train<- data.frame(ClaimID = c(1,2,3),
RearEnd = c(TRUE, FALSE, TRUE),
Fraud = c(TRUE, FALSE, TRUE))
train
## ClaimID RearEnd Fraud
## 1 1 TRUE TRUE
## 2 2 FALSE FALSE
## 3 3 TRUE TRUE
library(rpart)
## Warning: package 'rpart' was built under R version 4.3.3
mytree<-rpart(Fraud ~ RearEnd, data = train, method="class")
mytree
## n= 3
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 3 1 TRUE (0.3333333 0.6666667) *
mytree<-rpart(Fraud ~ RearEnd,
data = train,
method = "class",
minsplit=2,
minbucket=1)
mytree
## n= 3
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 3 1 TRUE (0.3333333 0.6666667)
## 2) RearEnd< 0.5 1 0 FALSE (1.0000000 0.0000000) *
## 3) RearEnd>=0.5 2 0 TRUE (0.0000000 1.0000000) *
library(rattle)
## Warning: package 'rattle' was built under R version 4.3.3
## Loading required package: tibble
## Loading required package: bitops
## Rattle: A free graphical interface for data science with R.
## Version 5.5.1 Copyright (c) 2006-2021 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.
library(rpart.plot)
## Warning: package 'rpart.plot' was built under R version 4.3.3
library(RColorBrewer)
fancyRpartPlot(mytree, caption = NULL)
mytree<- rpart(
Fraud ~ RearEnd,
data = train,
method = "class",
parms = list(split = 'information'),
minsplit = 2, minbucket = 1)
mytree
## n= 3
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 3 1 TRUE (0.3333333 0.6666667)
## 2) RearEnd< 0.5 1 0 FALSE (1.0000000 0.0000000) *
## 3) RearEnd>=0.5 2 0 TRUE (0.0000000 1.0000000) *
fancyRpartPlot(mytree, caption = NULL)
train<- data.frame(ClaimID = c(1,2,3),
RearEnd = c(TRUE, FALSE, TRUE),
Fraud = c(TRUE, FALSE, FALSE))
train
## ClaimID RearEnd Fraud
## 1 1 TRUE TRUE
## 2 2 FALSE FALSE
## 3 3 TRUE FALSE
mytree<-rpart(Fraud ~ RearEnd,
data = train,
method = "class",
minsplit=2,
minbucket=1,
cp = -1)
mytree
## n= 3
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 3 1 FALSE (0.6666667 0.3333333)
## 2) RearEnd< 0.5 1 0 FALSE (1.0000000 0.0000000) *
## 3) RearEnd>=0.5 2 1 FALSE (0.5000000 0.5000000) *
fancyRpartPlot(mytree, caption = NULL)
train<- data.frame(
claimID = 1:7,
RearEnd = c(TRUE, TRUE, FALSE,FALSE,FALSE,FALSE, FALSE),
Whiplash= c(TRUE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE),
Fraud = c(TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE)
)
train
## claimID RearEnd Whiplash Fraud
## 1 1 TRUE TRUE TRUE
## 2 2 TRUE TRUE TRUE
## 3 3 FALSE TRUE TRUE
## 4 4 FALSE TRUE FALSE
## 5 5 FALSE TRUE FALSE
## 6 6 FALSE FALSE FALSE
## 7 7 FALSE FALSE FALSE
mytree<- rpart(
Fraud ~ RearEnd + Whiplash,
data = train,
method = "class",
maxdepth =1,
minsplit=2,
minbucket=1)
fancyRpartPlot(mytree)
lossmatrix<-matrix(c(0,1,3,0), byrow = TRUE, nrow = 2)
lossmatrix
## [,1] [,2]
## [1,] 0 1
## [2,] 3 0
mytree<- rpart(
Fraud ~ RearEnd + Whiplash,
data = train,
method = "class",
maxdepth =1,
minsplit=2,
minbucket=1,
parms = list(loss = lossmatrix))
fancyRpartPlot(mytree)
train<-data.frame(
claimID = 1:5,
Activity = factor(x= c("active", "very active", "very active","inactive", "very inactive"), levels= c("very inactive", "inactive", "active", "very active"), order = TRUE),
Fraud = c(FALSE, TRUE, TRUE, FALSE, TRUE)
)
mytree<- rpart(
Fraud~ Activity,
data = train,
method = "class",
minsplit =2,
minbucket =1)
fancyRpartPlot(mytree, caption = NULL)
train<- data.frame(
claimID = 1:10,
RearEnd = c(TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE),
Whiplash = c(TRUE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE),
activity= factor(x= c("active", "very active", "very active", "inactive", "very active","inactive","very active", "active", "active", "very active"),
levels = c("very inactive", "inactive", "active", "very active"), ordered = TRUE),
Fraud = c(FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE))
train
## claimID RearEnd Whiplash activity Fraud
## 1 1 TRUE TRUE active FALSE
## 2 2 TRUE TRUE very active TRUE
## 3 3 TRUE TRUE very active TRUE
## 4 4 FALSE TRUE inactive FALSE
## 5 5 FALSE TRUE very active FALSE
## 6 6 FALSE FALSE inactive TRUE
## 7 7 FALSE FALSE very active TRUE
## 8 8 FALSE FALSE active FALSE
## 9 9 FALSE FALSE active FALSE
## 10 10 FALSE FALSE very active TRUE
mytree<- rpart(
Fraud ~ RearEnd + Whiplash + activity,
data = train,
method = "class",
minsplit = 2,
minbucket = 1,
cp = -1)
fancyRpartPlot(mytree, caption = NULL)
mytree$variable.importance
## Whiplash activity RearEnd
## 2.8266667 2.4000000 0.6266667
names(mytree)
## [1] "frame" "where" "call"
## [4] "terms" "cptable" "method"
## [7] "parms" "control" "functions"
## [10] "numresp" "splits" "csplit"
## [13] "variable.importance" "y" "ordered"
printcp(mytree)
##
## Classification tree:
## rpart(formula = Fraud ~ RearEnd + Whiplash + activity, data = train,
## method = "class", minsplit = 2, minbucket = 1, cp = -1)
##
## Variables actually used in tree construction:
## [1] activity RearEnd Whiplash
##
## Root node error: 5/10 = 0.5
##
## n= 10
##
## CP nsplit rel error xerror xstd
## 1 0.6 0 1.0 2.0 0.00000
## 2 0.1 1 0.4 0.4 0.25298
## 3 -1.0 5 0.0 0.4 0.25298
mytree<-prune(mytree, cp = 0.21)
fancyRpartPlot(mytree)
