Features

The AutoCarver.features module defines a set of features used in the AutoCarver project. This module includes classes and functions to handle different types of features, such as qualitative and quantitative features.

Features

A set of typed features

Parameters:

categoricals (list[CategoricalFeature | str], optional) – List of categorical features or column names, by default None
quantitatives (list[QuantitativeFeature | str], optional) – List of quantitative features or column names, by default None
ordinals (list[OrdinalFeature] | dict[str, list[str]], optional) – List of ordinal features or dict column names with associated value ordering, by default None

Warning

At least one of categoricals, ordinals or quantitatives should be provided.

Keyword Arguments:

ordinal_encoding (bool, optional) – Whether or not to ordinal encode labels, by default False
nan (str, optional) – Label for missing values, by default "__NAN__"
default (str, optional) – Label for default values, by default "__OTHER__"

property categoricals: list[CategoricalFeature]: Returns all categorical features

classmethod load(features_json: dict) → Features

Allows one to load a set of Features

Parameters:: features_json (dict) – Dictionary of serialized Features
Returns:: Loaded Features.
Return type:: Features

property names: list[str]: Returns names of all features

property ordinals: list[OrdinalFeature]: Returns all ordinal features

property qualitatives: list[OrdinalFeature | CategoricalFeature]: Returns all qualitative features

property quantitatives: list[QuantitativeFeature]: Returns all quantitative features

property summary: DataFrame: Summary of discretization process for all features

to_json(light_mode: bool = False) → dict

Serializes Features for JSON saving

Parameters:: light_mode (bool, optional) – Whether or not to serialize in light mode (without statistics and history), by default False

property versions: list[str]: Returns versions of all features

Qualitatitve features

class AutoCarver.features.CategoricalFeature(name: str, **kwargs)

Defines a categorical feature

Parameters:

name (str) – Name of the feature

Keyword Arguments:

ordinal_encoding (bool, optional) – Whether or not to ordinal encode labels, by default False
nan (str, optional) – Label for missing values, by default "__NAN__"
default (str, optional) – Label for default values, by default "__OTHER__"

property has_default: bool: Whether or not the feature has default values

property has_nan: bool: Wether or not feature has nans

property history: DataFrame: Feature’s combination history

is_categorical = True: Whether or not feature is categorical

is_ordinal = False: Whether or not feature is ordinal

is_qualitative = True: Whether or not feature is qualitative

property summary: dict: Summary of feature’s discretization process

class AutoCarver.features.OrdinalFeature(name: str, values: list[str], **kwargs)

Defines an ordinal feature

Parameters:: values (list[str]) – Ordered list of all unique values for the feature

property has_default: bool: Whether or not the feature has default values

property has_nan: bool: Wether or not feature has nans

property history: DataFrame: Feature’s combination history

is_categorical = False: Whether or not feature is categorical

is_ordinal = True: Whether or not feature is ordinal

is_qualitative = True: Whether or not feature is qualitative

property summary: dict: Summary of feature’s discretization process

Quantitative features

class AutoCarver.features.QuantitativeFeature(name: str, **kwargs)

Defines a quantitative feature

Parameters:

name (str) – Name of the feature

Keyword Arguments:

ordinal_encoding (bool, optional) – Whether or not to ordinal encode labels, by default False
nan (str, optional) – Label for missing values, by default "__NAN__"
default (str, optional) – Label for default values, by default "__OTHER__"

property has_default: bool: Whether or not the feature has default values

property has_nan: bool: Wether or not feature has nans

property history: DataFrame: Feature’s combination history

is_quantitative = True: Whether or not feature is quantitative

property summary: dict: Summary of feature’s discretization process