UTS statistika ekonomi industri Samuel Aditya Pratama 2304010012
Samuel
2024-10-17
MEMBUAT DAN MEMERIKSA DATA UNTUK DI CLEANING
data <- read.csv("uas sei.csv")
str(data)## 'data.frame': 100 obs. of 16 variables:
## $ Country : chr "AD" "AE" "AE-AZ" "AE-RK" ...
## $ X1 : num 17.5 18.2 18.7 NA 14 ...
## $ X2 : num 38675 40105 76038 27883 4251 ...
## $ X3 : num 172.8 103.5 31 24.8 89.6 ...
## $ X4 : num 0.68 1.77 2.63 1.29 1.44 ...
## $ X5 : num 1.221 0.87 1.489 1.753 0.256 ...
## $ X6 : num 1.79 2.66 1.85 2.23 4.75 ...
## $ X7 : num -2.084 -0.725 -1.901 -1.135 2.332 ...
## $ X8 : num 55 103 103 103 167 ...
## $ X9 : num -26.5 -13.6 -56.2 24.8 47.3 ...
## $ X10 : num 2.86 352.91 199.93 10.11 12.65 ...
## $ X11 : num 8 8.15 8.15 NA 6.6 ...
## $ X12 : num 23.1 24.9 20.4 21.7 19.4 ...
## $ X13 : num 26.9 32.5 31 17.3 15.1 ...
## $ X14 : num 3 2.45 NA NA 18.5 ...
## $ Risk.Level: chr "low" "low" "low" "low" ...summary(data)## Country X1 X2 X3
## Length:100 Min. : 4.20 Min. : 434.5 Min. : 13.63
## Class :character 1st Qu.:15.93 1st Qu.: 4265.9 1st Qu.: 42.96
## Mode :character Median :18.58 Median : 11659.1 Median : 70.42
## Mean :18.97 Mean : 22641.6 Mean : 191.94
## 3rd Qu.:21.80 3rd Qu.: 34815.2 3rd Qu.: 130.63
## Max. :47.50 Max. :124340.4 Max. :6908.35
## NA's :12
## X4 X5 X6 X7
## Min. :-0.151 Min. :-0.8862 Min. :-5.135 Min. :-9.84530
## 1st Qu.: 0.869 1st Qu.: 0.4419 1st Qu.: 1.765 1st Qu.:-1.18720
## Median : 1.700 Median : 1.1402 Median : 2.984 Median : 0.07155
## Mean : 3.263 Mean : 1.2019 Mean : 3.076 Mean : 0.10804
## 3rd Qu.: 3.939 3rd Qu.: 1.9502 3rd Qu.: 4.305 3rd Qu.: 1.94108
## Max. :36.703 Max. : 4.4021 Max. :10.076 Max. : 6.07120
##
## X8 X9 X10 X11
## Min. : 34.82 Min. :-1955.72 Min. : 1.171 Min. : 0.3357
## 1st Qu.: 76.95 1st Qu.: -14.11 1st Qu.: 32.813 1st Qu.: 1.9250
## Median : 90.19 Median : 12.67 Median : 106.872 Median : 3.9000
## Mean : 99.94 Mean : -13.58 Mean : 582.318 Mean : 5.5346
## 3rd Qu.:113.39 3rd Qu.: 36.67 3rd Qu.: 366.370 3rd Qu.: 7.9500
## Max. :359.14 Max. : 456.49 Max. :14866.703 Max. :26.9780
## NA's :7 NA's :17
## X12 X13 X14 Risk.Level
## Min. :12.67 Min. :10.95 Min. : 0.120 Length:100
## 1st Qu.:20.79 1st Qu.:19.06 1st Qu.: 4.818 Class :character
## Median :23.40 Median :24.28 Median : 6.800 Mode :character
## Mean :24.96 Mean :24.48 Mean : 8.441
## 3rd Qu.:28.38 3rd Qu.:29.36 3rd Qu.:10.500
## Max. :46.83 Max. :55.09 Max. :24.650
## NA's :11colSums(is.na(data))## Country X1 X2 X3 X4 X5 X6
## 1 12 0 0 0 0 0
## X7 X8 X9 X10 X11 X12 X13
## 0 7 0 0 17 0 0
## X14 Risk.Level
## 11 0Baris ini digunakan untuk membaca file CSV ke dalam R dan menyimpannya dalam variabel data.
MENANGANI MISING VALUES
data_clean <- na.omit(data)
for(i in 2:15){
data [is.na(data[,i]), i] <- mean(data[,i], na.rm = TRUE)
}library(naniar)
vis_miss(data)
##### Langkah di atas Menghapus seluruh baris yang memiliki missing
values, menciptakan dataset data_clean yang bersih tanpa missing values.
Loop untuk mengisi missing values: Untuk kolom 2 hingga 15, nilai-nilai
yang hilang (NA) diisi dengan rata-rata kolom tersebut. Ini adalah
alternatif untuk menghapus missing values, di mana kita tetap
mempertahankan baris yang hilang dengan mengisi data.
