#Bài tập ngày 1 ##Việc 1
ob=read.csv("C:\\Users\\N.X.HIEP\\Downloads\\Obesity data.csv")
dim(ob)## [1] 1217 13head(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 0tail(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 0ob$sex=ifelse(ob$gender == "F", 1, 0)
ob$obese <- cut(ob$bmi, breaks = c(-Inf, 18.5, 25.0, 30.0, Inf),labels = c("Underweight", "Normal", "Overweight", "Obese"), right = FALSE)
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 obese
## 1 1 1 Normal
## 2 0 0 Normal
## 3 0 1 Normal
## 4 0 1 Normal
## 5 0 0 Normal
## 6 0 1 Normaldemo=subset(ob, select = c(id, age, gender, height, weight, pcfat))
head(demo)## id age gender height weight pcfat
## 1 1 53 F 150 49 37.3
## 2 2 65 M 165 52 16.8
## 3 3 64 F 157 57 34.0
## 4 4 56 F 156 53 33.8
## 5 5 54 M 160 51 14.8
## 6 6 52 F 153 47 32.2dim(demo)## [1] 1217 6