[Part 1].Data-ETL
1-1.取得資料集的概述
head(miete)
## nm wfl bj bad0 zh ww0 badkach fenster kueche mvdauer bjkat
## 1 693.29 50 1971.5 0 1 0 0 0 0 2 4
## 2 736.60 70 1971.5 0 1 0 0 0 0 26 4
## 3 732.23 50 1971.5 0 1 0 0 0 0 1 4
## 4 1295.14 55 1893.0 0 1 0 0 0 0 0 1
## 5 394.97 46 1957.0 0 0 1 0 0 0 27 3
## 6 1285.64 94 1971.5 0 1 0 1 0 0 2 4
## wflkat nmqm rooms nmkat adr wohn
## 1 1 13.865800 1 3 2 2
## 2 2 10.522857 3 3 2 2
## 3 1 14.644600 1 3 2 2
## 4 2 23.548000 3 5 2 2
## 5 1 8.586304 3 1 2 2
## 6 3 13.677021 4 5 2 2
dim(miete)
## [1] 1082 17
summary(miete)
## nm wfl bj bad0 zh
## Min. : 127.1 Min. : 20.00 Min. :1800 0:1051 0:202
## 1st Qu.: 543.6 1st Qu.: 50.25 1st Qu.:1934 1: 31 1:880
## Median : 746.0 Median : 67.00 Median :1957
## Mean : 830.3 Mean : 69.13 Mean :1947
## 3rd Qu.:1030.0 3rd Qu.: 84.00 3rd Qu.:1972
## Max. :3130.0 Max. :250.00 Max. :1992
## ww0 badkach fenster kueche mvdauer bjkat wflkat
## 0:1022 0:446 0:1024 0:980 Min. : 0.00 1:218 1:271
## 1: 60 1:636 1: 58 1:102 1st Qu.: 2.00 2:154 2:513
## Median : 6.00 3:341 3:298
## Mean :10.63 4:226
## 3rd Qu.:17.00 5: 79
## Max. :82.00 6: 64
## nmqm rooms nmkat adr wohn
## Min. : 1.573 Min. :1.000 1:219 1: 25 1: 90
## 1st Qu.: 8.864 1st Qu.:2.000 2:230 2:1035 2:673
## Median :12.041 Median :3.000 3:210 3: 22 3:319
## Mean :12.647 Mean :2.635 4:208
## 3rd Qu.:16.135 3rd Qu.:3.000 5:215
## Max. :35.245 Max. :9.000
1-2.取出我們需要用的變數
library(sampling)
n=round(2/3*nrow(miete)/5) #依照資料的2/3比例，取出每一等級中應抽出的樣本數
n
## [1] 144
sub_train=strata(miete,stratanames="nmkat",size=rep(n,5),method="srswor")#以nmkat變數做為五個等及畫分
head(sub_train)
## nmkat ID_unit Prob Stratum
## 2 3 2 0.6857143 1
## 16 3 16 0.6857143 1
## 20 3 20 0.6857143 1
## 22 3 22 0.6857143 1
## 27 3 27 0.6857143 1
## 28 3 28 0.6857143 1
data_train=getdata(miete[,c(-1,-3,-12)],sub_train$ID_unit) #訓練集，剃除1.3.12變數?
data_test=getdata(miete[,c(-1,-3,-12)],-sub_train$ID_unit) #測試集，剃除1.3.12變數
dim(data_train);dim(data_test)
## [1] 720 14
## [1] 362 14
head(data_test)
## wfl bad0 zh ww0 badkach fenster kueche mvdauer bjkat nmqm rooms
## 1 50 0 1 0 0 0 0 2 4 13.86580 1
## 3 50 0 1 0 0 0 0 1 4 14.64460 1
## 4 55 0 1 0 0 0 0 0 1 23.54800 3
## 6 94 0 1 0 1 0 0 2 4 13.67702 4
## 8 36 0 1 0 0 0 1 3 4 19.71028 1
## 11 75 0 1 0 1 0 1 3 6 16.50453 3
## nmkat adr wohn
## 1 3 2 2
## 3 3 2 2
## 4 5 2 2
## 6 5 2 2
## 8 3 2 2
## 11 5 2 2
[Part 2].K-near neighbor Method
#install.packages("class")
library(class)
2-1.訓練集的屬性
fit_pre_knn=knn(data_train[,-12],data_test[,-12],cl=data_train[,12])
fit_pre_knn
## [1] 3 3 4 5 2 4 5 2 5 2 2 1 5 2 1 3 2 4 5 2 2 5 2 2 1 5 5 1 2 2 2 1 3 1 1
## [36] 2 5 4 2 3 3 5 2 2 5 1 1 2 4 2 2 5 3 3 5 1 3 4 1 4 4 2 1 4 2 1 5 2 4 2
## [71] 4 2 4 1 1 5 2 3 4 5 4 4 4 2 2 2 2 3 3 4 2 1 5 3 2 5 3 1 3 5 1 3 5 1 4
## [106] 5 4 2 2 2 3 1 1 1 4 4 1 5 1 5 5 3 4 5 5 1 1 3 4 3 2 2 1 2 4 4 5 1 3 4
## [141] 1 1 1 3 3 4 1 2 5 5 2 3 3 2 3 3 4 5 1 3 2 1 3 2 4 4 4 3 2 2 1 5 4 3 2
## [176] 1 4 2 3 1 5 5 5 2 3 2 2 5 1 2 3 3 4 3 4 3 3 1 1 1 2 2 3 1 3 5 1 3 3 4
## [211] 5 3 3 4 5 5 1 5 1 5 5 2 4 5 4 1 1 5 5 5 2 2 1 2 2 2 2 4 3 4 4 5 2 5 1
## [246] 1 3 4 2 2 5 4 2 3 3 3 2 1 4 2 5 5 4 2 2 3 3 2 1 1 4 1 1 5 4 4 1 4 5 3
## [281] 4 1 4 3 3 2 3 4 2 1 2 5 1 1 2 2 1 2 1 4 4 3 4 3 3 1 5 5 2 3 5 4 2 5 5
## [316] 2 3 4 1 2 5 5 3 4 4 3 2 5 5 5 1 4 5 5 5 5 4 2 1 3 2 2 4 3 1 2 3 3 3 2
## [351] 1 3 4 4 4 3 2 3 5 5 3 3
## Levels: 1 2 3 4 5
table(data_test$nmkat,fit_pre_knn) #產生混淆矩陣
