# Import dataset CKD
CKD <- read.table(
file.choose(),
header = TRUE,
sep = "\t",
dec = ",",
stringsAsFactors = FALSE
)
# Melihat data
CKD
## Age_of_the_patient Blood_pressure_.mm.Hg. Red_blood_cells_in_urine
## 1 54 167 normal
## 2 42 127 normal
## 3 38 148 abnormal
## 4 67 174 normal
## 5 67 100 normal
## 6 42 138 abnormal
## 7 84 104 normal
## 8 49 113 normal
## 9 65 126 abnormal
## 10 25 174 abnormal
## 11 89 113 abnormal
## 12 90 131 normal
## 13 27 110 abnormal
## 14 48 138 normal
## 15 55 90 abnormal
## 16 51 116 abnormal
## 17 60 95 abnormal
## 18 31 122 abnormal
## 19 90 130 normal
## 20 76 179 normal
## 21 40 91 normal
## 22 65 106 normal
## 23 38 121 normal
## 24 90 80 abnormal
## 25 25 119 normal
## 26 74 127 normal
## 27 80 110 abnormal
## 28 35 82 abnormal
## 29 73 173 abnormal
## 30 54 150 normal
## 31 41 174 abnormal
## 32 65 82 normal
## 33 83 158 abnormal
## 34 75 122 normal
## 35 56 178 normal
## 36 59 122 abnormal
## 37 89 135 abnormal
## 38 52 177 normal
## 39 67 141 abnormal
## 40 54 175 normal
## 41 37 139 normal
## 42 37 149 normal
## 43 53 121 abnormal
## 44 68 159 abnormal
## 45 37 174 normal
## 46 68 130 abnormal
## 47 27 81 abnormal
## 48 89 128 abnormal
## 49 38 170 normal
## 50 26 126 abnormal
## Bacteria_in_urine Blood_urea_.mg.dl. Serum_creatinine_.mg.dl.
## 1 not_present 169.101369 7.55
## 2 present 183.223479 13.37
## 3 not_present 193.141665 9.49
## 4 not_present 197.188600 3.01
## 5 present 27.308196 8.73
## 6 present 169.656648 6.92
## 7 present 198.725767 10.15
## 8 present 108.353368 5.84
## 9 present 174.729867 10.77
## 10 not_present 84.970714 8.35
## 11 not_present 35.942011 5.98
## 12 not_present 81.313035 2.12
## 13 not_present 83.172007 12.32
## 14 not_present 138.709486 1.37
## 15 not_present 58.010296 11.01
## 16 present 31.452576 10.33
## 17 not_present 40.847352 5.27
## 18 present 143.249229 10.36
## 19 not_present 51.308044 12.48
## 20 not_present 46.533183 12.52
## 21 present 189.114948 8.09
## 22 not_present 88.949851 5.06
## 23 not_present 153.430176 0.80
## 24 present 35.636823 13.71
## 25 not_present 110.202151 11.91
## 26 present 46.072322 4.85
## 27 present 61.629109 7.12
## 28 present 186.082297 10.27
## 29 not_present 16.864388 10.19
## 30 present 148.142526 4.90
## 31 not_present 141.177815 9.64
## 32 present 31.784104 11.39
## 33 present 87.966135 2.59
## 34 not_present 89.935422 0.97
## 35 present 105.299708 4.32
## 36 present 130.689826 2.60
## 37 present 49.525194 5.81
## 38 not_present 40.788617 6.41
## 39 present 89.437635 12.20
## 40 not_present 110.888999 0.76
## 41 present 36.337927 10.18
## 42 not_present 24.931325 1.33
## 43 not_present 182.286759 1.75
## 44 not_present 110.198402 11.77
## 45 not_present 149.083831 14.58
## 46 present 132.146330 6.07
## 47 present 143.654183 7.72
## 48 not_present 26.139680 8.31
## 49 present 8.685189 9.18
## 50 not_present 119.298778 8.25
## Hemoglobin_level_.gms. Hypertension_.yes.no. Diabetes_mellitus_.yes.no.
