feature

Represent a feature object.

Classes:

Name	Description
BaseFeature	Base Feature used if no convenient available feature.
NumericalFeature	Numerical feature.
CategoricalFeature	Categorical feature.
MultivariateNumericalFeature	MultivariateNumericalFeature feature.
UnivariateSynchronousTimeSerie	UnivariateSynchronousTimeSerie feature.
UnivariateAsynchronousTimeSerie	UnivariateAsynchronousTimeSerie feature.
MultivariateSynchronousTimeSerie	MultivariateSynchronousTimeSerie feature.
MultivariateAsynchronousTimeSerie	MultivariateAsynchronousTimeSerie feature.
Metadata	Metadata.

Attributes:

Name	Type	Description
ExposedFeature
Feature

__all__ = ['BaseFeature', 'CategoricalFeature', 'ExposedFeature', 'Feature', 'Metadata', 'MultivariateAsynchronousTimeSerie', 'MultivariateNumericalFeature', 'MultivariateSynchronousTimeSerie', 'NumericalFeature', 'UnivariateAsynchronousTimeSerie', 'UnivariateSynchronousTimeSerie']

ExposedFeature = ExposedCategoricalFeature | ExposedCategoricalFeatureList | ExposedNumericalFeature | ExposedMultivariateNumericalFeature | ExposedUnivariateSynchronousTimeSerie | ExposedUnivariateAsynchronousTimeSerie | ExposedMultivariateSynchronousTimeSerie | ExposedMultivariateAsynchronousTimeSerie | ExposedMetadata

EXPOSED_FEATURE_TYPE = TypeVar('EXPOSED_FEATURE_TYPE', bound=ExposedFeature)

Feature = NumericalFeature | CategoricalFeature | MultivariateNumericalFeature | UnivariateSynchronousTimeSerie | UnivariateAsynchronousTimeSerie | MultivariateSynchronousTimeSerie | MultivariateAsynchronousTimeSerie | Metadata

AbstractDataElement

Represent a schema column, with a name.

Parameters:

Name	Type	Description	Default
name	str		required

Attributes:

Name	Type	Description
name	str

name: str

TargetableFeature

A feature that can be a target.

Parameters:

Name	Type	Description	Default
is_target	bool		False

Attributes:

Name	Type	Description
is_target	bool

is_target: bool = False

BaseFeature

Base Feature used if no convenient available feature.

Methods:

Name	Description
from_exposed	BaseFeature from ExposedBaseFeature.

Attributes:

Name	Type	Description
as_exposed	ExposedBaseFeature	NumericalFeature as ExposedNumericalFeature.

as_exposed: ExposedBaseFeature

NumericalFeature as ExposedNumericalFeature.

from_exposed(exposed_feature: ExposedBaseFeature) -> Self

BaseFeature from ExposedBaseFeature.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedBaseFeature) -> Self:
    """BaseFeature from ExposedBaseFeature."""
    return cls(**msgspec_asdict(exposed_feature))

ExplainableFeature

Define a feature object.

Parameters:

Name	Type	Description	Default
preprocessor	SklearnPreprocessor | IdentityPreprocessor	feature preprocessor function used to preprocess the data.	required

Methods:

Name	Description
from_exposed	Feature from exposed feature.

Attributes:

Name	Type	Description
preprocessor	TorchPreprocessor | SklearnPreprocessor | IdentityPreprocessor
as_exposed	EXPOSED_FEATURE_TYPE	Feature as exposed feature.

preprocessor: TorchPreprocessor | SklearnPreprocessor | IdentityPreprocessor = field(kw_only=True)

as_exposed: EXPOSED_FEATURE_TYPE

Feature as exposed feature.

from_exposed(exposed_feature: EXPOSED_FEATURE_TYPE) -> Self

Feature from exposed feature.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: EXPOSED_FEATURE_TYPE) -> Self:
    """Feature from exposed feature."""
    raise NotImplementedError

NumericalFeature

Numerical feature.

It represents quantifiable values that can be measured and ordered. Its values may be continuous (e.g., real numbers) or discrete (e.g., integers). For instance, "age" or "price" could be set as numerical features.

Methods:

Name	Description
from_exposed	NumericalFeature from ExposedNumericalFeature.

Attributes:

Name	Type	Description
as_exposed	ExposedNumericalFeature	NumericalFeature as ExposedNumericalFeature.

as_exposed: ExposedNumericalFeature

NumericalFeature as ExposedNumericalFeature.

from_exposed(exposed_feature: ExposedNumericalFeature) -> Self

NumericalFeature from ExposedNumericalFeature.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedNumericalFeature) -> Self:
    """NumericalFeature from ExposedNumericalFeature."""
    return cast(Self, cls._from_exposed(exposed_feature))

CategoricalFeature

Categorical feature.

