setwd("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/SVM/2.Feature Set 1/TP/90")#install.packages("naivebayes")
library(naivebayes)## Warning: package 'naivebayes' was built under R version 3.4.3library(dplyr)## Warning: Installed Rcpp (0.12.16) different from Rcpp used to build dplyr (0.12.11).
## Please reinstall dplyr to avoid random crashes or undefined behavior.##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(psych)
library(ggplot2)##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphalibrary(e1071)
library(readxl)Import actual labels.
#Import Labels
Labels <- read_excel("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Naive Bayes/1.Labels/Source Data.xlsx")
Label <- Labels$ScoreImport the TP feature set with a 90th percentile cut-off.
#Import Features
Features <- read.csv("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/SVM/2.Feature Set 1/TP/90/Feature Set 1 90th TP.csv")
Features <- Features[-1]#Class 2
Label2 <- list()
for(i in 1:1000){
if(Label[i]==3| Label[i]==4){
Label2[i] <- 1
}else{
Label2[i] <- 0
}
}#As Factor
Label2 <- as.factor(unlist(Label2))#Class 3
Label3 <- list()
for(i in 1:1000){
if(Label[i]==5| Label[i]==6){
Label3[i] <- 1
}else{
Label3[i] <- 0
}
}#As Factor
Label3 <- as.factor(unlist(Label3))#Class 4
Label4 <- list()
for(i in 1:1000){
if(Label[i]==7| Label[i]==8){
Label4[i] <- 1
}else{
Label4[i] <- 0
}
}#As Factor
Label4 <- as.factor(unlist(Label4))#Class 5
Label5 <- list()
for(i in 1:1000){
if(Label[i]==9| Label[i]==10){
Label5[i] <- 1
}else{
Label5[i] <- 0
}
}#As Factor
Label5 <- as.factor(unlist(Label5))#All Labels
All <- list()
for(i in 1:1000){
if(Label[i]==9| Label[i]==10){
All[i] <- 5
}else if(Label[i]==7| Label[i]==8){
All[i] <- 4
}else if(Label[i]==5| Label[i]==6){
All[i] <- 3
}else{
All[i] <- 2
}
}#As Factor
All <- as.factor(unlist(All))#Transform Integer to Factor
for(i in 1:262){
Features[,i] <- as.numeric(Features[,i])
}
str(Features)## 'data.frame': 1000 obs. of 262 variables:
## $ access : num 0 0 0 0 0 0 0 0 0 0 ...
## $ air : num 0 0 0 0 0 0 0 0 0 0 ...
## $ airport : num 0 0 0 0 0 0 0 0 0 0 ...
## $ also : num 0 0 0 1 0 0 1 0 1 0 ...
## $ although : num 0 0 0 0 0 0 0 0 0 0 ...
## $ alway : num 0 0 0 0 0 0 0 0 0 0 ...
## $ amaz : num 0 0 0 0 1 0 0 0 0 0 ...
## $ amsterdam : num 0 1 0 1 0 0 0 0 0 0 ...
## $ and : num 1 0 0 0 0 0 0 0 0 0 ...
## $ area : num 0 0 0 1 0 0 0 0 0 0 ...
## $ around : num 0 0 0 1 0 0 0 0 0 0 ...
## $ arriv : num 1 0 0 0 1 0 0 0 0 0 ...
## $ ask : num 1 0 1 0 0 0 0 0 0 0 ...
## $ avail : num 1 0 0 0 0 0 0 0 0 0 ...
## $ away : num 0 0 0 0 0 0 0 0 0 0 ...
## $ back : num 0 1 1 0 0 0 0 0 0 0 ...
## $ bad : num 0 0 0 1 0 0 0 0 0 0 ...
## $ bar : num 0 0 1 1 0 0 0 0 0 0 ...
## $ bath : num 0 0 0 0 0 0 0 0 0 0 ...
## $ bathroom : num 0 0 0 0 0 0 0 0 0 0 ...
## $ beauti : num 1 0 0 0 0 0 1 0 0 0 ...
## $ bed : num 0 0 0 1 0 0 1 0 0 1 ...
## $ bedroom : num 0 0 0 0 0 0 0 0 0 0 ...
## $ best : num 1 0 0 0 0 0 0 0 0 0 ...
## $ better : num 0 0 0 0 0 0 0 0 0 0 ...
## $ big : num 1 0 0 0 0 0 0 0 0 1 ...
## $ bit : num 0 1 1 0 0 0 0 0 0 0 ...
## $ book : num 1 0 0 0 1 0 0 0 0 0 ...
## $ breakfast : num 0 0 1 0 0 0 0 1 0 1 ...
## $ buffet : num 0 0 0 0 0 0 0 0 0 0 ...
## $ build : num 0 0 0 1 1 0 0 0 0 0 ...
## $ busi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ but : num 0 0 0 0 0 0 0 0 0 0 ...
## $ can : num 1 1 0 0 0 0 0 0 0 0 ...
## $ center : num 0 0 0 0 0 0 0 0 0 0 ...
## $ centr : num 0 0 0 0 0 0 0 0 0 0 ...
## $ central : num 0 0 0 0 0 0 0 0 0 0 ...
## $ chang : num 1 0 0 0 0 0 1 0 0 0 ...
## $ charg : num 0 0 0 0 0 0 0 0 0 0 ...
## $ check : num 1 1 0 0 0 0 0 0 1 0 ...
## $ choic : num 0 0 0 0 0 0 0 0 0 0 ...
## $ citi : num 1 0 0 0 0 0 0 0 0 0 ...
## $ clean : num 0 0 0 1 0 0 1 0 1 0 ...
## $ close : num 1 0 0 0 0 0 0 0 0 0 ...
## $ coff : num 0 0 1 0 0 0 0 0 0 0 ...
## $ cold : num 0 0 0 0 0 0 0 0 0 0 ...
## $ come : num 0 0 0 0 0 0 0 0 0 0 ...
## $ comfi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ comfort : num 0 0 0 0 0 0 0 0 0 0 ...
## $ complet : num 0 0 0 0 1 0 0 0 0 0 ...
## $ condit : num 0 0 0 0 0 0 0 0 0 0 ...
## $ construct : num 0 0 0 0 0 0 0 0 0 0 ...
## $ conveni : num 0 0 0 0 0 0 0 0 0 0 ...
## $ cool : num 0 0 0 0 0 0 0 0 0 0 ...
## $ couldn : num 0 0 0 0 0 0 0 0 0 0 ...
## $ court : num 0 0 0 0 0 0 0 0 0 0 ...
## $ day : num 1 0 0 1 0 0 0 0 0 0 ...
## $ decor : num 0 0 0 0 0 0 0 0 0 0 ...
## $ definit : num 0 0 0 0 0 0 0 0 0 0 ...
## $ design : num 0 0 0 0 0 1 0 0 0 0 ...
## $ desk : num 0 0 0 0 0 0 0 0 0 0 ...
## $ didn : num 0 0 0 0 1 0 1 0 0 0 ...
## $ differ : num 0 0 0 1 0 0 0 0 0 0 ...
## $ direct : num 0 0 0 0 1 0 0 0 0 0 ...
## $ don : num 1 0 0 0 0 0 0 0 0 0 ...
## $ door : num 0 0 0 1 0 0 0 0 0 0 ...
## $ doubl : num 1 0 0 0 0 0 0 0 0 0 ...