## 1 11.8 yes yes
## 2 8.2 no yes
## 3 10.1 no no
## 4 16.1 no no
## 5 7.7 no no
## 6 8.8 yes no
## 7 7.2 yes no
## 8 12.6 no yes
## 9 7.5 yes no
## 10 15.6 no no
## 11 15.6 no yes
## 12 9.6 no no
## 13 11.6 no no
## 14 9.2 no no
## 15 6.8 no yes
## 16 11.8 no yes
## 17 16.7 no no
## 18 17.5 no no
## 19 10.3 no no
## 20 8.0 yes yes
## 21 11.0 yes no
## 22 12.8 no yes
## 23 16.9 yes no
## 24 6.8 no yes
## 25 14.0 no no
## 26 10.5 no yes
## 27 14.1 yes no
## 28 6.0 no yes
## 29 13.5 yes no
## 30 16.9 no no
## 31 16.4 no yes
## 32 13.8 yes no
## 33 9.9 no no
## 34 8.7 no no
## 35 16.6 yes yes
## 36 17.3 no yes
## 37 9.5 no yes
## 38 11.9 yes yes
## 39 12.8 no yes
## 40 16.8 yes yes
## 41 9.8 no yes
## 42 8.2 no yes
## 43 13.1 yes yes
## 44 11.1 no yes
## 45 13.9 yes no
## 46 10.3 yes no
## 47 13.4 no no
## 48 13.3 no yes
## 49 16.3 yes no
## 50 16.3 yes no
## Coronary_artery_disease_.yes.no. Anemia_.yes.no.
## 1 no no
## 2 no yes
## 3 yes no
## 4 no yes
## 5 yes yes
## 6 no yes
## 7 no yes
## 8 yes yes
## 9 yes yes
## 10 yes yes
## 11 no no
## 12 yes yes
## 13 no yes
## 14 no yes
## 15 no yes
## 16 no yes
## 17 yes yes
## 18 yes no
## 19 no yes
## 20 yes yes
## 21 no yes
## 22 yes no
## 23 yes yes
## 24 yes no
## 25 no yes
## 26 no yes
## 27 yes no
## 28 no yes
## 29 no yes
## 30 yes yes
## 31 yes no
## 32 no yes
## 33 no yes
## 34 no yes
## 35 yes yes
## 36 yes yes
## 37 no no
## 38 no yes
## 39 no yes
## 40 no no
## 41 yes no
## 42 no no
## 43 no no
## 44 yes no
## 45 yes yes
## 46 no no
## 47 yes no
## 48 yes yes
## 49 no no
## 50 yes yes
## Urine_protein.to.creatinine_ratio Urine_output_.ml.day. Cholesterol_level
## 1 2.51 1397 152
## 2 4.27 1632 242
## 3 1.56 889 103
## 4 1.23 893 149
## 5 2.61 1212 182
## 6 2.42 2720 260
## 7 1.67 2859 134
## 8 0.41 2076 229
## 9 2.80 862 276
## 10 0.46 663 206
## 11 2.53 461 113
## 12 2.78 1615 166
## 13 2.16 2444 158
## 14 2.67 1323 165
## 15 4.49 1682 117
## 16 3.73 1100 290
## 17 4.33 864 135
## 18 0.54 2058 256
## 19 1.05 948 292
## 20 3.41 308 205
## 21 0.46 2333 100
## 22 0.94 2899 246
## 23 1.23 1748 256
## 24 0.24 2650 110
## 25 3.65 841 228
## 26 3.63 1072 222
## 27 2.10 1845 135
## 28 1.80 2865 257
## 29 0.75 1733 296
## 30 3.18 2933 287
## 31 2.79 2118 159
## 32 2.04 2300 259
## 33 1.35 2911 298
## 34 4.36 2269 107
## 35 3.42 997 294
## 36 3.31 1922 255
## 37 3.78 1916 136
## 38 2.34 2661 267
## 39 2.71 2603 266
## 40 0.58 787 253
## 41 3.10 852 225
## 42 4.21 