Welcome to the TSProto documentation

TSProto (Post-host prototype-based explanations with rules for time-series classifiers) is an XAI algorithm that produces explanations for any type of machine-learning model. It provides local explanations in a form of human-readable (and executable) rules, but also provide counterfactual explanations as well as visualization of the explanations.

Install

TSProto can be installed from either PyPI or directly from source code GitHub

To install form PyPI:

pip install tsproto

To install from source code:

git clone https://github.com/sbobek/tsproto
cd tsproto
pip install .

Examples

• Interpreting TSProto
  • Basic interpretation of TSProto
  • Contrastive examples in healthcare data
  • Anomaly interpretation in Industry 4.0
• Basic Usage examples

Reference

• API reference
  • Explanation interface
  • Plots
  • Utilities

Development

• Release notes
• Contributing guide