## $ drink : num 0 0 0 0 0 0 0 0 0 0 ...
## $ due : num 1 0 0 0 0 0 0 0 0 0 ...
## $ earl : num 0 0 0 0 0 0 0 0 0 0 ...
## $ easi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ english : num 0 0 0 0 0 0 0 0 0 0 ...
## $ enjoy : num 0 0 0 0 0 0 0 1 0 0 ...
## $ enough : num 0 0 0 0 0 0 0 0 0 1 ...
## $ especi : num 0 0 0 0 1 0 0 0 0 0 ...
## $ etc : num 0 0 0 0 0 0 0 0 0 0 ...
## $ even : num 1 1 0 0 0 0 0 0 1 1 ...
## $ everi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ everyth : num 0 0 0 0 0 0 0 1 0 0 ...
## $ excel : num 0 1 0 0 0 0 0 0 0 0 ...
## $ except : num 0 0 0 0 0 0 0 0 0 0 ...
## $ expect : num 0 0 0 0 0 0 0 0 0 0 ...
## $ expen : num 0 0 0 0 0 0 0 0 0 0 ...
## $ experi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ extra : num 0 0 0 0 0 0 0 0 0 0 ...
## $ extrem : num 0 0 0 0 0 0 0 0 0 0 ...
## $ facil : num 0 0 0 0 0 0 0 0 0 0 ...
## $ fantast : num 0 1 0 0 0 0 0 0 0 0 ...
## $ far : num 0 0 0 0 0 0 0 0 0 0 ...
## $ feel : num 0 0 0 0 0 0 0 0 0 0 ...
## $ find : num 0 0 0 0 0 0 0 0 0 0 ...
## $ first : num 0 1 0 0 0 0 0 0 0 0 ...
## $ floor : num 1 0 0 1 0 0 1 0 0 0 ...
## $ food : num 0 1 0 0 0 0 0 1 0 1 ...
## $ free : num 0 0 0 0 0 0 0 0 0 0 ...
## $ fresh : num 0 0 0 0 0 0 0 0 0 0 ...
## $ friend : num 0 0 0 0 0 0 0 1 0 0 ...
## $ front : num 0 0 0 0 0 0 0 0 0 0 ...
## $ garden : num 1 0 0 0 0 0 0 0 0 0 ...
## [list output truncated]#Features
set.seed(1234)
ind <- sample(2,nrow(Features),replace = T, prob =c(0.8,0.2))
train <- Features[ind == 1,]
test <- Features[ind ==2,]train.labels.2 <- Label2[ind == 1]
test.labels.2 <- Label2[ind ==2]
train.labels.3 <- Label3[ind == 1]
test.labels.3 <- Label3[ind ==2]
train.labels.4 <- Label4[ind == 1]
test.labels.4 <- Label4[ind ==2]
train.labels.5 <- Label5[ind == 1]
test.labels.5 <- Label5[ind ==2]
train.labels <- All[ind == 1]
test.labels <- All[ind ==2]#SVM2
train2 <- train
train2$Score <- train.labels.2
SVM2 <- svm(Score~.,data = train2,scale = FALSE,probability=TRUE)
train3 <- train
train3$Score <- train.labels.3
SVM3 <- svm(Score~.,data = train3,scale = FALSE,probability=TRUE)
train4 <- train
train4$Score <- train.labels.4
SVM4 <- svm(Score~.,data = train4,scale = FALSE,probability=TRUE)
train5 <- train
train5$Score <- train.labels.5
SVM5 <- svm(Score~.,data = train5,scale = FALSE,probability=TRUE)P2 <- predict(SVM2,newdata = test,probability = TRUE)
P3 <- predict(SVM3,newdata = test,probability = TRUE)
P4 <- predict(SVM4,newdata = test,probability = TRUE)
P5 <- predict(SVM5,newdata = test,probability = TRUE)Prob2 <- attr(P2,"probabilities")
Prob3 <- attr(P3,"probabilities")
Prob4 <- attr(P4,"probabilities")
Prob5 <- attr(P5,"probabilities")Use probabilities as an input for the voting procedure. The class with the highest probability is chosen.
