lime (0.4.1)

0 users

Local Interpretable Model-Agnostic Explanations.

https://github.com/thomasp85/lime
http://cran.r-project.org/web/packages/lime

When building complex models, it is often difficult to explain why the model should be trusted. While global measures such as accuracy are useful, they cannot be used for explaining why a model made a specific prediction. 'lime' (a port of the 'lime' 'Python' package) is a method for explaining the outcome of black box models by fitting a local model around the point in question an perturbations of this point. The approach is described in more detail in the article by Ribeiro et al. (2016) .

Maintainer: Thomas Lin Pedersen
Author(s): Thomas Lin Pedersen [cre, aut], Michal Benesty [aut]

License: MIT + file LICENSE

Uses: assertthat, ggplot2, glmnet, gower, htmlwidgets, Matrix, Rcpp, shiny, shinythemes, stringi, MASS, testthat, devtools, knitr, mlr, h2o, xgboost, rmarkdown, covr, ranger, text2vec, magick, keras
Reverse suggests: iml

Released 7 months ago.


3 previous versions

Ratings

Overall:

  (0 votes)

Documentation:

  (0 votes)

Log in to vote.

Reviews

No one has written a review of lime yet. Want to be the first? Write one now.


Related packages:(20 best matches, based on common tags.)


Search for lime on google, google scholar, r-help, r-devel.

Visit lime on R Graphical Manual.