Python preprocessing.RobustScaler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 RobustScaler [as 别名]
def __init__(self, *args, scale=False, center=False, **kwargs):
        """
        A machine learned model.  Beyond :class:`revscoring.Model`, this
        "Learned" models implement
        :func:`~revscoring.scoring.models.Learned.fit` and
        :func:`~revscoring.scoring.models.Learned.cross_validate`.
        """
        super().__init__(*args, **kwargs)
        self.trained = None
        if scale or center:
            self.scaler = RobustScaler(with_centering=center,
                                       with_scaling=scale)
        else:
            self.scaler = None

        self.params.update({
            'scale': scale,
            'center': center
        }) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def __init__(self, options):
        self.handle_options(options)

        out_params = convert_params(
            options.get('params', {}),
            bools=['with_centering', 'with_scaling'],
            strs=['quantile_range'], 
        )

        if StrictVersion(sklearn_version) < StrictVersion(quantile_range_required_version) and 'quantile_range' in out_params.keys():
            out_params.pop('quantile_range')
            msg = 'The quantile_range option is ignored in this version of scikit-learn ({}): version {} or higher required'
            msg = msg.format(sklearn_version, quantile_range_required_version)
            messages.warn(msg)

        if 'quantile_range' in out_params.keys():
            try:
                out_params['quantile_range'] = tuple(int(i) for i in out_params['quantile_range'].split('-'))
                assert len(out_params['quantile_range']) == 2
            except:
                raise RuntimeError('Syntax Error: quantile_range requires a range, e.g., quantile_range=25-75')

        self.estimator = _RobustScaler(**out_params) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def fit(self, X):
        """Fit detector.
        Parameters
        ----------
        X : dataframe of shape (n_samples, n_features)
            The input samples.
        """
        scaler = preprocessing.RobustScaler().fit(X)
        X_train = scaler.transform(X)
        if self.hidden_neurons is None:
            self.hidden_neurons=[X_train.shape[1]//2+1,X_train.shape[1]//4+1,X_train.shape[1]//4+1,X_train.shape[1]//2+1]
        self.batch_size=X_train.shape[0]//10
        self.model=self._build_model()

        self.model.fit(X_train,X_train,epochs=self.epoch,batch_size=self.batch_size)

        return self 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def test_df_values(self):
        est1 = dpp.RobustScaler()
        est2 = dpp.RobustScaler()

        result_ar = est1.fit_transform(X)
        result_df = est2.fit_transform(df)
        if hasattr(result_df, "values"):
            result_df = result_df.values
        assert_eq_ar(result_ar, result_df)

        for attr in ["scale_", "center_"]:
            assert_eq_ar(getattr(est1, attr), getattr(est2, attr))

        assert_eq_ar(est1.transform(X), est2.transform(X))
        assert_eq_ar(est1.transform(df).values, est2.transform(X))
        assert_eq_ar(est1.transform(X), est2.transform(df).values)

        # different data types
        df["0"] = df["0"].astype("float32")
        result_ar = est1.fit_transform(X)
        result_df = est2.fit_transform(df)
        if hasattr(result_df, "values"):
            result_df = result_df.values
        assert_eq_ar(result_ar, result_df) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def transform(self, X):
        """Scale the data.

        Parameters
        ----------
        X : array-like, shape = (n_samples, n_timestamps)
            Data to scale.

        Returns
        -------
        X_new : array-like, shape = (n_samples, n_timestamps)
            Scaled data.

        """
        X = check_array(X, dtype='float64')
        scaler = SklearnRobustScaler(
            with_centering=self.with_centering,
            with_scaling=self.with_scaling,
            quantile_range=self.quantile_range
        )
        X_new = scaler.fit_transform(X.T).T
        return X_new 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def test_simple_feature_union(self):
        data = numpy.array([[0, 0], [0, 0], [2, 1], [2, 1]],
                           dtype=numpy.float32)
        model = FeatureUnion([("scaler1", StandardScaler()),
                             ("scaler2", RobustScaler())])
        model.fit(data)
        all_models = list(enumerate_pipeline_models(model))
        steps = collect_intermediate_steps(model, "feature union",
                                           [("input",
                                             FloatTensorType([None, 2]))])

        assert len(steps) == 2
        assert len(all_models) == 3

        model.transform(data)
        for step in steps:
            onnx_step = step['onnx_step']
            sess = onnxruntime.InferenceSession(onnx_step.SerializeToString())
            onnx_outputs = sess.run(None, {'input': data})
            onnx_output = onnx_outputs[0]
            skl_outputs = step['model']._debug.outputs['transform']
            assert_almost_equal(onnx_output, skl_outputs)
            compare_objects(onnx_output, skl_outputs) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [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 RobustScaler [as 别名]
def _iwp_model(self, processes, cv_folds):
        """Return the default model for the IWP regressor
        """
        # Estimators are normally objects that have a fit and predict method
        # (e.g. MLPRegressor from sklearn). To make their training easier we
        # scale the input data in advance. With Pipeline objects from sklearn
        # we can combine such steps easily since they behave like an
        # estimator object as well.
        estimator = Pipeline([
            # SVM or NN work better if we have scaled the data in the first
            # place. MinMaxScaler is the simplest one. RobustScaler or
            # StandardScaler could be an alternative.
            ("scaler", RobustScaler(quantile_range=(15, 85))),
            # The "real" estimator:
            ("estimator", MLPRegressor(max_iter=6000, early_stopping=True)),
        ])

