Learn R Programming

⚠️There's a newer version (2.4.3) of this package.Take me there.

DALEX (version 1.2.1)

moDel Agnostic Language for Exploration and eXplanation

Description

Unverified black box model is the path to the failure. Opaqueness leads to distrust. Distrust leads to ignoration. Ignoration leads to rejection. DALEX package xrays any model and helps to explore and explain its behaviour. Machine Learning (ML) models are widely used and have various applications in classification or regression. Models created with boosting, bagging, stacking or similar techniques are often used due to their high performance. But such black-box models usually lack of direct interpretability. DALEX package contains various methods that help to understand the link between input variables and model output. Implemented methods help to explore model on the level of a single instance as well as a level of the whole dataset. All model explainers are model agnostic and can be compared across different models. DALEX package is the cornerstone for 'DrWhy.AI' universe of packages for visual model exploration. Find more details in (Biecek 2018) .

Copy Link

Version

Install

install.packages('DALEX')

Monthly Downloads

5,324

Version

1.2.1

License

GPL

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/ModelOriented/DALEX

Homepage

https://ModelOriented.github.io/DALEX/

Maintainer

Przemyslaw Biecek

Last Published

April 25th, 2020

Functions in DALEX (1.2.1)

install_dependencies

Install all dependencies for the DALEX package

model_diagnostics

Dataset Level Model Diagnostics

loss_cross_entropy

Calculate Loss Functions

Exract info from model

Dataset Level Variable Importance as Change in Loss Function after Variable Permutations

plot.model_performance

Plot Dataset Level Model Performance Explanations

print.model_diagnostics

Print Dataset Level Model Diagnostics

print.model_info

Print model_info

model_performance

Dataset Level Model Performance Measures

Instance Level Parts of the Model Predictions

predict_profile

Instance Level Profile as Ceteris Paribus

plot.model_profile

Plot Dataset Level Model Profile Explanations

colors_discrete_drwhy

DrWhy color palettes for ggplot objects

Apartments Data

predict.explainer

Predictions for the Explainer

print.model_performance

Print Dataset Level Model Performance Summary

predict_diagnostics

Instance Level Residual Diagnostics

print.model_profile

Print Dataset Level Model Profile

Dataset Level Variable Profile as Partial Dependence or Accumulated Local Dependence Explanations

Update label of explainer object

variable_effect

Dataset Level Variable Effect as Partial Dependency Profile or Accumulated Local Effects

explain.default

Create Model Explainer

print.predict_diagnostics

Print Instance Level Residual Diagnostics

plot.model_diagnostics

Plot Dataset Level Model Diagnostics

DrWhy Theme for ggplot objects

FIFA 20 preprocessed data

Wrap Various Predict Functions

plot.predict_diagnostics

Plot Instance Level Residual Diagnostics

plot.predict_profile

Plot Variable Profile Explanations

print.description

Print Natural Language Descriptions

print.explainer

Print Explainer Summary

Update data of an explainer object

Passengers and Crew on the RMS Titanic Data

Human Resources Data