API reference

This page provides a summary of scoringrules’ API. All functions are available in the top-level namespace of the package and are here organized by category.

Ensemble forecasts

Univariate

crps_ensemble(obs, fct[, m_axis, ens_w, ...])	Estimate the Continuous Ranked Probability Score (CRPS) for a finite ensemble.
twcrps_ensemble(obs, fct[, a, b, m_axis, ...])	Estimate the threshold-weighted CRPS (twCRPS) for a finite ensemble.
owcrps_ensemble(obs, fct[, a, b, m_axis, ...])	Estimate the outcome-weighted CRPS (owCRPS) for a finite ensemble.
vrcrps_ensemble(obs, fct[, a, b, m_axis, ...])	Estimate the vertically re-scaled CRPS (vrCRPS) for a finite ensemble.
gksuv_ensemble(obs, fct[, m_axis, ens_w, ...])	Compute the univariate Gaussian Kernel Score (GKS) for a finite ensemble.
twgksuv_ensemble(obs, fct[, a, b, m_axis, ...])	Compute the Threshold-Weighted univariate Gaussian Kernel Score (GKS) for a finite ensemble.
owgksuv_ensemble(obs, fct[, a, b, m_axis, ...])	Compute the univariate Outcome-Weighted Gaussian Kernel Score (owGKS) for a finite ensemble.
vrgksuv_ensemble(obs, fct[, a, b, m_axis, ...])	Estimate the Vertically Re-scaled Gaussian Kernel Score (vrGKS) for a finite ensemble.
crps_quantile(obs, fct, alpha[, m_axis, backend])	Approximate the CRPS from quantile predictions via the Pinball Loss.
dssuv_ensemble(obs, fct[, m_axis, bias, backend])	Compute the Dawid-Sebastiani-Score for a finite univariate ensemble.

Multivariate

es_ensemble(obs, fct[, m_axis, v_axis, ...])	Compute the Energy Score for a finite multivariate ensemble.
owes_ensemble(obs, fct, w_func[, m_axis, ...])	Compute the Outcome-Weighted Energy Score (owES) for a finite multivariate ensemble.
twes_ensemble(obs, fct, v_func[, m_axis, ...])	Compute the Threshold-Weighted Energy Score (twES) for a finite multivariate ensemble.
vres_ensemble(obs, fct, w_func, *[, ens_w, ...])	Compute the Vertically Re-scaled Energy Score (vrES) for a finite multivariate ensemble.
vs_ensemble(obs, fct[, w, m_axis, v_axis, ...])	Compute the Variogram Score for a finite multivariate ensemble.
owvs_ensemble(obs, fct, w_func[, w, m_axis, ...])	Compute the Outcome-Weighted Variogram Score (owVS) for a finite multivariate ensemble.
twvs_ensemble(obs, fct, v_func[, w, m_axis, ...])	Compute the Threshold-Weighted Variogram Score (twVS) for a finite multivariate ensemble.
vrvs_ensemble(obs, fct, w_func[, w, m_axis, ...])	Compute the Vertically Re-scaled Variogram Score (vrVS) for a finite multivariate ensemble.
gksmv_ensemble(obs, fct[, m_axis, v_axis, ...])	Compute the multivariate Gaussian Kernel Score (GKS) for a finite ensemble.
twgksmv_ensemble(obs, fct, v_func[, m_axis, ...])	Compute the Threshold-Weighted Gaussian Kernel Score (twGKS) for a finite multivariate ensemble.
owgksmv_ensemble(obs, fct, w_func[, m_axis, ...])	Compute the multivariate Outcome-Weighted Gaussian Kernel Score (owGKS) for a finite ensemble.
vrgksmv_ensemble(obs, fct, w_func[, m_axis, ...])	Compute the Vertically Re-scaled Gaussian Kernel Score (vrGKS) for a finite multivariate ensemble.
dssmv_ensemble(obs, fct[, m_axis, v_axis, ...])	Compute the Dawid-Sebastiani-Score for a finite multivariate ensemble.

