Data

Tools

Indexes

Applications

Experiments

Open Source Science

interpretability-hierarchy-zenodo

https://github.com/alessandrolovo/interpretability-hierarchy-zenodo

Science Score: 49.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org, zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 6 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: AlessandroLovo
  • License: mit
  • Language: PureBasic
  • Default Branch: main
  • Size: 363 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 3
  • Releases: 3
Created almost 2 years ago · Last pushed 10 months ago
Metadata Files
Readme License Citation

README.md

Code for the paper "Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwaves"

DOI

Links

Preprint of paper

For authorn only

repo of manuscript

repo of supplementary material

Raw data

The raw data used in by this code is available at -INSERT LINK-. However, you need to adapt the various config.json files present in this repository to properly load the data. The guide for how to do this is the kwarg_correction.md file in the data repository.

Setup

To be able to run the notebooks in this repository, you need to clone the Climate-Learning repository.

To do put yourself in the same directory of this file and run

bash git clone --recursive https://github.com/georgemilosh/Climate-Learning.git

Reproducing the figures will use only the submodule general_purpose, but training the neural networks and visualizing them needs the full Climate-Learning framework.

Contents of this repo

This repo contains data and notebooks to reproduce the figures and tables presented in our paper. The best way to navigate it is through its notebooks: inside each of them you'll find some explanatory markdown text.

List of notebooks

  • Data normalization procedure here
  • Performance of the hierarchy here
  • Interpretability
    • GA and IINN here
    • CNN
      • Expected Gradient Feature Importance maps here
      • Optimal Input Maps here
    • Scatnet here

Debugging help

  • Test if you can properly load our neural networks here

Owner

  • Name: Alessandro Lovo
  • Login: AlessandroLovo
  • Kind: user
  • Location: Lyon
  • Company: Ecole Normale Superieure de Lyon

Climate Physics & Machine Learning PhD student @ Ecole Normale Superieure de Lyon

GitHub Events

Total
  • Release event: 2
  • Push event: 16
  • Create event: 3
Last Year
  • Release event: 2
  • Push event: 16
  • Create event: 3