## fit_pre_knn
## 1 2 3 4 5
## 1 54 17 1 3 0
## 2 14 50 20 2 0
## 3 0 17 37 11 1
## 4 0 2 14 44 4
## 5 0 0 0 6 65
error_knn=sum(as.numeric(as.numeric(fit_pre_knn)!=as.numeric(data_test$nmkat)))/nrow(data_test)
error_knn #計算錯誤率
## [1] 0.3093923
2-2.找出最適合的K值
error_knn=rep(0,20) #從0到20
for(i in 1:20)
{ fit_pre_knn=knn(data_train[,-12],data_test[,-12],cl=data_train[,12],k=i)
error_knn[i]=sum(as.numeric(as.numeric(fit_pre_knn)!=as.numeric(data_test$nmkat)))/nrow(data_test)}
error_knn
## [1] 0.3093923 0.3922652 0.3314917 0.3232044 0.3259669 0.3259669 0.3287293
## [8] 0.3342541 0.3591160 0.3535912 0.3618785 0.3425414 0.3867403 0.3674033
## [15] 0.3756906 0.3729282 0.3839779 0.3950276 0.3895028 0.3977901
plot(error_knn,type="l",xlab="K")
- 當K=3時錯誤率最小
2-3.如果有加權時，K應該是多少
#install.packages("kknn")
library(kknn)
fit_pre_kknn=kknn(nmkat~.,data_train,data_test[,-12])
fit_pre_kknn
##
## Call:
## kknn(formula = nmkat ~ ., train = data_train, test = data_test[, -12])
##
## Response: "ordinal"
summary(fit_pre_kknn)
##
## Call:
## kknn(formula = nmkat ~ ., train = data_train, test = data_test[, -12])
##
## Response: "ordinal"
## fit prob.1 prob.2 prob.3 prob.4 prob.5
## 1 2 0.26656291 0.56541549 0.98771757 1.00000000 1
## 2 2 0.26656291 0.57769792 0.96079089 1.00000000 1
## 3 4 0.00000000 0.00000000 0.03920911 0.75927889 1
## 4 4 0.00000000 0.00000000 0.07067845 0.57769792 1
## 5 3 0.01228243 0.05149154 0.82051886 0.92932155 1
## 6 5 0.00000000 0.03920911 0.03920911 0.19696934 1
## 7 5 0.00000000 0.07067845 0.07067845 0.07067845 1
## 8 5 0.00000000 0.17948114 0.33724137 0.33724137 1
## 9 4 0.00000000 0.00000000 0.03920911 0.50810435 1
## 10 2 0.23097268 0.77182587 1.00000000 1.00000000 1
## 11 2 0.38873291 1.00000000 1.00000000 1.00000000 1
## 12 3 0.07067845 0.07067845 0.82995734 1.00000000 1
## 13 5 0.00000000 0.00000000 0.10988756 0.35034412 1
## 14 2 0.00000000 0.50701947 1.00000000 1.00000000 1
## 15 1 0.73261677 1.00000000 1.00000000 1.00000000 1
## 16 3 0.22843868 0.46889524 0.57769792 0.96079089 1
## 17 1 0.50701947 0.89011244 1.00000000 1.00000000 1
## 18 4 0.00000000 0.00000000 0.15776023 0.96079089 1
## 19 5 0.00000000 0.00000000 0.00000000 0.20925177 1
## 20 2 0.00000000 0.89119731 1.00000000 1.00000000 1
## 21 3 0.01228243 0.01228243 0.59234474 1.00000000 1
## 22 4 0.00000000 0.00000000 0.12108512 0.89011244 1
## 23 2 0.43458451 0.73343709 1.00000000 1.00000000 1
## 24 3 0.00000000 0.38309297 0.69422798 1.00000000 1
## 25 2 0.22817413 0.72006978 1.00000000 1.00000000 1
## 26 4 0.00000000 0.00000000 0.07067845 0.66302319 1
## 27 3 0.00000000 0.03920911 0.59234474 0.92932155 1
## 28 1 0.62354952 0.89119731 1.00000000 1.00000000 1
## 29 2 0.15776023 0.59234474 0.92932155 1.00000000 1
## 30 2 0.30577202 0.91703912 1.00000000 1.00000000 1
## 31 2 0.39821678 0.89011244 0.92932155 1.00000000 1
## 32 2 0.49189565 0.84223977 1.00000000 1.00000000 1
## 33 3 0.01228243 0.34925924 0.96079089 1.00000000 1
## 34 1 0.82051886 0.89119731 1.00000000 