Parametric distributions forecasts

crps_beta(obs, a, b[, lower, upper, backend])	Compute the closed form of the CRPS for the beta distribution.
crps_binomial(obs, n, prob, *[, backend])	Compute the closed form of the CRPS for the binomial distribution.
crps_exponential(obs, rate, *[, backend])	Compute the closed form of the CRPS for the exponential distribution.
crps_exponentialM(obs[, mass, location, ...])	Compute the closed form of the CRPS for the standard exponential distribution with a point mass at the boundary.
crps_2pexponential(obs, scale1, scale2, ...)	Compute the closed form of the CRPS for the two-piece exponential distribution.
crps_gamma(obs, shape[, rate, scale, backend])	Compute the closed form of the CRPS for the gamma distribution.
crps_csg0(obs, shape[, rate, scale, shift, ...])	Compute the closed form of the CRPS for the censored, shifted gamma distribution.
crps_gev(obs, shape[, location, scale, backend])	Compute the closed form of the CRPS for the generalised extreme value (GEV) distribution.
crps_gpd(obs, shape[, location, scale, ...])	Compute the closed form of the CRPS for the generalised pareto distribution (GPD).
crps_gtclogistic(obs, location, scale[, ...])	Compute the closed form of the CRPS for the generalised truncated and censored logistic distribution.
crps_tlogistic(obs, location, scale[, ...])	Compute the closed form of the CRPS for the truncated logistic distribution.
crps_clogistic(obs, location, scale[, ...])	Compute the closed form of the CRPS for the censored logistic distribution.
crps_gtcnormal(obs, location, scale[, ...])	Compute the closed form of the CRPS for the generalised truncated and censored normal distribution.
crps_tnormal(obs, location, scale[, lower, ...])	Compute the closed form of the CRPS for the truncated normal distribution.
crps_cnormal(obs, location, scale[, lower, ...])	Compute the closed form of the CRPS for the censored normal distribution.
crps_gtct(obs, df[, location, scale, lower, ...])	Compute the closed form of the CRPS for the generalised truncated and censored t distribution.
crps_tt(obs, df[, location, scale, lower, ...])	Compute the closed form of the CRPS for the truncated t distribution.
crps_ct(obs, df[, location, scale, lower, ...])	Compute the closed form of the CRPS for the censored t distribution.
crps_hypergeometric(obs, m, n, k, *[, backend])	Compute the closed form of the CRPS for the hypergeometric distribution.
crps_laplace(obs[, location, scale, backend])	Compute the closed form of the CRPS for the laplace distribution.
crps_logistic(obs, mu, sigma, *[, backend])	Compute the closed form of the CRPS for the logistic distribution.
crps_loglaplace(obs, locationlog, scalelog, *)	Compute the closed form of the CRPS for the log-Laplace distribution.
crps_loglogistic(obs, mulog, sigmalog[, backend])	Compute the closed form of the CRPS for the log-logistic distribution.
crps_lognormal(obs, mulog, sigmalog[, backend])	Compute the closed form of the CRPS for the lognormal distribution.
crps_mixnorm(obs, m, s[, w, m_axis, backend])	Compute the closed form of the CRPS for a mixture of normal distributions.
crps_negbinom(obs, n[, prob, mu, backend])	Compute the closed form of the CRPS for the negative binomial distribution.
crps_normal(obs, mu, sigma, *[, backend])	Compute the closed form of the CRPS for the normal distribution.
crps_2pnormal(obs, scale1, scale2, location, *)	Compute the closed form of the CRPS for the two-piece normal distribution.
crps_poisson(obs, mean, *[, backend])	Compute the closed form of the CRPS for the Poisson distribution.
crps_quantile(obs, fct, alpha[, m_axis, backend])	Approximate the CRPS from quantile predictions via the Pinball Loss.
