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)
local_attributions_uncertainty()
now supports path = "average"
argument and plots shapley values (#29).local_attributions_uncertainty()
is renamed to break_down_uncertainty()
.shap()
is an alias for break_down_uncertainty()
.iBreakDown
is described on arXiv and linked in the CITATIONlocal_attributions_uncertainty()
function that measures uncertanity behind additive attributionsbreakDown2
has changed name to iBreakDown
local_attributions()
function user can force order in which variables shall be presentedplotD3()
function, that uses r2d3
package to generate interactive D3 plotsiBreakDown
is forked from breakDown
version 0.2.0