py-why/causaltune

View on GitHub

AutoML for causal inference.

Stars: 242
Forks: 34
Open beginner issues: 0
Indexed issues: 22

Dominant language: Jupyter Notebook
License: Apache-2.0
Last GitHub push: Jul 19, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

22 open issues indexed

Decouple from dowhy internals & adopt new econml/dowhy features (follow-up to #338) Open

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

py-why/causaltune#339 · Opened Jul 6, 2026
We should require flaml[blendsearch] instead of just flaml, and also install catboost Open

bug

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

py-why/causaltune#329 · Opened Nov 29, 2024
Add a ranking-based score for ITE problems Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#324 · Opened Sep 20, 2024
Speed up calculation of energy score Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#323 · Opened Sep 12, 2024
Update to latest versions of DoWhy and EconML Open

enhancement

Difficulty 3/5 1-2 days Newbie friendliness 25/100

py-why/causaltune#322 · 1 comment · 1 reaction · Opened Sep 12, 2024
Add tests for mac, solve lightgbm install for mac Open

enhancement

Difficulty 3/5 1-2 days Newbie friendliness 20/100

py-why/causaltune#319 · Opened Sep 10, 2024
Don't force a time budget at all, and use default n_samples Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#318 · Opened Sep 9, 2024
Correctly handle weights if they are passed to the fit() method of an outcome function Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

py-why/causaltune#316 · Opened Sep 9, 2024
Enable early stopping (and maybe direct categorical feature handling?) in XGBoost etc estimators used for outcome function Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 20/100

py-why/causaltune#315 · Opened Sep 9, 2024
Stop saving copies of the dataset in fitted estimators Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 20/100

py-why/causaltune#218 · Opened Dec 6, 2022
Experiment with different propensity functions for the confounded CATE case with synthetic data Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 20/100

py-why/causaltune#215 · Opened Dec 2, 2022
Add other scores besides energy_distance to the multitreatment case Open

bug

Difficulty 5/5 Over a week Newbie friendliness 20/100

py-why/causaltune#213 · Opened Nov 29, 2022
Make TransformedOutcome model support multivalue treatments Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 20/100

py-why/causaltune#212 · Opened Nov 29, 2022
Create synthetic datasets reproducing the structure of our real production ones Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 10/100

py-why/causaltune#173 · Opened Aug 23, 2022
Independence test-based score for IV models Open

enhancement

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

py-why/causaltune#172 · Opened Aug 23, 2022
Add confidence intervals to at least ERUPT, ideally all other supported metrics Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 18/100

py-why/causaltune#114 · Opened Apr 30, 2022
Test whether the random W feature is still necessary for DoWhy graph construction Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#111 · Opened Apr 27, 2022
Cache fitted component models for reuse in different estimator fits Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#98 · Opened Apr 13, 2022
Fix the annoying Pandas warnings Open

bug P1

py-why/causaltune#92 · 1 assignee · Opened Apr 7, 2022
Inference stage 2: post-fit, make it easy to re-run selected estimators with inference turned on Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 15/100

py-why/causaltune#55 · Opened Mar 19, 2022
Gracefully handle 'inference' setting: stage 1, explicitly set inference=False in all model configs Open

enhancement

Difficulty 3/5 1-2 days Newbie friendliness 30/100

py-why/causaltune#54 · Opened Mar 19, 2022
Option to save best scores dict and model file (per estimator type) to disk Open

enhancement

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

py-why/causaltune#27 · Opened Mar 4, 2022

py-why/causaltune

Get new issues in your inbox