Python preprocessing.FunctionTransformer方法代码示例

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def __init__(self, pos_features, pipeline_obj_path):
        """
        Args:
          pos_features: list of positional features to use
          pipeline_obj_path: path to the serialized pipeline obj_path
        """
        self.pos_features = pos_features
        self.pipeline_obj_path = pipeline_obj_path

        # deserialize the pickle file
        with open(self.pipeline_obj_path, "rb") as f:
            pipeline_obj = pickle.load(f)
        self.POS_FEATURES = pipeline_obj[0]
        self.minmax_scaler = pipeline_obj[1]
        self.imp = pipeline_obj[2]

        self.funct_transform = FunctionTransformer(func=sign_log_func,
                                                   inverse_func=sign_log_func_inverse)
        # for simplicity, assume all current pos_features are the
        # same as from before
        assert self.POS_FEATURES == self.pos_features 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def __init__(
        self,
        alpha=1.0,
        threshold=0.1,
        degree=3,
        operators=None,
        dt=1.0,
        n_jobs=1,
        derivative=None,
        feature_names=None,
        kw={},
    ):
        self.alpha = alpha
        self.threshold = threshold
        self.degree = degree
        self.operators = operators
        self.n_jobs = n_jobs
        self.derivative = derivative or FunctionTransformer(func=_derivative, kw_args={"dt": dt})
        self.feature_names = feature_names
        self.kw = kw 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
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 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_different_implementations():
    random_state = 1233
    X_train, y_train = make_classification_problem()

    # Compare with chained transformations.
    tran1 = RandomIntervalSegmenter(n_intervals='sqrt',
                                    random_state=random_state)
    tran2 = RowTransformer(FunctionTransformer(func=np.mean, validate=False))
    A = tran2.fit_transform(tran1.fit_transform(X_train))

    tran = RandomIntervalFeatureExtractor(n_intervals='sqrt',
                                          features=[np.mean],
                                          random_state=random_state)
    B = tran.fit_transform(X_train)

    np.testing.assert_array_equal(A, B)


# Compare with transformer pipeline using TSFeatureUnion. 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_different_pipelines():
    random_state = 1233
    X_train, y_train = make_classification_problem()
    steps = [
        ('segment', RandomIntervalSegmenter(n_intervals='sqrt',
                                            random_state=random_state)),
        ('transform', FeatureUnion([
            ('mean', RowTransformer(
                FunctionTransformer(func=np.mean, validate=False))),
            ('std',
             RowTransformer(FunctionTransformer(func=np.std, validate=False))),
            ('slope', RowTransformer(
                FunctionTransformer(func=time_series_slope, validate=False))),
        ])),
    ]
    pipe = Pipeline(steps)
    a = pipe.fit_transform(X_train)
    tran = RandomIntervalFeatureExtractor(n_intervals='sqrt',
                                          features=[np.mean, np.std,
                                                    time_series_slope],
                                          random_state=random_state)
    b = tran.fit_transform(X_train)
    np.testing.assert_array_equal(a, b)
    np.testing.assert_array_equal(pipe.steps[0][1].intervals_, tran.intervals_) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_ColumnTransformer_pipeline():
    X_train, y_train = load_basic_motions(split="train", return_X_y=True)
    X_test, y_test = load_basic_motions(split="test", return_X_y=True)

    # using Identity function transformers (transform series to series)
    def id_func(X):
        return X
    column_transformer = ColumnTransformer([
        ('id0', FunctionTransformer(func=id_func, validate=False), ['dim_0']),
        ('id1', FunctionTransformer(func=id_func, validate=False), ['dim_1'])
    ])
    steps = [
        ('extract', column_transformer),
        ('tabularise', Tabularizer()),
        ('classify', RandomForestClassifier(n_estimators=2, random_state=1))]
    model = Pipeline(steps=steps)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    assert y_pred.shape[0] == y_test.shape[0]
    np.testing.assert_array_equal(np.unique(y_pred), np.unique(y_test)) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_FeatureUnion_pipeline():
    # pipeline with segmentation plus multiple feature extraction
    steps = [
        ('segment', RandomIntervalSegmenter(n_intervals=3)),
        ('transform', FeatureUnion([
            ('mean', RowTransformer(
                FunctionTransformer(func=np.mean, validate=False))),
            ('std',
             RowTransformer(FunctionTransformer(func=np.std, validate=False)))
        ])),
        ('clf', DecisionTreeClassifier())
    ]
    clf = Pipeline(steps)

