Python ColumnTransformer.fit_transform方法代码示例

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_special_strings():

    # one 'drop' -> ignore
    X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
    ct = ColumnTransformer(
        [('trans1', Trans(), [0]), ('trans2', 'drop', [1])])
    exp = np.array([[0.], [1.], [2.]])
    assert_array_equal(ct.fit_transform(X_array), exp)
    assert_array_equal(ct.fit(X_array).transform(X_array), exp)

    # all 'drop' -> return shape 0 array
    ct = ColumnTransformer(
        [('trans1', 'drop', [0]), ('trans2', 'drop', [1])])
    assert_array_equal(ct.fit(X_array).transform(X_array).shape, (3, 0))
    assert_array_equal(ct.fit_transform(X_array).shape, (3, 0))

    # 'passthrough'
    X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
    ct = ColumnTransformer(
        [('trans1', Trans(), [0]), ('trans2', 'passthrough', [1])])
    exp = X_array
    assert_array_equal(ct.fit_transform(X_array), exp)
    assert_array_equal(ct.fit(X_array).transform(X_array), exp)

    # None itself / other string is not valid
    for val in [None, 'other']:
        ct = ColumnTransformer(
            [('trans1', Trans(), [0]), ('trans2', None, [1])])
        assert_raise_message(TypeError, "All estimators should implement",
                             ct.fit_transform, X_array)
        assert_raise_message(TypeError, "All estimators should implement",
                             ct.fit, X_array)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_sparse_array():
    X_sparse = sparse.eye(3, 2).tocsr()

    # no distinction between 1D and 2D
    X_res_first = X_sparse[:, 0]
    X_res_both = X_sparse

    for col in [0, [0], slice(0, 1)]:
        for remainder, res in [('drop', X_res_first),
                               ('passthrough', X_res_both)]:
            ct = ColumnTransformer([('trans', Trans(), col)],
                                   remainder=remainder,
                                   sparse_threshold=0.8)
            assert sparse.issparse(ct.fit_transform(X_sparse))
            assert_allclose_dense_sparse(ct.fit_transform(X_sparse), res)
            assert_allclose_dense_sparse(ct.fit(X_sparse).transform(X_sparse),
                                         res)

    for col in [[0, 1], slice(0, 2)]:
        ct = ColumnTransformer([('trans', Trans(), col)],
                               sparse_threshold=0.8)
        assert sparse.issparse(ct.fit_transform(X_sparse))
        assert_allclose_dense_sparse(ct.fit_transform(X_sparse), X_res_both)
        assert_allclose_dense_sparse(ct.fit(X_sparse).transform(X_sparse),
                                     X_res_both)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_callable_specifier():
    # assert that function gets the full array / dataframe
    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
    X_res_first = np.array([[0, 1, 2]]).T

    def func(X):
        assert_array_equal(X, X_array)
        return [0]

    ct = ColumnTransformer([('trans', Trans(), func)],
                           remainder='drop')
    assert_array_equal(ct.fit_transform(X_array), X_res_first)
    assert_array_equal(ct.fit(X_array).transform(X_array), X_res_first)

    pd = pytest.importorskip('pandas')
    X_df = pd.DataFrame(X_array, columns=['first', 'second'])

    def func(X):
        assert_array_equal(X.columns, X_df.columns)
        assert_array_equal(X.values, X_df.values)
        return ['first']

    ct = ColumnTransformer([('trans', Trans(), func)],
                           remainder='drop')
    assert_array_equal(ct.fit_transform(X_df), X_res_first)
    assert_array_equal(ct.fit(X_df).transform(X_df), X_res_first)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
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(([0], Trans()))
    assert ct.remainder == 'drop'

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer():
    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T

    X_res_first1D = np.array([0, 1, 2])
    X_res_second1D = np.array([2, 4, 6])
    X_res_first = X_res_first1D.reshape(-1, 1)
    X_res_both = X_array

    cases = [
        # single column 1D / 2D
        (0, X_res_first),
        ([0], X_res_first),
        # list-like
        ([0, 1], X_res_both),
        (np.array([0, 1]), X_res_both),
        # slice
        (slice(0, 1), X_res_first),
        (slice(0, 2), X_res_both),
        # boolean mask
        (np.array([True, False]), X_res_first),
    ]

    for selection, res in cases:
        ct = ColumnTransformer([('trans', Trans(), selection)],
                               remainder='drop')
        assert_array_equal(ct.fit_transform(X_array), res)
        assert_array_equal(ct.fit(X_array).transform(X_array), res)

