keyword arguments: "transformer_weights"',
make_column_transformer, (scaler, 'first'),
(norm, ['second']),
transformer_weights={
'pca': 10,
'Transf': 1
})
def test_column_transformer_mixed_cols_sparse():
df = np.array([['a', 1, True], ['b', 2, False]], dtype='O')
ct = make_column_transformer((OneHotEncoder(), [0]),
('passthrough', [1, 2]),
sparse_threshold=1.0)
# this shouldn't fail, since boolean can be coerced into a numeric
# See: https://github.com/scikit-learn/scikit-learn/issues/11912
X_trans = ct.fit_transform(df)
assert X_trans.getformat() == 'csr'
assert_array_equal(X_trans.toarray(), np.array([[1, 0, 1, 1], [0, 1, 2,
0]]))
ct = make_column_transformer((OneHotEncoder(), [0]), ('passthrough', [0]),
sparse_threshold=1.0)
with pytest.raises(ValueError,
match="For a sparse output, all columns should"):
# this fails since strings `a` and `b` cannot be
# coerced into a numeric.
ct.fit_transform(df)