#defining dataset
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
#specify the model formula, data, and method parameters
#classify the feature Fraud using the predictor RearEnd
#syntax: function(dependent var ~ independent var)
#syntax to list more than 1 ind. var: function(dependent var ~ independent var + ...)
#syntax to list all ind. var: function(dependent var ~ .)
#mytree is our decision tree
library(rpart)
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)
#plot mytree
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)
#change values
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) #what does this mean?
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, caption = NULL)
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, #min number of observactions that can exist on a leaf
parms = list(loss = lossmatrix))
fancyRpartPlot(mytree, caption = NULL)
train <- data.frame(
ClaimID = c(1,2,3,4,5),
Activity = factor( x = c("active", "very active", "very active", "inactive",
"very active"), levels = c("very inactive", "inactive", "active", "very active"),
order = TRUE),
Fraud = c(FALSE, TRUE, TRUE, FALSE, TRUE))
train
## ClaimID Activity Fraud
## 1 1 active FALSE
## 2 2 very active TRUE
## 3 3 very active TRUE
## 4 4 inactive FALSE
## 5 5 very active TRUE
mytree<- rpart(
Fraud~Activity,
data = train,
method = "class", #use class for classifications problems
minsplit = 2, #min obeservations that must exist in order for a split to be made
minbucket = 1) #min number of observactions that can exist on a leaf
fancyRpartPlot(mytree, caption = NULL)
train <- data.frame(
ClaimID = 1:10,
RearEnd = c(TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE),
Whiplash = c(TRUE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE, FALSE, FALSE, TRUE),
Activity = factor( x = c("active", "very active", "very active", "inactive",
"very inactive", "inactive", "very inactive", "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 inactive FALSE
## 6 6 FALSE FALSE inactive TRUE
## 7 7 FALSE FALSE very inactive TRUE
## 8 8 TRUE FALSE active FALSE
## 9 9 TRUE FALSE active FALSE
## 10 10 FALSE TRUE very active TRUE
#Grow a full tree
mytree<- rpart(
Fraud~RearEnd + Whiplash + Activity,
data = train,
method = "class",
minsplit = 2,
minbucket = 1,
cp = -1) #cp: complexity parameter
fancyRpartPlot(mytree, caption = NULL)
names(mytree) #will display the attributes
## [1] "frame" "where" "call"
## [4] "terms" "cptable" "method"
## [7] "parms" "control" "functions"
## [10] "numresp" "splits" "csplit"
## [13] "variable.importance" "y" "ordered"
mytree$method
## [1] "class"
print(mytree$method)
## [1] "class"
print(mytree$finalmodel)
## NULL
mytree$variable.importance
## Activity Whiplash RearEnd
## 3.0000000 2.0000000 0.8571429
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 0.2 1 0.4 0.4 0.25298
## 3 -1.0 3 0.0 0.4 0.25298
mytree <- prune(mytree, cp = 0.21)
fancyRpartPlot(mytree)