547 114
## 43 1.71 2766 151
## 44 0.35 1580 113
## 45 2.10 2873 260
## 46 2.31 2321 257
## 47 0.64 926 161
## 48 2.10 852 102
## 49 2.60 2684 104
## 50 3.61 2166 228
## Family_history_of_chronic_kidney_disease Smoking_status
## 1 no yes
## 2 yes no
## 3 no no
## 4 no yes
## 5 yes yes
## 6 no yes
## 7 yes no
## 8 no yes
## 9 no no
## 10 no no
## 11 no no
## 12 no no
## 13 no no
## 14 no yes
## 15 no no
## 16 no no
## 17 no yes
## 18 yes yes
## 19 yes no
## 20 yes yes
## 21 no no
## 22 no yes
## 23 yes no
## 24 no yes
## 25 no yes
## 26 yes yes
## 27 no no
## 28 no yes
## 29 yes no
## 30 no no
## 31 yes yes
## 32 no no
## 33 yes yes
## 34 yes no
## 35 yes no
## 36 no yes
## 37 yes no
## 38 no no
## 39 yes yes
## 40 no no
## 41 no yes
## 42 no yes
## 43 yes no
## 44 no no
## 45 no yes
## 46 no yes
## 47 no yes
## 48 yes yes
## 49 no no
## 50 no no
## Body_Mass_Index_.BMI. Physical_activity_level CKD_Status
## 1 25.3 low Yes
## 2 20.6 moderate Yes
## 3 38.4 high No
## 4 17.6 high Yes
## 5 37.2 moderate No
## 6 23.5 moderate No
## 7 23.0 moderate Yes
## 8 30.6 low Yes
## 9 16.8 high No
## 10 28.5 low Yes
## 11 34.7 low Yes
## 12 27.4 low No
## 13 23.2 low Yes
## 14 23.3 low No
## 15 32.7 moderate No
## 16 16.6 low No
## 17 19.7 moderate No
## 18 32.4 high No
## 19 34.7 low No
## 20 38.1 moderate No
## 21 32.0 high No
## 22 38.1 moderate No
## 23 19.8 moderate Yes
## 24 38.9 high Yes
## 25 18.1 high No
## 26 31.7 high No
## 27 18.5 low No
## 28 24.9 moderate No
## 29 27.0 high Yes
## 30 18.6 low No
## 31 32.0 moderate Yes
## 32 18.0 moderate Yes
## 33 23.1 moderate No
## 34 31.5 low No
## 35 15.2 high Yes
## 36 37.2 high No
## 37 29.6 low No
## 38 16.6 high No
## 39 18.0 moderate No
## 40 16.7 moderate No
## 41 29.0 low Yes
## 42 16.4 high No
## 43 17.5 high No
## 44 37.9 low Yes
## 45 30.4 moderate Yes
## 46 20.5 high No
## 47 21.0 moderate No
## 48 31.9 low Yes
## 49 22.9 high No
## 50 39.0 high Yes
# Ukuran dataset
dim(CKD)
## [1] 50 19
# Jumlah baris
nrow(CKD)
## [1] 50
# Jumlah kolom
ncol(CKD)
## [1] 19
# Nama variabel
names(CKD)
## [1] "Age_of_the_patient"
## [2] "Blood_pressure_.mm.Hg."
## [3] "Red_blood_cells_in_urine"
## [4] "Bacteria_in_urine"
## [5] "Blood_urea_.mg.dl."
## [6] "Serum_creatinine_.mg.dl."
## [7] "Hemoglobin_level_.gms."
## [8] "Hypertension_.yes.no."
## [9] "Diabetes_mellitus_.yes.no."
## [10] "Coronary_artery_disease_.yes.no."
## [11] "Anemia_.yes.no."
## [12] "Urine_protein.to.creatinine_ratio"
## [13] "Urine_output_.ml.day."
## [14] "Cholesterol_level"
## [15] "Family_history_of_chronic_kidney_disease"
## [16] "Smoking_status"
## [17] "Body_Mass_Index_.BMI."
## [18] "Physical_activity_level"
## [19] "CKD_Status"
# Struktur data
str(CKD)