    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)

    assert y_pred.shape[0] == y_test.shape[0]
    np.testing.assert_array_equal(np.unique(y_pred), np.unique(y_test)) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.preprocessing.Binarizer, pp.Binarizer)
        self.assertIs(df.preprocessing.FunctionTransformer,
                      pp.FunctionTransformer)
        self.assertIs(df.preprocessing.Imputer, pp.Imputer)
        self.assertIs(df.preprocessing.KernelCenterer, pp.KernelCenterer)
        self.assertIs(df.preprocessing.LabelBinarizer, pp.LabelBinarizer)
        self.assertIs(df.preprocessing.LabelEncoder, pp.LabelEncoder)
        self.assertIs(df.preprocessing.MultiLabelBinarizer, pp.MultiLabelBinarizer)
        self.assertIs(df.preprocessing.MaxAbsScaler, pp.MaxAbsScaler)
        self.assertIs(df.preprocessing.MinMaxScaler, pp.MinMaxScaler)
        self.assertIs(df.preprocessing.Normalizer, pp.Normalizer)
        self.assertIs(df.preprocessing.OneHotEncoder, pp.OneHotEncoder)
        self.assertIs(df.preprocessing.PolynomialFeatures, pp.PolynomialFeatures)
        self.assertIs(df.preprocessing.RobustScaler, pp.RobustScaler)
        self.assertIs(df.preprocessing.StandardScaler, pp.StandardScaler) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def _get_transformations_one_to_many_greater(self, feature_names):
        # results in number of features greater than original features
        # copy all features except last one. For last one, replicate columns to create 3 more features
        transformations = []
        feature_names = list(feature_names)
        index = 0
        for f in feature_names[:-1]:
            transformations.append(("{}".format(index), "passthrough", [f]))
            index += 1

        def copy_func(x):
            return np.tile(x, (1, 3))

        copy_transformer = FunctionTransformer(copy_func)

        transformations.append(("copy_transformer", copy_transformer, [feature_names[-1]]))

        return ColumnTransformer(transformations) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_multiply_by_function_transformer(self):
        from gordo.machine.model.transformer_funcs.general import multiply_by

        # Provide a require argument
        tf = FunctionTransformer(func=multiply_by, kw_args={"factor": 2})
        self._validate_transformer(tf)

        # Ignore the required argument
        tf = FunctionTransformer(func=multiply_by)
        with self.assertRaises(TypeError):
            self._validate_transformer(tf) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_transform_target_regressor_1d_transformer(X, y):
    # All transformer in scikit-learn expect 2D data. FunctionTransformer with
    # validate=False lift this constraint without checking that the input is a
    # 2D vector. We check the consistency of the data shape using a 1D and 2D y
    # array.
    transformer = FunctionTransformer(func=lambda x: x + 1,
                                      inverse_func=lambda x: x - 1,
                                      validate=False)
    regr = TransformedTargetRegressor(regressor=LinearRegression(),
                                      transformer=transformer)
    y_pred = regr.fit(X, y).predict(X)
    assert y.shape == y_pred.shape
    # consistency forward transform
    y_tran = regr.transformer_.transform(y)
    _check_shifted_by_one(y, y_tran)
    assert y.shape == y_pred.shape
    # consistency inverse transform
    assert_allclose(y, regr.transformer_.inverse_transform(
        y_tran).squeeze())
    # consistency of the regressor
    lr = LinearRegression()
    transformer2 = clone(transformer)
    lr.fit(X, transformer2.fit_transform(y))
    y_lr_pred = lr.predict(X)
    assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
    assert_allclose(regr.regressor_.coef_, lr.coef_) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_np_log():
    X = np.arange(10).reshape((5, 2))

    # Test that the numpy.log example still works.
    assert_array_equal(
        FunctionTransformer(np.log1p).transform(X),
        np.log1p(X),
    ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_kw_arg():
    X = np.linspace(0, 1, num=10).reshape((5, 2))

    F = FunctionTransformer(np.around, kw_args=dict(decimals=3))

    # Test that rounding is correct
    assert_array_equal(F.transform(X),
                       np.around(X, decimals=3)) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_kw_arg_update():
    X = np.linspace(0, 1, num=10).reshape((5, 2))

    F = FunctionTransformer(np.around, kw_args=dict(decimals=3))

    F.kw_args['decimals'] = 1

    # Test that rounding is correct
    assert_array_equal(F.transform(X), np.around(X, decimals=1)) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import FunctionTransformer [as 别名]
def test_inverse_transform():
    X = np.array([1, 4, 9, 16]).reshape((2, 2))

    # Test that inverse_transform works correctly
    F = FunctionTransformer(
        func=np.sqrt,
        inverse_func=np.around, inv_kw_args=dict(decimals=3),
    )
    assert_array_equal(
        F.inverse_transform(F.transform(X)),
        np.around(np.sqrt(X), decimals=3),
    )