Python base.TransformerMixin方法代码示例

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def create_pandas_only_svm_classifier(X, y, probability=True):
    class PandasOnlyEstimator(TransformerMixin):
        def fit(self, X, y=None, **fitparams):
            return self

        def transform(self, X, **transformparams):
            dataset_is_df = isinstance(X, pd.DataFrame)
            if not dataset_is_df:
                raise Exception("Dataset must be a pandas dataframe!")
            return X

    pandas_only = PandasOnlyEstimator()

    clf = svm.SVC(gamma=0.001, C=100.0, probability=probability, random_state=777)
    pipeline = Pipeline([("pandas_only", pandas_only), ("clf", clf)])
    return pipeline.fit(X, y) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_template_1():
    """Assert that TPOT template option generates pipeline when each step is a type of operator."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='Selector-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 3
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_template_2():
    """Assert that TPOT template option generates pipeline when each step is operator type with a duplicate main type."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='Selector-Selector-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 4
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[3][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_template_3():
    """Assert that TPOT template option generates pipeline when one of steps is a specific operator."""

    tpot_obj = TPOTClassifier(
        random_state=42,
        verbosity=0,
        template='SelectPercentile-Transformer-Classifier'
    )
    tpot_obj._fit_init()
    pop = tpot_obj._toolbox.population(n=10)
    for deap_pipeline in pop:
        operator_count = tpot_obj._operator_count(deap_pipeline)
        sklearn_pipeline = tpot_obj._toolbox.compile(expr=deap_pipeline)
        assert operator_count == 3
        assert sklearn_pipeline.steps[0][0] == 'SelectPercentile'.lower()
        assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
        assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
        assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_template_4():
    """Assert that TPOT template option generates pipeline when one of steps is a specific operator."""

    tpot_obj = TPOTClassifier(
        population_size=5,
        generations=2,
        random_state=42,
        verbosity=0,
        config_dict = 'TPOT light',
        template='SelectPercentile-Transformer-Classifier'
    )
    tpot_obj.fit(pretest_X, pretest_y)

    assert isinstance(tpot_obj._optimized_pipeline, creator.Individual)
    assert not (tpot_obj._start_datetime is None)

    sklearn_pipeline = tpot_obj.fitted_pipeline_
    operator_count = tpot_obj._operator_count(tpot_obj._optimized_pipeline)
    assert operator_count == 3
    assert sklearn_pipeline.steps[0][0] == 'SelectPercentile'.lower()
    assert issubclass(sklearn_pipeline.steps[0][1].__class__, SelectorMixin)
    assert issubclass(sklearn_pipeline.steps[1][1].__class__, TransformerMixin)
    assert issubclass(sklearn_pipeline.steps[2][1].__class__, ClassifierMixin) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def track_selected_features(pipeline_stages, num_features):
    """

    Args:
        pipeline_stages (list [tuple[str, TransformerMixin]]): list of steps. each step is a tuple of Name and
                                                               Transformer Object.
        num_features (int):

    Returns:
        np.ndarray:
    """
    selected_features = np.arange(num_features)
    for p_name, p in pipeline_stages:
        if not isinstance(p, BaseFeatureSelector):
            continue
        p_features = p.selected_features
        selected_features = selected_features[p_features]
    return selected_features 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def create_pandas_only_svm_classifier(X, y, probability=True):
    class PandasOnlyEstimator(TransformerMixin):
        def fit(self, X, y=None, **fitparams):
            return self

        def transform(self, X, **transformparams):
            dataset_is_df = isinstance(X, pd.DataFrame)
            if not dataset_is_df:
                raise Exception("Dataset must be a pandas dataframe!")
            return X

    pandas_only = PandasOnlyEstimator()

    clf = svm.SVC(gamma=0.001, C=100., probability=probability, random_state=777)
    pipeline = Pipeline([('pandas_only', pandas_only), ('clf', clf)])
    return pipeline.fit(X, y) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def metric_wrapper(metric, scaler: Optional[TransformerMixin] = None):
    """
    Ensures that a given metric works properly when the model itself returns
    a y which is shorter than the target y, and allows scaling the data
    before applying the metrics.