MENANGANI OUTLIER
detect_outliers <- function(x) {
Q1 <- quantile(x, 0.25, na.rm = TRUE) # Kuartil pertama
Q3 <- quantile(x, 0.75, na.rm = TRUE) # Kuartil ketiga
IQR <- Q3 - Q1 # Interquartile range (IQR)
lower_bound <- Q1 - 1.5 * IQR
upper_bound <- Q3 + 1.5 * IQR
return(x < lower_bound | x > upper_bound)
}Fungsi ini sangat berguna untuk mendeteksi outliers menggunakan metode yang umum dan robust, yaitu IQR. Ini membantu mengidentifikasi nilai-nilai yang terlalu ekstrem dalam data numerik, yang mungkin memengaruhi hasil analisis atau model prediktif.
MENERAPKAN FUNGSI PADA KOLOM NUMBERIK
for (i in 2:15) {
outliers <- detect_outliers(data[,i])
print(paste("Outliers in column", names(data)[i], ":", sum(outliers, na.rm = TRUE)))
}## [1] "Outliers in column X1 : 3"
## [1] "Outliers in column X2 : 4"
## [1] "Outliers in column X3 : 9"
## [1] "Outliers in column X4 : 7"
## [1] "Outliers in column X5 : 1"
## [1] "Outliers in column X6 : 3"
## [1] "Outliers in column X7 : 2"
## [1] "Outliers in column X8 : 5"
## [1] "Outliers in column X9 : 12"
## [1] "Outliers in column X10 : 16"
## [1] "Outliers in column X11 : 6"
## [1] "Outliers in column X12 : 5"
## [1] "Outliers in column X13 : 2"
## [1] "Outliers in column X14 : 9"proses deteksi outliers ini merupakan langkah penting dalam pembersihan data, memastikan data lebih andal sebelum digunakan dalam analisis lebih mendalam.
MEMPERBAIKI FORMAT DATA
for(i in 2:ncol(data)) {
h <- as.numeric(data[,i])
qs <- as.numeric(runif(nrow(data)))
result <- (1 - h) * qs
print(result)
}## [1] -11.73540711 -1.27472386 -12.49421210 -15.65433219 -2.75522455
## [6] -10.47349048 -1.74184224 -1.13236159 -10.61141920 -4.72073484
## [11] -7.95006680 -1.13819973 -13.84031152 -7.53684516 -14.79508163
## [16] -5.71975508 -3.58455158 -8.53054689 -10.16711547 -0.62257203
## [21] -3.09967207 -12.41297576 -16.84242050 -11.71150521 -0.55145959
## [26] -5.29194452 -13.30295430 -2.91220832 -14.70753621 -3.83782040
## [31] -4.07821245 -16.34723948 -5.00777657 -11.57326458 -0.02752677
## [36] -7.37131474 -2.94838366 -2.64982261 -6.60741204 -3.54277962
## [41] -16.22313405 -9.70730630 -13.71714574 -4.14005482 -10.48258963
## [46] -12.05730534 -2.70898583 -3.50370847 -15.80074489 -16.31971949
## [51] -15.98888261 -3.45031442 -11.69689169 -8.06270148 -2.08649785
## [56] -9.83643021 -9.35656143 -8.52156652 -11.41731285 -1.55761215
## [61] -15.90617150 -7.09414023 -0.99480299 -10.23851643 -5.09035841
## [66] -5.99617639 -7.45962484 -17.33638817 -12.96764875 -1.46190461
## [71] -9.74162777 -7.67266126 -13.25140453 -12.70635237 -22.68075483
## [76] -31.89300694 -14.68950100 -11.45163738 -0.73380299 -3.87979239
## [81] -10.98075978 -12.18904892 -1.55390846 -3.29401337 -17.59081646
## [86] -6.98349962 -13.13495696 -5.01110504 -11.27496850 -5.77765819
## [91] -9.83296883 -13.22408614 -3.77389179 -3.68365301 -7.94730726
## [96] -17.81913651 -3.83125454 -12.89327135 -2.62053964 -8.78352738
## [1] -12021.62895 -34689.66864 -18729.15350 -26966.70022 -1108.12254
## [6] -1829.40222 -9153.52096 -2420.93349 -37757.98176 -15404.80041
## [11] -4495.66334 -543.72138 -18255.79728 -4935.80117 -1432.47724
## [16] -758.63020 -2703.54593 -1518.58094 -2823.86217 -36896.31904
## [21] -302.76755 -62177.14298 -34.46839 -10646.89959 -895.17239
## [26] -5573.05780 -1621.80015 -8545.87649 -2369.55602 -2541.75456
## [31] -21070.87913 -13238.51615 -61500.32317 -2970.30967 -2111.49416
## [36] -8241.37632 -31.88511 -9194.23205 -529.04550 -45367.95406
## [41] -43163.96631 -2149.23545 -10869.71242 -3894.85827 -2036.98779
## [46] -15110.16900 -4135.22862 -18645.39674 -105.27630 -17298.73524
## [51] -2219.72313 -47070.89305 -36788.12980 -1112.96500 -1405.64380
## [56] -39037.69560 -9178.86090 -3665.00165 -3430.11757 -18621.68223
## [61] -1351.87544 -28153.41962 -28310.83361 -444.75624 -2464.18150
## [66] -855.46722 -1865.86721 -7519.66399 -55574.68500 -9010.15678
## [71] -1457.72766 -5981.13891 -1164.53401 -23521.91930 -17265.69138
## [76] -4880.03241 -1414.87983 -4836.90961 -349.84462 -161.41857
## [81] -83.46546 -743.12999 -10652.29966 -54231.69129 -6509.88976
## [86] -387.80714 -5626.20542 -5418.17085 -3036.30856 -774.02077
## [91] -14049.25974 -13185.50533 -4820.59476 -50239.42061 -13880.13734
## [96] -1819.22793 -3525.38340 -427.95375 -6152.38264 -2496.90428
## [1] -40.307428 -64.016515 -16.610486 -8.185248 -69.401397 -31.668975
## [7] -17.960305 -55.384204 -21.748066 -53.464717 -28.477927 -8.900698
## [13] -6.562644 -15.304129 -166.908916 -30.829359 -25.085729 -25.370027
## [19] -3.035243 -62.413299 -11.729554 -252.779880 -31.448802 -33.245502
## [25] -23.244363 -5.317039 -31.609018 -1.605808 -92.818557 -110.902726
## [31] -53.191659 -38.118156 -52.374663 -41.213028 -27.413561 -6.193561
## [37] -5.270383 -22.434977 -1.899531 -136.405987 -72.540682 -33.632148
## [43] -262.955906 -94.745028 -25.865170 -236.330145 -23.498112 -202.118705
## [49] -8.486780 -102.785078 -18.093946 -724.913296 -5.674893 -1.597936
## [55] -15.059188 -3.015635 -32.559289 -39.985012 -2.717630 -27.646043
## [61] -44.658005 -12.609558 -31.397800 -46.175843 -42.091617 -9.725988
## [67] -61.707418 -28.042533 -520.826266 -121.133344 -19.300620 -48.162722
## [73] -199.176327 -131.554649 -288.662931 -33.268262 -18.418119 -60.692069
## [79] -24.273090 -7.725624 -1.657050 -68.627646 -301.218921 -37.624910
## [85] -83.831167 -12.474782 -109.849722 -6.255734 -21.283098 -5.315421
## [91] -46.400448 -107.949771 -6.271877 -33.035095 -40.624695 -36.423899
## [97] -8.530859 -31.721491 -25.545196 -56.038253
## [1] 0.244853325 -0.203705419 -0.626577987 -0.163346184 -0.241370458
## [6] -15.904687851 -17.710861620 -0.154822650 -0.368904268 -0.006518398
## [11] -1.277207809 -2.919481305 -0.533739166 0.053083764 -0.133635576
## [16] 0.625868861 -0.907627221 -0.936164348 -3.976749968 -0.006531118
## [21] -0.822663277 0.064289321 0.181916452 -0.148734993 -0.309492787
## [26] -0.568917799 -1.268223797 -0.195801928 0.128024261 0.192345411
## [31] -0.566692953 -0.179923136 0.360347439 -0.914253039 -0.049283390
## [36] -0.567245304 -2.505967025 0.063401589 -3.575118435 0.091151522
## [41] 0.007531787 -0.278671166 -0.378098814 -0.464918265 -4.506068452
## [46] 0.311830859 -0.925892787 -0.991139822 0.237431426 -0.316551645
## [51] -2.297109674 0.393172970 0.197246318 -0.490135354 0.055528207
## [56] 0.276451483 0.167391750 -0.309182357 -0.272539160 0.167206771
## [61] -2.478518616 -0.001005648 -0.275123223 -1.090797699 -1.940051352
## [66] -0.756465097 -0.617855625 -0.566858717 -0.162972048 -0.190472899
## [71] -0.143067164 0.271325396 -2.316968456 -1.226349535 -0.127243857
## [76] 0.119214010 -0.599891492 -0.323652446 -6.930046383 -2.743161884
## [81] -3.773323729 -1.657789623 -0.082907429 -0.061186173 -0.034579962
## [86] 0.105266546 0.471695969 -1.361744120 -1.045829380 -2.446291185
## [91] 0.074620291 0.143670710 -2.409041640 0.020915251 -0.032901941
## [96] -0.014605245 -2.988247761 -0.217293406 0.225298104 -0.006031149
## [1] -0.066194008 0.119487815 -0.313092075 -0.107492324 0.167377010
## [6] -0.306994431 0.022133504 0.219276517 -0.031641237 0.190664788
## [11] -0.040233914 -0.021782163 0.109608662 1.509027674 -0.105557371
## [16] -0.766279265 -0.223543449 0.185829516 0.306356458 -0.111656255
## [21] -0.559512201 0.031768723 -1.213910737 -0.186636399 -0.109640798
## [26] 0.057944181 -0.132940403 0.001673024 -0.155881782 0.721986439
## [31] 0.094330175 0.502341341 0.099641268 0.033706390 -0.411080204
## [36] 0.684343005 -0.088711926 0.111016617 -0.493558728 0.568645023
## [41] 0.483293846 -0.256347591 0.148249746 0.950671656 -0.263307486
## [46] 0.916839341 -0.174488147 0.069179417 0.160660688 0.450014042
## [51] -0.059942589 -0.189855626 -0.001263646 -0.045339543 -1.024253251
## [56] -0.452611230 0.059474557 0.230171363 -0.676588573 1.141056866
## [61] -1.262962127 0.042883373 -0.483239330 -0.289443859 0.045745731
## [66] 0.195831460 -0.066934377 0.319804957 -0.448787088 0.848571599
## [71] -0.232843893 0.311669190 -0.167633005 -0.189569121 -0.061305718
## [76] -2.404441507 -0.089099522 -0.058259430 -0.590256748 -0.476180509
## [81] -0.719579610 -0.027555458 0.028836283 0.051063094 -0.408871496
## [86] -0.392359017 -0.269253428 -0.016092887 -0.197677656 -0.344559398
## [91] 0.649898360 1.147250499 -0.185322045 -0.483581889 1.561758503
## [96] 0.901047058 0.179179825 -1.095998097 -1.458561072 -0.010327841
## [1] -0.2685786613 -1.5754446029 -0.5856509095 -0.1005830415 -0.0387314210
## [6] 1.6428053999 0.3450883808 -0.7536319394 -0.1681746915 -0.0383722840
## [11] 0.3813501008 -0.9566152073 -0.3345862347 -2.5949983719 -1.5193324563
## [16] -3.2918701609 -0.1585443970 1.3983267618 0.8674734091 -0.7865336122
## [21] 6.0851609088 -0.6700299786 -0.8685720232 -0.0606248181 -2.4585598902
## [26] -1.9341585428 -1.4285355505 -0.9698330809 -2.1104384604 -2.5285505105
## [31] -0.1931072328 -0.2306517113 -0.7765701114 -2.9351332191 0.1388983383
## [36] -2.6687381400 -2.5186606634 -1.5769068709 -7.9734696995 -0.8005012792
## [41] -0.2368419598 -1.0364587724 -0.5415167251 -2.6185432529 -1.4836936829
## [46] 0.1114363857 -0.5038470386 -0.0680473650 -0.1713290047 -0.6988072259
## [51] -2.5437952164 -0.4785278045 -0.0005583597 -3.9238647160 -2.7223431656
## [56] -0.0821944752 0.0121869761 -0.1347701119 -0.7842677019 0.0420485789
## [61] -2.5970761421 -1.2703148126 0.6504126692 -0.0582518219 -0.0436438318
## [66] 0.5613148874 -5.5667309244 -0.5268179824 -1.2602590394 -0.1128695322
## [71] -1.8915460681 -1.5967837482 -2.1058662822 2.4939368766 -5.4287623187
## [76] -2.1717253540 -0.8666129954 -1.2479446791 -0.9470752916 0.0037945819
## [81] -0.0092637075 -0.3028288223 -0.5339502760 -0.4010870611 -1.9016137939
## [86] -0.7891511707 -3.2167937523 -1.4501410741 -1.8849949888 -3.2802260005
## [91] -2.4394761772 -1.1477854288 -0.7594179540 -0.0564823837 -1.1313310236
## [96] -1.7935531665 0.0033190681 -3.4654676157 -0.4447096316 -1.0267925579
## [1] 1.672970931 0.648638458 1.934461430 1.718736716 -1.019161561
## [6] 1.168147368 0.216470511 0.799630856 0.756761741 1.188437482
## [11] 0.539289353 -3.068565688 0.007039277 -1.237618608 4.004766250
## [16] -0.838053550 1.003460013 0.088018776 0.173849517 1.575029649
## [21] 8.782444712 0.381744280 -0.579780144 0.077282182 0.123044481
## [26] -1.025348265 1.159585901 0.110272751 0.360506024 -1.038382493
## [31] -0.163438557 0.976276238 -0.036529615 -0.169423526 1.778543976
## [36] -0.275508495 -0.357861410 0.875844947 -2.804716720 0.020870526
## [41] 1.116444105 0.624023966 1.866612086 -0.552313957 -0.883752881
## [46] 0.692086108 0.093731393 1.185299509 -0.523507967 -0.557507086
## [51] -1.244068961 -2.572180438 0.211681991 -0.296077246 1.433926995
## [56] 0.237375433 1.070463836 0.668800260 1.107195123 1.121601906
## [61] -0.030368283 -0.327988788 3.004576046 0.013056476 -0.060857028
## [66] 0.008238033 -0.212430784 -0.454682715 0.126794980 -1.026755481
## [71] 1.088117552 -0.054681543 0.051826997 7.918598406 0.518734566
## [76] 0.776014404 1.857244042 -0.192687954 1.182160876 1.086789491
## [81] 2.046338350 1.139229756 0.249946803 0.251500847 0.491678344
## [86] 1.872114322 2.628047098 0.146675656 -0.080052222 -0.057608210
## [91] -2.091466496 0.002234893 0.042849153 3.312726386 -1.486136499
## [96] -1.535817602 0.100371917 -0.209211838 2.740398087 0.336632623
## [1] -38.8994638 -35.1451819 -32.1584311 -11.8943468 -111.0035568
## [6] -16.1305235 -66.6018694 -78.6206601 -21.3762163 -9.1037982
## [11] -50.2895122 -72.8963648 -13.4373367 -16.4316025 -89.8310309
## [16] -4.3134765 -56.0881721 -66.3260932 -36.0511079 -17.4622221
## [21] -53.9075052 -29.8647311 -27.2978198 -33.4477110 -8.9479315
## [26] -35.8212334 -28.7088173 -73.7160829 -38.6901656 -56.9755900
## [31] -3.4864338 -31.3526086 -14.4161147 -32.8874817 -44.7712691
## [36] -20.4839325 -37.6247854 -74.6350332 -24.8618842 -9.5829132
