Skip to content

Latest commit

 

History

History
46 lines (34 loc) · 1.37 KB

README.md

File metadata and controls

46 lines (34 loc) · 1.37 KB
Raw

How Non-Experts Perceive and Teach with Machine Learning Uncertainties

This repository is the official implementation of How Non-Experts Perceive and Teach with Machine Learning Uncertainties. It contains:

  • benchmark: jupyter notebooks presenting the benchmark presented in section 3.
  • app: the Marcelle source code of the application used in the user study presented in section 4.
  • analysis: the quantitative analysis of the user study logs. Results are presented in section 5.
  • setup: contains python configurations of the project
  • common: contains common functions used both in the app, the benchmark and the analysis.

Requirements

Python requirements

To install requirements in a conda environment: On MacOS:

pip install -r setup/conda_env_macos.yml

On Linux:

pip install -r setup/conda_env_linux.yml

Application requirements

To install the app:

cd app
npm install

or

cd app
yarn install

See the README in app for more details.

To install Marcelle, please refers to the official website

Contributing

The code here might be incomplete and not systematically documented. It aims at making the research process more transparent for reviewers and peers. Please contact me if you have any suggestions or find any problems.