jpt.distributions.univariate.distribution

Attributes

`SYMBOLIC`
`NUMERIC`
`CONTINUOUS`
`DISCRETE`

Classes

`ValueMap`
`Identity`	Simple identity mapping that mimics the __getitem__ protocol of dicts.
`Distribution`	Abstract supertype of all domains and distributions

Module Contents

jpt.distributions.univariate.distribution.SYMBOLIC = 'symbolic'

jpt.distributions.univariate.distribution.NUMERIC = 'numeric'

jpt.distributions.univariate.distribution.CONTINUOUS = 'continuous'

jpt.distributions.univariate.distribution.DISCRETE = 'discrete'

class jpt.distributions.univariate.distribution.ValueMap

Bases: collections.abc.Hashable

abstract __iter__()

abstract __len__()

abstract __getitem__(label: Any)

abstract __hash__()

property map

abstract __eq__(other)

abstract __contains__(item)

class jpt.distributions.univariate.distribution.Identity

Bases: ValueMap

Simple identity mapping that mimics the __getitem__ protocol of dicts.

__getitem__(item)

property map

__eq__(o)

__hash__()

__contains__(item)

class jpt.distributions.univariate.distribution.Distribution(**settings)

Abstract supertype of all domains and distributions

values: ValueMap = None

labels: ValueMap = None

SETTINGS

_cl = 'jpt.distributions.univariate.distribution.Distribution'

settings

__getattr__(name)

classmethod hash()

Abstractmethod:

__hash__()

__getitem__(value)

classmethod value2label(value)

Abstractmethod:

classmethod label2value(label)

Abstractmethod:

abstract _sample(n: int) → Iterable

abstract _sample_one()

sample(n: int) → Iterable

sample_one() → Any

abstract p(value) → float

abstract _p(value) → float

abstract mpe()

abstract crop(restriction: Set) → Distribution

abstract _crop(restriction: Set) → Distribution

abstract entropy() → float

static merge(distributions: Iterable[Distribution], weights: Iterable[numbers.Real]) → Distribution

Abstractmethod:

abstract update(dist: Distribution, weight: float) → Distribution

abstract fit(data: numpy.ndarray, rows: numpy.ndarray = None, col: numbers.Integral = None) → Distribution

abstract _fit(data: numpy.ndarray, rows: numpy.ndarray = None, col: numbers.Integral = None) → Distribution

abstract set(params: Any) → Distribution

abstract kl_divergence(other: Distribution)

abstract number_of_parameters() → int

static jaccard_similarity(d1: Distribution, d2: Distribution) → float

Abstractmethod:

abstract plot(engine: str, title: str = None, fname: str = None, directory: str = '/tmp', view: bool = False, **kwargs) → Any

Generates a plot of the distribution.

Parameters:

title – the name of the variable this distribution represents
fname – the name of the file to be stored. Available file formats: png, svg, jpeg, webp, html
directory – the directory to store the generated plot files
view – whether to display generated plots, default False (only stores files)

Returns:

the figure object of the plotting engine

abstract to_json()

__reduce__()

static type_from_json(data: Dict[str, Any]) → Type[Distribution]

static from_json(dtype: Dict[str, Any], dinst: Dict[str, Any] = None) → Distribution | Type[Distribution]