You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is an R port of the Python lime package
(https://github.com/marcotcr/lime) developed by the authors of the
lime (Local Interpretable Model-agnostic Explanations) approach for
black-box model explanations. All credits for the invention of the
approach goes to the original developers.
The purpose of lime is to explain the predictions of black box
classifiers. What this means is that for any given prediction and any
given classifier it is able to determine a small set of features in the
original data that has driven the outcome of the prediction. To learn
more about the methodology of lime read the
paper and visit the repository of
the original implementation.
The lime package for R does not aim to be a line-by-line port of its
Python counterpart. Instead it takes the ideas laid out in the original
code and implements them in an API that is idiomatic to R.
An example
Out of the box lime supports a long range of models, e.g. those
created with caret, parsnip, and mlr. Support for unsupported models are
easy to achieve by adding a predict_model and model_type method for
the given model.
The following shows how a random forest model is trained on the iris
data set and how lime is then used to explain a set of new
observations:
library(caret)
library(lime)
# Split up the data setiris_test<-iris[1:5, 1:4]
iris_train<-iris[-(1:5), 1:4]
iris_lab<-iris[[5]][-(1:5)]
# Create Random Forest model on iris datamodel<- train(iris_train, iris_lab, method='rf')
# Create an explainer objectexplainer<- lime(iris_train, model)
# Explain new observationexplanation<- explain(iris_test, explainer, n_labels=1, n_features=2)
# The output is provided in a consistent tabular format and includes the# output from the model.explanation#> # A tibble: 10 × 13#> model_type case label label_prob model_r2 model_intercept model_prediction#> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>#> 1 classificat… 1 seto… 1 0.700 0.120 0.984#> 2 classificat… 1 seto… 1 0.700 0.120 0.984#> 3 classificat… 2 seto… 1 0.681 0.128 0.978#> 4 classificat… 2 seto… 1 0.681 0.128 0.978#> 5 classificat… 3 seto… 1 0.686 0.126 0.976#> 6 classificat… 3 seto… 1 0.686 0.126 0.976#> 7 classificat… 4 seto… 1 0.708 0.119 0.982#> 8 classificat… 4 seto… 1 0.708 0.119 0.982#> 9 classificat… 5 seto… 1 0.682 0.126 0.981#> 10 classificat… 5 seto… 1 0.682 0.126 0.981#> # ℹ 6 more variables: feature <chr>, feature_value <dbl>, feature_weight <dbl>,#> # feature_desc <chr>, data <list>, prediction <list># And can be visualised directly
plot_features(explanation)
#> Warning: `aes_()` was deprecated in ggplot2 3.0.0.#> ℹ Please use tidy evaluation idioms with `aes()`#> ℹ The deprecated feature was likely used in the lime package.#> Please report the issue at <https://github.com/tidymodels/lime/issues>.#> This warning is displayed once every 8 hours.#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was#> generated.
lime also supports explaining image and text models. For image
explanations the relevant areas in an image can be highlighted:
Here we see that the second most probably class is hardly true, but is
due to the model picking up waxy areas of the produce and interpreting
them as wax-light surface.
For text the explanation can be shown by highlighting the important
words. It even includes a shiny application for interactively
exploring text models:
interactive text explainer
Installation
lime is available on CRAN and can be installed using the standard
approach:
install.packages('lime')
To get the development version, install from GitHub instead:
