medil

This package is for causal inference, focusing on the Measurement Dependence Inducing Latent (MeDIL) Causal Model framework.

Modules

medil.decomposable_score

Module containing the DecomposableScore class, inherited by all classes which implement a locally decomposable score for directed acyclic graphs.

medil.ecc_algorithms

Implementations of edge clique clover finding algorithms.

medil.evaluate

medil.examples

Example graphs and data, for use in testing and tutorials.

medil.gauss_obs_l0_pen

l0-penalized Gaussian log-likelihood score for a sample from a single (observational) environment

medil.graph

Various types and representations of graphs.

medil.simulate

medil.visualize

Create and display various graphs, plots, and visualizations.