It represents data that can be divided into distinct groups or categories.

It may be nominal or ordinal. For instance, "Education level" or "gender" could be set as categorical features.

Parameters:

Name	Type	Description	Default
categories	list[Union[str, int, bool]]		required

Methods:

Name	Description
from_exposed	CategoricalFeature from ExposedCategoricalFeature.

Attributes:

Name	Type	Description
categories	list[str | int | bool]
as_exposed	ExposedCategoricalFeature	CategoricalFeature as ExposedCategoricalFeature.

categories: list[str | int | bool] = field(kw_only=True)

as_exposed: ExposedCategoricalFeature

CategoricalFeature as ExposedCategoricalFeature.

from_exposed(exposed_feature: ExposedCategoricalFeature) -> Self

CategoricalFeature from ExposedCategoricalFeature.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedCategoricalFeature) -> Self:
    """CategoricalFeature from ExposedCategoricalFeature."""
    return cast(Self, cls._from_exposed(exposed_feature))

MultivariateNumericalFeature

MultivariateNumericalFeature feature.

It represents numerical data points divided into several channels. Oppositely as time serie features, there is no time relationship between points here.

Parameters:

Name	Type	Description	Default
size	int	Number of channels	required
channel_names	List[str] | None	List of channel names, optional.	None.

Methods:

Name	Description
from_exposed	MultivariateNumericalFeature from ExposedMultivariateNumericalFeature.

Attributes:

Name	Type	Description
size	int
channel_names	list[str] | None
as_exposed	ExposedMultivariateNumericalFeature	MultivariateNumericalFeature as ExposedMultivariateNumericalFeature.

size: int = field(kw_only=True)

channel_names: list[str] | None = field(default=None, kw_only=True)

as_exposed: ExposedMultivariateNumericalFeature

MultivariateNumericalFeature as ExposedMultivariateNumericalFeature.

from_exposed(exposed_feature: ExposedMultivariateNumericalFeature) -> Self

MultivariateNumericalFeature from ExposedMultivariateNumericalFeature.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedMultivariateNumericalFeature) -> Self:
    """MultivariateNumericalFeature from ExposedMultivariateNumericalFeature."""
    return cast(Self, cls._from_exposed(exposed_feature))

UnivariateSynchronousTimeSerie

UnivariateSynchronousTimeSerie feature.

It represents a time serie with a single channel, already synchronized (no dynamic time warping required).

Parameters:

Name	Type	Description	Default
size	int	The size of the time series. This typically refers to the number of time points or observations in the time series.	required
mirrored_channel	str | None	Used in XpViz. Indeed, if the same channel is used for both input (as a lookback, under a first feature object) and target (as a horizon to predict, under a second feature object), this parameter may be specified to visualize on the same curve both features, (the lookback and its corresponding horizon).	None.

Methods:

Name	Description
from_exposed	UnivariateSynchronousTimeSerie from ExposedUnivariateSynchronousTimeSerie.

Attributes:

Name	Type	Description
size	int
mirrored_channel	str | None
as_exposed	ExposedUnivariateSynchronousTimeSerie	UnivariateSynchronousTimeSerie as ExposedUnivariateSynchronousTimeSerie.

size: int = field(kw_only=True)

mirrored_channel: str | None = field(default=None, kw_only=True)

as_exposed: ExposedUnivariateSynchronousTimeSerie

UnivariateSynchronousTimeSerie as ExposedUnivariateSynchronousTimeSerie.

from_exposed(exposed_feature: ExposedUnivariateSynchronousTimeSerie) -> Self

UnivariateSynchronousTimeSerie from ExposedUnivariateSynchronousTimeSerie.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedUnivariateSynchronousTimeSerie) -> Self:
    """UnivariateSynchronousTimeSerie from ExposedUnivariateSynchronousTimeSerie."""
    return cast(Self, cls._from_exposed(exposed_feature))

UnivariateAsynchronousTimeSerie

UnivariateAsynchronousTimeSerie feature.

This class represents a univariate time series that is not synchronized, meaning that it does require Dynamic Time Warping (DTW). The DTW will be applied automatically if this feature is chosen.

Parameters:

Name	Type	Description	Default
size	int	The size of the time series. This typically refers to the number of time points or observations in the time series.	required
mirrored_channel	str | None	Used in XpViz. Indeed, if the same channel is used for both input (as a lookback, under a first feature object) and target (as a horizon to predict, under a second feature object), this parameter may be specified to visualize on the same curve both features, (the lookback and its corresponding horizon).	None.

Methods:

Name	Description
from_exposed	UnivariateAsynchronousTimeSerie from ExposedUnivariateAsynchronousTimeSerie.

