# treeexplainer-study

**Repository Path**: salty_23fish/treeexplainer-study

## Basic Information

- **Project Name**: treeexplainer-study
- **Description**: Code and documentation for experiments in the TreeExplainer paper
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-06-02
- **Last Updated**: 2021-06-20

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# TreeExplainer Paper Repository

<p align="center">
  <img src="https://raw.githubusercontent.com/suinleelab/treeexplainer/master/images/overview_header.png" width="750" />
</p>

---

This repository contains notebook code and data for the paper: *Explainable AI for Trees: From Local Explanations to Global Understanding*

This paper presents the first exact game theoretic solution for explaining predictions from tree ensemble models, the most widely used non-linear machine learning models; this solution is the only one that guarantees desirable properties and so enables new insights into individual predictions and global behavior of the model.

**Ways to explore the results and code behind the paper:**
- Use TreeExplainer to explain your own tree-based models with the popular Python [shap package](https://github.com/slundberg/shap).
    *  System requirements: Any recent Mac, Windows, or Linux OS. See https://anaconda.org/conda-forge/shap/files for a list of systems with precompiled binaries the codes is unit tested on.
    * Installation: See https://github.com/slundberg/shap (install time is typically < 1 min)
    * Demo: See the TreeExplainer demos at https://github.com/slundberg/shap, the demo on the front page runs in a few seconds on any modern computer.

- Check out the [local explanation benchmark](https://suinleelab.github.io/treeexplainer-study/benchmark/cric/index.html) results.

- Download the [NHANES I data](https://github.com/suinleelab/treeexplainer-study/tree/master/notebooks/mortality) (the chronic kidney disease and hospital datasets require approval for access)

- Browse the [released notebooks](https://github.com/suinleelab/treeexplainer-study/tree/master/notebooks) (still under construction).