Việc 1
Việc 2
options(repos = c(CRAN = "https://cran.rstudio.com/"))
install.packages(c("lessR", "table1", "compareGroups", "simpleboot", "boot", "GGally", "gapminder", "ggfortify", "BMA", "ggplot2", "gridExtra"), dependencies = T)
## Installing packages into 'C:/Users/OS/AppData/Local/R/win-library/4.5'
## (as 'lib' is unspecified)
## package 'lessR' successfully unpacked and MD5 sums checked
## package 'table1' successfully unpacked and MD5 sums checked
## package 'compareGroups' successfully unpacked and MD5 sums checked
## package 'simpleboot' successfully unpacked and MD5 sums checked
## package 'boot' successfully unpacked and MD5 sums checked
## package 'GGally' successfully unpacked and MD5 sums checked
## package 'gapminder' successfully unpacked and MD5 sums checked
## package 'ggfortify' successfully unpacked and MD5 sums checked
## package 'BMA' successfully unpacked and MD5 sums checked
## package 'ggplot2' successfully unpacked and MD5 sums checked
## package 'gridExtra' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\OS\AppData\Local\Temp\Rtmpu4sGCP\downloaded_packages
Việc 3: Đọc dữ liệu R
ob = read.csv("C:\\Users\\OS\\Downloads\\tap-huan-phan-tich-du-lieu\\Obesity data.csv")
Việc 4: Thông tin về dữ liệu ob
4.1. Có bao nhiêu biến số quan sát
dim(ob)
## [1] 1217 13
4.2. Liệt kê 6 quan sát đầu tiên
head(ob)
## id gender height weight bmi age WBBMC wbbmd fat lean pcfat hypertension
## 1 1 F 150 49 21.8 53 1312 0.88 17802 28600 37.3 0
## 2 2 M 165 52 19.1 65 1309 0.84 8381 40229 16.8 1
## 3 3 F 157 57 23.1 64 1230 0.84 19221 36057 34.0 1
## 4 4 F 156 53 21.8 56 1171 0.80 17472 33094 33.8 1
## 5 5 M 160 51 19.9 54 1681 0.98 7336 40621 14.8 0
## 6 6 F 153 47 20.1 52 1358 0.91 14904 30068 32.2 1
## diabetes
## 1 1
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
4.3. Liệt kê 6 quan sát cuối cùng
tail(ob)
## id gender height weight bmi age WBBMC wbbmd fat lean pcfat
## 1212 1222 F 153 50 21.4 59 1309 0.87 18328 29147 37.6
## 1213 1223 F 150 44 19.6 44 1474 0.95 12906 28534 30.1
## 1214 1224 F 148 51 23.3 58 1522 0.97 14938 33931 29.6
## 1215 1225 F 149 50 22.5 57 1409 0.93 16777 30598 34.4
## 1216 1226 F 144 49 23.6 67 1266 0.90 20094 27272 41.3
## 1217 1227 F 141 45 22.6 58 1228 0.91 14567 28111 33.2
## hypertension diabetes
## 1212 1 0
## 1213 0 1
## 1214 0 0
## 1215 1 0
## 1216 1 0
## 1217 0 0
4.4. Tóm tắt dữ liệu bằng hàm summary
summary(ob)
## id gender height weight
## Min. : 1.0 Length:1217 Min. :136.0 Min. :34.00
## 1st Qu.: 309.0 Class :character 1st Qu.:151.0 1st Qu.:49.00
## Median : 615.0 Mode :character Median :155.0 Median :54.00
## Mean : 614.5 Mean :156.7 Mean :55.14
## 3rd Qu.: 921.0 3rd Qu.:162.0 3rd Qu.:61.00
## Max. :1227.0 Max. :185.0 Max. :95.00
## bmi age WBBMC wbbmd fat
## Min. :14.5 Min. :13.00 Min. : 695 Min. :0.650 Min. : 4277
## 1st Qu.:20.2 1st Qu.:35.00 1st Qu.:1481 1st Qu.:0.930 1st Qu.:13768
## Median :22.2 Median :48.00 Median :1707 Median :1.010 Median :16955
## Mean :22.4 Mean :47.15 Mean :1725 Mean :1.009 Mean :17288
## 3rd Qu.:24.3 3rd Qu.:58.00 