Metadata-Version: 2.4
Name: mechanism-learn
Version: 2.3.1
Summary: Mechanism-learn is a simple method to deconfound observational data such that any appropriate machine learning model is forced to learn predictive relationships between effects and their causes, despite the potential presence of multiple unknown and unmeasured confounding. The library is compatible with most existing ML deployments. The library is compatible with most existing ML deployments such as models built with Scikit-learn and Keras.
Author-email: Jianqiao Mao <jxm1417@student.bham.ac.uk>
Project-URL: Homepage, https://github.com/JianqiaoMao/mechanism-learn
Requires-Python: >=3.9
Description-Content-Type: text/plain
Requires-Dist: causalBootstrapping>=0.2.0
Requires-Dist: grapl-causal
Requires-Dist: scipy
Requires-Dist: graphviz
Requires-Dist: tqdm

To run the experiment code, please install the mechanism-learn package using the distribution file 'mechanism_learn-2.2.1-py3-none-any.whl' in the 'dist' folder.

In Python, use: import mechanism_learn.pipeline to import the mechanism learning algorithms.

Please note that due to the limit of file size, we cannot attach all experiment data, such as ICH CT scans and the Background-MNIST data. The original ICH data is available at https://physionet.org/content/ct-ich/1.3.1/. For the Background-MNIST data, it is modified from the original MNIST dataset. This semi-synthetic Background MNIST dataset can be generated by using the Python code file: .\test_data\semi_synthetic_data\semi-synthetic_data_gen.py.
