Alibi Explain — Alibi 0.9.5 documentation (original) (raw)

stable

Alibi

• Alibi Explain
• Edit on GitHub

Alibi Explain is an open source Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-quality implementations of black-box, white-box, local and global explanation methods for classification and regression models.

Overview

• Introduction
• Getting Started
• Algorithm overview
• White-box and black-box models
• Saving and loading
• Frequently Asked Questions

Explanations

• Methods
  • Accumulated Local Effects
  • Anchors
  • Contrastive Explanation Method
  • Counterfactual Instances
  • Counterfactuals Guided by Prototypes
  • Counterfactuals with Reinforcement Learning
  • Integrated Gradients
  • Kernel SHAP
  • Partial Dependence
  • Partial Dependence Variance
  • Permutation Importance
  • Similarity explanations
  • Tree SHAP
• Examples
  • Alibi Overview Example
  • Accumulated Local Effects
  • Anchors
  • Contrastive Explanation Method
  • Counterfactual Instances
  • Counterfactuals Guided by Prototypes
  • Counterfactuals with Reinforcement Learning
  • Integrated Gradients
  • Kernel SHAP
  • Partial Dependence
  • Partial Dependence Variance
  • Permutation Importance
  • Similarity explanations
  • Tree SHAP

Model Confidence

• Methods
  • Measuring the linearity of machine learning models
  • Trust Scores
• Examples
  • Measuring the linearity of machine learning models
  • Trust Scores

Prototypes

• Methods
  • ProtoSelect
• Examples
  • ProtoSelect