Probability distributions

The sktime.distributions module contains probability distributions which combine a pandas.DataFrame-like API with a scikit-base compatible object interface.

All distributions in skpro can be listed using the skpro.registry.all_objects utility, using object_types="distribution", optionally filtered by tags. Valid tags can be listed using sktime.registry.all_tags.

Base

BaseDistribution([index, columns])

Base probability distribution.

Parametric distributions

Continuous support - full reals

Laplace(mu, scale[, index, columns])	Laplace distribution.
Logistic(mu, scale[, index, columns])	Logistic distribution.
Normal(mu, sigma[, index, columns])	Normal distribution (skpro native).
SkewNormal(mu, sigma[, alpha, index, columns])	Skew-Normal Probability Distribution.
TDistribution(mu, sigma[, df, index, columns])	Student's t-distribution (skpro native).
TruncatedNormal(mu, sigma, l_trunc, r_trunc)	A truncated normal probability distribution.

Continuous support - non-negative reals

Alpha(a[, index, columns])	Alpha distribution.
Beta(alpha, beta[, index, columns])	Beta distribution.
ChiSquared(dof[, index, columns])	Chi-Squared distribution (skpro native).
Exponential(rate[, index, columns])	Exponential Distribution.
Erlang(rate[, k, index, columns])	Erlang Distribution.
Fisk([alpha, beta, index, columns])	Fisk distribution, aka log-logistic distribution.
Gamma(alpha, beta[, index, columns])	Gamma Distribution.
HalfCauchy(beta[, index, columns])	Half-Cauchy distribution.
HalfLogistic(beta[, index, columns])	Half-Logistic distribution.
HalfNormal(sigma[, index, columns])	Half-Normal distribution.
InverseGamma(alpha, beta[, index, columns])	Inverse Gamma Distribution.
LogLaplace(scale[, index, columns])	Log-Laplace distribution.
Pareto(scale, alpha[, index, columns])	Pareto distribution (skpro native).
Weibull(scale, k[, index, columns])	Weibull distribution.

Integer support

Binomial(n, p[, index, columns])	Binomial distribution.
Hurdle(p, distribution[, index, columns])	A Hurdle distribution.
NegativeBinomial(mu, alpha[, index, columns])	Negative binomial distribution.
Poisson(mu[, index, columns])	Poisson distribution.

Non-parametric and empirical distributions

Delta(c[, index, columns])	Delta distribution aka constant distribution aka certain distribution.
Empirical(spl[, weights, time_indep, index, ...])	Empirical distribution, or weighted sum of delta distributions.
Histogram(bins, bin_mass[, index, columns])	Histogram Probability Distribution.
QPD_Empirical(quantiles[, time_indep, ...])	Empirical quantile parametrized distribution.
QPD_Johnson(alpha, qv_low, qv_median, qv_high)	Johnson Quantile-Parameterized Distribution.
QPD_U(alpha, qv_low, qv_median, qv_high[, ...])	Johnson Quantile-Parameterized Distributions with bounded mode.
QPD_S(alpha, qv_low, qv_median, qv_high, lower)	Johnson Quantile-Parameterized Distributions with semi-bounded mode.
QPD_B(alpha, qv_low, qv_median, qv_high, ...)	Johnson Quantile-Parameterized Distributions with bounded mode.

Composite distributions

Parametric families

MeanScale(d[, mu, sigma, index, columns])	Composition for offset and scaling, and mean/scale family of distributions.
TruncatedDistribution(distribution, *[, ...])	A truncated distribution _not_ including the lower bound.
LeftTruncated(distribution, lower[, index, ...])	A left truncated distribution _not_ including the lower bound.

Mixture composition

Mixture(distributions[, weights, ...])

Mixture of distributions.

Sampling and multivariate composition

IID(distribution[, index, columns])

An i.i.d.