Plots Variable Importance from Random Forest in R

random-forest.r

library(randomForest)
library(dplyr)
library(ggplot2)

set.seed(42)

rf_out <- randomForest(Species ~ ., data=iris)

# Extracts variable importance (Mean Decrease in Gini Index)
# Sorts by variable importance and relevels factors to match ordering
var_importance <- data_frame(variable=setdiff(colnames(iris), "Species"),
                             importance=as.vector(importance(rf_out)))
var_importance <- arrange(var_importance, desc(importance))
var_importance$variable <- factor(var_importance$variable, levels=var_importance$variable)

p <- ggplot(var_importance, aes(x=variable, weight=importance, fill=variable))
p <- p + geom_bar() + ggtitle("Variable Importance from Random Forest Fit")
p <- p + xlab("Demographic Attribute") + ylab("Variable Importance (Mean Decrease in Gini Index)")
p <- p + scale_fill_discrete(name="Variable Name")
p + theme(axis.text.x=element_blank(),
          axis.text.y=element_text(size=12),
          axis.title=element_text(size=16),
          plot.title=element_text(size=18),
          legend.title=element_text(size=16),
          legend.text=element_text(size=12))