## 'data.frame': 50 obs. of 19 variables:
## $ Age_of_the_patient : int 54 42 38 67 67 42 84 49 65 25 ...
## $ Blood_pressure_.mm.Hg. : int 167 127 148 174 100 138 104 113 126 174 ...
## $ Red_blood_cells_in_urine : chr "normal" "normal" "abnormal" "normal" ...
## $ Bacteria_in_urine : chr "not_present" "present" "not_present" "not_present" ...
## $ Blood_urea_.mg.dl. : num 169.1 183.2 193.1 197.2 27.3 ...
## $ Serum_creatinine_.mg.dl. : num 7.55 13.37 9.49 3.01 8.73 ...
## $ Hemoglobin_level_.gms. : num 11.8 8.2 10.1 16.1 7.7 8.8 7.2 12.6 7.5 15.6 ...
## $ Hypertension_.yes.no. : chr "yes" "no" "no" "no" ...
## $ Diabetes_mellitus_.yes.no. : chr "yes" "yes" "no" "no" ...
## $ Coronary_artery_disease_.yes.no. : chr "no" "no" "yes" "no" ...
## $ Anemia_.yes.no. : chr "no" "yes" "no" "yes" ...
## $ Urine_protein.to.creatinine_ratio : num 2.51 4.27 1.56 1.23 2.61 2.42 1.67 0.41 2.8 0.46 ...
## $ Urine_output_.ml.day. : int 1397 1632 889 893 1212 2720 2859 2076 862 663 ...
## $ Cholesterol_level : int 152 242 103 149 182 260 134 229 276 206 ...
## $ Family_history_of_chronic_kidney_disease: chr "no" "yes" "no" "no" ...
## $ Smoking_status : chr "yes" "no" "no" "yes" ...
## $ Body_Mass_Index_.BMI. : num 25.3 20.6 38.4 17.6 37.2 23.5 23 30.6 16.8 28.5 ...
## $ Physical_activity_level : chr "low" "moderate" "high" "high" ...
## $ CKD_Status : chr "Yes" "Yes" "No" "Yes" ...
# Ringkasan data
summary(CKD)
## Age_of_the_patient Blood_pressure_.mm.Hg. Red_blood_cells_in_urine
## Min. :25.00 Min. : 80.0 Length:50
## 1st Qu.:38.50 1st Qu.:113.0 Class :character
## Median :54.50 Median :127.5 Mode :character
## Mean :56.90 Mean :131.9
## 3rd Qu.:71.75 3rd Qu.:156.0
## Max. :90.00 Max. :179.0
## Bacteria_in_urine Blood_urea_.mg.dl. Serum_creatinine_.mg.dl.
## Length:50 Min. : 8.685 Min. : 0.760
## Class :character 1st Qu.: 46.188 1st Qu.: 4.940
## Mode :character Median : 97.618 Median : 8.170
## Mean :101.266 Mean : 7.613
## 3rd Qu.:147.020 3rd Qu.:10.352
## Max. :198.726 Max. :14.580
## Hemoglobin_level_.gms. Hypertension_.yes.no. Diabetes_mellitus_.yes.no.
## Min. : 6.000 Length:50 Length:50
## 1st Qu.: 9.525 Class :character Class :character
## Median :11.850 Mode :character Mode :character
## Mean :12.092
## 3rd Qu.:15.225
## Max. :17.500
## Coronary_artery_disease_.yes.no. Anemia_.yes.no.
## Length:50 Length:50
## Class :character Class :character
## Mode :character Mode :character
##
##
##
## Urine_protein.to.creatinine_ratio Urine_output_.ml.day. Cholesterol_level
## Min. :0.240 Min. : 308.0 Min. :100.0
## 1st Qu.:1.260 1st Qu.: 931.5 1st Qu.:135.2
## Median :2.380 Median :1740.5 Median :214.0
## Mean :2.300 Mean :1739.5 Mean :199.5
## 3rd Qu.:3.277 3rd Qu.:2416.2 3rd Qu.:257.0
## Max. :4.490 Max. :2933.0 Max. :298.0
## Family_history_of_chronic_kidney_disease Smoking_status
## Length:50 Length:50
## Class :character Class :character
## Mode :character Mode :character
##
##
##
## Body_Mass_Index_.BMI. Physical_activity_level CKD_Status
## Min. :15.20 Length:50 Length:50
## 1st Qu.:18.88 Class :character Class :character
## Median :25.10 Mode :character Mode :character
## Mean :26.33
## 3rd Qu.:32.00
## Max. :39.00
#Mengubah Variabel Kategorik Menjadi Factor
names(CKD) <- make.names(names(CKD))
names(CKD)
## [1] "Age_of_the_patient"
## [2] "Blood_pressure_.mm.Hg."
## [3] "Red_blood_cells_in_urine"
## [4] "Bacteria_in_urine"
## [5] "Blood_urea_.mg.dl."
## [6] "Serum_creatinine_.mg.dl."
## [7] "Hemoglobin_level_.gms."
## [8] "Hypertension_.yes.no."
## [9] "Diabetes_mellitus_.yes.no."
## [10] "Coronary_artery_disease_.yes.no."
## [11] "Anemia_.yes.no."
## [12] "Urine_protein.to.creatinine_ratio"
## [13] "Urine_output_.ml.day."
## [14] "Cholesterol_level"
## [15] "Family_history_of_chronic_kidney_disease"
## [16] "Smoking_status"
## [17] "Body_Mass_Index_.BMI."
## [18] "Physical_activity_level"
## [19] "CKD_Status"
CKD$Red_blood_cells_in_urine <- factor(CKD$Red_blood_cells_in_urine)
CKD$Bacteria_in_urine <- factor(CKD$Bacteria_in_urine)
CKD$Hypertension_.yes.no. <- factor(CKD$Hypertension_.yes.no.)
