Skip to main content

A Ground Truth eXplanation Dataset

Project description

Ground Truth eXplanation Dataset

  1. Please run the setup.sh file to downlad the datasets.
  2. Please run conda env create --name hddds --file environment.yml to install the necessary packages.
  3. Please find the notebook example.ipynb for the sample access to our dataset and potential use of dataloaders.
  4. Please find the code for experiments in hddds.py (which is going to be slow). The detailed code is consist of three parts, and separated in three files:
  • experiments/train.py: training the predictive models;
  • experiments/get_explanations.py: generating the explanations using different feature atrribution methods;
  • experiments/summary.py: evaluating the performance of the explanations against ground truth.

PS: If you ever wonder why there are so many 'd's in hddds, it is pinyin for Hao Da De DataSet (very large dataset) :)

Project details


Release history Release notifications | RSS feed

This version

1.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

gtx-1.0-py3-none-any.whl (81.1 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page