1.00000000 1
## 35 1 0.98771757 0.98771757 1.00000000 1.00000000 1
## 36 2 0.00000000 0.91703912 1.00000000 1.00000000 1
## 37 5 0.00000000 0.00000000 0.00000000 0.38593435 1
## 38 4 0.00000000 0.00000000 0.29885258 0.83970577 1
## 39 3 0.39537540 0.43458451 0.59234474 0.92932155 1
## 40 3 0.00000000 0.15776023 0.80823643 0.98771757 1
## 41 4 0.00000000 0.33697681 0.38846835 1.00000000 1
## 42 5 0.00000000 0.00000000 0.00000000 0.03920911 1
## 43 2 0.49473704 0.89011244 1.00000000 1.00000000 1
## 44 3 0.00000000 0.38309297 0.54085320 0.82051886 1
## 45 5 0.00000000 0.00000000 0.00000000 0.49473704 1
## 46 2 0.45661281 1.00000000 1.00000000 1.00000000 1
## 47 2 0.00000000 0.61126709 0.66275863 0.92932155 1
## 48 2 0.34925924 0.57769792 0.96079089 1.00000000 1
## 49 4 0.00000000 0.00000000 0.15776023 0.89119731 1
## 50 3 0.00000000 0.42514346 0.98771757 1.00000000 1
## 51 2 0.22817413 0.68194555 0.85198820 1.00000000 1
## 52 5 0.00000000 0.03920911 0.03920911 0.26738323 1
## 53 4 0.00000000 0.17948114 0.17948114 0.56541549 1
## 54 2 0.10880269 0.64965588 0.70114742 1.00000000 1
## 55 4 0.00000000 0.00000000 0.15776023 0.61690703 1
## 56 2 0.46889524 0.50810435 0.61690703 1.00000000 1
## 57 4 0.00000000 0.07067845 0.45377142 1.00000000 1
## 58 4 0.00000000 0.26738323 0.37618592 1.00000000 1
## 59 3 0.45661281 0.46889524 1.00000000 1.00000000 1
## 60 4 0.00000000 0.00000000 0.10880269 0.61406565 1
## 61 4 0.15776023 0.19696934 0.43742589 0.82051886 1
## 62 1 0.50701947 0.92932155 0.92932155 1.00000000 1
## 63 2 0.00000000 0.83970577 1.00000000 1.00000000 1
## 64 3 0.14801180 0.37645048 0.60462460 1.00000000 1
## 65 2 0.12216999 0.50810435 1.00000000 1.00000000 1
## 66 1 0.65047620 0.92932155 1.00000000 1.00000000 1
## 67 4 0.00000000 0.00000000 0.07067845 0.80303066 1
## 68 1 0.50417808 0.54338719 1.00000000 1.00000000 1
## 69 3 0.00000000 0.00000000 0.53394615 0.60462460 1
## 70 1 0.50526296 0.66302319 1.00000000 1.00000000 1
## 71 4 0.00000000 0.22817413 0.38593435 0.82051886 1
## 72 3 0.14801180 0.37618592 0.84223977 1.00000000 1
## 73 4 0.00000000 0.00000000 0.10988756 0.84223977 1
## 74 3 0.00000000 0.45377142 0.57485654 0.57485654 1
## 75 1 0.87891488 1.00000000 1.00000000 1.00000000 1
## 76 5 0.00000000 0.00000000 0.10880269 0.30577202 1
## 77 2 0.38593435 1.00000000 1.00000000 1.00000000 1
## 78 2 0.27966566 0.54622858 0.92932155 1.00000000 1
## 79 4 0.00000000 0.38309297 0.49189565 0.73235221 1
## 80 4 0.00000000 0.00000000 0.45377142 0.50526296 1
## 81 4 0.00000000 0.14801180 0.38846835 0.92932155 1
## 82 4 0.00000000 0.00000000 0.14801180 0.91703912 1
## 83 4 0.00000000 0.00000000 0.22817413 0.72006978 1
## 84 4 0.00000000 0.45661281 0.45661281 0.89119731 1
## 85 2 0.27884534 0.70114742 1.00000000 1.00000000 1
## 86 3 0.00000000 0.03920911 0.80823643 0.91703912 1
## 87 3 0.00000000 0.08296088 0.73261677 1.00000000 1
## 88 2 0.26738323 0.50810435 0.89119731 1.00000000 1
## 89 3 0.00000000 0.00000000 0.66302319 1.00000000 1
## 90 3 0.10880269 0.10880269 0.66193831 0.92932155 1
## 91 2 0.03920911 0.65047620 0.80823643 1.00000000 1
## 92 1 0.72006978 0.94850846 1.00000000 1.00000000 1
## 93 4 0.00000000 0.00000000 0.00000000 