kategori <- c(
"Red_blood_cells_in_urine",
"Bacteria_in_urine",
"Hypertension_.yes.no.",
"Diabetes_mellitus_.yes.no.",
"Coronary_artery_disease_.yes.no.",
"Anemia_.yes.no.",
"Family_history_of_chronic_kidney_disease",
"Smoking_status",
"Physical_activity_level",
"CKD_Status"
)
CKD[kategori] <- lapply(CKD[kategori], factor)
library(ggplot2)
#Distribusi Status CKD
ggplot(CKD, aes(x = CKD_Status)) +
geom_bar() +
labs(
title = "Distribusi Status Chronic Kidney Disease",
x = "Status CKD",
y = "Jumlah Pasien"
) +
theme_minimal()
#Histogram Usia
ggplot(CKD, aes(x = Age_of_the_patient)) +
geom_histogram(
bins = 10,
fill = "steelblue",
color = "black"
) +
labs(
title = "Distribusi Usia Pasien",
x = "Usia",
y = "Frekuensi"
) +
theme_minimal()
#Usia berdasarkan Status CKD
ggplot(CKD, aes(x = CKD_Status, y = Age_of_the_patient)) +
geom_boxplot() +
labs(
title = "Distribusi Usia Berdasarkan Status CKD",
x = "Status CKD",
y = "Usia"
) +
theme_minimal()
#Serum Creatinine
ggplot(CKD, aes(x = Serum_creatinine_.mg.dl.)) +
geom_histogram(
bins = 10,
fill = "orange",
color = "black"
) +
labs(
title = "Distribusi Serum Creatinine",
x = "Serum Creatinine (mg/dl)",
y = "Frekuensi"
) +
theme_minimal()
#Blood Urea
ggplot(CKD, aes(x = Blood_urea_.mg.dl.)) +
geom_histogram(
bins = 10,
fill = "skyblue",
color = "black"
) +
labs(
title = "Distribusi Blood Urea",
x = "Blood Urea (mg/dl)",
y = "Frekuensi"
) +
theme_minimal()
#BMI Berdasarkan Status CKD
ggplot(CKD, aes(x = CKD_Status, y = Body_Mass_Index_.BMI.)) +
geom_boxplot() +
labs(
title = "BMI Berdasarkan Status CKD",
x = "Status CKD",
y = "BMI"
) +
theme_minimal()
#Hubungan Blood Urea dan Serum Creatinine
cor(
CKD$Blood_urea_.mg.dl.,
CKD$Serum_creatinine_.mg.dl.,
method = "pearson"
)
## [1] -0.08488131
ggplot(
CKD,
aes(
x = Blood_urea_.mg.dl.,
y = Serum_creatinine_.mg.dl.,
color = CKD_Status
)
) +
geom_point(size = 3) +
labs(
title = "Hubungan Blood Urea dan Serum Creatinine",
x = "Blood Urea (mg/dl)",
y = "Serum Creatinine (mg/dl)",
color = "Status CKD"
) +
theme_minimal()
#Faktor Kategorik
#Hipertensi
ggplot(CKD, aes(x = Hypertension_.yes.no.)) +
geom_bar() +
labs(
title = "Distribusi Hipertensi",
x = "Hipertensi",
y = "Jumlah"
) +
theme_minimal()
#Diabetes
ggplot(CKD, aes(x = Diabetes_mellitus_.yes.no.)) +
geom_bar() +
labs(
title = "Distribusi Diabetes Mellitus",
x = "Diabetes Mellitus",
y = "Jumlah"
) +
theme_minimal()
#Anemia
ggplot(CKD, aes(x = Anemia_.yes.no.)) +
geom_bar() +
labs(
title = "Distribusi Anemia",
x = "Anemia",
y = "Jumlah"
) +
theme_minimal()
#Analisis Statistik Deskriptif
summary(
CKD[, c(
"Age_of_the_patient",
"Blood_pressure_.mm.Hg.",
"Blood_urea_.mg.dl.",
"Serum_creatinine_.mg.dl.",
"Hemoglobin_level_.gms.",
"Urine_protein.to.creatinine_ratio",
"Urine_output_.ml.day.",
"Cholesterol_level",
"Body_Mass_Index_.BMI."
