Mutiple02

tidyHeatmap

rm(list=ls())
set.seed(1)
library(mlbench)
library(randomForest)

## randomForest 4.6-14

## Type rfNews() to see new features/changes/bug fixes.

library(forestFloor)
library(AUC)

## AUC 0.3.0

## Type AUCNews() to see the change log and ?AUC to get an overview.

library(data.table)

setwd("C:/Users/s-das/Syncplicity/MyProjects_IMP/MY_Papers_V2/TRB 2021/EScotter_BayesianRule/")
it01 <- fread("IT_aadtMaster.csv")

## Warning in require_bit64_if_needed(ans): Some columns are type 'integer64'
## but package bit64 is not installed. Those columns will print as strange
## looking floating point data. There is no need to reload the data. Simply
## install.packages('bit64') to obtain the integer64 print method and print the
## data again.

mn= subset(it01, State=="MT")
dim(mn)

## [1] 1024   86

mn01 <- mn[, c("FC_RU", "Default_AADT", "HU", "Pop" , "WAC", "RAC", "Agg_Inc", "Agg_Veh", "Empl" )]
mn02= na.omit(mn01)
mn02$FC_RU= as.factor(mn02$FC_RU)
mn02 <- mn02[,-c(2)]

x <- mn02[, -1]
y <- mn02$FC_RU

#train default model and the most regularized model with same predictive performance
rf.default = randomForest(x,y,ntree=5000)
rf.robust = randomForest(x,y,sampsize=25,ntree=5000,mtry=4,
                         keep.inbag = T,keep.forest = T)
#verify similar performance
plot(roc(rf.default$votes[,2],y),main="ROC: default black, robust is red")
plot(roc(rf.robust$votes[,2],y),col=2,add = T)

auc(roc(rf.default$votes[,2],y))

## [1] 0.7506225

auc(roc(rf.robust$votes[,2],y))

## [1] 0.581554

#compute feature contributions
ff = forestFloor(rf.robust,x,calc_np=T)
Col = fcol(ff,cols=1,outlier.lim = 2.5)

#the plot in this blog
plot(ff,col=Col,plot_GOF = T)

#some 3d plots
##show3d(ff,c(1,5),5,col=Col,plot_GOF = T)