Python sklearn.compose.make_column_transformer() Examples

def get_estimator():

    categorical_cols = ['Sex', 'Pclass', 'Embarked']
    numerical_cols = ['Age', 'SibSp', 'Parch', 'Fare']

    preprocessor = make_column_transformer(
        (OneHotEncoder(handle_unknown='ignore'), categorical_cols),
        (SimpleImputer(strategy='constant', fill_value=-1), numerical_cols),
    )

    pipeline = Pipeline([
        ('transformer', preprocessor),
        ('classifier', LogisticRegression()),
    ])

    return pipeline 

def get_estimator():

    categorical_cols = ['Sex', 'Pclass', 'Embarked']
    numerical_cols = ['Age', 'SibSp', 'Parch', 'Fare']

    preprocessor = make_column_transformer(
        (OneHotEncoder(handle_unknown='ignore'), categorical_cols),
        (SimpleImputer(strategy='constant', fill_value=-1), numerical_cols),
    )

    pipeline = Pipeline([
        ('transformer', preprocessor),
        ('classifier', LogisticRegression()),
    ])

    return pipeline 

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_equal(ct.transformers, make_column_transformer(
        (scaler, 'first'), (norm, ['second'])).transformers)
    assert_equal(ct.n_jobs, 3)
    assert_equal(ct.remainder, 'drop')
    assert_equal(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) 

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()
    # 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((scaler, 'first'), (norm, ['second']),
                                 remainder=remainder)
    assert ct.remainder == remainder 

def get_estimator():
    merge_transformer = FunctionTransformer(_merge_external_data,
                                            validate=False)
    categorical_cols = ['Arrival', 'Departure']
    drop_col = ['DateOfDeparture']
    preoprocessor = make_column_transformer(
        (OneHotEncoder(handle_unknown='ignore'), categorical_cols),
        ('drop', drop_col),
        remainder='passthrough'
    )
    pipeline = Pipeline(steps=[
        ('merge', merge_transformer),
        ('transfomer', preoprocessor),
        ('regressor', RandomForestRegressor(n_estimators=10, max_depth=10,
                                            max_features=10)),
    ])
    return pipeline 

def create_preprocessing_pipeline(num_columns):
    preprocessor = make_column_transformer(
        (np.arange(num_columns), StandardScaler()),
        remainder='passthrough'
    )
    return preprocessor