)]
)
## Age_of_the_patient Blood_pressure_.mm.Hg. Blood_urea_.mg.dl.
## Min. :25.00 Min. : 80.0 Min. : 8.685
## 1st Qu.:38.50 1st Qu.:113.0 1st Qu.: 46.188
## Median :54.50 Median :127.5 Median : 97.618
## Mean :56.90 Mean :131.9 Mean :101.266
## 3rd Qu.:71.75 3rd Qu.:156.0 3rd Qu.:147.020
## Max. :90.00 Max. :179.0 Max. :198.726
## Serum_creatinine_.mg.dl. Hemoglobin_level_.gms.
## Min. : 0.760 Min. : 6.000
## 1st Qu.: 4.940 1st Qu.: 9.525
## Median : 8.170 Median :11.850
## Mean : 7.613 Mean :12.092
## 3rd Qu.:10.352 3rd Qu.:15.225
## Max. :14.580 Max. :17.500
## Urine_protein.to.creatinine_ratio Urine_output_.ml.day. Cholesterol_level
## Min. :0.240 Min. : 308.0 Min. :100.0
## 1st Qu.:1.260 1st Qu.: 931.5 1st Qu.:135.2
## Median :2.380 Median :1740.5 Median :214.0
## Mean :2.300 Mean :1739.5 Mean :199.5
## 3rd Qu.:3.277 3rd Qu.:2416.2 3rd Qu.:257.0
## Max. :4.490 Max. :2933.0 Max. :298.0
## Body_Mass_Index_.BMI.
## Min. :15.20
## 1st Qu.:18.88
## Median :25.10
## Mean :26.33
## 3rd Qu.:32.00
## Max. :39.00
#Statistik Deskriptif Variabel Kategorik
table(CKD$CKD_Status)
##
## No Yes
## 31 19
prop.table(table(CKD$CKD_Status)) * 100
##
## No Yes
## 62 38
lapply(CKD[kategori], table)
## $Red_blood_cells_in_urine
##
## abnormal normal
## 25 25
##
## $Bacteria_in_urine
##
## not_present present
## 26 24
##
## $Hypertension_.yes.no.
##
## no yes
## 32 18
##
## $Diabetes_mellitus_.yes.no.
##
## no yes
## 27 23
##
## $Coronary_artery_disease_.yes.no.
##
## no yes
## 27 23
##
## $Anemia_.yes.no.
##
## no yes
## 17 33
##
## $Family_history_of_chronic_kidney_disease
##
## no yes
## 33 17
##
## $Smoking_status
##
## no yes
## 26 24
##
## $Physical_activity_level
##
## high low moderate
## 17 16 17
##
## $CKD_Status
##
## No Yes
## 31 19
#Menentukan DIstribusi Data
ggplot(CKD, aes(x = Age_of_the_patient)) +
geom_histogram(bins = 10) +
theme_minimal()
ggplot(CKD, aes(sample = Age_of_the_patient)) +
stat_qq() +
stat_qq_line() +
theme_minimal()
#Uji Normalitas Shapiro-Wilk
numerik <- CKD[, sapply(CKD, is.numeric)]
hasil_normalitas <- data.frame(
Variabel = names(numerik),
P_Value = sapply(numerik, function(x) {
shapiro.test(x)$p.value
})
)
hasil_normalitas
## Variabel
## Age_of_the_patient Age_of_the_patient
## Blood_pressure_.mm.Hg. Blood_pressure_.mm.Hg.
## Blood_urea_.mg.dl. Blood_urea_.mg.dl.
## Serum_creatinine_.mg.dl. Serum_creatinine_.mg.dl.
## Hemoglobin_level_.gms. Hemoglobin_level_.gms.
## Urine_protein.to.creatinine_ratio Urine_protein.to.creatinine_ratio
## Urine_output_.ml.day. Urine_output_.ml.day.
## Cholesterol_level Cholesterol_level
## Body_Mass_Index_.BMI. Body_Mass_Index_.BMI.
## P_Value
## Age_of_the_patient 0.0271433612
## Blood_pressure_.mm.Hg. 0.0242657877
## Blood_urea_.mg.dl. 0.0088667748
## Serum_creatinine_.mg.dl. 0.0676612273
## Hemoglobin_level_.gms. 0.0292847580
## Urine_protein.to.creatinine_ratio 0.0777071587
## Urine_output_.ml.day. 0.0052555589
## Cholesterol_level 0.0005181311
## Body_Mass_Index_.BMI. 0.0021065104
#Melihat Skewness
library(moments)
## Warning: package 'moments' was built under R version 4.5.2
sapply(numerik, skewness)