## [41] -38.1494966 -54.9711005 -84.5476399 -2.8780477 -6.1698948
## [46] -26.8810706 -23.7042496 -23.6631396 -35.7080468 -65.7202292
## [51] -19.8426994 -17.0478286 -36.2813141 -8.5456801 -1.9414947
## [56] -52.5205175 -66.4930596 -14.5683035 -23.1734358 -54.7962677
## [61] -13.3593784 -13.5525417 -46.8887580 -49.0148179 -44.6712114
## [66] -21.9243142 -74.1926504 -48.2437026 -14.8303274 -55.2068677
## [71] -16.5104802 -32.7332067 -5.3494337 -41.5891258 -52.1687117
## [76] -35.1651581 -7.9172526 -98.0447674 -34.5344168 -70.1855929
## [81] -0.4650487 -75.9278932 -24.4651885 -68.9332884 -67.1790077
## [86] -57.2928821 -65.0730908 -87.1141547 -16.2569543 -26.2327943
## [91] -7.2528475 -48.0211983 -16.4366737 -101.1912171 -19.3780803
## [96] -13.8273039 -80.1158729 -82.2174928 -81.8867608 -36.6293221
## [1] 26.74875237 6.67270025 0.53016149 -8.15440548 -18.34557210
## [6] -0.68250707 0.46518310 -0.52560308 -31.44894104 -23.95200767
## [11] 29.07852111 -1.25828930 6.88090647 8.39916786 18.94632894
## [16] -7.40622728 10.87506129 -5.59100170 -11.65075503 -40.90208529
## [21] -53.25195275 38.16791540 -2.74693904 -0.48947181 -14.91803422
## [26] 24.80757181 -1.42498405 -0.30296913 -7.05583726 -292.83423642
## [31] 6.83428744 5.06629901 3.84362216 -13.63900573 -5.42837910
## [36] 3.39466012 -6.00832996 -63.76568874 -12.06459808 -35.51179291
## [41] -31.56306115 -16.43951548 -22.14560719 -7.37302444 -21.25700145
## [46] -126.38283296 -1.45265236 15.30406240 -16.83329247 -4.65735791
## [51] -1.39027804 120.06256075 41.59345252 0.11301438 -0.03513337
## [56] -24.37781031 -46.40669455 -3.56213250 -4.43570566 11.58928905
## [61] -15.78184474 3.50353027 240.76752987 17.02424672 -19.50942671
## [66] -5.95378741 -49.13949286 -1.64649731 759.51755198 -2.50080932
## [71] -4.18744074 -8.17754652 -113.32876917 76.29912216 184.63893710
## [76] 0.98398835 -6.13756283 11.25617419 -52.24579654 -16.66424879
## [81] 0.81825640 -41.57563321 -1.65409921 6.43607350 -3.30475688
## [86] -15.10958301 -18.17478760 18.96593251 3.78087542 -15.44512044
## [91] -6.89033155 -53.51048437 -1.10340167 -0.17168614 -0.35329904
## [96] -23.32155103 13.65853781 -5.23286246 53.75501343 -23.94157803
## [1] -1.697515e+00 -2.704334e+02 -1.692230e+01 -6.157914e+00 -1.136563e+01
## [6] -3.623234e+01 -1.833250e+02 -6.493614e+01 -1.319700e+03 -4.244155e-01
## [11] -1.366023e+01 -2.853280e+02 -4.054327e+02 -4.055119e+01 -2.224734e+01
## [16] -1.202827e+01 -1.506171e+01 -4.901774e+02 -4.126683e+01 -5.812177e+02
## [21] -4.484745e+00 -2.678195e+02 -4.911292e+01 -1.792118e+02 -3.210102e+01
## [26] -6.098877e+03 -2.260125e+01 -2.035692e+00 -6.633865e-01 -5.348117e+00
## [31] -7.745885e+01 -3.263472e+03 -2.389856e+02 -2.973687e+01 -5.989197e+01
## [36] -3.927456e+00 -3.091776e+01 -3.795281e+02 -6.662878e+01 -2.390304e+02
## [41] -1.905581e+02 -1.177711e+01 -1.534065e+03 -8.106326e+00 -1.745451e+01
## [46] -4.864114e+00 -8.498997e+00 -2.904860e+02 -1.660749e+01 -3.223069e+01
## [51] -5.578329e+02 -3.446719e+02 -8.955379e+01 -1.102564e+03 -1.349629e+02
## [56] -7.362171e+00 -6.532951e+02 -6.948865e+00 -3.176124e+01 -1.563979e+03
## [61] -1.949893e+01 -1.149269e+03 -6.213406e+01 -1.102933e+02 -6.983868e+01
## [66] -3.378879e-01 -3.450582e-01 -2.898484e+01 -4.945696e+01 -3.051190e+01
## [71] -4.866075e+01 -2.662586e+00 -1.398343e+00 -3.276251e+00 -4.876704e+00
## [76] -1.361130e+00 -1.773854e+02 -3.002267e+02 -1.110715e+01 -8.356482e+00
## [81] -3.104810e+02 -7.985584e+00 -6.832893e+02 -6.875714e+01 -6.356310e+01
## [86] -2.199262e+01 -3.930081e+01 -1.822991e+02 -3.410213e+02 -2.210750e+02
## [91] -2.343409e+02 -5.953245e+00 -1.105025e+01 -7.439905e+01 -1.201645e+01
## [96] -4.345533e+01 -1.078821e+03 -6.565198e+00 -5.779749e+02 -4.249325e-03
## [1] -2.990905552 -5.375959052 -6.243472525 -1.213260154 -4.130092108
## [6] -8.748237038 -0.913383796 -0.681638402 0.001331254 -0.330867026
## [11] -1.482313860 -3.637097195 -1.982012461 -4.710966626 -1.536280767
