synthcity.plugins.core.models.feature_encoder module

class BayesianGMMEncoder(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

Bayesian Gaussian Mixture encoder

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class DatetimeEncoder(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

Datetime variables encoder

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 1

n_dim_out: int = 1

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class FeatureEncoder(*args: Any, **kwargs: Any)

Bases: sklearn.base.TransformerMixin, sklearn.base.BaseEstimator

Base feature encoder with sklearn-style API.

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 1

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class GaussianQuantileTransformer(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

Quantile transformer with Gaussian distribution

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class LabelEncoder(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = True

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 1

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class MinMaxScaler(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class OneHotEncoder(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = True

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

handle_unknown = 'ignore'

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class OrdinalEncoder(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = True

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class RobustScaler(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

class StandardScaler(*args: Any, **kwargs: Any)

Bases: synthcity.plugins.core.models.feature_encoder.FeatureEncoder

categorical: bool = False

feature_name_in: str

feature_names_out: List[str]

feature_types_out: List[str]

fit(x: pandas.core.series.Series, y: Any = None, **kwargs: Any) → Any

get_feature_names_out() → List[str]

get_feature_types_out(output: numpy.ndarray) → List[str]

inverse_transform(df: Union[pandas.core.frame.DataFrame, pandas.core.series.Series]) → pandas.core.series.Series

n_dim_in: int = 2

n_dim_out: int = 2

n_features_out: int

transform(x: pandas.core.series.Series) → Union[pandas.core.frame.DataFrame, pandas.core.series.Series]

classmethod wraps(encoder_class: sklearn.base.TransformerMixin, **params: Any) → Type[Any]: Wraps sklearn transformer to FeatureEncoder.

validate_shape(x: numpy.ndarray, n_dim: int) → numpy.ndarray