Learn R Programming
⚠️There's a newer version (2.3.0) of this package.Take me there.

DALEXtra (version 1.3.2)

Extension for 'DALEX' Package

Description

Provides wrapper of various machine learning models. In applied machine learning, there is a strong belief that we need to strike a balance between interpretability and accuracy. However, in field of the interpretable machine learning, there are more and more new ideas for explaining black-box models, that are implemented in 'R'. 'DALEXtra' creates 'DALEX' Biecek (2018) explainer for many type of models including those created using 'python' 'scikit-learn' and 'keras' libraries, and 'java' 'h2o' library. Important part of the package is Champion-Challenger analysis and innovative approach to model performance across subsets of test data presented in Funnel Plot. Third branch of 'DALEXtra' package is aspect importance analysis that provides instance-level explanations for the groups of explanatory variables.

Copy Link

Version

Install

install.packages('DALEXtra')

Monthly Downloads

1,902

Version

1.3.2

License

GPL

Issues

2

Pull Requests

1

Stars

67

Forks

10

Maintainer

Szymon Maksymiuk

Last Published

July 28th, 2020

Functions in DALEXtra (1.3.2)

explain_mlr

Create explainer from your mlr model
explain_h2o

Create explainer from your h2o model
explain_scikitlearn

Wrapper for Python Scikit-Learn Models
explain_mlr3

Create explainer from your mlr model
champion_challenger

Compare machine learning models
aspect_importance

Calculates the feature groups importance (called aspects importance) for a selected observation
create_env

Create your conda virtual env with DALEX
explain_keras

Wrapper for Python Keras Models
aspect_importance_single

Aspects importance for single aspects
explain_xgboost

Create explainer from your xgboost model
overall_comparison

Compare champion with challengers globally
training_test_comparison

Compare performance of model between training and test set
plot_aspects_importance_grouping

Function plots tree with aspect importance values
print.training_test_comparison

Print funnel_measure object
plot.training_test_comparison

Plot and compare performance of model between training and test set
plot.aspect_importance

Function for plotting aspect_importance results
print.funnel_measure

Print funnel_measure object
plot_group_variables

Plots tree with correlation values
plot.funnel_measure

Funnel plot for difference in measures
plot.overall_comparison

Plot function for overall_comparison
funnel_measure

Caluculate difference in performance in models across different categories
triplot

Three plots that sum up automatic aspect importance grouping
get_sample

Function for getting binary matrix
yhat.WrappedModel

Wrapper over the predict function
print.scikitlearn_set

Prints scikitlearn_set class
print.overall_comparison

Print overall_comparison object
group_variables

Groups numeric features into aspects
model_info.WrappedModel

Exract info from model