Local Interpretable Model-Agnostic Explanations (R port of original Python package)
order()
on data.frame
objectsexplain()
will now pass ...
on to the relevant predict()
method (#150)explain.data.frame()
gains a gower_pow
argument to modify the calculatedlime()
now warns when quantile binning is not feasible and uses standardlambda
value in the local model fit to match the one used in the
Python version according to the relationship given here:
https://stats.stackexchange.com/a/270705
NEWS.md
file to track changes to the package.NA
values (#8)plot_features()
(#38)h2o
(@mdancho84) (#40)NA
values (#45)Date
and POSIXt
columns. They will be kept constant during
permutations so that lime
will explain the model behaviour at the given
timepoint based on the remaining features (#39).plot_explanations()
for an overview plot of a large explanation set