Z_Scores_Script

#Z_Scores_Script
#Author:David_Moshi

#Load packages
pacman::p_load(rio,  here, janitor, lubridate, matchmaker,
               epikit, tidyverse,  gtsummary, anthro)

sample <- import("sample.xlsx")

#Matching data for anthro package
sample1 <- sample %>%
  rename(sex = chld_sex, age = chld_age_month, lenhei = chld_len, weight = chld_wght) %>%
  select(sex, age, lenhei, weight)

#Z-scores analysis 
sample1 <- anthro_zscores(
  sex = c(sample1$sex),
  age = c(sample1$age),
  weight = c(sample1$weight),
  lenhei = c(sample1$lenhei), is_age_in_month = TRUE
)
#sample1 <- export(sample1, "z-scores.xlsx")

#Output table Categories
sample2 <- sample1 %>%
  mutate(Stunting = case_when(
    zlen < -3 ~ "Severe",
    zlen >= -3 & zlen < -2 ~ "Moderate",
    zlen >= -2 & zlen <= 3 ~ "Normal",
    zlen > 3 ~ "Extreme"
  ),
  Underweight = case_when(
    zwei < -3 ~ "Severe",
    zwei >= -3 & zwei < -2 ~ "Moderate",
    zwei >= -2 & zwei <= 1 ~ "Normal",
  ),
  Wasting = case_when(
    zbmi < -3 ~ "Severe",
    zbmi >= -3 & zbmi < -2 ~ "Moderate",
    zbmi >= -2 & zbmi <= 1 ~ "Normal",
    zbmi > 1 & zbmi <= 2 ~ "Risk of overweight",
    zbmi > 2 & zbmi <= 3 ~ "Risk of overweight",
    zbmi > 3 ~ "Obesity")
  )

#Table
sample2 %>%
  select(csex, Stunting, Underweight, Wasting) %>% 
  tbl_summary (by = csex) %>% 
  as_flex_table() %>% 
print(preview = "docx")