setwd("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/SVM/2.Feature Set 1/TFIDF/50")#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 Labels
Labels <- read_excel("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/Naive Bayes/1.Labels/Source Data.xlsx")
Label <- Labels$Score#Import Features
Features <- read.csv("~/Google Drive/UM/Smart Services/Thesis/Thesis/Code/SVM/2.Feature Set 1/TFIDF/50/Feature Set 1 50th TFIDF.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 1:1336){
Features[,i] <- as.numeric(Features[,i])
}
str(Features)## 'data.frame': 1000 obs. of 1336 variables:
## $ abl : num 0.0351 0 0 0 0 ...
## $ about : num 0 0 0 0 0 0 0 0 0 0 ...
## $ absolut : num 0 0 0 0 0 0 0 0 0 0 ...
## $ accent : num 0 0 0 0 0 0 0 0 0 0 ...
## $ accept : num 0 0 0 0 0 0 0 0 0 0 ...
## $ access : num 0 0 0 0 0 0 0 0 0 0 ...
## $ accommod : num 0 0 0 0 0 0 0 0 0 0 ...
## $ accomplish : num 0 0 0 0 0 0 0 0 0 0 ...
## $ across : num 0 0 0 0 0 0 0 0 0 0 ...
## $ actual : num 0 0 0 0 0 ...
## $ adequ : num 0 0 0 0 0 0 0 0 0 0 ...
## $ adjac : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ador : num 0 0 0 0 0 0 0 0 0 0 ...
## $ adult : num 0 0 0 0 0 0 0 0 0 0 ...
## $ advanc : num 0 0 0 0 0 0 0 0 0 0 ...
## $ adverti : num 0 0 0 0 0.105 ...
## $ advi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ advic : num 0 0 0 0 0 0 0 0 0 0 ...
## $ affect : num 0 0 0 0 0 0 0 0 0 0 ...
## $ after : num 0 0 0 0 0.112 ...
## $ ago : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ahead : num 0 0 0 0 0 0 0 0 0 0 ...
## $ air : num 0 0 0 0 0 0 0 0 0 0 ...
## $ aircon : num 0 0 0 0 0 0 0 0 0 0 ...
## $ aircondit : num 0 0 0 0 0 ...
## $ airi : num 0 0 0 0 0 0 0 0 0 0 ...
## $ airport : num 0 0 0 0 0 0 0 0 0 0 ...
## $ alarm : num 0 0 0 0 0 0 0 0 0 0 ...
## $ albert : num 0 0 0 0 0 0 0 0 0 0 ...
## $ albrt : num 0 0 0 0 0 0 0 0 0 0 ...
## $ aldo : num 0 0 0 0 0 0 0 0 0 0 ...
## $ alittl : num 0 0 0 0 0 0 0 0 0 0 ...
## $ all : num 0 0 0 0 0 0 0 0 0 0 ...
## $ alloc : num 0 0 0 0 0 0 0 0 0 0 ...
## $ allow : num 0 0 0 0 0 0 0 0 0 0 ...
## $ alreadi : num 0 0 0 0.062 0 ...
## $ also : num 0 0 0 0.0933 0 ...
## $ altern : num 0 0 0 0 0 0 0 0 0 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 0.0653 ...
## $ ambianc : num 0 0 0 0 0 0 0 0 0 0 ...
## $ amen : num 0 0.107 0 0 0 ...
## $ american : num 0 0 0 0 0 0 0 0 0 0 ...
## $ amount : num 0 0 0 0 0 0 0 0 0 0 ...
## $ amsterdam : num 0 0.0847 0 0.0463 0 ...
## $ and : num 0.031 0 0 0 0 ...
## $ anna : num 0 0 0 0 0 0 0 0 0 0 ...
## $ annoy : num 0.0357 0 0 0 0 ...
## $ anoth : num 0 0 0 0 0 0 0 0 0 0 ...
## $ answer : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ant : num 0 0 0 0 0 0 0 0 0 0 ...
## $ anymor : num 0 0 0 0 0 0 0 0 0 0 ...
## $ anyon : num 0 0.102 0 0 0 ...
## $ anyth : num 0 0 0 0 0 0 0 0 0 0 ...
## $ anyway : num 0 0 0 0 0 0 0 0 0 0 ...
## $ anywh : num 0 0 0 0 0 0 0 0 0 0 ...
## $ apart : num 0 0 0 0 0 ...