crps_t(obs, df[, location, scale, backend])	Compute the closed form of the CRPS for the student's t distribution.
crps_uniform(obs, min, max[, lmass, umass, ...])	Compute the closed form of the CRPS for the uniform distribution.
logs_beta(obs, a, b[, lower, upper, backend])	Compute the logarithmic score (LS) for the beta distribution.
logs_binomial(obs, n, prob, *[, backend])	Compute the logarithmic score (LS) for the binomial distribution.
logs_ensemble(obs, fct[, m_axis, bw, backend])	Estimate the Logarithmic score for a finite ensemble via kernel density estimation.
logs_exponential(obs, rate, *[, backend])	Compute the logarithmic score (LS) for the exponential distribution.
logs_exponential2(obs[, location, scale, ...])	Compute the logarithmic score (LS) for the exponential distribution with location and scale parameters.
logs_2pexponential(obs, scale1, scale2, ...)	Compute the logarithmic score (LS) for the two-piece exponential distribution.
logs_gamma(obs, shape[, rate, scale, backend])	Compute the logarithmic score (LS) for the gamma distribution.
logs_gev(obs, shape[, location, scale, backend])	Compute the logarithmic score (LS) for the generalised extreme value (GEV) distribution.
logs_gpd(obs, shape[, location, scale, backend])	Compute the logarithmic score (LS) for the generalised Pareto distribution (GPD).
logs_hypergeometric(obs, m, n, k, *[, backend])	Compute the logarithmic score (LS) for the hypergeometric distribution.
logs_laplace(obs[, location, scale, backend])	Compute the logarithmic score (LS) for the Laplace distribution.
logs_loglaplace(obs, locationlog, scalelog, *)	Compute the logarithmic score (LS) for the log-Laplace distribution.
logs_logistic(obs, mu, sigma, *[, backend])	Compute the logarithmic score (LS) for the logistic distribution.
logs_loglogistic(obs, mulog, sigmalog[, backend])	Compute the logarithmic score (LS) for the log-logistic distribution.
logs_lognormal(obs, mulog, sigmalog[, backend])	Compute the logarithmic score (LS) for the log-normal distribution.
logs_mixnorm(obs, m, s[, w, mc_axis, backend])	Compute the logarithmic score for a mixture of normal distributions.
logs_negbinom(obs, n[, prob, mu, backend])	Compute the logarithmic score (LS) for the negative binomial distribution.
logs_normal(obs, mu, sigma, *[, negative, ...])	Compute the logarithmic score (LS) for the normal distribution.
logs_2pnormal(obs, scale1, scale2, location, *)	Compute the logarithmic score (LS) for the two-piece normal distribution.
logs_poisson(obs, mean, *[, backend])	Compute the logarithmic score (LS) for the Poisson distribution.
logs_t(obs, df[, location, scale, backend])	Compute the logarithmic score (LS) for the Student's t distribution.
logs_tlogistic(obs, location, scale[, ...])	Compute the logarithmic score (LS) for the truncated logistic distribution.
logs_tnormal(obs, location, scale[, lower, ...])	Compute the logarithmic score (LS) for the truncated normal distribution.
logs_tt(obs, df[, location, scale, lower, ...])	Compute the logarithmic score (LS) for the truncated Student's t distribution.
logs_uniform(obs, min, max, *[, backend])	Compute the logarithmic score (LS) for the uniform distribution.

Consistent scoring functions

interval_score(obs, lower, upper, alpha, *)	Compute the Interval Score or Winkler Score.
weighted_interval_score(obs, median, lower, ...)	Compute the weighted interval score (WIS).

Categorical forecasts

brier_score(obs, fct, *[, backend])	Brier Score
rps_score(obs, fct[, k_axis, onehot, backend])	(Discrete) Ranked Probability Score (RPS)
log_score(obs, fct, *[, backend])	Compute the Logarithmic Score (LS) for probability forecasts for binary outcomes.
rls_score(obs, fct[, k_axis, onehot, backend])	Compute the (Discrete) Ranked Logarithmic Score (RLS).

Backends

register_backend(backend)