Python compose.make_column_transformer函数代码示例

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)

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()
    # XXX remove in v0.22
    with pytest.warns(DeprecationWarning,
                      match='`make_column_transformer` now expects'):
        ct1 = make_column_transformer((X_df.columns, norm))
    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_remainder_transformer():
    scaler = StandardScaler()
    norm = Normalizer()
    remainder = StandardScaler()
    ct = make_column_transformer(('first', scaler), (['second'], norm),
                                 remainder=remainder)
    assert ct.remainder == remainder

def test_make_column_transformer_kwargs():
    scaler = StandardScaler()
    norm = Normalizer()
    ct = make_column_transformer(('first', scaler), (['second'], norm),
                                 n_jobs=3, remainder='drop')
    assert_equal(ct.transformers, make_column_transformer(
        ('first', scaler), (['second'], norm)).transformers)
    assert_equal(ct.n_jobs, 3)
    assert_equal(ct.remainder, 'drop')
    # invalid keyword parameters should raise an error message
    assert_raise_message(
        TypeError,
        'Unknown keyword arguments: "transformer_weights"',
        make_column_transformer, ('first', scaler), (['second'], norm),
        transformer_weights={'pca': 10, 'Transf': 1}
    )

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'

def test_make_column_transformer():
    scaler = StandardScaler()
    norm = Normalizer()
    ct = make_column_transformer(('first', scaler), (['second'], norm))
    names, transformers, columns = zip(*ct.transformers)
    assert_equal(names, ("standardscaler", "normalizer"))
    assert_equal(transformers, (scaler, norm))
    assert_equal(columns, ('first', ['second']))

def test_make_column_transformer():
    scaler = StandardScaler()
    norm = Normalizer()
    ct = make_column_transformer((scaler, 'first'), (norm, ['second']))
    names, transformers, columns = zip(*ct.transformers)
    assert_equal(names, ("standardscaler", "normalizer"))
    assert_equal(transformers, (scaler, norm))
    assert_equal(columns, ('first', ['second']))

    # XXX remove in v0.22
    with pytest.warns(DeprecationWarning,
                      match='`make_column_transformer` now expects'):
        ct1 = make_column_transformer(([0], norm))
    ct2 = make_column_transformer((norm, [0]))
    X_array = np.array([[0, 1, 2], [2, 4, 6]]).T
    assert_almost_equal(ct1.fit_transform(X_array),
                        ct2.fit_transform(X_array))

    with pytest.warns(DeprecationWarning,
                      match='`make_column_transformer` now expects'):
        make_column_transformer(('first', 'drop'))

    with pytest.warns(DeprecationWarning,
                      match='`make_column_transformer` now expects'):
        make_column_transformer(('passthrough', 'passthrough'),
                                ('first', 'drop'))

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 fit(self, X, y):
     encode_columns = [item for item in X.columns if 'suit' in item]
     scale_columns = [item for item in X.columns if item not in encode_columns]
     
     self.column_transformer = make_column_transformer(
         (StandardScaler(), scale_columns),
         (OneHotEncoder(categories='auto'), encode_columns))
     self.column_transformer.fit(X)
     
     return self

# - pclass: ordinal integers {1, 2, 3}.
numeric_features = ['age', 'fare']
categorical_features = ['embarked', 'sex', 'pclass']

# Provisionally, use pd.fillna() to impute missing values for categorical
# features; SimpleImputer will eventually support strategy="constant".
data[categorical_features] = data[categorical_features].fillna(value='missing')

# We create the preprocessing pipelines for both numeric and categorical data.
numeric_transformer = make_pipeline(SimpleImputer(), StandardScaler())
categorical_transformer = CategoricalEncoder('onehot-dense',
                                             handle_unknown='ignore')

preprocessing_pl = make_column_transformer(
    (numeric_features, numeric_transformer),
    (categorical_features, categorical_transformer),
    remainder='drop'
)

# Append classifier to preprocessing pipeline.
# Now we have a full prediction pipeline.
clf = make_pipeline(preprocessing_pl, LogisticRegression())

X = data.drop('survived', axis=1)
y = data.survived.values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
                                                    shuffle=True)

clf.fit(X_train, y_train)
print("model score: %f" % clf.score(X_test, y_test))