0.54338719 1
## 94 2 0.12108512 0.54622858 0.54622858 1.00000000 1
## 95 3 0.00000000 0.01228243 0.50701947 1.00000000 1
## 96 5 0.00000000 0.00000000 0.00000000 0.49189565 1
## 97 2 0.00000000 0.68194555 0.83970577 0.98771757 1
## 98 3 0.33697681 0.34925924 0.92932155 1.00000000 1
## 99 4 0.00000000 0.10988756 0.38873291 1.00000000 1
## 100 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 101 2 0.38309297 0.65047620 1.00000000 1.00000000 1
## 102 2 0.33806169 0.72115466 1.00000000 1.00000000 1
## 103 5 0.00000000 0.00000000 0.00000000 0.19696934 1
## 104 1 0.55313563 0.78130975 1.00000000 1.00000000 1
## 105 1 0.61126709 0.76902732 0.76902732 0.92932155 1
## 106 3 0.00000000 0.22817413 0.89011244 1.00000000 1
## 107 4 0.00000000 0.00000000 0.22817413 0.60462460 1
## 108 2 0.17948114 1.00000000 1.00000000 1.00000000 1
## 109 3 0.01228243 0.35034412 0.73343709 1.00000000 1
## 110 2 0.22843868 0.56541549 0.96079089 1.00000000 1
## 111 2 0.49189565 0.77182587 1.00000000 1.00000000 1
## 112 2 0.35034412 0.73343709 1.00000000 1.00000000 1
## 113 1 0.80303066 0.84223977 0.84223977 1.00000000 1
## 114 1 0.82995734 0.84223977 0.84223977 1.00000000 1
## 115 1 0.50417808 0.73261677 0.77182587 1.00000000 1
## 116 5 0.00000000 0.00000000 0.22817413 0.26738323 1
## 117 1 0.50701947 0.92932155 1.00000000 1.00000000 1
## 118 2 0.39537540 0.73235221 0.92932155 1.00000000 1
## 119 2 0.15776023 0.61153165 1.00000000 1.00000000 1
## 120 4 0.38309297 0.38309297 0.38309297 0.65047620 1
## 121 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 122 3 0.10880269 0.12108512 1.00000000 1.00000000 1
## 123 4 0.00000000 0.03920911 0.23097268 0.84223977 1
## 124 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 125 4 0.00000000 0.10880269 0.10880269 0.66193831 1
## 126 1 0.61690703 1.00000000 1.00000000 1.00000000 1
## 127 4 0.10988756 0.21869025 0.44686437 1.00000000 1
## 128 3 0.00000000 0.22817413 0.76902732 0.98771757 1
## 129 4 0.00000000 0.00000000 0.49582192 1.00000000 1
## 130 3 0.01228243 0.46889524 0.57769792 0.57769792 1
## 131 2 0.26656291 0.60462460 0.98771757 1.00000000 1
## 132 2 0.10880269 0.60178322 0.60178322 1.00000000 1
## 133 2 0.20925177 0.70114742 0.92932155 1.00000000 1
## 134 2 0.12108512 0.66193831 0.70114742 1.00000000 1
## 135 3 0.10880269 0.33697681 0.73235221 0.96079089 1
## 136 2 0.37645048 0.98771757 1.00000000 1.00000000 1
## 137 5 0.00000000 0.08296088 0.08296088 0.24072111 1
## 138 2 0.22817413 1.00000000 1.00000000 1.00000000 1
## 139 3 0.14801180 0.37645048 0.61690703 1.00000000 1
## 140 2 0.26738323 0.75927889 0.82995734 1.00000000 1
## 141 2 0.19696934 0.66302319 0.89119731 1.00000000 1
## 142 2 0.17948114 0.75954344 0.98771757 1.00000000 1
## 143 2 0.26738323 1.00000000 1.00000000 1.00000000 1
## 144 2 0.03920911 0.98771757 1.00000000 1.00000000 1
## 145 3 0.15776023 0.45661281 0.85198820 1.00000000 1
## 146 2 0.22817413 0.61126709 0.66275863 0.77156132 1
## 147 1 0.69422798 1.00000000 1.00000000 1.00000000 1
## 148 2 0.15776023 0.87783001 0.98771757 1.00000000 1
## 149 5 0.00000000 0.00000000 0.00000000 0.12216999 1
## 150 2 0.03920911 0.80823643 0.89119731 0.89119731 1
## 151 1 0.53110476 0.70114742 0.92932155 