## $ apolog : num 0 0 0 0 0 0 0 0 0 0 ...
## $ appal : num 0 0 0 0 0 0 0 0 0 0 ...
## $ appeal : num 0 0 0 0 0 0 0 0 0 0 ...
## $ appear : num 0 0 0 0 0 0 0 0 0 0 ...
## $ applic : num 0 0 0 0 0 0 0 0 0 0 ...
## $ appoint : num 0 0 0 0 0 0 0 0 0 0 ...
## $ appreci : num 0 0 0 0 0 0 0 0 0 0 ...
## $ approach : num 0 0 0 0 0 0 0 0 0 0 ...
## $ april : num 0 0 0 0 0 0 0 0 0 0 ...
## $ architectur : num 0 0 0 0 0 0 0 0 0 0 ...
## $ area : num 0 0 0 0.0285 0 ...
## $ arena : num 0 0 0 0 0 0 0 0 0 0 ...
## $ aroom : num 0 0 0 0 0 0 0 0 0 0 ...
## $ around : num 0 0 0 0.0371 0 ...
## $ arrang : num 0 0 0 0 0 0 0 0 0 0 ...
## $ arriv : num 0.0239 0 0 0 0.064 ...
## $ art : num 0 0 0 0 0 0 0 0 0 0 ...
## $ artwork : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ask : num 0.0239 0 0.1319 0 0 ...
## $ aspect : num 0 0 0 0 0 0 0 0 0 0 ...
## $ athmosph : num 0 0 0 0 0 0 0 0 0 0 ...
## $ atm : num 0 0 0 0 0 0 0 0 0 0 ...
## $ atmosph : num 0 0 0 0 0 0 0 0 0 0 ...
## $ attend : num 0 0 0 0 0 0 0 0 0 0 ...
## $ attent : num 0 0 0 0 0 0 0 0 0 0 ...
## $ attic : num 0 0 0 0 0 0 0 0 0 0 ...
## $ attitud : num 0 0 0 0 0 0 0 0 0 0 ...
## $ attract : num 0 0 0 0 0 0 0 0 0 0 ...
## $ atttent : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avail : num 0.031 0 0 0 0 ...
## $ averag : num 0 0 0 0 0 0 0 0 0 0 ...
## $ awar : num 0 0 0 0 0 0 0 0 0 0 ...
## $ away : num 0 0 0 0 0 0 0 0 0 0 ...
## $ awesom : num 0 0 0 0 0 ...
## $ back : num 0 0.0698 0.1376 0 0 ...
## $ backyard : num 0 0 0 0 0 ...
## $ bacon : num 0 0 0 0 0 0 0 0 0 0 ...
## $ bad : num 0 0 0 0.0417 0 ...
## $ bag : num 0 0 0 0 0 0 0 0 0 0 ...
## $ bake : num 0 0 0 0 0 0 0 0 0 0 ...
## $ bang : num 0 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 thevoting procedure pick class with the highest probability.
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 0.04484328 0.9551567 0.8420299 0.15797008 0.7090221 0.2909779
## 14 0.02329448 0.9767055 0.9195713 0.08042869 0.6792998 0.3207002
## 16 0.01854669 0.9814533 0.9205178 0.07948224 0.7575615 0.2424385
## 26 0.03711053 0.9628895 0.9030260 0.09697404 0.7237737 0.2762263
## 28 0.03493567 0.9650643 0.7268440 0.27315599 0.7379065 0.2620935
## 29 0.02592096 0.9740790 0.8839534 0.11604661 0.6974833 0.3025167
## Class 5: 0 Class5: 1
## 5 0.7015602 0.2984398
## 14 0.5545259 0.4454741
## 16 0.3928097 0.6071903
## 26 0.5436832 0.4563168
## 28 0.6837344 0.3162656
## 29 0.6166213 0.3833787SEQ <- 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 0.04484328 0.15797008 0.2909779 0.2984398
## 14 0.02329448 0.08042869 0.3207002 0.4454741
## 16 0.01854669 0.07948224 0.2424385 0.6071903
## 26 0.03711053 0.09697404 0.2762263 0.4563168
## 28 0.03493567 0.27315599 0.2620935 0.3162656
## 29 0.02592096 0.11604661 0.3025167 0.3833787Evaluation <- 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 0.044843277 0.15797008 0.2909779 0.2984397677 5 4
## 14 0.023294478 0.08042869 0.3207002 0.4454741000 5 5
## 16 0.018546687 