Я пришел к решению проблемы выше и решил опубликовать его в качестве своего собственного ответа.Я написал небольшую функцию для отображения важности переменных, не полагаясь на вспомогательные функции caret
для создания графиков.Я использовал dotplot
и levelplot
, потому что caret
возвращает data.frame
, который отличается в зависимости от предоставленного алгоритма.Он может не работать на разных алгоритмах и моделях, которые не подходят.
# Libraries ---------------------------------------------------------------
library(caret) # To train ML algorithms
library(dplyr) # Required for %>% operators in custom function below
library(caretEnsemble) # To train multiple caret models
library(lattice) # Required for plotting, should be loaded alongside caret
library(gridExtra) # Required for plotting multiple plots
# Custom function ---------------------------------------------------------
# The function requires list of models as input and is used in for loop
plot_importance <- function(importance_list, imp, algo_names) {
importance <- importance_list[[imp]]$importance
model_title <- algo_names[[imp]]
if (ncol(importance) < 2) { # Plot dotplot if dim is ncol < 2
importance %>%
as.matrix() %>%
dotplot(main = model_title)
} else { # Plot heatmap if ncol > 2
importance %>%
as.matrix() %>%
levelplot(xlab = NULL, ylab = NULL, main = model_title, scales = list(x = list(rot = 45)))
}
}
# Tuning parameters -------------------------------------------------------
# Set algorithms I wish to fit
# Rather than using methodList as provided above, I've switched to tuneList because I need to control tuning parameters of random forest algorithm.
my_algorithms <- list(
glmnet = caretModelSpec(method = "glmnet"),
rpart = caretModelSpec(method = "rpart"),
svmRadial = caretModelSpec(method = "svmRadial"),
rf = caretModelSpec(method = "rf", importance = TRUE), # Importance is not computed for "rf" by default
nnet = caretModelSpec(method = "nnet"),
knn = caretModelSpec(method = "knn")
)
# Define controls
my_controls <- trainControl(
method = "cv",
savePredictions = "final",
number = 3
)
# Run the models all at once with caretEnsemble
my_list_of_models <- caretList(Species ~ .,
data = iris,
tuneList = my_algorithms,
trControl = my_controls
)
# Extract variable importance ---------------------------------------------
importance <- lapply(my_list_of_models, varImp)
# Plotting variable immportance -------------------------------------------
# Create second loop to go over extracted importance and plot it using plot()
importance_plots <- list()
for (imp in seq_along(importance)) {
# importance_plots[[imp]] <- plot(importance[[imp]])
importance_plots[[imp]] <- plot_importance(importance_list = importance, imp = imp, algo_names = names(my_list_of_models))
}
# Multiple plots at once
do.call("grid.arrange", c(importance_plots))