causal-learn 0.1.1.6

causal-learn Python Package

causal-learn: Causal Discovery for Python

causal-learn is an open-source causal discovery library for Python, which is a Python translation and extension of Tetrad.

The package is on its very first version and we are actively developing it. Please, as a beta user, if you are willing, would you please kindly share any feedbacks (issues, suggestions, etc.) about it with us?

Package Overview

Our causal-learn implements methods for causal discovery:

• Constrained-based causal discovery methods.
• Score-based causal discovery methods.
• Causal discovery methods based on constrained functional causal models.
• Hidden causal representation learning.
• Granger causality.
• Multiple utilities for building your own method, such as independence tests, score functions, graph operations, and evaluations.

Install

causal-learn needs the following packages to be installed beforehand:

• python 3
• numpy
• networkx
• pandas
• scipy
• scikit-learn
• statsmodels
• pydot

(For visualization)

• matplotlib
• graphviz

To use causal-learn, we could install it using pip:

pip install causal-learn

Documentation

Please kindly refer to causal-learn Doc for detailed tutorials and usages.