DATA333 Recoding SD

library(readr)
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

data <- read.csv("/Users/Nazija/Desktop/SD4 NHIS Data.csv")
head(data)

##   health sex   bmi
## 1      3   1 33.36
## 2      1   2 20.19
## 3      3   1 27.27
## 4      3   2 38.62
## 5      1   2 39.95
## 6      2   2 18.83

1.

final <-data%>%
  mutate(health = ifelse(health == 1, "Excellent",
                  ifelse(health == 2, "Very Good",
                  ifelse(health == 3, "Good",
                  ifelse(health == 4, "Fair",
                  ifelse(health == 5, "Poor", NA))))),
         sex = ifelse(sex == 1, "Male",
               ifelse(sex == 2, "Female", NA)),
         BMI = ifelse(bmi <= 0, NA,
               ifelse(bmi >= 9999, NA, bmi)),
         BMI_category = ifelse(BMI < 19, "Underweight",
                       ifelse(BMI <25, "Normal",
                       ifelse(BMI < 30, "Overweight",
                       ifelse(BMI < 40, "Obese",
                       ifelse(BMI >= 40, "Extremely Obese", NA))))))

2.

health <- final%>%
  select(health)%>%
  filter(!is.na(health))
table(health)%>%
  prop.table()

## health
##  Excellent       Fair       Good       Poor  Very Good 
## 0.25221105 0.10985583 0.26938454 0.03313545 0.33541313

sex<-final%>%
  select(sex)%>%
  filter(!is.na(sex))
table(sex)%>%
  prop.table()

## sex
##    Female      Male 
## 0.5461124 0.4538876

final%>%
  summarize(avgBMI = mean(BMI, na.rm = TRUE))

##     avgBMI
## 1 27.96422

BMI<-final%>%
  select(BMI_category)%>%
  filter(!is.na(BMI_category))
table(BMI)%>%
  prop.table()

## BMI
## Extremely Obese          Normal           Obese      Overweight     Underweight 
##      0.04937768      0.32231871      0.25212402      0.34928050      0.02689908