0.92932155 1
## 152 2 0.03920911 0.98771757 1.00000000 1.00000000 1
## 153 2 0.07067845 1.00000000 1.00000000 1.00000000 1
## 154 4 0.00000000 0.07067845 0.37645048 0.98771757 1
## 155 4 0.00000000 0.07067845 0.33724137 0.94850846 1
## 156 3 0.00000000 0.12216999 1.00000000 1.00000000 1
## 157 5 0.00000000 0.05149154 0.16029423 0.31805445 1
## 158 5 0.00000000 0.00000000 0.00000000 0.07067845 1
## 159 1 0.64965588 0.94850846 0.96079089 1.00000000 1
## 160 2 0.14801180 0.54622858 0.54622858 1.00000000 1
## 161 2 0.29885258 0.82995734 0.82995734 1.00000000 1
## 162 1 0.54338719 0.84223977 1.00000000 1.00000000 1
## 163 3 0.00000000 0.29885258 0.69422798 1.00000000 1
## 164 2 0.03920911 1.00000000 1.00000000 1.00000000 1
## 165 4 0.00000000 0.00000000 0.07067845 0.75954344 1
## 166 3 0.07067845 0.29885258 0.87891488 1.00000000 1
## 167 3 0.00000000 0.24045656 0.50810435 1.00000000 1
## 168 4 0.00000000 0.01228243 0.41993769 0.80303066 1
## 169 4 0.00000000 0.49582192 0.49582192 0.89119731 1
## 170 2 0.15776023 0.55313563 0.59234474 1.00000000 1
## 171 1 0.82051886 0.92932155 1.00000000 1.00000000 1
## 172 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 173 4 0.10880269 0.19176357 0.41993769 0.61690703 1
## 174 2 0.12108512 0.70114742 0.70114742 1.00000000 1
## 175 3 0.01228243 0.46889524 0.61690703 1.00000000 1
## 176 2 0.43458451 1.00000000 1.00000000 1.00000000 1
## 177 5 0.00000000 0.00000000 0.03920911 0.37645048 1
## 178 2 0.39537540 0.50417808 0.73235221 0.92932155 1
## 179 3 0.00000000 0.00000000 0.56257411 1.00000000 1
## 180 2 0.40765526 0.84223977 1.00000000 1.00000000 1
## 181 5 0.00000000 0.00000000 0.00000000 0.31805445 1
## 182 5 0.00000000 0.00000000 0.00000000 0.15776023 1
## 183 4 0.00000000 0.00000000 0.07067845 0.61690703 1
## 184 2 0.00000000 0.87891488 0.89119731 1.00000000 1
## 185 2 0.00000000 0.61126709 0.87783001 1.00000000 1
## 186 2 0.29885258 0.80303066 1.00000000 1.00000000 1
## 187 1 0.56541549 0.94850846 1.00000000 1.00000000 1
## 188 4 0.00000000 0.01228243 0.24045656 0.89119731 1
## 189 1 0.80823643 1.00000000 1.00000000 1.00000000 1
## 190 2 0.00000000 0.87891488 0.87891488 1.00000000 1
## 191 4 0.00000000 0.46605385 0.46605385 0.96079089 1
## 192 1 0.66193831 0.89011244 0.96079089 1.00000000 1
## 193 4 0.00000000 0.01228243 0.34952380 0.77182587 1
## 194 3 0.00000000 0.38309297 0.72006978 0.77156132 1
## 195 2 0.00000000 0.65047620 0.75927889 1.00000000 1
## 196 3 0.01228243 0.16029423 1.00000000 1.00000000 1
## 197 1 0.57485654 0.61406565 0.84223977 1.00000000 1
## 198 2 0.27966566 0.50810435 0.89119731 1.00000000 1
## 199 4 0.00000000 0.45377142 0.45377142 0.85198820 1
## 200 1 0.61406565 1.00000000 1.00000000 1.00000000 1
## 201 2 0.00000000 0.54085320 0.87783001 1.00000000 1
## 202 3 0.00000000 0.38309297 0.58006231 0.89119731 1
## 203 3 0.00000000 0.17004266 1.00000000 1.00000000 1
## 204 3 0.49298053 0.49298053 0.82995734 1.00000000 1
## 205 3 0.03920911 0.03920911 0.60462460 1.00000000 1
## 206 5 0.00000000 0.00000000 0.00000000 0.07067845 1
## 207 1 0.53394615 0.98771757 1.00000000 1.00000000 1
## 208 2 0.19176357 0.57485654 0.96079089 1.00000000 1
## 209 2 0.17004266 0.66193831 0.96079089 