## Age_of_the_patient Blood_pressure_.mm.Hg.
## 0.12935346 0.05185305
## Blood_urea_.mg.dl. Serum_creatinine_.mg.dl.
## 0.13535807 -0.23633035
## Hemoglobin_level_.gms. Urine_protein.to.creatinine_ratio
## 0.02266149 -0.02312773
## Urine_output_.ml.day. Cholesterol_level
## -0.01194403 -0.09909627
## Body_Mass_Index_.BMI.
## 0.21327223
#Kurtosis
kurtosis(CKD$Age_of_the_patient)
## [1] 1.911541
#Matriks Korelasi
variabel_numerik <- CKD[, c(
"Age_of_the_patient",
"Blood_pressure_.mm.Hg.",
"Blood_urea_.mg.dl.",
"Serum_creatinine_.mg.dl.",
"Hemoglobin_level_.gms.",
"Urine_protein.to.creatinine_ratio",
"Urine_output_.ml.day.",
"Cholesterol_level",
"Body_Mass_Index_.BMI."
)]
# Menghitung korelasi Pearson
matriks_korelasi <- cor(variabel_numerik, method = "pearson")
# Menampilkan matriks korelasi
round(matriks_korelasi, 3)
## Age_of_the_patient Blood_pressure_.mm.Hg.
## Age_of_the_patient 1.000 -0.056
## Blood_pressure_.mm.Hg. -0.056 1.000
## Blood_urea_.mg.dl. -0.354 0.005
## Serum_creatinine_.mg.dl. -0.110 -0.129
## Hemoglobin_level_.gms. -0.265 0.286
## Urine_protein.to.creatinine_ratio -0.002 0.007
## Urine_output_.ml.day. -0.026 -0.163
## Cholesterol_level -0.122 0.202
## Body_Mass_Index_.BMI. 0.183 -0.120
## Blood_urea_.mg.dl. Serum_creatinine_.mg.dl.
## Age_of_the_patient -0.354 -0.110
## Blood_pressure_.mm.Hg. 0.005 -0.129
## Blood_urea_.mg.dl. 1.000 -0.085
## Serum_creatinine_.mg.dl. -0.085 1.000
## Hemoglobin_level_.gms. 0.012 -0.243
## Urine_protein.to.creatinine_ratio -0.221 -0.075
## Urine_output_.ml.day. 0.242 0.059
## Cholesterol_level 0.065 0.064
## Body_Mass_Index_.BMI. -0.136 0.252
## Hemoglobin_level_.gms.
## Age_of_the_patient -0.265
## Blood_pressure_.mm.Hg. 0.286
## Blood_urea_.mg.dl. 0.012
## Serum_creatinine_.mg.dl. -0.243
## Hemoglobin_level_.gms. 1.000
## Urine_protein.to.creatinine_ratio -0.154
## Urine_output_.ml.day. -0.056
## Cholesterol_level 0.171
## Body_Mass_Index_.BMI. -0.163
## Urine_protein.to.creatinine_ratio
## Age_of_the_patient -0.002
## Blood_pressure_.mm.Hg. 0.007
## Blood_urea_.mg.dl. -0.221
## Serum_creatinine_.mg.dl. -0.075
## Hemoglobin_level_.gms. -0.154
## Urine_protein.to.creatinine_ratio 1.000
## Urine_output_.ml.day. -0.182
## Cholesterol_level -0.044
## Body_Mass_Index_.BMI. -0.161
## Urine_output_.ml.day. Cholesterol_level
## Age_of_the_patient -0.026 -0.122
## Blood_pressure_.mm.Hg. -0.163 0.202
## Blood_urea_.mg.dl. 0.242 0.065
## Serum_creatinine_.mg.dl. 0.059 0.064
## Hemoglobin_level_.gms. -0.056 0.171
## Urine_protein.to.creatinine_ratio -0.182 -0.044
## Urine_output_.ml.day. 1.000 0.156
## Cholesterol_level 0.156 1.000
## Body_Mass_Index_.BMI. -0.021 -0.283
## Body_Mass_Index_.BMI.
## Age_of_the_patient 0.183
## Blood_pressure_.mm.Hg. -0.120
## Blood_urea_.mg.dl. -0.136
## Serum_creatinine_.mg.dl. 0.252
## Hemoglobin_level_.gms. -0.163
## Urine_protein.to.creatinine_ratio -0.161
## Urine_output_.ml.day. -0.021
## Cholesterol_level -0.283
## Body_Mass_Index_.BMI. 1.000
library(ggplot2)
# Mengubah matriks korelasi menjadi data frame
korelasi_long <- as.data.frame(as.table(matriks_korelasi))
# Heatmap
ggplot(korelasi_long, aes(Var1, Var2, fill = Freq)) +
geom_tile() +
geom_text(aes(label = round(Freq, 2)), size = 3) +
scale_fill_gradient2(
low = "blue",
mid = "white",
high = "red",
midpoint = 0,
limits = c(-1, 1)
) +
labs(
title = "Heatmap Matriks Korelasi Variabel Numerik",
x = "",
y = "",
fill = "Korelasi"
) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 45, hjust = 1)
)
#Tabel Kontingensi
