Skip to content

Latest commit

 

History

History
38 lines (36 loc) · 1.12 KB

README.md

File metadata and controls

38 lines (36 loc) · 1.12 KB

automl-xai-metabolomics

code base for the paper: Automated machine learning and explainable AI (AutoML-XAI) for metabolomics

How to use code

  • Clone the repository.
  • Build the docker. docker build -t Dockerfile.
  • Run the docker container.
  • Run jupyter notebook.
    Note that the autoML models are saved as askl_17_OC_3600.pkl and askl_RCC_600.pkl for the OC and RCC dataset respectively. You will need to unzip.

Notebook contents

Name Description
automl-SHAP-RCC.ipynb Implementation of autosklearn and SHAP for the RCC Dataset.
RCC-model-error-analysis.ipynb Error analysis of the autoML RCC diagnostic model.
data-preparation.ipynb Data preparation for the RCC metabolomics dataset.
automl-SHAP-OC.ipynb Implementation of autosklearn and SHAP for the OC Dataset.
OC-model-error-analysis.ipynb Error analysis of the autoML OC diagnostic model.