gCastle: A Python Toolbox for Causal Discovery

TL;DR

gCastle is a comprehensive Python toolbox for causal discovery that supports data generation, structure learning, evaluation, and includes recent gradient-based methods with GPU support, aiding researchers and practitioners.

Contribution

It introduces a versatile, user-friendly Python package integrating recent causal discovery methods, data handling, and evaluation tools, with GPU acceleration and real-world datasets.

Findings

Includes recent gradient-based causal discovery methods

Supports GPU acceleration for faster computation

Provides real-world datasets for benchmarking

Abstract

$\texttt{gCastle}$ is an end-to-end Python toolbox for causal structure learning. It provides functionalities of generating data from either simulator or real-world dataset, learning causal structure from the data, and evaluating the learned graph, together with useful practices such as prior knowledge insertion, preliminary neighborhood selection, and post-processing to remove false discoveries. Compared with related packages, $\texttt{gCastle}$ includes many recently developed gradient-based causal discovery methods with optional GPU acceleration. $\texttt{gCastle}$ brings convenience to researchers who may directly experiment with the code as well as practitioners with graphical user interference. Three real-world datasets in telecommunications are also provided in the current version. $\texttt{gCastle}$ is available under Apache License 2.0 at \url{https://github.com/huawei-noah/trustworthyAI/tree/master/gcastle}.