文献 Survey
-
因果表征学习
Schölkopf B, Locatello F, Bauer S, et al. Toward causal representation learning[J]. Proceedings of the IEEE, 2021, 109(5): 612-634.
-
因果机器学习
Kaddour J, Lynch A, Liu Q, et al. Causal machine learning: A survey and open problems[J]. arXiv preprint arXiv:2206.15475, 2022.
-
因果强化学习 A Survey on Causal Reinforcement Learning
书籍
-
统计因果推理入门【读起来比较简单】
-
The book of why
-
因果论
-
可解释人工智能导论
实战
因果发现和因果推理
Causal-learn
-
代码包:https://github.com/cmu-phil/causal-learn
-
文档: https://causal-learn.readthedocs.io/en/latest/
-
简单使用案例:https://github.com/cmu-phil/causal-learn/tree/main/tests
支持:
Constrained-based causal discovery methods.
Score-based causal discovery methods.
Causal discovery methods based on constrained functional causal models.
Hidden causal representation learning.
Granger causal analysis.
多个独立的基础模块,比如独立性测试,评分函数,图操作,评测指标。
更多最新的因果发现算法,如gradient-based methods等
DoWhy
-
一个Python因果推理库,支持因果假设的显式建模和测试。DoWhy基于因果推理的统一语言,将因果图形模型和潜在结果框架相结合。
-
代码包:https://github.com/microsoft/dowhy
-
Awesome Causality用数据学习因果关系的算法列表
-
代码包:https://github.com/rguo12/awesome-causality-algorithms
Tigramite
-
用于因果发现的时间序列分析
-
代码包:https://github.com/jakobrunge/tigramite
Causal Discovery Toolbox
-
是一个用于在图形和 Python>=3.5 的成对设置中进行因果推理的包, 包括用于图结构恢复和依赖关系的工具。
-
代码包:https://github.com/FenTechSolutions/CausalDiscoveryToolbox
Ylearn
-
用于因果学习的python包,支持因果推理的各个方面,包括因果发现、因果效应识别、因果效应估计、反事实推理、策略学习等
-
代码包:https://github.com/DataCanvasIO/YLearn/blob/main/docs/en_US/source/index.rst
Causalml
-
代码包:https://github.com/uber/causalml
Econml
Tigramite
-
用于因果发现的时间序列分析
-
代码包:https://github.com/jakobrunge/tigramite