Voting.df <- data.frame(Prob2, Prob3,Prob4,Prob5)
colnames(Voting.df) <- c("Class 2: 1","Class2: 0","Class 3: 0","Class3: 1","Class 4: 0","Class4: 1","Class 5: 0","Class5: 1")
head(Voting.df)## Class 2: 1 Class2: 0 Class 3: 0 Class3: 1 Class 4: 0 Class4: 1
## 5 0.064345578 0.9356544 0.8824737 0.11752628 0.7478428 0.2521572
## 14 0.003140714 0.9968593 0.9067159 0.09328414 0.6059613 0.3940387
## 16 0.011047721 0.9889523 0.9147052 0.08529480 0.7694530 0.2305470
## 26 0.019067343 0.9809327 0.8693469 0.13065312 0.5985427 0.4014573
## 28 0.050646282 0.9493537 0.8605175 0.13948247 0.6567651 0.3432349
## 29 0.007679017 0.9923210 0.8491336 0.15086641 0.5143996 0.4856004
## Class 5: 0 Class5: 1
## 5 0.8217617 0.1782383
## 14 0.3497058 0.6502942
## 16 0.2345536 0.7654464
## 26 0.5807305 0.4192695
## 28 0.5852482 0.4147518
## 29 0.8479913 0.1520087SEQ <- c(1,4,6,8)
Transformed.Voting.df <- Voting.df[SEQ]
colnames(Transformed.Voting.df) <- c("2","3","4","5")
head(Transformed.Voting.df)## 2 3 4 5
## 5 0.064345578 0.11752628 0.2521572 0.1782383
## 14 0.003140714 0.09328414 0.3940387 0.6502942
## 16 0.011047721 0.08529480 0.2305470 0.7654464
## 26 0.019067343 0.13065312 0.4014573 0.4192695
## 28 0.050646282 0.13948247 0.3432349 0.4147518
## 29 0.007679017 0.15086641 0.4856004 0.1520087Evaluation <- Transformed.Voting.df
Index <- as.numeric(apply(Transformed.Voting.df,MARGIN = 1,which.max))
Index <- Index+1
Evaluation$Vote <- Index
Evaluation$Actual <- test.labelshead(Evaluation,100)## 2 3 4 5 Vote Actual
## 5 6.434558e-02 0.11752628 0.2521572 0.17823829 4 4
## 14 3.140714e-03 0.09328414 0.3940387 0.65029423 5 5
## 16 1.104772e-02 0.08529480 0.2305470 0.76544642 5 5
## 26 1.906734e-02 0.13065312 0.4014573 0.41926951 5 4
## 28 5.064628e-02 0.13948247 0.3432349 0.41475184 5 4
## 29 7.679017e-03 0.15086641 0.4856004 0.15200872 4 4
## 39 3.143766e-01 0.10624041 0.1843009 0.36686858 5 5
## 40 1.394859e-02 0.10914323 0.5797749 0.13861024 4 3
## 60 1.095387e-02 0.05171991 0.2437510 0.88509316 5 5
## 61 2.905198e-02 0.17082158 0.2728018 0.55248164 5 3
## 72 6.894445e-06 0.11041464 0.3082627 0.66388564 5 4
## 81 5.049476e-03 0.12709565 0.3438308 0.44249915 5 3
## 86 6.373419e-02 0.11663115 0.2640885 0.68405481 5 5
## 90 1.329941e-01 0.13455773 0.3276392 0.17031717 4 4
## 92 4.023990e-02 0.11258798 0.3407654 0.20589777 4 4
## 113 1.034119e-01 0.11530881 0.2952860 0.49180861 5 5
## 116 3.084220e-02 0.10590475 0.2668665 0.50000000 5 4
## 117 2.614230e-02 0.09476127 0.3351825 0.34843488 5 5
## 122 5.201759e-02 0.11894136 0.3385569 0.09462056 4 4
## 123 1.219155e-02 0.09563621 0.3474495 0.26415009 4 2
## 124 3.900060e-02 