options(scipen = 999)

setwd("C:/Users/irina/Documents/DND/EOHI/eohi1")

data <- read.csv("ehi1.csv")

# Check the levels of the demo_edu variable
print(levels(factor(data$demo_edu)))

# Also show the unique values and their frequencies
print("\nUnique values and frequencies:")
print(table(data$demo_edu, useNA = "ifany"))

# Recode demo_edu into 3 ordinal levels
data$edu3 <- NA

# HS_TS: High School and Trade School
data$edu3[data$demo_edu %in% c("High School (or equivalent)", "Trade School (non-military)")] <- "HS_TS"

# C_Ug: College and University - Undergraduate  
data$edu3[data$demo_edu %in% c("College Diploma/Certificate", "University - Undergraduate")] <- "C_Ug"

# grad_prof: University - Graduate, University - PhD, and Professional Degree
data$edu3[data$demo_edu %in% c("University - Graduate (Masters)", "University - PhD", "Professional Degree (ex. JD/MD)")] <- "grad_prof"

# Convert to ordered factor
data$edu3 <- factor(data$edu3, 
                    levels = c("HS_TS", "C_Ug", "grad_prof"),
                    ordered = TRUE)

# Check the recoded variable
print(table(data$edu3, useNA = "ifany"))

# Verify the recoding
print(table(data$demo_edu, data$edu3, useNA = "ifany"))

# Save the updated dataset with the new edu3 variable
write.csv(data, "ehi1.csv", row.names = FALSE)