Continuous

fenbux.univariate.Normal

Normal distribution.

Parameters:

Name	Type	Description	Default
mean	ArrayLike	Mean of the distribution.	0.0
sd	ArrayLike	Standard deviation of the distribution.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from jax import vmap
>>> from fenbux import logpdf
>>> from fenbux.univariate import Normal
>>> dist = Normal(0.0, jnp.ones((10, )))

fenbux.univariate.Uniform

Uniform distribution. X ~ Uniform(lower, upper)

Parameters:

Name	Type	Description	Default
lower	PyTree	Lower bound of the distribution.	0.0
upper	PyTree	Upper bound of the distribution.	1.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Uniform
>>> dist = Uniform(0.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Logistic

Logistic distribution. X ~ Logistic(μ, σ)

Parameters:

Name	Type	Description	Default
loc	ArrayLike	Loc of the distribution.	0.0
scale	ArrayLike	Scale of the distribution.	1.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Logistic
>>> dist = Logistic(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.LogNormal

LogNormal distribution. X ~ LogNormal(μ, σ)

Parameters:

Name	Type	Description	Default
mean	ArrayLike	Mean of the distribution.	0.0
sd	ArrayLike	Standard deviation of the distribution.	1.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import LogNormal
>>> dist = LogNormal(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Exponential

Exponential distribution.

Parameters:

Name	Type	Description	Default
rate	PyTree	Rate parameter.	1.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Exponential
>>> dist = Exponential(1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Beta

Beta distribution.

Parameters:

Name	Type	Description	Default
a	PyTreeVar	Shape parameter a.	0.0
b	PyTreeVar	Shape parameter b.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Beta
>>> dist = Beta(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Gamma

Gamma distribution.

X ~ Gamma(shape, rate)

Parameters:

Name	Type	Description	Default
shape	PyTree	Shape parameter of the distribution.	0.0
rate	PyTree	Rate parameter of the distribution.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Gamma
>>> dist = Gamma(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Chisquare

Chisquare distribution.

Parameters:

Name	Type	Description	Default
df	ArrayLike	Degrees of freedom.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Chisquare
>>> dist = Chisquare(1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.F

F distribution.

Parameters:

Name	Type	Description	Default
dfn	PyTree	Degrees of freedom in the numerator.	required
dfd	PyTree	Degrees of freedom in the denominator.	required
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import F
>>> dist = F(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.StudentT

Student's t distribution.

Parameters:

Name	Type	Description	Default
df	PyTree	Degrees of freedom.	1.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import StudentT
>>> dist = StudentT(1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Weibull

Weibull distribution.

X ~ Weibull(shape, scale)

Parameters:

Name	Type	Description	Default
shape	PyTree	Shape parameter of the distribution.	0.0
scale	PyTree	Scale parameter of the distribution.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Weibull
>>> dist = WeiBull(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Pareto

Pareto distribution.

X ~ Pareto(shape, scale)

Parameters:

Name	Type	Description	Default
shape	PyTree	Shape parameter of the distribution.	0.0
scale	PyTree	Scale parameter of the distribution.	0.0
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Pareto
>>> dist = Pareto(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Wald

Wald distribution.

X ~ Wald(mu)

Parameters:

Name	Type	Description	Default
mu	PyTree	Mean parameter of the distribution.	required
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Wald
>>> dist = Wald(1.0)
>>> logpdf(dist, jnp.ones((10, )))

fenbux.univariate.Cauchy

Cauchy distribution.

Parameters:

Name	Type	Description	Default
loc	PyTreeVar	Location parameter of the distribution.	required
scale	PyTreeVar	Scale parameter of the distribution.	required
dtype	jax.numpy.dtype	dtype of the distribution, default jnp.float_.	<class 'jax.numpy.float64'>
use_batch	bool	Whether to use with vmap. Default False.	False

Examples:

>>> import jax.numpy as jnp
>>> from fenbux import logpdf
>>> from fenbux.univariate import Cauchy
>>> dist = Cauchy(1.0, 1.0)
>>> logpdf(dist, jnp.ones((10, )))