https://github.com/marrlab/causalspyne

Python data generation tool with unobserved confounding as testbed for causal discovery and causal abstraction
https://github.com/marrlab/causalspyne

Last synced: over 1 year ago
JSON representation

Python data generation tool with unobserved confounding as testbed for causal discovery and causal abstraction

• Host: GitHub
• URL: https://github.com/marrlab/causalspyne
• Owner: marrlab
• Created: 2024-08-06T11:02:39.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2025-02-19T14:58:48.000Z (over 1 year ago)
• Last Synced: 2025-03-29T12:16:49.256Z (over 1 year ago)
• Language: Python
• Homepage: https://pypi.org/project/causalspyne/
• Size: 755 KB
• Stars: 3
• Watchers: 4
• Forks: 0
• Open Issues: 7
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# CausalSpyne

[![PyPI version](https://badge.fury.io/py/causalspyne.svg)](https://badge.fury.io/py/causalspyne)  [![test coverage](https://marrlab.github.io/causalspyne/coverage-badge.svg)](https://marrlab.github.io/causalspyne/)

A Python package for simulating data from confounded causal models.

## Quick start

Install with: `pip install causalspyne`

Generate some data:

```

from causalspyne import gen_partially_observed

gen_partially_observed(size_micro_node_dag=4,

                       num_macro_nodes=4,

                       degree=2,  # average vertex/node degree

                       list_confounder2hide=[0.5, 0.9], # choie of confounder to hide: percentile or index of all toplogically sorted confounders

                       num_sample=200,

                       output_dir="output",

                       rng=0)

```

## Submodules

```

git submodule update --init

```