0.07948224 0.2424385 0.6071903350 5 5
## 26 0.037110531 0.09697404 0.2762263 0.4563168401 5 4
## 28 0.034935668 0.27315599 0.2620935 0.3162656140 5 4
## 29 0.025920956 0.11604661 0.3025167 0.3833786867 5 4
## 39 0.034445041 0.08783595 0.2853168 0.5000000000 5 5
## 40 0.025011598 0.14731906 0.3387985 0.3195846343 4 3
## 60 0.021556690 0.10523305 0.2561904 0.5800867423 5 5
## 61 0.036826420 0.19943335 0.2834452 0.3705419045 5 3
## 72 0.017692520 0.05025872 0.2789928 0.5483896054 5 4
## 81 0.025929730 0.12610579 0.3179549 0.3780857888 5 3
## 86 0.033691095 0.12372089 0.3027465 0.4919849910 5 5
## 90 0.083393297 0.12223073 0.3012856 0.2157613107 4 4
## 92 0.025362784 0.15394049 0.2972471 0.2564524018 4 4
## 113 0.033505632 0.07474724 0.3204596 0.3729722568 5 5
## 116 0.051635397 0.17330145 0.2533199 0.3648648446 5 4
## 117 0.032876886 0.07933628 0.3765655 0.4476159385 5 5
## 122 0.045705296 0.14021964 0.3524011 0.1230021687 4 4
## 123 0.026776282 0.06784839 0.4057345 0.3393499452 4 2
## 124 0.022576459 0.10680457 0.3196773 0.3592469139 5 4
## 131 0.029327622 0.11955361 0.3203576 0.4061352394 5 4
## 135 0.041586590 0.13346915 0.3062325 0.2791259144 4 3
## 137 0.012752184 0.08377862 0.2921319 0.5819487502 5 5
## 140 0.037006442 0.14975757 0.3067204 0.3081576635 5 4
## 142 0.021267996 0.06359000 0.3479308 0.4475342488 5 5
## 149 0.027478775 0.08776605 0.3385043 0.4659088421 5 4
## 154 0.021239138 0.10635658 0.2376051 0.6198451327 5 5
## 156 0.041952186 0.09709812 0.3441434 0.3293036668 4 3
## 158 0.044048580 0.16968360 0.2742555 0.3459777451 5 3
## 169 0.026656860 0.06655193 0.2152478 0.7610319068 5 5
## 185 0.028691593 0.08193249 0.2544690 0.5399131768 5 5
## 187 0.016154122 0.10460300 0.3365687 0.4614469242 5 5
## 192 0.028752804 0.17967179 0.3206408 0.2665901050 4 3
## 194 0.192278808 0.63808789 0.2513519 0.1337142564 3 4
## 195 0.019649677 0.27884510 0.2770518 0.2326310516 3 4
## 196 0.042180610 0.13502026 0.3090300 0.3042031473 4 5
## 197 0.076347837 0.16768984 0.2483006 0.2406451824 4 3
## 199 0.023230455 0.06329765 0.2499905 0.7418951206 5 5
## 210 0.086090931 0.13525136 0.3084900 0.1709104942 4 3
## 216 0.040003454 0.07279322 0.1835453 0.7922669812 5 5
## 220 0.025458903 0.17020207 0.2663765 0.3734043382 5 4
## 227 0.040989328 0.07589788 0.2926312 0.4739886434 5 5
## 234 0.025371093 0.11749097 0.3668373 0.3022107418 4 3
## 240 0.024163102 0.07187264 0.5487187 0.1598821975 4 5
## 245 0.114409546 0.16134609 0.4015219 0.1660770761 4 4
## 249 0.037307996 0.11506568 0.3570669 0.3338219241 4 5
## 261 0.044735235 0.34891100 0.3975316 0.1935281394 4 3
## 277 0.022553592 0.04912727 0.2029803 0.8898157573 5 5
## 283 0.038169270 0.11556694 0.2818945 0.5123777143 5 5
## 290 0.009140046 0.02575375 0.1540439 0.9715000230 5 4
## 293 0.036308669 0.06629986 0.3855401 0.2809980358 4 5
## 302 0.025682323 0.18399418 0.2503642 0.4691492793 5 4
## 305 0.046908211 0.11262462 0.3728527 0.3103478231 4 4
## 308 