## [16] -2.824350949 -0.296435352 -1.344717366 -1.841516977 0.016417520
## [21] -16.144319490 0.030419243 -6.109720201 -0.105136060 -11.930527960
## [26] -0.806682030 -0.945019069 -1.153564375 -8.352117287 -0.349923044
## [31] -1.044097431 -0.992032716 -0.271020238 -0.840520764 -4.418162094
## [36] 0.129745710 -1.169730480 -0.994385714 -7.747052019 -0.194778087
## [41] -1.401768900 -3.073031978 -0.064827671 -1.153247184 -3.438008653
## [46] -19.078582960 -0.714882965 0.058439523 -5.910812333 0.023597116
## [51] -1.371869023 -1.426482086 -0.379208794 -2.651839399 -3.279190720
## [56] -1.014225459 -2.096819355 -1.789508533 -0.574230972 -0.028800293
## [61] -12.422737382 0.000000000 -2.217353036 -3.537588218 -3.846004845
## [66] -0.696228006 -1.253287626 0.008385559 -0.002493939 -2.295606329
## [71] -2.216816572 -0.905416677 -3.220703366 0.026034495 -0.215059468
## [76] -1.436311797 -0.002858434 -0.521909005 -10.603428387 -4.837287963
## [81] -3.384646337 -0.212602704 -1.115029418 -2.732555918 -3.594695334
## [86] -0.640149743 -1.038554879 -1.020338318 -0.046055242 -5.953302022
## [91] -2.436375866 -4.803441211 -0.975339114 -0.624438063 -2.332370927
## [96] -3.637693836 -0.669972307 -2.346807790 -4.011207717 -1.990283098
## [1] -15.35892234 -7.86983189 -15.38955145 -8.25437652 -9.24079193
## [6] -26.22059005 -12.19227978 -16.16090990 -0.51065566 -5.84819410
## [11] -13.10984701 -24.90386274 -23.14866354 -3.17802789 -17.88141064
## [16] -10.09406361 -11.59573038 -2.42973805 -3.00995492 -10.90905155
## [21] -20.11628064 -1.89351891 -5.14141614 -12.26330661 -9.43899737
## [26] -41.56175791 -17.58930973 -3.45049930 -32.49769080 -0.20310192
## [31] -18.65968707 -13.88206312 -18.06405479 -4.04328527 -4.06890599
## [36] -7.52806293 -0.08225075 -8.95258993 -1.11693298 -21.09411985
## [41] -8.58910476 -22.58528318 -16.86663993 -21.77619007 -12.80462398
## [46] -6.19300708 -13.03380432 -17.79108711 -19.28914996 -17.76477977
## [51] -23.99329463 -17.47335600 -17.80929958 -28.72949869 -11.19063872
## [56] -11.19808822 -2.59731578 -19.73937635 -13.08708228 -21.73030946
## [61] -10.67311133 -29.61139821 -3.58226384 -8.93884134 -13.87644664
## [66] -20.89443528 -2.72077685 -0.81702954 -13.53259244 -6.99977321
## [71] -23.19195638 -21.78057254 -6.49132483 -10.79592427 -12.82464186
## [76] -7.33354558 -14.31711028 -9.04663258 -12.20857822 -16.11480662
## [81] -7.65373192 -19.46825471 -4.63952368 -5.13581263 -19.27311218
## [86] -19.36289117 -11.23672124 -11.21001854 -20.58151281 -10.85738051
## [91] -5.56686377 -12.80927628 -19.53173680 -32.72114933 -16.34187702
## [96] -8.18479606 -10.21202085 -21.68213783 -6.10143099 -15.09809501
## [1] -16.53691953 -20.97551404 -24.45179909 -7.24979094 -0.06260526
## [6] -14.99558603 -0.76799312 -25.02719574 -7.89095033 -22.00568204
## [11] -27.39485114 -7.58990197 -23.57197710 -2.87765592 -3.78037258
## [16] -5.50671137 -5.53039520 -8.99645819 -6.24683348 -3.07775519
## [21] -6.68126599 -18.96342200 -4.04158123 -4.01003133 -18.53628156
## [26] -34.80987924 -11.72734092 -2.72750368 -18.70939998 -9.51839160
## [31] -12.95154993 -3.98038763 -0.30556522 -8.63503806 -8.74255907
## [36] -24.85251200 -1.11937852 -1.35326273 -6.91817121 -1.74837094
## [41] -12.97330791 -21.29127714 -5.94528968 -16.65002996 -11.57979199
## [46] -2.64547827 -5.24437453 -22.62301111 -1.75982380 -20.73510375
## [51] -25.69113700 -19.30155504 -12.92635501 -4.89938430 -10.77598686
## [56] -12.27807799 -8.62941608 -0.32047115 -9.34807435 -1.19123399
## [61] -0.19061025 -11.73085225 -23.19025714 -1.24794706 -2.40137530
## [66] -6.60680202 -13.49641799 -18.06254521 -31.07479043 -14.41541235
## [71] -16.53144724 -7.81338290 -3.88120397 -29.50873050 -18.33366092
## [76] -2.88448401 -2.34267968 -20.29440357 -0.95271634 -4.43184068
## [81] -2.08183709 -17.99444376 -28.00744388 -17.27881298 -16.04134093
## [86] -7.60182989 -23.69767731 -16.81494849 -9.95587588 -9.21588029
## [91] -15.51812483 -15.62202816 -16.90978390 -28.50208175 -7.48053299
## [96] -11.87275125 -5.30830929 -5.29070239 -17.99186651 -0.22495419
## [1] -1.20189117 -0.43041323 -0.39463688 -0.43527591 -13.26093994
## [6] -5.94948687 -5.17131322 -0.17154639 -3.48127301 -1.04879458
## [11] -4.87252872 -1.26047214 -0.53075037 -3.99454423 -1.26807689
## [16] -0.72109793 -1.30512856 -9.17821680 -1.78810223 -2.08879359
## [21] -2.86660707 -1.41840621 -3.69061723 -6.24770521 -5.50420041
## [26] -3.49940571 -0.54142161 -11.35309637 -4.46934539 -3.79512264
## [31] -0.47205695 -1.85710378 -2.32067450 -3.78602177 -5.39708421
## [36] -0.54572442 -0.74155257 -5.27388374 -12.65766476 -6.26979822
## [41] -4.09333191 -5.25090014 -0.39452686 -10.64556969 -0.67518315
## [46] -6.11210534 -0.18279784 -4.00532652 -5.88438132 -0.92185550
## [51] -4.14815221 -4.10872443 -3.10720889 -0.36520672 -9.47109304
## [56] -1.32948260 -2.75930679 -0.74036773 -0.99392019 -0.77664720
## [61] -8.65141940 -2.69450455 -7.02854268 -1.15005407 -1.02880555
## [66] -14.86895806 -6.16925346 -3.34358673 -4.69937047 -0.35122147
## [71] -7.85994010 -0.85333146 -3.06004717 -0.98918383 -0.37045761
## [76] -4.50811772 -1.32646308 -2.55063686 -5.59286314 -5.54939993
## [81] -3.07658974 -2.16648812 -1.86667184 -0.31571248 -1.20118886
## [86] -6.97233685 -6.99150496 -1.72450306 -6.90266634 -5.24421913
## [91] -0.22732723 -0.37103339 -0.08059306 0.78890056 -0.90849856
## [96] -1.78667888 -0.47148130 -3.42781884 -6.34700234 -0.12501924## Warning: NAs introduced by coercion## [1] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
## [26] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
## [51] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
## [76] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NAKode ini mengonversi kolom data menjadi numerik dan melakukan operasi berbasis nilai acak.Tujuannya adalah memperbaiki format data, maka ini berhasil dalam hal memastikan bahwa setiap kolom numerik dapat diolah secara matematis.
MENGKONVERSI DATA
data$Risk.Level <- as.factor(data$Risk.Level)
for(i in 2:15) {
data[,i] <- as.numeric(as.character(data[,i]))
}Bagian ini bertujuan untuk membersihkan data dengan memastikan bahwa kolom kategori diubah menjadi faktor dan kolom lainnya yang seharusnya numerik dikonversi dengan benar.
MEMBERSIHKAN DAN MENSTANDARKAN DATA
data$Risk.Level <- tolower(data$Risk.Level)
data$Risk.Level <- factor(data$Risk.Level, levels = c("low", "high"))Langkah diatas untuk membersihkan dan menstandarkan data dalam kolom Risk.Level dengan cara mengonversi teks menjadi huruf kecil dan mendefinisikan ulang level faktor.
MENGHAPUS DUPLKAT
data_unique <- unique(data)ini menggunakan untuk menghapus baris duplikat dalam dataset data.
MEMERIKSA DAN MEMPERBAIKI KESALAHAN PENGERTIAN
unique(data$Country)## [1] "AD" "AE" "AE-AZ" "AE-RK" "AM" "AO" "AR" "AT" "AU"
## [10] "AW" "AZ" "BD" "BE" "BG" "BH" "BJ" "BO" "BR"
## [19] "BY" "CA" "CG" "CH" "CI" "CL" "CM" "CN" "CO"
## [28] "CR" "CV" "CY" "CZ" "DE" "DK" "DO" "EC" "EE"
## [37] "EG" "ES" "ET" "FI" "FR" "GA" "GB" "GE" "GH"
## [46] "GR" "GT" "HK" "HR" "HU" "ID" "IE" "IL" "IN"
## [55] "IQ" "IS" "IT" "JM" "JO" "JP" "KE" "KR" "KW"
## [64] "KZ" "LK" "LS" "LT" "LU" "LV" "MA" "MK" "MN"
## [73] "MO" "MT" "MV" "MX" "MY" "MZ" NA "NG" "NI"
## [82] "NL" "NO" "NZ" "OM" "PA" "PE" "PH" "PK" "PL"
## [91] "PT" "PY" "QA" "RO" "RS" "RU" "RW" "SA" "SC"data$Country [data$Country == "AE-AZ"] <- "AE-AZ"Baris ini menampilkan semua nilai unik yang ada dalam kolom Country. Ini berguna untuk mengidentifikasi apakah ada kesalahan penulisan (typo) atau variasi dalam penamaan
MENORMALISASIKAN DATA DAN MENYIMPAN DATA YANG SUDAH DI CLEANING
normalize <- function(x) {
return ((x - min(x)) / (max(x) - min(x)))
}
for(i in 2:15) {
data[,i] <- normalize(data[,i])
}
write.csv(data, "data_clean.csv", row.names = FALSE)Bagian ini untuk menormalisasi data. Normalisasi adalah proses mengubah skala nilai ke dalam rentang tertentu, biasanya [0, 1].
