Membuat data frame dalam R
data <- data.frame(
Age = c(30.83, 58.67, 24.50, 27.83, 20.17),
Debt = c(0.000, 4.460, 0.500, 1.540, 5.625),
YearsEmployed = c(1.25, 3.04, 1.50, 3.75, 1.71),
PriorDefault = c(1, 1, 0, 1, 0),
Employed = c(1, 0, 0, 1, 0),
CreditScore = c(1, 6, 0, 5, 0),
DriversLicense = c(0, 0, 0, 0, 0),
ZipCode = c(202, 43, 280, 100, 120),
Income = c(0, 560, 824, 3, 0),
Approved = c(1, 1, 1, 1, 1)
)
# Menampilkan data dalam format tabel
print(data)
## Age Debt YearsEmployed PriorDefault Employed CreditScore DriversLicense
## 1 30.83 0.000 1.25 1 1 1 0
## 2 58.67 4.460 3.04 1 0 6 0
## 3 24.50 0.500 1.50 0 0 0 0
## 4 27.83 1.540 3.75 1 1 5 0
## 5 20.17 5.625 1.71 0 0 0 0
## ZipCode Income Approved
## 1 202 0 1
## 2 43 560 1
## 3 280 824 1
## 4 100 3 1
## 5 120 0 1
Menghitung matriks kovarians
cov_matrix <- cov(data)
print(cov_matrix)
## Age Debt YearsEmployed PriorDefault Employed
## Age 231.361400 9.345663 6.999375 5.03250 -1.5350
## Debt 9.345663 6.187675 0.605225 -0.31875 -0.8275
## YearsEmployed 6.999375 0.605225 1.182050 0.32250 0.1250
## PriorDefault 5.032500 -0.318750 0.322500 0.30000 0.2000
## Employed -1.535000 -0.827500 0.125000 0.20000 0.3000
## CreditScore 33.300000 1.340000 2.810000 1.20000 0.3000
## DriversLicense 0.000000 0.000000 0.000000 0.00000 0.0000
## ZipCode -831.032500 -161.461250 -73.207500 -25.50000 1.0000
## Income 2046.972500 -112.313750 -42.775000 -67.30000 -137.9500
## Approved 0.000000 0.000000 0.000000 0.00000 0.0000
## CreditScore DriversLicense ZipCode Income Approved
## Age 33.30 0 -831.0325 2046.9725 0
## Debt 1.34 0 -161.4613 -112.3137 0
## YearsEmployed 2.81 0 -73.2075 -42.7750 0
## PriorDefault 1.20 0 -25.5000 -67.3000 0
## Employed 0.30 0 1.0000 -137.9500 0
## CreditScore 8.30 0 -207.0000 11.5500 0
## DriversLicense 0.00 0 0.0000 0.0000 0
## ZipCode -207.00 0 8612.0000 12109.2500 0
## Income 11.55 0 12109.2500 151957.8000 0
## Approved 0.00 0 0.0000 0.0000 0
Menghitung eigenvalue dan eigenvector
eig <- eigen(cov_matrix)
print(eig$values) # Eigenvalues
## [1] 1.529992e+05 7.738332e+03 7.515414e+01 4.717491e+00 1.215279e-11
## [6] 7.070453e-12 6.607548e-13 3.488948e-16 0.000000e+00 -6.754622e-30
print(eig$vectors) # Eigenvectors
## [,1] [,2] [,3] [,4] [,5]
## [1,] -1.289705e-02 -0.131560229 0.97799000 0.141469482 0.000000000
## [2,] 8.188079e-04 -0.019605359 -0.12814854 0.630698935 -0.628131610
## [3,] 3.179450e-04 -0.009024758 -0.01824824 -0.329216783 0.182256524
## [4,] 4.517912e-04 -0.002638170 0.04509838 -0.114695526 -0.459932382
## [5,] 8.979962e-04 0.001599490 0.02672140 -0.147878113 -0.206044809
## [6,] 3.495501e-05 -0.027135490 0.08415703 -0.662340287 -0.563476803
## [7,] 0.000000e+00 0.000000000 0.00000000 0.000000000 0.000000000
## [8,] -8.349355e-02 0.987375699 0.12806318 0.009892629 -0.027072540
## [9,] -9.964240e-01 -0.081052237 -0.02345292 -0.002455306 0.001396488
## [10,] 0.000000e+00 0.000000000 0.00000000 0.000000000 0.000000000
## [,6] [,7] [,8] [,9] [,10]
## [1,] 0.077765836 0.000000000 0.000000e+00 0 