sktime/skpro

View on GitHub

A unified framework for tabular probabilistic regression, time-to-event prediction, and probability distributions in python

Stars: 335
Forks: 206
Open beginner issues: 1
Indexed issues: 125
Avg merge: 1d 20h
Merged PRs (30d): 16

Dominant language: Python
License: BSD-3-Clause
Last GitHub push: Sep 15, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue

Beginner friendly Everything

Open All

125 open issues indexed

[ENH] add at least one usage example to docstrings of estimators Open

documentation good first issue

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

sktime/skpro#1135 · 7 comments · Opened Sep 10, 2026
[DOC] add explicit formulae to docstrings of distributions Open

documentation good first issue module:distributions&simulation

Difficulty 3/5 1-2 days Newbie friendliness 68/100

sktime/skpro#1120 · 5 comments · Opened Aug 7, 2026
[API] API for distribution fitters in multivariate case Open

API design module:distribution-fitters

Difficulty 5/5 Over a week Newbie friendliness 25/100

sktime/skpro#1111 · 6 comments · 1 reaction · Opened Jul 10, 2026
[ENH] expand distribution fitters module with new fitters Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 42/100

sktime/skpro#1109 · 2 comments · Opened Jul 8, 2026
[ENH] Add OnlineSlidingWindow and OnlineExponentialForgetting meta-strategies Open

feature request module:regression

Difficulty 3/5 1-2 days Newbie friendliness 68/100

sktime/skpro#1096 · 1 comment · Opened Jul 1, 2026
[ENH] fork `cyclic_boosting` into `skpro` and update `numpy` compatibility Open

enhancement module:regression

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sktime/skpro#1090 · Opened Jun 30, 2026
[ENH] `EmpiricalFitter` distribution fitter Open

enhancement feature request implementing algorithms module:distributions&simulation

Difficulty 3/5 1-2 days Newbie friendliness 65/100

sktime/skpro#1087 · Opened Jun 29, 2026
[ENH] interface `distfit` as distribution fitter Open

enhancement feature request interfacing algorithms

Difficulty 4/5 3-5 days Newbie friendliness 35/100

sktime/skpro#1086 · 2 comments · Opened Jun 29, 2026
[ENH] update `skpro` base framework with `sktime` upgrades Open

enhancement feature request module:base-framework

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sktime/skpro#1083 · 3 comments · Opened Jun 29, 2026
[MNT] Backport workflow-hardening fix (excessive-permissions) to 5 release branches Open

maintenance

Difficulty 3/5 1-2 days Newbie friendliness 75/100

sktime/skpro#1082 · 1 comment · Opened Jun 29, 2026
[ENH] Add save/load serialization for all skpro objects Open

feature request

sktime/skpro#1072 · 1 assignee · Opened Jun 18, 2026
[ENH] Implement `Categorical` distribution Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 35/100

sktime/skpro#1071 · 4 comments · Opened Jun 16, 2026
[ENH] RiverRegressor adapter and online regressor support Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 50/100

sktime/skpro#1066 · Opened Jun 8, 2026
[ENH] add `hyperactive` tuner as importable directly from `skpro` Open

enhancement good first issue interfacing algorithms module:regression module:survival&time-to-event

Difficulty 3/5 1-2 days Newbie friendliness 65/100

sktime/skpro#1051 · 4 comments · Opened May 17, 2026
[ENH] `update` capability for `GridSearchCV` and `RandomizedSearchCV` Open

enhancement feature request module:regression module:survival&time-to-event

Difficulty 5/5 Over a week Newbie friendliness 35/100

sktime/skpro#1050 · 5 comments · Opened May 17, 2026
[ENH] online versions of Jackknife+-after-bootstrap and bagging regressors Open

enhancement feature request module:regression

sktime/skpro#1049 · 5 comments · 1 reaction · 1 assignee · Opened May 17, 2026
[BUG] `MeanScale` should expose `.spl` Open

bug module:distributions&simulation module:regression

sktime/skpro#1047 · 2 comments · 1 assignee · Opened May 6, 2026
[MNT] Eliminate global np.random.seed calls to prevent global state mutation. Open

maintenance

Difficulty 3/5 1-2 days Newbie friendliness 68/100

sktime/skpro#1039 · 2 comments · Opened Apr 16, 2026
[ENH] External Regressor Distribution Tags + Unified Conversion Method Open

feature request module:regression

Difficulty 5/5 Over a week Newbie friendliness 32/100

sktime/skpro#1023 · 5 comments · Opened Mar 31, 2026
[BUG] RandomizedSearchCV documentation includes backend parameter but not in the constructor. Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 64/100

sktime/skpro#1013 · Opened Mar 30, 2026
[DOC] Fix broken "Contributors" link in example notebooks Open

documentation

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

sktime/skpro#1011 · 1 comment · Opened Mar 30, 2026
[BUG] GridSearchCV scoring=None gives AttributeError Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

sktime/skpro#1009 · Opened Mar 30, 2026
[ENH] Support for discrete output distributions and probabilistic classification Open

enhancement feature request good first issue

Difficulty 5/5 Over a week Newbie friendliness 35/100

sktime/skpro#1003 · 3 comments · Opened Mar 28, 2026
[DOC] Complete Related Software documentation page Open