3rd Qu.:1945 3rd Qu.:1.090 3rd Qu.:20325
## Max. :37.1 Max. :88.00 Max. :3040 Max. :1.350 Max. :40825
## lean pcfat hypertension diabetes
## Min. :19136 Min. : 9.2 Min. :0.000 Min. :0.0000
## 1st Qu.:30325 1st Qu.:27.0 1st Qu.:0.000 1st Qu.:0.0000
## Median :33577 Median :32.4 Median :1.000 Median :0.0000
## Mean :35463 Mean :31.6 Mean :0.507 Mean :0.1109
## 3rd Qu.:39761 3rd Qu.:36.8 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :63059 Max. :48.4 Max. :1.000 Max. :1.0000
Việc 5: Biên tập dữ liệu
5.1. Mã hóa biến gender
ob$sex.b = ifelse(ob$gender== "F", 1, 0)
table(ob$sex.b, ob$gender)
##
## F M
## 0 0 355
## 1 862 0
head(ob)
## id gender height weight bmi age WBBMC wbbmd fat lean pcfat hypertension
## 1 1 F 150 49 21.8 53 1312 0.88 17802 28600 37.3 0
## 2 2 M 165 52 19.1 65 1309 0.84 8381 40229 16.8 1
## 3 3 F 157 57 23.1 64 1230 0.84 19221 36057 34.0 1
## 4 4 F 156 53 21.8 56 1171 0.80 17472 33094 33.8 1
## 5 5 M 160 51 19.9 54 1681 0.98 7336 40621 14.8 0
## 6 6 F 153 47 20.1 52 1358 0.91 14904 30068 32.2 1
## diabetes sex.b
## 1 1 1
## 2 0 0
## 3 0 1
## 4 0 1
## 5 0 0
## 6 0 1
5.2. Mã hóa biến BMI
ob$obese[ob$bmi< 18.5] = "Underweight"
ob$obese[ob$bmi>= 18.5 & ob$bmi< 25] = "Normal"
ob$obese[ob$bmi>= 25 & ob$bmi< 30] = "Overweight"
ob$obese[ob$bmi>= 30] = "Obese"
head(ob)
## id gender height weight bmi age WBBMC wbbmd fat lean pcfat hypertension
## 1 1 F 150 49 21.8 53 1312 0.88 17802 28600 37.3 0
## 2 2 M 165 52 19.1 65 1309 0.84 8381 40229 16.8 1
## 3 3 F 157 57 23.1 64 1230 0.84 19221 36057 34.0 1
## 4 4 F 156 53 21.8 56 1171 0.80 17472 33094 33.8 1
## 5 5 M 160 51 19.9 54 1681 0.98 7336 40621 14.8 0
## 6 6 F 153 47 20.1 52 1358 0.91 14904 30068 32.2 1
## diabetes sex.b obese
## 1 1 1 Normal
## 2 0 0 Normal
## 3 0 1 Normal
## 4 0 1 Normal
## 5 0 0 Normal
## 6 0 1 Normal
5.3. Tạo biến số mơi
ob$lean.kg = ob$lean/1000
ob$fat.kg = ob$fat/1000
head(ob)
## id gender height weight bmi age WBBMC wbbmd fat lean pcfat hypertension
## 1 1 F 150 49 21.8 53 1312 0.88 17802 28600 37.3 0
## 2 2 M 165 52 19.1 65 1309 0.84 8381 40229 16.8 1
## 3 3 F 157 57 23.1 64 1230 0.84 19221 36057 34.0 1
## 4 4 F 156 53 21.8 56 1171 0.80 17472 33094 33.8 1
## 5 5 M 160 51 19.9 54 1681 0.98 7336 40621 14.8 0
## 6 6 F 153 47 20.1 52 1358 0.91 14904 30068 32.2 1
## diabetes sex.b obese lean.kg fat.kg
## 1 1 1 Normal 28.600 17.802
## 2 0 0 Normal 40.229 8.381
## 3 0 1 Normal 36.057 19.221
## 4 0 1 Normal 33.094 17.472
## 5 0 0 Normal 40.621 7.336
## 6 0 1 Normal 30.068 14.904
5.4. Tạo tập dữ liệu “men.overweight”
men.overweight = subset(ob, gender == "M" & bmi>= 25)
dim(men.overweight)
## [1] 85 17
table(men.overweight$obese)
##
## Obese Overweight
## 4 81
5.5. Tạo tập dữ liệu Demo chỉ gồm 6 biến số lad id, age, gender,
height, weight, pcfat
Demo = subset(ob, select = c(id, age, gender, weight, height, pcfat))
dim(Demo)
## [1] 1217 6
head(Demo)
## id age gender weight height pcfat
## 1 1 53 F 49 150 37.3
## 2 2 65 M 52 165 16.8
## 3 3 64 F 57 157 34.0
## 4 4 56 F 53 156 33.8
## 5 5 54 M 51 160 14.8
## 6 6 52 F 47 153 32.2