Causal-TS: A Python Library for Causal Discovery in High-Dimensional and Nonstationary Time Series

Causal-TS is a new Python library for causal discovery in high-dimensional, nonstationary time series, bundling multiple algorithms into one toolchain.

It adds a shared conditional independence testing layer with GPU support and regime detection for structural breaks.

The library also includes synthetic data generation and optional DoWhy integration to help estimate causal effects from real-world sequences.