Load the spam data
library(kernlab)
data(spam)
head(spam)
## make address all num3d our over remove internet order mail receive
## 1 0.00 0.64 0.64 0 0.32 0.00 0.00 0.00 0.00 0.00 0.00
## 2 0.21 0.28 0.50 0 0.14 0.28 0.21 0.07 0.00 0.94 0.21
## 3 0.06 0.00 0.71 0 1.23 0.19 0.19 0.12 0.64 0.25 0.38
## 4 0.00 0.00 0.00 0 0.63 0.00 0.31 0.63 0.31 0.63 0.31
## 5 0.00 0.00 0.00 0 0.63 0.00 0.31 0.63 0.31 0.63 0.31
## 6 0.00 0.00 0.00 0 1.85 0.00 0.00 1.85 0.00 0.00 0.00
## will people report addresses free business email you credit your font
## 1 0.64 0.00 0.00 0.00 0.32 0.00 1.29 1.93 0.00 0.96 0
## 2 0.79 0.65 0.21 0.14 0.14 0.07 0.28 3.47 0.00 1.59 0
## 3 0.45 0.12 0.00 1.75 0.06 0.06 1.03 1.36 0.32 0.51 0
## 4 0.31 0.31 0.00 0.00 0.31 0.00 0.00 3.18 0.00 0.31 0
## 5 0.31 0.31 0.00 0.00 0.31 0.00 0.00 3.18 0.00 0.31 0
## 6 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0
## num000 money hp hpl george num650 lab labs telnet num857 data num415
## 1 0.00 0.00 0 0 0 0 0 0 0 0 0 0
## 2 0.43 0.43 0 0 0 0 0 0 0 0 0 0
## 3 1.16 0.06 0 0 0 0 0 0 0 0 0 0
## 4 0.00 0.00 0 0 0 0 0 0 0 0 0 0
## 5 0.00 0.00 0 0 0 0 0 0 0 0 0 0
## 6 0.00 0.00 0 0 0 0 0 0 0 0 0 0
## num85 technology num1999 parts pm direct cs meeting original project
## 1 0 0 0.00 0 0 0.00 0 0 0.00 0
## 2 0 0 0.07 0 0 0.00 0 0 0.00 0
## 3 0 0 0.00 0 0 0.06 0 0 0.12 0
## 4 0 0 0.00 0 0 0.00 0 0 0.00 0
## 5 0 0 0.00 0 0 0.00 0 0 0.00 0
## 6 0 0 0.00 0 0 0.00 0 0 0.00 0
## re edu table conference charSemicolon charRoundbracket
## 1 0.00 0.00 0 0 0.00 0.000
## 2 0.00 0.00 0 0 0.00 0.132
## 3 0.06 0.06 0 0 0.01 0.143
## 4 0.00 0.00 0 0 0.00 0.137
## 5 0.00 0.00 0 0 0.00 0.135
## 6 0.00 0.00 0 0 0.00 0.223
## charSquarebracket charExclamation charDollar charHash capitalAve
## 1 0 0.778 0.000 0.000 3.756
## 2 0 0.372 0.180 0.048 5.114
## 3 0 0.276 0.184 0.010 9.821
## 4 0 0.137 0.000 0.000 3.537
## 5 0 0.135 0.000 0.000 3.537
## 6 0 0.000 0.000 0.000 3.000
## capitalLong capitalTotal type
## 1 61 278 spam
## 2 101 1028 spam
## 3 485 2259 spam
## 4 40 191 spam
## 5 40 191 spam
## 6 15 54 spam
Let’s use “your” as the word to predict spam
plot(density(spam$your[spam$type=="nonspam"]),
col="blue",main="",xlab="Frequency of 'your'")
lines(density(spam$your[spam$type=="spam"]),col="red")
##From the graph, we can see the spam email will have a higher frequencies of your, so, in our algorithm, we use frequencies of 'your'>0.5 as the evidence to predict this email is spam.
abline(v=0.5,col="black")
And make the prediction and evaluation
prediction<- ifelse(spam$your>0.5,"spam","nonspam")
table(prediction,spam$type)/length(spam$type)
##
## prediction nonspam spam
## nonspam 0.4590306 0.1017170
## spam 0.1469246 0.2923278
The accuracy is 0.459+0.292=0.751=75.1%