UTS

data_kesehatan <- read.csv("data_kesehatan.csv")
head(data_kesehatan)

##   X id umur jenis_kelamin tinggi_badan berat_badan gula_darah tekanan_sistolik
## 1 1  1   33     Perempuan     159.5587    62.85027   80.08403         129.2978
## 2 2  2   59     Perempuan     152.9881    54.73592   79.20090         108.6373
## 3 3  3   39     Perempuan     156.1915    66.84162   99.64040         132.7729
## 4 4  4   64     Laki-laki     173.8024    54.83932   97.35650         108.7811
## 5 5  5   67     Perempuan     164.0242    62.21020   49.01314         129.4536
## 6 6  6   20     Perempuan     150.0967    61.15284  120.81147         136.4499
##   tekanan_diastolik kolesterol skor_kesehatan
## 1          69.13882   181.3293      100.00000
## 2          73.34697   209.6954      100.00000
## 3          87.14848   176.3801       88.52949
## 4          75.68339   172.1841      100.00000
## 5          82.27615   138.6886      100.00000
## 6          92.94946   183.7165       75.39378

table(data_kesehatan$jenis_kelamin)

## 
## Laki-laki Perempuan 
##       108        92

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

rata_rata_tinggi_badan <- data_kesehatan %>%
  group_by(jenis_kelamin) %>%
  summarise(rata_rata_tinggi_badan = mean(tinggi_badan, na.rm = TRUE))
rata_rata_tinggi_badan

## # A tibble: 2 × 2
##   jenis_kelamin rata_rata_tinggi_badan
##   <chr>                          <dbl>
## 1 Laki-laki                       171.
## 2 Perempuan                       160.

getwd()

## [1] "C:/Users/user/Documents/r psd/UTS"

data_kesehatan <- data_kesehatan %>%
  mutate(bmi = berat_badan / (tinggi_badan / 100)^2)

obesitas <- data_kesehatan %>%
  filter(bmi > 30)

rata_skor_obesitas <- mean(obesitas$skor_kesehatan, na.rm = TRUE)
round(rata_skor_obesitas, 1)

## [1] 74.9