MEMASUKAN LIBARY
library(ggplot2)
library(class)Bagian diatas digunakan untuk berguna untuk membuat grafik dan plot yang informatif dan untuk melakukan klasifikasi.
MELAKUKAN PCA DATA NUMERIK
data_numeric <- data[, 2:14]
pca_result <- prcomp(data_numeric, center = TRUE, scale. = TRUE)Mengambil kolom numerik dari dataset data untuk dianalisis dengan PCA. Biasanya, kolom pertama adalah ID atau label, sehingga dimulai dari kolom ke-2 hingga ke-14.
VISUALISASI HASIL PCA
pca_data <- as.data.frame(pca_result$x)
pca_data$Risk.Level <- data$Risk.Level
ggplot(pca_data, aes(x = PC1, y = PC2, color = Risk.Level)) +
geom_point() +
labs(title = "PCA Biplot", x = "Principal Component 1", y = "Principal Component 2") +
theme_minimal()
##### Untuk membuat plot dengan komponen utama PC1 dan PC2 sebagai
sumbu,menampilkan titik pada plot untuk setiap observasi,menambahkan
judul dan label untuk sumbu,menggunakan tema minimal untuk tampilan plot
yang lebih bersih.
MENAMBAHKAN KOMPONEN UTAMA KEDATASET ASLI
data$PC1 <- pca_result$x[,1]
data$PC2 <- pca_result$x[,2]Kolom PC1 dan PC2 dari hasil PCA ditambahkan ke dataset data. Ini akan digunakan dalam analisis selanjutnya, termasuk klasifikasi.
KLASIFIKASI MENGGUNAKAN KNN
set.seed(123)
train_index <- sample(1:nrow(data), 0.7 * nrow(data))
train_data <- data[train_index, ]
test_data <- data[-train_index, ]
knn_model <- knn(train = train_data[, c("PC1", "PC2")],
test = test_data[, c("PC1", "PC2")],
cl = train_data$Risk.Level, k = 3)untuk pengacakan sehingga hasil yang dihasilkan dapat direproduksi.
HASIL KLASIFIKASI
table(Predicted = knn_model, Actual = test_data$Risk.Level)## Actual
## Predicted low high
## low 12 5
## high 2 11Interpretasi Confusion Matrix
1.True Positives (TP): Ini berarti model dengan benar memprediksi 12 kasus sebagai “low”.
2.False Positives (FP): Ini berarti model salah memprediksi 5 kasus sebagai “low” ketika sebenarnya kasus tersebut adalah “high”.
4.True Negatives (TN): Ini berarti model dengan benar memprediksi 11 kasus sebagai “high”.
INSTALL DAN LOAD LIBARY RANDOM FOREST
library(randomForest)## randomForest 4.7-1.2## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## marginPada bagian ini yang memuat library randomForest, yang diperlukan untuk menggunakan algoritma Random Forest dalam R.Yang berfungsi ini memastikan bahwa semua fungsi yang ada di dalam paket randomForest tersedia untuk digunakan.
MEMBAGI DATASET MENJADI DATA TRAINING DAN TESTING
set.seed(123)
train_index <- sample(1:nrow(data), 0.7 * nrow(data))
train_data <- data[train_index, ]
test_data <- data[-train_index, ]Kita perlu memisahkan dataset menjadi data training (70%) dan data testing (30%).Data training digunakan untuk membangun (melatih) model.Data testing digunakan untuk mengevaluasi performa model setelah dilatih.
MEMBUAT MODEL RANDOM FOREST
rf_model <- randomForest(Risk.Level ~ PC1 + PC2, data = train_data, ntree = 100)Di sini, kita melatih model Random Forest menggunakan data training dengan variabel PC1 dan PC2 (komponen utama dari PCA) sebagai fitur, dan sebagai target yang akan diklasifikasikan.
MELAKUKAN PREDIKSI MENGGUNAKAN DATA TESTING
rf_predictions <- predict(rf_model, test_data)Langkah ini bertujuan untuk memprediksi nilai kelas dari data testing menggunakan model Random Forest yang sudah dilatih sebelumnya.
MEMBUAT CONFUSION MATRIX
confusion_matrix <- table(Predicted = rf_predictions, Actual = test_data$Risk.Level)Langkah ini bertujuan untuk membuat confusion matrix, yang merupakan alat evaluasi yang berguna untuk melihat bagaimana performa model dalam memprediksi kelas yang benar.
MENAMPILKAN CONFUSION MARTIX DAN MENGHITUNG AKURASI MODEL
print(confusion_matrix)## Actual
## Predicted low high
## low 13 2
## high 1 14accuracy <- sum(diag(confusion_matrix)) / sum(confusion_matrix)
print(paste("Accuracy:", round(accuracy * 100, 2), "%"))## [1] "Accuracy: 90 %"MENAMPILKAN HASIL PREDIKSI
new_data <- data[1:17, ]
predictions <- predict(rf_model, new_data)
print(predictions)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
## low low low low high high high low low low high high low low high high
## 17
## high
## Levels: low high