Model Agnostic Instance Level Variable Attributions

Model agnostic tool for decomposition of predictions from black boxes. Supports additive attributions and attributions with interactions. The Break Down Table shows contributions of every variable to a final prediction. The Break Down Plot presents variable contributions in a concise graphical way. This package works for classification and regression models. It is an extension of the 'breakDown' package (Staniak and Biecek 2018) , with new and faster strategies for orderings. It supports interactions in explanations and has interactive visuals (implemented with 'D3.js' library). The methodology behind is described in the 'iBreakDown' article (Gosiewska and Biecek 2019) This package is a part of the 'DrWhy.AI' universe (Biecek 2018) .


iBreakDown 0.9.6

  • Function local_attributions_uncertainty() now supports path = "average" argument and plots shapley values (#29).
  • Function local_attributions_uncertainty() is renamed to break_down_uncertainty().
  • Function shap() is an alias for break_down_uncertainty().

iBreakDown 0.9.5

  • methodology behind iBreakDown is described on arXiv and linked in the CITATION

iBreakDown 0.9.4

  • code refactoring
  • added local_attributions_uncertainty() function that measures uncertanity behind additive attributions

iBreakDown 0.9.3

  • breakDown2 has changed name to iBreakDown

iBreakDown 0.9.2

  • in the local_attributions() function user can force order in which variables shall be presented

iBreakDown 0.9.1

  • added plotD3() function, that uses r2d3 package to generate interactive D3 plots

iBreakDown 0.9.0

  • Greedy strategies with time complexity O(p^2) are removed.
  • iBreakDown is forked from breakDown version 0.2.0

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


2.0.1 by Przemyslaw Biecek, 7 months ago,

Report a bug at

Browse source code at

Authors: Przemyslaw Biecek [aut, cre] , Alicja Gosiewska [aut] , Hubert Baniecki [aut] , Adam Izdebski [aut] , Dariusz Komosinski [ctb]

Documentation:   PDF Manual  

GPL-3 license

Imports ggplot2

Suggests DALEX, knitr, rmarkdown, randomForest, e1071, ranger, nnet, testthat, r2d3, jsonlite, covr

Imported by DALEX, EIX, arenar, modelStudio.

See at CRAN