        # callable that returns any of the allowed specifiers
        ct = ColumnTransformer([('trans', Trans(), lambda x: selection)],
                               remainder='drop')
        assert_array_equal(ct.fit_transform(X_array), res)
        assert_array_equal(ct.fit(X_array).transform(X_array), res)

    ct = ColumnTransformer([('trans1', Trans(), [0]),
                            ('trans2', Trans(), [1])])
    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

    # test with transformer_weights
    transformer_weights = {'trans1': .1, 'trans2': 10}
    both = ColumnTransformer([('trans1', Trans(), [0]),
                              ('trans2', Trans(), [1])],
                             transformer_weights=transformer_weights)
    res = np.vstack([transformer_weights['trans1'] * X_res_first1D,
                     transformer_weights['trans2'] * X_res_second1D]).T
    assert_array_equal(both.fit_transform(X_array), res)
    assert_array_equal(both.fit(X_array).transform(X_array), res)
    assert len(both.transformers_) == 2

    both = ColumnTransformer([('trans', Trans(), [0, 1])],
                             transformer_weights={'trans': .1})
    assert_array_equal(both.fit_transform(X_array), 0.1 * X_res_both)
    assert_array_equal(both.fit(X_array).transform(X_array), 0.1 * X_res_both)
    assert len(both.transformers_) == 1

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_negative_column_indexes():
    X = np.random.randn(2, 2)
    X_categories = np.array([[1], [2]])
    X = np.concatenate([X, X_categories], axis=1)

    ohe = OneHotEncoder(categories='auto')

    tf_1 = ColumnTransformer([('ohe', ohe, [-1])], remainder='passthrough')
    tf_2 = ColumnTransformer([('ohe', ohe,  [2])], remainder='passthrough')
    assert_array_equal(tf_1.fit_transform(X), tf_2.fit_transform(X))

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_cloning():
    X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T

    ct = ColumnTransformer([('trans', StandardScaler(), [0])])
    ct.fit(X_array)
    assert_false(hasattr(ct.transformers[0][1], 'mean_'))
    assert_true(hasattr(ct.transformers_[0][1], 'mean_'))

    ct = ColumnTransformer([('trans', StandardScaler(), [0])])
    ct.fit_transform(X_array)
    assert_false(hasattr(ct.transformers[0][1], 'mean_'))
    assert_true(hasattr(ct.transformers_[0][1], 'mean_'))

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_remainder_numpy(key):
    # test different ways that columns are specified with passthrough
    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
    X_res_both = X_array

    ct = ColumnTransformer([('trans1', Trans(), key)],
                           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)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
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))

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_remainder_pandas(key):
    # test different ways that columns are specified with passthrough
    pd = pytest.importorskip('pandas')

    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
    X_df = pd.DataFrame(X_array, columns=['first', 'second'])
    X_res_both = X_array

    ct = ColumnTransformer([('trans1', Trans(), key)],
                           remainder='passthrough')
    assert_array_equal(ct.fit_transform(X_df), X_res_both)
    assert_array_equal(ct.fit(X_df).transform(X_df), X_res_both)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_no_remaining_remainder_transformer():
    X_array = np.array([[0, 1, 2],
                        [2, 4, 6],
                        [8, 6, 4]]).T

    ct = ColumnTransformer([('trans1', Trans(), [0, 1, 2])],
                           remainder=DoubleTrans())

    assert_array_equal(ct.fit_transform(X_array), X_array)
    assert_array_equal(ct.fit(X_array).transform(X_array), X_array)
    assert len(ct.transformers_) == 1
    assert ct.transformers_[-1][0] != 'remainder'

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
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 passthrough
    ct = ColumnTransformer([('trans', Trans(), [0])])
    assert_array_equal(ct.fit_transform(X_array), X_res_both)
    assert_array_equal(ct.fit(X_array).transform(X_array), X_res_both)

    # specify to drop remaining columns
    ct = ColumnTransformer([('trans1', Trans(), [0])],
                           remainder='drop')
    assert_array_equal(ct.fit_transform(X_array), X_res_first)
    assert_array_equal(ct.fit(X_array).transform(X_array), X_res_first)