0.12276789 0.3533404 0.10816492 4 4
## 131 3.716960e-03 0.14622326 0.2734960 0.63056942 5 4
## 135 1.843947e-01 0.16108118 0.3525966 0.11057667 4 3
## 137 2.879472e-03 0.06591619 0.3895492 0.51954155 5 5
## 140 8.129223e-03 0.12141892 0.3935291 0.24600361 4 4
## 142 1.316361e-02 0.08724861 0.2805907 0.56726149 5 5
## 149 8.862847e-03 0.10356001 0.3508577 0.54595382 5 4
## 154 2.506550e-02 0.16517912 0.2250569 0.38857288 5 5
## 156 3.867297e-02 0.10739135 0.2959658 0.33238097 5 3
## 158 6.495675e-01 0.11681685 0.3880595 0.11792258 2 3
## 169 2.911855e-03 0.09841891 0.2224985 0.80030930 5 5
## 185 6.176478e-03 0.10892171 0.2172351 0.62406916 5 5
## 187 3.355239e-03 0.09790061 0.4650272 0.34700973 4 5
## 192 2.615147e-02 0.13008427 0.5568990 0.03821665 4 3
## 194 2.013992e-02 0.12510830 0.4286132 0.24193512 4 4
## 195 1.414909e-02 0.14887441 0.2923213 0.24660259 4 4
## 196 1.000022e-01 0.14211186 0.3923096 0.06986487 4 5
## 197 7.677740e-02 0.16776507 0.2416225 0.08935651 4 3
## 199 8.269897e-06 0.09295268 0.2870651 0.90346058 5 5
## 210 1.474080e-01 0.15381881 0.4213175 0.03284862 4 3
## 216 1.969575e-02 0.08161874 0.1403844 0.94722109 5 5
## 220 1.396573e-02 0.24489623 0.2842126 0.14003148 4 4
## 227 1.752587e-01 0.06167314 0.4398098 0.17356627 4 5
## 234 4.070017e-02 0.11956006 0.4619118 0.21754467 4 3
## 240 3.006334e-02 0.09350269 0.4343373 0.23347643 4 5
## 245 7.573167e-02 0.12694671 0.3135291 0.32239918 5 4
## 249 1.464371e-02 0.14163176 0.3061407 0.40469376 5 5
## 261 2.601235e-02 0.12091497 0.3411455 0.35523177 5 3
## 277 7.665763e-03 0.08815058 0.2487138 0.93732754 5 5
## 283 9.536890e-03 0.10280992 0.2875084 0.72243735 5 5
## 290 6.074725e-03 0.09039409 0.2147304 0.90230944 5 4
## 293 1.417258e-02 0.09211249 0.3416283 0.23891072 4 5
## 302 5.827514e-03 0.12726795 0.3075887 0.39753419 5 4
## 305 1.683449e-02 0.10902146 0.3913637 0.51949656 5 4
## 308 2.554649e-02 0.14778721 0.2229979 0.34842207 5 4
## 311 7.662605e-03 0.08679717 0.2473303 0.83505517 5 5
## 320 9.938439e-03 0.09937463 0.2552621 0.80551473 5 2
## 322 1.577391e-02 0.08202979 0.1842364 0.92055182 5 5
## 330 1.238635e-02 0.10288393 0.2092315 0.84773179 5 4
## 332 5.826713e-02 0.11134454 0.4241504 0.16970175 4 4
## 333 1.868893e-02 0.09863607 0.2898077 0.82328639 5 5
## 339 6.146743e-03 0.10102642 0.2928187 0.69963390 5 5
## 341 3.023034e-02 0.10555934 0.4653307 0.16461911 4 4
## 344 2.909234e-02 0.07930089 0.2970706 0.77080424 5 5
## 349 7.122446e-03 0.08665113 0.1602857 0.92872943 5 5
## 355 9.334903e-03 0.07264405 0.2303190 0.94986307 5 5
## 356 1.815696e-02 0.10093731 0.2890656 0.67908958 5 3
## 365 1.079369e-02 0.14358711 