dodiscover

dodiscover is a Python package for representing causal graphs. For example, Acyclic Directed Mixed Graphs (ADMG), also known as causal DAGs and Partial Ancestral Graphs (PAGs). We build on top of networkx's MixedEdgeGraph such that we maintain all the well-tested and efficient algorithms and data structures of networkx.

We encourage you to use the package for your causal inference research and also build on top with relevant Pull Requests.

See our examples for walk-throughs of how to use the package, or

Please refer to our User Guide for details on all the tools that we provide. You can also find an exhaustive list of the public API in the API. You can also look at our numerous examples that illustrate the use of dodiscover in many different contexts.

Contents

Getting started:

• Installation
• Reference API
  • Context for causal discovery
  • Constraint-based structure learning
  • Order-based structure learning
  • Comparing causal discovery algorithms
  • Typing
  • Graph protocols
  • Conditional Independence Testing
  • Conditional k-sample testing
  • Utilities
• Simple Examples
  • Examples
• User Guide
  • 1. Constraint-based causal discovery
  • 2. Independence
  • 3. Conditional Discrepancy
• Tutorials
  • Basic causal discovery models without latent confounders
• Release History
  • What’s new?
  • Version 0.1

Team

dodiscover is developed and maintained by pywhy. To learn more about who specifically contributed to this codebase, see our contributors page.

Indices and tables

• Index

• Module Index