AxeldeRomblay / interpret

Fit interpretable models. Explain blackbox machine learning.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

InterpretML - Alpha Release

License Python Version Package Version Build Status Maintenance

Equal contributions: Samuel Jenkins & Harsha Nori & Paul Koch & Rich Caruana


In the beginning machines learned in darkness, and data scientists struggled in the void to explain them.

Let there be light.


InterpretML is an open-source package for training interpretable models and explaining blackbox systems. Interpretability is essential for:

  • Model debugging - Why did my model make this mistake?
  • Detecting bias - Does my model discriminate?
  • Human-AI cooperation - How can I understand and trust the model's decisions?
  • Regulatory compliance - Does my model satisfy legal requirements?
  • High-risk applications - Healthcare, finance, judicial, ...

Historically, the most intelligible models were not very accurate, and the most accurate models were not intelligible. Microsoft Research has developed an algorithm called the Explainable Boosting Machine (EBM)* which has both high accuracy and intelligibility. EBM uses modern machine learning techniques like bagging and boosting to breathe new life into traditional GAMs (Generalized Additive Models). This makes them as accurate as random forests and gradient boosted trees, and also enhances their intelligibility and editability.


Notebook for reproducing table

Dataset/AUROC Domain Logistic Regression Random Forest XGBoost Explainable Boosting Machine
Adult Income Finance .907±.003 .903±.002 .922±.002 .928±.002
Heart Disease Medical .895±.030 .890±.008 .870±.014 .916±.010
Breast Cancer Medical .995±.005 .992±.009 .995±.006 .995±.006
Telecom Churn Business .804±.015 .824±.002 .850±.006 .851±.005
Credit Fraud Security .979±.002 .950±.007 .981±.003 .975±.005

In addition to EBM, InterpretML also supports methods like LIME, SHAP, linear models, partial dependence, decision trees and rule lists. The package makes it easy to compare and contrast models to find the best one for your needs.

* EBM is a fast implementation of GA2M. Details on the algorithm can be found here.


Installation

Python 3.5+ | Linux, Mac OS X, Windows

pip install numpy scipy pyscaffold
pip install -U interpret

Getting Started

Let's fit an Explainable Boosting Machine

from interpret.glassbox import ExplainableBoostingClassifier

ebm = ExplainableBoostingClassifier()
ebm.fit(X_train, y_train)

# EBM supports pandas dataframes, numpy arrays, and handles "string" data natively.

Understand the model

from interpret import show

ebm_global = ebm.explain_global()
show(ebm_global)

Global Explanation Image


Understand individual predictions

ebm_local = ebm.explain_local(X_test, y_test)
show(ebm_local)

Local Explanation Image


And if you have multiple models, compare them

show([logistic_regression, decision_tree])

Dashboard Image


Example Notebooks

Roadmap

Currently we're working on:

  • Multiclass Classification Support
  • Missing Values Support
  • Improved Categorical Encoding

...and lots more! Get in touch to find out more.

Contributing

If you are interested contributing directly to the code base, please see CONTRIBUTING.md

Acknowledgements

Many people have supported us along the way. Check out ACKNOWLEDGEMENTS.md!


We also build on top of many great packages. Please check them out!

plotly | dash | scikit-learn | lime | shap | salib | skope-rules | gevent | joblib | pytest | jupyter

Contact us

Multiple ways to get in touch:

Reporting Security Issues (we had to include this...)

Security issues and bugs should be reported privately, via email, to the Microsoft Security Response Center (MSRC) at secure@microsoft.com. You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Further information, including the MSRC PGP key, can be found in the Security TechCenter.









































If a tree fell in your random forest, would anyone notice?

About

Fit interpretable models. Explain blackbox machine learning.

License:MIT License


Languages

Language:C++ 55.9%Language:Python 35.6%Language:Jupyter Notebook 2.6%Language:CSS 2.4%Language:Shell 2.3%Language:C 1.0%Language:Batchfile 0.1%Language:JavaScript 0.1%