        # To optimize the results, we try different hyper parameters by
        # using a grid search
        hidden_layer_sizes = [
            (15, 10, 3),
            #(50, 20),
        ]
        hyper_parameter = [
            {   # Hyper parameter for lbfgs solver
                'estimator__solver': ['lbfgs'],
                'estimator__activation': ['tanh'],
                'estimator__hidden_layer_sizes': hidden_layer_sizes,
                'estimator__random_state': [0, 42, 100, 3452],
                'estimator__alpha': [0.1, 0.001, 0.0001],
            },
        ]

        return GridSearchCV(
            estimator, hyper_parameter, refit=True,
            n_jobs=processes, cv=cv_folds, verbose=self.verbose,
        ) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def fit_transform(self, X):
        compact_category_counts_catscale = X / X.sum(axis=0)
        compact_category_counts_catscale_std = (
                compact_category_counts_catscale.T - compact_category_counts_catscale.mean(axis=1)).T
        return RobustScaler().fit_transform(compact_category_counts_catscale_std) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def __init__(
        self,
        base_estimator: BaseEstimator = KerasAutoEncoder(kind="feedforward_hourglass"),
        scaler: TransformerMixin = RobustScaler(),
        require_thresholds: bool = True,
        window=None,
    ):
        """
        Classifier which wraps a ``base_estimator`` and provides a diff error
        based approach to anomaly detection.

        It trains a ``scaler`` to the target **after** training, purely for
        error calculations. The underlying ``base_estimator`` is trained
        with the original, unscaled, ``y``.

        Parameters
        ----------
        base_estimator: sklearn.base.BaseEstimator
            The model to which normal ``.fit``, ``.predict`` methods will be used.
            defaults to py:class:`gordo.machine.model.models.KerasAutoEncoder` with
            ``kind='feedforward_hourglass``
        scaler: sklearn.base.TransformerMixin
            Defaults to ``sklearn.preprocessing.RobustScaler``
            Used for transforming model output and the original ``y`` to calculate
            the difference/error in model output vs expected.
        require_thresholds: bool
            Requires calculating ``thresholds_`` via a call to :func:`~DiffBasedAnomalyDetector.cross_validate`.
            If this is set (default True), but :func:`~DiffBasedAnomalyDetector.cross_validate`
            was not called before calling :func:`~DiffBasedAnomalyDetector.anomaly` an ``AttributeError``
            will be raised.
        window: int
            Window size for smoothed thresholds
        """
        self.base_estimator = base_estimator
        self.scaler = scaler
        self.require_thresholds = require_thresholds
        self.window = window 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def __init__(self, params, dataset):
        """Initializes a UMAPTransformer object.

        Args:
            params (Namespace): Contains parameters used to instantiate the transformer.
            dataset (Dataset): Dataset used to "train" the projection mapping.
        """

        # TODO: decide whether to make n_epochs a parameter
        #default_n_epochs = None
        default_n_epochs = 500

        if params.prediction_type == 'classification':
            target_metric = 'categorical'
        else:
            target_metric = 'l2'
        self.scaler = RobustScaler()
        # Use Imputer to replace missing values (NaNs) with means for each column
        self.imputer = Imputer()
        scaled_X = self.scaler.fit_transform(self.imputer.fit_transform(dataset.X))
        self.mapper = umap.UMAP(n_neighbors=params.umap_neighbors, 
                                n_components=params.umap_dim,
                                metric=params.umap_metric,
                                target_metric=target_metric,
                                target_weight=params.umap_targ_wt,
                                min_dist=params.umap_min_dist,
                                n_epochs=default_n_epochs)
        # TODO: How to deal with multitask data?
        self.mapper.fit(scaled_X, y=dataset.y.flatten())

    # **************************************************************************************** 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def ini_scaler(self, joint_transform=False):
        assert self.scaler_id in SCALER_ID
        if self.scaler_id == 'MinMaxScaler':
            self.scaler = MinMaxScaler()
        elif self.scaler_id == 'RobustScaler':
            self.scaler = RobustScaler()
        elif self.scaler_id == 'StandardScaler':
            self.scaler = StandardScaler()

        if self.train and 'DATASET' == self.scaler_level:
            f_mat = self.df[self.feature_cols]
            self.scaler.fit(f_mat)

            if joint_transform: self.df[self.feature_cols] = self.scaler.transform(f_mat) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def fit(self, X, y=None):
        self.rs = RobustScaler()
        self.rs.fit(X)
        self.center_ = pd.Series(self.rs.center_, index=X.columns)
        self.scale_ = pd.Series(self.rs.scale_, index=X.columns)
        return self 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def test_generate_import_code():
    """Assert that generate_import_code() returns the correct set of dependancies for a given pipeline."""

    pipeline = creator.Individual.from_string('GaussianNB(RobustScaler(input_matrix))', tpot_obj._pset)

    expected_code = """import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import RobustScaler
"""
    assert expected_code == generate_import_code(pipeline, tpot_obj.operators) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import RobustScaler [as 别名]
def __init__(self, feature_range, robust=0, normalize=False, truncate=False):
        self.feature_range = feature_range
        self.robust = robust
        self.normalize = normalize
        self.truncate = truncate

        if self.robust:
            self.skprepro = skpreprocessing.RobustScaler()