A library for debugging/inspecting machine learning classifiers and explaining their predictions

Last update: Dec 30, 2022

Overview

ELI5

ELI5 is a Python package which helps to debug machine learning classifiers and explain their predictions.

It provides support for the following machine learning frameworks and packages:

scikit-learn. Currently ELI5 allows to explain weights and predictions of scikit-learn linear classifiers and regressors, print decision trees as text or as SVG, show feature importances and explain predictions of decision trees and tree-based ensembles. ELI5 understands text processing utilities from scikit-learn and can highlight text data accordingly. Pipeline and FeatureUnion are supported. It also allows to debug scikit-learn pipelines which contain HashingVectorizer, by undoing hashing.
Keras - explain predictions of image classifiers via Grad-CAM visualizations.
xgboost - show feature importances and explain predictions of XGBClassifier, XGBRegressor and xgboost.Booster.
LightGBM - show feature importances and explain predictions of LGBMClassifier and LGBMRegressor.
CatBoost - show feature importances of CatBoostClassifier, CatBoostRegressor and catboost.CatBoost.
lightning - explain weights and predictions of lightning classifiers and regressors.
sklearn-crfsuite. ELI5 allows to check weights of sklearn_crfsuite.CRF models.

ELI5 also implements several algorithms for inspecting black-box models (see Inspecting Black-Box Estimators):

TextExplainer allows to explain predictions of any text classifier using LIME algorithm (Ribeiro et al., 2016). There are utilities for using LIME with non-text data and arbitrary black-box classifiers as well, but this feature is currently experimental.
Permutation importance method can be used to compute feature importances for black box estimators.

Explanation and formatting are separated; you can get text-based explanation to display in console, HTML version embeddable in an IPython notebook or web dashboards, a pandas.DataFrame object if you want to process results further, or JSON version which allows to implement custom rendering and formatting on a client.

License is MIT.

Check docs for more.

A library for debugging/inspecting machine learning classifiers and explaining their predictions

Related tags

Overview

ELI5

Owner

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

Code for visualizing the loss landscape of neural nets

GNNLens2 is an interactive visualization tool for graph neural networks (GNN).

Visual analysis and diagnostic tools to facilitate machine learning model selection.

A library for debugging/inspecting machine learning classifiers and explaining their predictions

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

Visualization Toolbox for Long Short Term Memory networks (LSTMs)

Code for "High-Precision Model-Agnostic Explanations" paper

Model analysis tools for TensorFlow

An intuitive library to add plotting functionality to scikit-learn objects.

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

Interactive convnet features visualization for Keras

Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)

A collection of infrastructure and tools for research in neural network interpretability.

A python library for decision tree visualization and model interpretation.

A library that implements fairness-aware machine learning algorithms

PyTorch implementation of DeepDream algorithm

Visualization toolkit for neural networks in PyTorch! Demo -->

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

L2X - Code for replicating the experiments in the paper Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.