Difficulty 1/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#998 · Opened Mar 26, 2026
[ENH] add "ISJ" bandwidth option to kernel base models Open

feature request module:regression

Difficulty 4/5 3-5 days Newbie friendliness 48/100

sktime/skpro#980 · 4 comments · Opened Mar 20, 2026
[ENH] Make missing alpha error message in PinballLoss more informative. Open

feature request

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#977 · Opened Mar 20, 2026
[BUG] DummyProbaRegressor._predict_var returns std dev (σ) instead of variance (σ²) Open

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#975 · 1 comment · Opened Mar 20, 2026
[BUG] Mixture._sample handles indep_cols and indep_rows backward, destroying independence assumptions Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#974 · 1 comment · Opened Mar 20, 2026
[BUG] Incorrect variance computation and misleading capability tags in Hurdle Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

sktime/skpro#972 · 1 comment · Opened Mar 19, 2026
[BUG] Pareto _pdf and _log_pdf return nonzero values outside support (x < scale) Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

sktime/skpro#967 · 1 comment · Opened Mar 17, 2026
[ENH] Make PinballLoss alpha mismatch error message more informative Open

feature request

Difficulty 2/5 1-3 hours Newbie friendliness 58/100

sktime/skpro#966 · Opened Mar 17, 2026
[BUG] GeneralizedPareto: false log_pdf exact tag, missing distr:paramtype, insufficient test params Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 52/100

sktime/skpro#961 · 2 comments · Opened Mar 17, 2026
[BUG] Normal and Laplace accept non-positive sigma/scale and return invalid pdf values Open

bug module:distributions&simulation

Difficulty 3/5 1-2 days Newbie friendliness 57/100

sktime/skpro#959 · 2 comments · Opened Mar 17, 2026
[BUG] _SksurvAdapter fails to preserve total probability mass and shifts distributions Open

bug module:survival&time-to-event

Difficulty 3/5 1-2 days Newbie friendliness 58/100

sktime/skpro#958 · 2 comments · Opened Mar 16, 2026
[BUG] Zero predicted variance causes instability in BaseProbaRegressor.predict_proba Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

sktime/skpro#955 · Opened Mar 16, 2026
Suppressed `RecursionError` tracebacks in `BaseProbaMetric._evaluate_by_index` Open

Difficulty 1/5 Under an hour Newbie friendliness 25/100

sktime/skpro#948 · Opened Mar 16, 2026
[BUG] Data leakage in _LifelinesAdapter when y has multiple columns Open

AI overuse suspected bug module:survival&time-to-event

Difficulty 3/5 1-2 days Newbie friendliness 72/100

sktime/skpro#947 · 2 comments · Opened Mar 16, 2026
[MNT] Add missing distr:paramtype tag to Skellam, GumbelL, GumbelR, FDist, Rayleigh Open

maintenance

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#942 · 1 comment · Opened Mar 16, 2026
[MNT] Inconsistent CRLF line endings in some distribution files Open

maintenance

Difficulty 1/5 Under an hour Newbie friendliness 72/100

sktime/skpro#929 · 1 comment · Opened Mar 15, 2026
[BUG] component estimator fitted state mutates constructor params in wrapper estimators Open

bug module:regression

Difficulty 4/5 3-5 days Newbie friendliness 38/100

sktime/skpro#922 · 3 comments · Opened Mar 14, 2026
[MNT] CRON job for regular running of estimator tests Open

enhancement good first issue module:tests

Difficulty 4/5 3-5 days Newbie friendliness 38/100

sktime/skpro#913 · 7 comments · Opened Mar 14, 2026
[ENH] Add spell checking Open

feature request

Difficulty 3/5 1-2 days Newbie friendliness 35/100

sktime/skpro#905 · 1 comment · Opened Mar 14, 2026
[BUG] investigate `sksurv` (`scikit-survival`) based failures Open

bug good first issue module:survival&time-to-event

Difficulty 3/5 1-2 days Newbie friendliness 48/100

sktime/skpro#899 · 5 comments · Opened Mar 13, 2026
[ENH] Ensure testing of parameter mutation through `predict` methods, and in components Open

good first issue module:regression

Difficulty 3/5 1-2 days Newbie friendliness 45/100

sktime/skpro#896 · 3 comments · Opened Mar 13, 2026
[DOC] Fix malformed Binder URL in conf.py Open

documentation

Difficulty 1/5 Under an hour Newbie friendliness 70/100

sktime/skpro#890 · Opened Mar 13, 2026
[BUG] RuntimeWarning: invalid value encountered in log when evaluating QPD_S.cdf at or below bounds Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

sktime/skpro#885 · Opened Mar 13, 2026
[BUG] None valued distribution parameters are accepted and fail inconsistently later Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

sktime/skpro#884 · 2 comments · Opened Mar 13, 2026
[ENH] Add numerically stable log_cdf method to BaseDistribution Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 45/100

sktime/skpro#866 · Opened Mar 11, 2026
[BUG] Pipeline._transform does not chain transformer outputs during prediction Open

bug enhancement module:regression

Difficulty 2/5 1-3 hours Newbie friendliness 52/100

sktime/skpro#864 · 3 comments · Opened Mar 11, 2026
[DOC] Improve type hints and documentation for prep_skl_df utility function Open

documentation

Difficulty 1/5 Under an hour Newbie friendliness 55/100

sktime/skpro#857 · Opened Mar 10, 2026

sktime/skpro

Get new issues in your inbox