1.00000000 1
## 210 1 0.53110476 0.60178322 0.82995734 0.84223977 1
## 211 4 0.00000000 0.00000000 0.07067845 0.61690703 1
## 212 5 0.10880269 0.10880269 0.21869025 0.38873291 1
## 213 1 0.76902732 0.89011244 0.89011244 1.00000000 1
## 214 2 0.00000000 0.76902732 0.80823643 1.00000000 1
## 215 5 0.00000000 0.00000000 0.01228243 0.24045656 1
## 216 5 0.00000000 0.00000000 0.03920911 0.27966566 1
## 217 2 0.42514346 0.89119731 1.00000000 1.00000000 1
## 218 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 219 1 0.77156132 0.92932155 1.00000000 1.00000000 1
## 220 3 0.03920911 0.10988756 0.77182587 0.77182587 1
## 221 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 222 1 0.53110476 0.91703912 0.98771757 1.00000000 1
## 223 5 0.00000000 0.00000000 0.00000000 0.15776023 1
## 224 5 0.00000000 0.00000000 0.07067845 0.33806169 1
## 225 4 0.00000000 0.00000000 0.22817413 0.65047620 1
## 226 1 0.82051886 0.82051886 0.92932155 1.00000000 1
## 227 1 0.82051886 0.92932155 1.00000000 1.00000000 1
## 228 5 0.00000000 0.00000000 0.00000000 0.03920911 1
## 229 3 0.42230208 0.49298053 0.60178322 0.98771757 1
## 230 5 0.00000000 0.00000000 0.08296088 0.31113501 1
## 231 1 0.56257411 0.94850846 1.00000000 1.00000000 1
## 232 1 0.50701947 0.50701947 0.92932155 1.00000000 1
## 233 1 0.56541549 0.56541549 0.98771757 1.00000000 1
## 234 2 0.22817413 0.98771757 1.00000000 1.00000000 1
## 235 2 0.17948114 1.00000000 1.00000000 1.00000000 1
## 236 3 0.00000000 0.05149154 0.66302319 1.00000000 1
## 237 3 0.00000000 0.05149154 0.82051886 1.00000000 1
## 238 2 0.49473704 0.54622858 0.61690703 1.00000000 1
## 239 1 0.85198820 0.96079089 0.96079089 1.00000000 1
## 240 2 0.49473704 0.54622858 0.61690703 1.00000000 1
## 241 1 0.62381408 0.73261677 1.00000000 1.00000000 1
## 242 4 0.07067845 0.21869025 0.38873291 1.00000000 1
## 243 2 0.40765526 0.60462460 0.60462460 1.00000000 1
## 244 4 0.00000000 0.00000000 0.00000000 0.92932155 1
## 245 1 0.87891488 1.00000000 1.00000000 1.00000000 1
## 246 2 0.12216999 0.73343709 0.89119731 0.89119731 1
## 247 3 0.00000000 0.00000000 0.54338719 1.00000000 1
## 248 4 0.00000000 0.01228243 0.01228243 0.89011244 1
## 249 2 0.27966566 0.89119731 0.89119731 1.00000000 1
## 250 1 0.83970577 0.96079089 1.00000000 1.00000000 1
## 251 2 0.26738323 0.54622858 0.54622858 1.00000000 1
## 252 4 0.00000000 0.19176357 0.34952380 0.61690703 1
## 253 1 0.76902732 0.94850846 0.98771757 0.98771757 1
## 254 1 0.65047620 0.98771757 1.00000000 1.00000000 1
## 255 1 0.76902732 0.85198820 0.89119731 1.00000000 1
## 256 3 0.00000000 0.38309297 0.62354952 0.73235221 1
## 257 3 0.00000000 0.05149154 0.54338719 0.61406565 1
## 258 3 0.00000000 0.45661281 0.83970577 0.85198820 1
## 259 4 0.00000000 0.01228243 0.39537540 0.77182587 1
## 260 3 0.03920911 0.37618592 0.91703912 1.00000000 1
## 261 5 0.00000000 0.00000000 0.15776023 0.15776023 1
## 262 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 263 5 0.00000000 0.00000000 0.22817413 0.38593435 1
## 264 2 0.00000000 0.60178322 0.75954344 0.75954344 1
## 265 3 0.05149154 0.45914680 1.00000000 1.00000000 1
## 266 3 0.00000000 0.01228243 0.77156132 1.00000000 1
## 267 3 0.00000000 0.07067845 