    Parameters
    ----------
    metric
        Metric which must accept y_true and y_pred of the same length
    scaler :  Optional[TransformerMixin]
        Transformer which will be applied on y and y_pred before the metrics is
        calculated. Must have method `transform`, so for most scalers it must already
        be fitted on `y`.
    """

    @functools.wraps(metric)
    def _wrapper(y_true, y_pred, *args, **kwargs):
        if scaler:
            logger.debug(
                "Transformer provided to metrics wrapper, scaling y and y_pred before "
                "passing to metrics"
            )
            y_true = scaler.transform(y_true)
            y_pred = scaler.transform(y_pred)
        return metric(y_true[-len(y_pred) :], y_pred, *args, **kwargs)

    return _wrapper 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [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 base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_clone_pandas_dataframe():

    class DummyEstimator(BaseEstimator, TransformerMixin):
        """This is a dummy class for generating numerical features

        This feature extractor extracts numerical features from pandas data
        frame.

        Parameters
        ----------

        df: pandas data frame
            The pandas data frame parameter.

        Notes
        -----
        """
        def __init__(self, df=None, scalar_param=1):
            self.df = df
            self.scalar_param = scalar_param

        def fit(self, X, y=None):
            pass

        def transform(self, X):
            pass

    # build and clone estimator
    d = np.arange(10)
    df = MockDataFrame(d)
    e = DummyEstimator(df, scalar_param=1)
    cloned_e = clone(e)

    # the test
    assert (e.df == cloned_e.df).values.all()
    assert_equal(e.scalar_param, cloned_e.scalar_param) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def vectorizer_factory(self) -> TransformerMixin:
        raise NotImplementedError 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def transformer_factory(self) -> TransformerMixin:
        return LatentDirichletAllocation(n_components=self.width, learning_method='online', random_state=71) 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def _generate_bases_test(est, pd_est):
    def test(self):
        self.assertTrue(isinstance(pd_est, FrameMixin), pd_est)
        self.assertFalse(isinstance(est, FrameMixin))
        self.assertTrue(isinstance(pd_est, base.BaseEstimator))
        try:
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.DensityMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        except:
            if _sklearn_ver > 17:
                raise
            mixins = [
                base.ClassifierMixin,
                base.ClusterMixin,
                base.BiclusterMixin,
                base.TransformerMixin,
                base.MetaEstimatorMixin,
                base.ClassifierMixin,
                base.RegressorMixin]
        for mixin in mixins:
            self.assertEqual(
                isinstance(pd_est, mixin),
                isinstance(est, mixin),
                mixin)

    return test 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_get_params_without_init(self, teardown):
        """Test edge case where the base class does not define
        an __init__ method. get_params should resolve to object.__init__
        which results in an empty dict.
        """

        class TransformerWithoutInit(TransformerMixin, BaseEstimator):
            pass

        class TransformerWithoutInitStep(Step, TransformerWithoutInit):
            pass

        step = TransformerWithoutInitStep()
        assert step.get_params() == {} 

# 需要导入模块: from sklearn import base [as 别名]
# 或者: from sklearn.base import TransformerMixin [as 别名]
def test_basic():
    bags = [np.random.normal(5, 3, size=(np.random.randint(10, 100), 20))
            for _ in xrange(50)]
    feats = Features(bags, stack=True)

    stder = BagStandardizer()
    stdized = stder.fit_transform(bags)
    stdized.make_stacked()

    assert np.allclose(np.mean(stdized.stacked_features), 0)
    assert np.allclose(np.std(stdized.stacked_features), 1)

    first_five = stder.transform(bags[:5])
    assert first_five == stdized[:5]

    minmaxer = BagMinMaxScaler([3, 7])
    minmaxed = minmaxer.fit_transform(feats)
    minmaxed.make_stacked()
    assert np.allclose(np.min(minmaxed.stacked_features, 0), 3)
    assert np.allclose(np.max(minmaxed.stacked_features, 0), 7)

    normer = BagNormalizer('l1')
    normed = normer.fit_transform(Features(bags))
    normed.make_stacked()
    assert np.allclose(np.sum(np.abs(normed.stacked_features), 1), 1)

    class GetMean(BaseEstimator, TransformerMixin):
        def fit(self, X, y=None):
            return self
        def transform(self, X):
            return X.mean(axis=1)[None, :]
    m = BagPreprocesser(GetMean())
    assert_raises(ValueError, lambda: m.transform(bags))