0.2940487 0.35424798 5 3
## 366 5.178081e-03 0.13157487 0.3353260 0.49062049 5 4
## 369 5.546381e-03 0.08892608 0.4041705 0.42344980 5 4
## 371 8.071242e-03 0.10077718 0.2208245 0.87411148 5 5
## 373 1.613584e-02 0.08775244 0.2733257 0.81306648 5 5
## 389 3.509779e-02 0.11018153 0.3173099 0.37742754 5 2
## 390 3.512564e-02 0.13640850 0.2824723 0.36525984 5 4
## 396 7.293403e-03 0.08077494 0.3725835 0.36968643 4 4
## 412 3.993373e-03 0.10900422 0.4473064 0.40164896 4 5
## 413 7.651270e-03 0.08257739 0.3483247 0.42963666 5 3
## 415 8.432408e-03 0.12344330 0.3577052 0.49052940 5 4
## 422 1.685935e-02 0.12452610 0.3632660 0.40816459 5 5
## 425 1.265866e-02 0.08873525 0.2162444 0.96093354 5 5
## 434 7.660618e-03 0.07996161 0.2915099 0.54259669 5 5
## 438 4.472700e-03 0.10493778 0.2865419 0.77416456 5 4
## 441 3.969360e-02 0.10216197 0.3305820 0.33414174 5 5
## 442 1.089806e-02 0.08729440 0.1819261 0.81368704 5 5
## 445 1.228262e-02 0.09167825 0.3869560 0.54605313 5 5
## 447 2.023141e-02 0.12180284 0.4244067 0.14463667 4 3
## 453 4.451156e-02 0.13824693 0.3767113 0.28730308 4 4
## 454 2.169805e-01 0.09338169 0.2158372 0.23618541 5 5
## 462 4.982413e-03 0.06375749 0.2403289 0.88722064 5 5
## 474 6.214756e-02 0.07769308 0.3276354 0.46186681 5 3
## 476 1.327708e-02 0.13749798 0.3136843 0.31291309 4 3
## 493 1.463813e-02 0.12535188 0.2550065 0.52119612 5 5
## 502 4.336261e-02 0.21443593 0.4649346 0.19465123 4 4
## 503 2.180776e-02 0.05726446 0.2955252 0.42344585 5 5
## 506 7.924923e-03 0.09942034 0.2977777 0.65799909 5 5
## 508 9.584197e-03 0.07548826 0.3352238 0.84463529 5 5
## 512 2.768218e-02 0.09998153 0.2271349 0.72925542 5 5
## 513 5.601449e-02 0.12231975 0.2165934 0.44299130 5 5
## 521 2.075592e-01 0.08213464 0.3211687 0.56738059 5 2
## 524 3.742517e-02 0.11903718 0.3198005 0.30522678 4 5CM <- table(Evaluation$Actual,Evaluation$Vote)
CM##
## 2 4 5
## 2 0 2 5
## 3 1 14 10
## 4 0 29 33
## 5 0 14 100#Proportions
Overall <- length(Evaluation$Actual)
Length2 <- length(which(Evaluation$Actual==2))
Length3 <- length(which(Evaluation$Actual==3))
Length4 <- length(which(Evaluation$Actual==4))
Length5 <- length(which(Evaluation$Actual==5))
#Accuracy
Accuracy <- sum(0,29,100)/sum(CM)
#Precision
Rows <- rowSums(CM)
Precision2 <- CM[1,1]/Rows[1]
Precision3 <- CM[3,2]/Rows[3]
Precision4 <- CM[4,3]/Rows[4]
Precision <- (Precision2*Length3+Precision3*Length4+Precision4*Length5)/208
#Recall
Col <- colSums(CM)
Recall2 <- CM[1,1]/Col[1]
Recall3 <- CM[3,2]/Col[2]
Recall4 <- CM[4,3]/Col[3]
Recall <- (Recall2*Length3+Recall3*Length4+Recall4*Length5)/208
Accuracy## [1] 0.6201923Precision## 2
## 0.6201923Recall## 2
## 0.5168346