Attributes:

Name	Type	Description
size	int
mirrored_channel	str | None
as_exposed	ExposedUnivariateAsynchronousTimeSerie	UnivariateAsynchronousTimeSerie as ExposedUnivariateAsynchronousTimeSerie.

size: int = field(kw_only=True)

mirrored_channel: str | None = field(default=None, kw_only=True)

as_exposed: ExposedUnivariateAsynchronousTimeSerie

UnivariateAsynchronousTimeSerie as ExposedUnivariateAsynchronousTimeSerie.

from_exposed(exposed_feature: ExposedUnivariateAsynchronousTimeSerie) -> Self

UnivariateAsynchronousTimeSerie from ExposedUnivariateAsynchronousTimeSerie.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedUnivariateAsynchronousTimeSerie) -> Self:
    """UnivariateAsynchronousTimeSerie from ExposedUnivariateAsynchronousTimeSerie."""
    return cast(Self, cls._from_exposed(exposed_feature))

MultivariateSynchronousTimeSerie

MultivariateSynchronousTimeSerie feature.

This class represents a multivariate time series (multiple channels), already synchronized (no dynamic time warping required).

Parameters:

Name	Type	Description	Default
size	tuple	Sequence_length x Number of channels	required
channel_names	List[str] | None	List of channel names, optional.	None.

Methods:

Name	Description
from_exposed	MultivariateSynchronousTimeSerie from ExposedMultivariateSynchronousTimeSerie.

Attributes:

Name	Type	Description
size	list[int]
channel_names	str | None
as_exposed	ExposedMultivariateSynchronousTimeSerie	MultivariateSynchronousTimeSerie as ExposedMultivariateSynchronousTimeSerie.

size: list[int] = field(kw_only=True)

channel_names: str | None = field(default=None, kw_only=True)

as_exposed: ExposedMultivariateSynchronousTimeSerie

MultivariateSynchronousTimeSerie as ExposedMultivariateSynchronousTimeSerie.

from_exposed(exposed_feature: ExposedMultivariateSynchronousTimeSerie) -> Self

MultivariateSynchronousTimeSerie from ExposedMultivariateSynchronousTimeSerie.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedMultivariateSynchronousTimeSerie) -> Self:
    """MultivariateSynchronousTimeSerie from ExposedMultivariateSynchronousTimeSerie."""
    return cast(Self, cls._from_exposed(exposed_feature))

MultivariateAsynchronousTimeSerie

MultivariateAsynchronousTimeSerie feature.

This class represents a multivariate time series (multiple channels), that is not synchronized, meaning that it does require Dynamic Time Warping (DTW). The DTW will be applied automatically if this feature is chosen.

Parameters:

Name	Type	Description	Default
size	tuple	Sequence_length x Number of channels	required
channel_names	List[str] | None	List of channel names, optional.	None.

Methods:

Name	Description
from_exposed	MultivariateAsynchronousTimeSerie from ExposedMultivariateAsynchronousTimeSerie.

Attributes:

Name	Type	Description
size	list[int]
channel_names	list[str] | None
as_exposed	ExposedMultivariateAsynchronousTimeSerie	MultivariateAsynchronousTimeSerie as ExposedMultivariateAsynchronousTimeSerie.

size: list[int] = field(kw_only=True)

channel_names: list[str] | None = field(default=None, kw_only=True)

as_exposed: ExposedMultivariateAsynchronousTimeSerie

MultivariateAsynchronousTimeSerie as ExposedMultivariateAsynchronousTimeSerie.

from_exposed(exposed_feature: ExposedMultivariateAsynchronousTimeSerie) -> Self

MultivariateAsynchronousTimeSerie from ExposedMultivariateAsynchronousTimeSerie.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_feature: ExposedMultivariateAsynchronousTimeSerie) -> Self:
    """MultivariateAsynchronousTimeSerie from ExposedMultivariateAsynchronousTimeSerie."""
    return cast(Self, cls._from_exposed(exposed_feature))

Metadata

Metadata.

Represents a metadata, for instance the "index_xp_deep" metadata, cf doc dataset/concept.

Methods:

Name	Description
from_exposed	Create Metadata from exposed metadata.

Attributes:

Name	Type	Description
as_exposed	ExposedMetadata	Generate the corresponding exposed feature.

as_exposed: ExposedMetadata

Generate the corresponding exposed feature.

from_exposed(exposed_metadata: ExposedMetadata) -> Self

Create Metadata from exposed metadata.

Source code in src/xpdeep/dataset/schema/feature/feature.py

@classmethod
def from_exposed(cls, exposed_metadata: ExposedMetadata) -> Self:
    """Create Metadata from exposed metadata."""
    return cls(name=exposed_metadata.name)