autoInterpret: Automated model interpretability
In XanderHorn/autoML: Automated machine learning

Description Usage Arguments Value Author(s) Examples

Generates various plots for model interpretability

1 2	autoInterpret(train, trainedModel, sample = NULL, seed = 1991, verbose = TRUE)

`train`	[data.frame \| Required] Training set on which the original model was trained
`trainedModel`	[mlr model object \| Required] A trained model using the mlr pacakge or produced via autoLearn
`sample`	[numeric \| Optional] A number between 0 - 1 to sub-sample the training set for faster computational time. Default of NULL which will result in a small sample
`seed`	[integer \| Optional] Random seed number for reproducable results. Default of 1991

List containing plots

Xander Horn

train <- iris
mod <- mlr::train(makeLearner("classif.ranger", predict.type = "prob"), iris.task)

plots <- autoInterpret(train = iris,
trainedModel = mod)