    # 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])

    # 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)

    # error on invalid arg
    ct = ColumnTransformer([('trans1', Trans(), [0])], remainder=1)
    assert_raise_message(
        ValueError,
        "remainder keyword needs to be one of \'drop\' or \'passthrough\'",
        ct.fit, X_array)
    assert_raise_message(
        ValueError,
        "remainder keyword needs to be one of \'drop\' or \'passthrough\'",
        ct.fit_transform, X_array)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_empty_columns(pandas, column):
    # test case that ensures that the column transformer does also work when
    # a given transformer doesn't have any columns to work on
    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
    X_res_both = X_array

    if pandas:
        pd = pytest.importorskip('pandas')
        X = pd.DataFrame(X_array, columns=['first', 'second'])
    else:
        X = X_array

    ct = ColumnTransformer([('trans1', Trans(), [0, 1]),
                            ('trans2', Trans(), column)])
    assert_array_equal(ct.fit_transform(X), X_res_both)
    assert_array_equal(ct.fit(X).transform(X), X_res_both)
    assert len(ct.transformers_) == 2
    assert isinstance(ct.transformers_[1][1], Trans)

    ct = ColumnTransformer([('trans1', Trans(), column),
                            ('trans2', Trans(), [0, 1])])
    assert_array_equal(ct.fit_transform(X), X_res_both)
    assert_array_equal(ct.fit(X).transform(X), X_res_both)
    assert len(ct.transformers_) == 2
    assert isinstance(ct.transformers_[0][1], Trans)

    ct = ColumnTransformer([('trans', Trans(), column)],
                           remainder='passthrough')
    assert_array_equal(ct.fit_transform(X), X_res_both)
    assert_array_equal(ct.fit(X).transform(X), X_res_both)
    assert len(ct.transformers_) == 2  # including remainder
    assert isinstance(ct.transformers_[0][1], Trans)

    fixture = np.array([[], [], []])
    ct = ColumnTransformer([('trans', Trans(), column)],
                           remainder='drop')
    assert_array_equal(ct.fit_transform(X), fixture)
    assert_array_equal(ct.fit(X).transform(X), fixture)
    assert len(ct.transformers_) == 2  # including remainder
    assert isinstance(ct.transformers_[0][1], Trans)

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_sparse_threshold():
    X_array = np.array([['a', 'b'], ['A', 'B']], dtype=object).T
    # above data has sparsity of 4 / 8 = 0.5

    # apply threshold even if all sparse
    col_trans = ColumnTransformer([('trans1', OneHotEncoder(), [0]),
                                   ('trans2', OneHotEncoder(), [1])],
                                  sparse_threshold=0.2)
    res = col_trans.fit_transform(X_array)
    assert not sparse.issparse(res)
    assert not col_trans.sparse_output_

    # mixed -> sparsity of (4 + 2) / 8 = 0.75
    for thres in [0.75001, 1]:
        col_trans = ColumnTransformer(
            [('trans1', OneHotEncoder(sparse=True), [0]),
             ('trans2', OneHotEncoder(sparse=False), [1])],
            sparse_threshold=thres)
        res = col_trans.fit_transform(X_array)
        assert sparse.issparse(res)
        assert col_trans.sparse_output_

    for thres in [0.75, 0]:
        col_trans = ColumnTransformer(
            [('trans1', OneHotEncoder(sparse=True), [0]),
             ('trans2', OneHotEncoder(sparse=False), [1])],
            sparse_threshold=thres)
        res = col_trans.fit_transform(X_array)
        assert not sparse.issparse(res)
        assert not col_trans.sparse_output_

    # if nothing is sparse -> no sparse
    for thres in [0.33, 0, 1]:
        col_trans = ColumnTransformer(
            [('trans1', OneHotEncoder(sparse=False), [0]),
             ('trans2', OneHotEncoder(sparse=False), [1])],
            sparse_threshold=thres)
        res = col_trans.fit_transform(X_array)
        assert not sparse.issparse(res)
        assert not col_trans.sparse_output_

# 需要导入模块: from sklearn.compose import ColumnTransformer [as 别名]
# 或者: from sklearn.compose.ColumnTransformer import fit_transform [as 别名]
def test_column_transformer_no_estimators():
    X_array = np.array([[0, 1, 2],
                        [2, 4, 6],
                        [8, 6, 4]]).astype('float').T
    ct = ColumnTransformer([], remainder=StandardScaler())

    params = ct.get_params()
    assert params['remainder__with_mean']

    X_trans = ct.fit_transform(X_array)
    assert X_trans.shape == X_array.shape
    assert len(ct.transformers_) == 1
    assert ct.transformers_[-1][0] == 'remainder'
    assert ct.transformers_[-1][2] == [0, 1, 2]