0.024746170 0.11954208 0.3011358 0.1707038424 4 4
## 311 0.030405864 0.05648742 0.2531105 0.7407365254 5 5
## 320 0.025313179 0.04896257 0.1955893 0.9552963563 5 2
## 322 0.027284490 0.04798359 0.2305270 0.8197997138 5 5
## 330 0.015829428 0.04546294 0.1637183 0.7963694520 5 4
## 332 0.040932149 0.10938490 0.8249230 0.0300783356 4 4
## 333 0.035628877 0.02806733 0.3199496 0.8230636432 5 5
## 339 0.016812132 0.13033850 0.2365946 0.5745127650 5 5
## 341 0.036510081 0.08322201 0.4761905 0.1288393992 4 4
## 344 0.031039791 0.07372983 0.3151945 0.6478638245 5 5
## 349 0.020655759 0.05597628 0.2082354 0.9015559291 5 5
## 355 0.024109186 0.02246100 0.1574725 0.9712647522 5 5
## 356 0.052070444 0.10487416 0.3020308 0.3927775201 5 3
## 365 0.055362828 0.19365189 0.3196933 0.2172368087 4 3
## 366 0.046065309 0.08945879 0.2431204 0.5521433141 5 4
## 369 0.019491612 0.05945159 0.3175882 0.4753637500 5 4
## 371 0.013887435 0.08627243 0.2565713 0.8349696311 5 5
## 373 0.037660094 0.05202472 0.3490168 0.5693459206 5 5
## 389 0.225639433 0.06157733 0.8619585 0.0002290760 4 2
## 390 0.186231567 0.52690288 0.7715212 0.0001802053 4 4
## 396 0.021269460 0.04887285 0.2967983 0.6389128022 5 4
## 412 0.014336337 0.07427548 0.3474837 0.4896260781 5 5
## 413 0.023900242 0.10043002 0.2775893 0.4545048022 5 3
## 415 0.019448387 0.08844494 0.3807358 0.4501459432 5 4
## 422 0.027057554 0.13724690 0.2664378 0.4029691379 5 5
## 425 0.019923749 0.06073585 0.2791036 0.6340446793 5 5
## 434 0.041466073 0.08994411 0.3136761 0.3845290163 5 5
## 438 0.014082896 0.07663476 0.2879811 0.6856191414 5 4
## 441 0.035105016 0.11735036 0.2909235 0.4275498312 5 5
## 442 0.029463411 0.09472811 0.2254451 0.6421508951 5 5
## 445 0.024822767 0.09609986 0.3387221 0.3920191404 5 5
## 447 0.031178452 0.10571820 0.2723423 0.3750032411 5 3
## 453 0.078493857 0.26947859 0.3104531 0.2256228901 4 4
## 454 0.024346528 0.10861382 0.2747973 0.4556753947 5 5
## 462 0.014957269 0.05324530 0.2525274 0.7485326641 5 5
## 474 0.062824380 0.15270043 0.3099880 0.4006963640 5 3
## 476 0.024871589 0.12903631 0.2550365 0.4613581351 5 3
## 493 0.014704760 0.07590691 0.5000000 0.2272418504 4 5
## 502 0.020219822 0.11225153 0.4030491 0.3196949215 4 4
## 503 0.030334854 0.09345805 0.2596635 0.5272908677 5 5
## 506 0.023360859 0.16785164 0.2546083 0.4432451875 5 5
## 508 0.027736107 0.05733879 0.3560391 0.5669470421 5 5
## 512 0.030303688 0.12756247 0.3162203 0.4839702275 5 5
## 513 0.025573997 0.12939597 0.2897328 0.4834765188 5 5
## 521 0.054791527 0.11372946 0.2642512 0.3630869582 5 2
## 524 0.086410156 0.12558859 0.3645862 0.1930278752 4 5CM <- table(Evaluation$Actual,Evaluation$Vote)
CM##
## 3 4 5
## 2 0 4 3
## 3 0 14 11
## 4 2 25 35
## 5 1 13 100#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[2,1]/Rows[2]
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[2,1]/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## 3
## 0.6009615Recall## 3
## 0.5009069