# Sel darah merah dengan CKD
table(CKD$Red_blood_cells_in_urine, CKD$CKD_Status)
##
## No Yes
## abnormal 16 9
## normal 15 10
# Bakteri urine dengan CKD
table(CKD$Bacteria_in_urine, CKD$CKD_Status)
##
## No Yes
## not_present 14 12
## present 17 7
# Hipertensi dengan CKD
table(CKD$Hypertension_.yes.no., CKD$CKD_Status)
##
## No Yes
## no 21 11
## yes 10 8
# Diabetes dengan CKD
table(CKD$Diabetes_mellitus_.yes.no., CKD$CKD_Status)
##
## No Yes
## no 18 9
## yes 13 10
# Penyakit jantung koroner dengan CKD
table(CKD$Coronary_artery_disease_.yes.no., CKD$CKD_Status)
##
## No Yes
## no 19 8
## yes 12 11
# Anemia dengan CKD
table(CKD$Anemia_.yes.no., CKD$CKD_Status)
##
## No Yes
## no 11 6
## yes 20 13
# Riwayat keluarga CKD dengan CKD
table(CKD$Family_history_of_chronic_kidney_disease, CKD$CKD_Status)
##
## No Yes
## no 21 12
## yes 10 7
# Merokok dengan CKD
table(CKD$Smoking_status, CKD$CKD_Status)
##
## No Yes
## no 15 11
## yes 16 8
# Aktivitas fisik dengan CKD
table(CKD$Physical_activity_level, CKD$CKD_Status)
##
## No Yes
## high 12 5
## low 8 8
## moderate 11 6
for (x in kategori) {
cat("\n==============================\n")
cat(x, "\n")
cat("==============================\n")
tab <- table(CKD[[x]], CKD$CKD_Status)
print(tab)
print(chisq.test(tab))
}
##
## ==============================
## Red_blood_cells_in_urine
## ==============================
##
## No Yes
## abnormal 16 9
## normal 15 10
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0, df = 1, p-value = 1
##
##
## ==============================
## Bacteria_in_urine
## ==============================
##
## No Yes
## not_present 14 12
## present 17 7
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0.89257, df = 1, p-value = 0.3448
##
##
## ==============================
## Hypertension_.yes.no.
## ==============================
##
## No Yes
## no 21 11
## yes 10 8
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0.16049, df = 1, p-value = 0.6887
##
##
## ==============================
## Diabetes_mellitus_.yes.no.
## ==============================
##
## No Yes
## no 18 9
## yes 13 10
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0.19739, df = 1, p-value = 0.6568
##
##
## ==============================
## Coronary_artery_disease_.yes.no.
## ==============================
##
## No Yes
## no 19 8
## yes 12 11
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 1.0586, df = 1, p-value = 0.3035
##
##
## ==============================
## Anemia_.yes.no.
## ==============================
##
## No Yes
## no 11 6
## yes 20 13
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 1.7631e-31, df = 1, p-value = 1
##
##
## ==============================
## Family_history_of_chronic_kidney_disease
## ==============================
##
## No Yes
## no 21 12
## yes 10 7
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0.00060527, df = 1, p-value = 0.9804
##
##
## ==============================
## Smoking_status
## ==============================
##
## No Yes
## no 15 11
## yes 16 8
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 0.13074, df = 1, p-value = 0.7177
##
##
## ==============================
## Physical_activity_level
## ==============================
##
## No Yes
## high 12 5
## low 8 8
## moderate 11 6
##
## Pearson's Chi-squared test
##
## data: tab
## X-squared = 1.563, df = 2, p-value = 0.4577
##
##
## ==============================
## CKD_Status
## ==============================
##
## No Yes
## No 31 0
## Yes 0 19
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab
## X-squared = 45.846, df = 1, p-value = 1.28e-11