0.83970577 1.00000000 1
## 268 3 0.14801180 0.31805445 0.70114742 1.00000000 1
## 269 2 0.49189565 0.53110476 0.92932155 1.00000000 1
## 270 1 0.59234474 0.59234474 0.92932155 1.00000000 1
## 271 4 0.00000000 0.22817413 0.33697681 0.53394615 1
## 272 2 0.38309297 0.59234474 1.00000000 1.00000000 1
## 273 1 0.61126709 0.68194555 1.00000000 1.00000000 1
## 274 5 0.00000000 0.00000000 0.07067845 0.22843868 1
## 275 5 0.00000000 0.00000000 0.00000000 0.26738323 1
## 276 4 0.00000000 0.01228243 0.12108512 1.00000000 1
## 277 1 0.54338719 1.00000000 1.00000000 1.00000000 1
## 278 3 0.00000000 0.00000000 0.61690703 1.00000000 1
## 279 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 280 4 0.00000000 0.00000000 0.22817413 1.00000000 1
## 281 4 0.00000000 0.10880269 0.30577202 0.77182587 1
## 282 2 0.38309297 0.75954344 0.98771757 0.98771757 1
## 283 2 0.01228243 0.78130975 0.89119731 0.89119731 1
## 284 2 0.05149154 0.82051886 0.92932155 0.92932155 1
## 285 2 0.05149154 0.82051886 0.92932155 0.92932155 1
## 286 2 0.05149154 0.82051886 0.89119731 0.89119731 1
## 287 2 0.12108512 0.89011244 0.92932155 0.92932155 1
## 288 4 0.00000000 0.00000000 0.01228243 0.57769792 1
## 289 2 0.17948114 0.79074823 0.98771757 1.00000000 1
## 290 1 0.82995734 0.98771757 1.00000000 1.00000000 1
## 291 1 0.53110476 0.98771757 1.00000000 1.00000000 1
## 292 5 0.00000000 0.01228243 0.08296088 0.38873291 1
## 293 1 0.53394615 0.92932155 1.00000000 1.00000000 1
## 294 1 0.53394615 0.91703912 1.00000000 1.00000000 1
## 295 1 0.82051886 1.00000000 1.00000000 1.00000000 1
## 296 3 0.41993769 0.45914680 1.00000000 1.00000000 1
## 297 2 0.29885258 0.87891488 0.87891488 1.00000000 1
## 298 4 0.00000000 0.22817413 0.34925924 1.00000000 1
## 299 1 0.82995734 0.98771757 1.00000000 1.00000000 1
## 300 4 0.00000000 0.00000000 0.42514346 1.00000000 1
## 301 3 0.00000000 0.19696934 0.50810435 1.00000000 1
## 302 3 0.00000000 0.49473704 0.91703912 1.00000000 1
## 303 3 0.03920911 0.30577202 0.60462460 1.00000000 1
## 304 2 0.00000000 0.80823643 0.98771757 1.00000000 1
## 305 2 0.38593435 0.87891488 0.87891488 1.00000000 1
## 306 1 0.72115466 0.98771757 1.00000000 1.00000000 1
## 307 5 0.00000000 0.00000000 0.00000000 0.07067845 1
## 308 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 309 3 0.00000000 0.14801180 0.70114742 1.00000000 1
## 310 3 0.00000000 0.42514346 1.00000000 1.00000000 1
## 311 5 0.00000000 0.00000000 0.03920911 0.03920911 1
## 312 4 0.00000000 0.00000000 0.26656291 1.00000000 1
## 313 2 0.42230208 0.50526296 0.73343709 0.73343709 1
## 314 5 0.00000000 0.22817413 0.38593435 0.39821678 1
## 315 5 0.00000000 0.00000000 0.01228243 0.27993022 1
## 316 5 0.00000000 0.00000000 0.03920911 0.26738323 1
## 317 3 0.03920911 0.16029423 0.92932155 0.92932155 1
## 318 4 0.00000000 0.00000000 0.10988756 0.75954344 1
## 319 1 0.72033434 0.98771757 1.00000000 1.00000000 1
## 320 3 0.00000000 0.21869025 0.82995734 1.00000000 1
## 321 5 0.00000000 0.00000000 0.07067845 0.07067845 1
## 322 5 0.00000000 0.00000000 0.00000000 0.00000000 1
## 323 2 0.01228243 0.82051886 0.82051886 1.00000000 1
## 324 4 0.00000000 0.03920911 0.14801180 1.00000000 1
## 325 4 0.00000000 0.01228243 