0.000000e+00
## [2,] 0.431225581 0.070041447 1.066456e-03 0 -1.162768e-15
## [3,] 0.813178810 -0.443523534 3.379390e-03 0 -3.719722e-15
## [4,] -0.362898395 -0.772631073 -2.112158e-01 0 2.309823e-13
## [5,] -0.064180056 -0.086384006 9.609261e-01 0 -1.051044e-12
## [6,] 0.100644552 0.440345042 -1.787384e-01 0 1.955233e-13
## [7,] 0.000000000 0.000000000 1.093792e-12 0 1.000000e+00
## [8,] 0.028014100 0.007422346 -6.870959e-03 0 7.515694e-15
## [9,] -0.002958961 -0.001118632 1.341661e-03 0 -1.467538e-15
## [10,] 0.000000000 0.000000000 0.000000e+00 1 0.000000e+00
Menghitung variance-covariance matrix
var_cov_matrix <- cov(data)
print(var_cov_matrix)
## Age Debt YearsEmployed PriorDefault Employed
## Age 231.361400 9.345663 6.999375 5.03250 -1.5350
## Debt 9.345663 6.187675 0.605225 -0.31875 -0.8275
## YearsEmployed 6.999375 0.605225 1.182050 0.32250 0.1250
## PriorDefault 5.032500 -0.318750 0.322500 0.30000 0.2000
## Employed -1.535000 -0.827500 0.125000 0.20000 0.3000
## CreditScore 33.300000 1.340000 2.810000 1.20000 0.3000
## DriversLicense 0.000000 0.000000 0.000000 0.00000 0.0000
## ZipCode -831.032500 -161.461250 -73.207500 -25.50000 1.0000
## Income 2046.972500 -112.313750 -42.775000 -67.30000 -137.9500
## Approved 0.000000 0.000000 0.000000 0.00000 0.0000
## CreditScore DriversLicense ZipCode Income Approved
## Age 33.30 0 -831.0325 2046.9725 0
## Debt 1.34 0 -161.4613 -112.3137 0
## YearsEmployed 2.81 0 -73.2075 -42.7750 0
## PriorDefault 1.20 0 -25.5000 -67.3000 0
## Employed 0.30 0 1.0000 -137.9500 0
## CreditScore 8.30 0 -207.0000 11.5500 0
## DriversLicense 0.00 0 0.0000 0.0000 0
## ZipCode -207.00 0 8612.0000 12109.2500 0
## Income 11.55 0 12109.2500 151957.8000 0
## Approved 0.00 0 0.0000 0.0000 0
Menghitung correlation matrix
cor_matrix <- cor(data)
## Warning in cor(data): the standard deviation is zero
print(cor_matrix)
## Age Debt YearsEmployed PriorDefault Employed
## Age 1.0000000 0.2470022 0.4232489 0.6040567 -0.18424780
## Debt 0.2470022 1.0000000 0.2237872 -0.2339515 -0.60735642
## YearsEmployed 0.4232489 0.2237872 1.0000000 0.5415657 0.20990919
## PriorDefault 0.6040567 -0.2339515 0.5415657 1.0000000 0.66666667
## Employed -0.1842478 -0.6073564 0.2099092 0.6666667 1.00000000
## CreditScore 0.7599058 0.1869829 0.8971175 0.7604691 0.19011728
## DriversLicense NA NA NA NA NA
## ZipCode -0.5887359 -0.6994434 -0.7255806 -0.5016809 0.01967376
## Income 0.3452272 -0.1158264 -0.1009278 -0.3152049 -0.64609976
## Approved NA NA NA NA NA
## CreditScore DriversLicense ZipCode Income Approved
## Age 0.75990576 NA -0.58873594 0.34522724 NA
## Debt 0.18698295 NA -0.69944336 -0.11582643 NA
## YearsEmployed 0.89711754 NA -0.72558057 -0.10092775 NA
## PriorDefault 0.76046910 NA -0.50168087 -0.31520488 NA
## Employed 0.19011728 NA 0.01967376 -0.64609976 NA
## CreditScore 1.00000000 NA -0.77424657 0.01028446 NA
## DriversLicense NA 1 NA NA NA
## ZipCode -0.77424657 NA 1.00000000 0.33473701 NA
## Income 0.01028446 NA 0.33473701 1.00000000 NA
## Approved NA NA NA NA 1