Causal inference/uplift in Python
Project description
-
Causal inference/uplift in Python
Application • Included Datasets • Contribute • References • License
Getting Started
Latest release version: 0.0.1
Installation
pip install causeinfer
Application
Causal inference algorithms:
1. The Two Model Approach
- Separate models for treatment and control groups are trained and combined to derive average treatment effects.
2. Interaction Term Approach - Lo 2002
- An interaction term between treatment and covariates is added to the data to allow for a basic single model application.
3. Response Transformation Approach - Lai 2006; Kane, Lo and Zheng 2014
- Units are categorized to allow for the derivation of treatment effected covariates through classification.
4. Generalized Random Forest - Athey, Tibshirani, and Wager 2019
- An application of an honest causalaity based splitting random forest.
Evaluation metrics:
1. Qini and AUUC Scores
- Comparisons across stratefied, ordered treatment response groups are used to derive model efficiency
2. GRF Confidence Intervals
- Confidence intervals are created using GRF's standard deviation across trials
Included Datasets
Contribute
Contributions are more than welcome!
Similar Packages
The following are similar packages/modules to causeinfer:
Python:
- https://github.com/uber/causalml
- https://github.com/Minyus/causallift
- https://github.com/jszymon/uplift_sklearn
- https://github.com/duketemon/pyuplift
- https://github.com/microsoft/EconML
- https://github.com/wayfair/pylift/
Other Languages:
- https://github.com/grf-labs/grf (R/C++)
- https://github.com/imbs-hl/ranger (R/C++)
- https://github.com/soerenkuenzel/causalToolbox/blob/a06d81d74f4d575a8b34dc6b718db2778cfa0be9/R/XRF.R (R/C++)
- https://github.com/soerenkuenzel/forestry (R/C++)
- https://github.com/cran/uplift/tree/master/R (R)
References
Full list of theoretical references
-
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
causeinfer-0.0.2.tar.gz
(12.9 kB
view hashes)