0.17004266 1.00000000 1
## 326 4 0.00000000 0.00000000 0.27884534 1.00000000 1
## 327 3 0.00000000 0.10880269 0.53110476 0.77182587 1
## 328 5 0.00000000 0.00000000 0.01228243 0.08296088 1
## 329 4 0.00000000 0.17004266 0.17004266 0.62381408 1
## 330 5 0.00000000 0.00000000 0.00000000 0.40765526 1
## 331 2 0.15776023 0.70114742 0.92932155 1.00000000 1
## 332 4 0.00000000 0.00000000 0.15776023 0.82051886 1
## 333 5 0.00000000 0.00000000 0.10880269 0.37618592 1
## 334 5 0.00000000 0.00000000 0.00000000 0.16029423 1
## 335 5 0.00000000 0.00000000 0.00000000 0.23097268 1
## 336 4 0.00000000 0.00000000 0.10880269 0.61690703 1
## 337 4 0.00000000 0.22843868 0.37645048 0.77182587 1
## 338 3 0.19696934 0.38873291 1.00000000 1.00000000 1
## 339 2 0.00000000 0.66193831 0.96079089 1.00000000 1
## 340 2 0.37618592 0.98771757 1.00000000 1.00000000 1
## 341 3 0.00000000 0.03920911 0.75954344 0.98771757 1
## 342 2 0.15776023 0.83970577 0.85198820 1.00000000 1
## 343 4 0.00000000 0.00000000 0.49189565 0.80303066 1
## 344 2 0.24072111 0.73261677 0.77182587 1.00000000 1
## 345 2 0.45661281 0.60462460 0.61690703 1.00000000 1
## 346 2 0.00000000 0.57485654 0.73261677 1.00000000 1
## 347 3 0.00000000 0.00000000 0.72006978 1.00000000 1
## 348 3 0.03920911 0.42514346 0.89119731 1.00000000 1
## 349 3 0.00000000 0.00000000 0.50810435 1.00000000 1
## 350 3 0.00000000 0.34952380 0.77182587 0.77182587 1
## 351 1 0.61126709 0.98771757 0.98771757 1.00000000 1
## 352 3 0.00000000 0.42230208 0.82995734 1.00000000 1
## 353 3 0.16029423 0.45914680 0.84223977 1.00000000 1
## 354 3 0.03920911 0.20925177 0.70114742 0.92932155 1
## 355 5 0.00000000 0.00000000 0.00000000 0.22817413 1
## 356 2 0.15776023 0.59234474 0.59234474 1.00000000 1
## 357 3 0.00000000 0.27884534 0.92932155 1.00000000 1
## 358 3 0.33806169 0.45914680 1.00000000 1.00000000 1
## 359 5 0.00000000 0.00000000 0.07067845 0.07067845 1
## 360 5 0.00000000 0.00000000 0.17948114 0.37645048 1
## 361 3 0.00000000 0.15776023 0.61153165 0.98771757 1
## 362 3 0.16029423 0.38846835 0.92932155 1.00000000 1
fit=fitted(fit_pre_kknn)
fit
## [1] 2 2 4 4 3 5 5 5 4 2 2 3 5 2 1 3 1 4 5 2 3 4 2 3 2 4 3 1 2 2 2 2 3 1 1
## [36] 2 5 4 3 3 4 5 2 3 5 2 2 2 4 3 2 5 4 2 4 2 4 4 3 4 4 1 2 3 2 1 4 1 3 1
## [71] 4 3 4 3 1 5 2 2 4 4 4 4 4 4 2 3 3 2 3 3 2 1 4 2 3 5 2 3 4 5 2 2 5 1 1
## [106] 3 4 2 3 2 2 2 1 1 1 5 1 2 2 4 5 3 4 5 4 1 4 3 4 3 2 2 2 2 3 2 5 2 3 2
## [141] 2 2 2 2 3 2 1 2 5 2 1 2 2 4 4 3 5 5 1 2 2 1 3 2 4 3 3 4 4 2 1 5 4 2 3
## [176] 2 5 2 3 2 5 5 4 2 2 2 1 4 1 2 4 1 4 3 2 3 1 2 4 1 2 3 3 3 3 5 1 2 2 1
## [211] 4 5 1 2 5 5 2 5 1 3 5 1 5 5 4 1 1 5 3 5 1 1 1 2 2 3 3 2 1 2 1 4 2 4 1
## [246] 2 3 4 2 1 2 4 1 1 1 3 3 3 4 3 5 5 5 2 3 3 3 3 2 1 4 2 1 5 5 4 1 3 5 4
## [281] 4 2 2 2 2 2 2 4 2 1 1 5 1 1 1 3 2 4 1 4 3 3 3 2 2 1 5 5 3 3 5 4 2 5 5
## [316] 5 3 4 1 3 5 5 2 4 4 4 3 5 4 5 2 4 5 5 5 4 4 3 2 2 3 2 4 2 2 2 3 3 3 3
## [351] 1 3 3 3 5 2 3 3 5 5 3 3
## Levels: 1 < 2 < 3 < 4 < 5
table(data_test$nmkat,fit)
## fit
## 1 2 3 4 5
## 1 36 29 8 0 2
## 2 14 42 25 5 0
## 3 5 22 28 10 1
## 4 2 7 14 36 5
## 5 0 3 3 16 49
error_kknn=sum(as.numeric(as.numeric(fit)!=as.numeric(data_test$nmkat)))/nrow(data_test)
error_kknn
## [1] 0.4723757