![]() # Permutation scores (boxplot colored by feature) library(ggplot2) # for `aes_string()` function vip(model, method = "permute", train = mtcars, target = "mpg", nsim = 10 , Metric = "rmse", pred_wrapper = pfun, geom = "boxplot" ) # Permutation scores (boxplot) vip(model, method = "permute", train = mtcars, target = "mpg", nsim = 10 , Vip(model, method = "permute", train = mtcars, target = "mpg", nsim = 10 ,Īesthetics = list (color = "grey50", fill = "grey50" ),Īll_permutations = TRUE, jitter = TRUE ) # Permutation scores (barplot w/ raw values and jittering) pfun <- function (object, newdata) predict(object, newdata = newdata) # Fit a projection pursuit regression model model \%` operator is imported for convenience see ?magrittr::`%T>%` # for details vi_scores % # A projection pursuit regression example # Load the sample data data(mtcars) Variable importance computed in the axis label. Logical indicating whether or not to include the type of Logical indicating whether or not to jitter the raw permutation Used for permutation scores when nsim > 1.) Permutation scores along with the average. Logical indicating whether or not to plot all Logical indicating whether or not to plot the importance These are often aesthetics, used to set anĪesthetic to a fixed value, like colour = "red" or size = 3. List specifying additional arguments passed on to Only for the permutation-based importance method with nsim > 1 andĬonstruct a violin plot of the variable importance scores. ![]() The currently available options are described below.Ī bar chart of the variable importance scores.Ĭonstruct a Cleveland dot plot of the variable importance scores.Ĭonstruct a boxplot plot of the variable importance scores. Integer specifying the number of variable importanceĬharacter string specifying which type of plot to construct. A fitted model object (e.g., a "randomForest" object) orĪdditional optional arguments to be passed on to vi. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |