# Script to combine and recode Likert scale items in eohi2.csv
# Combines 01 and 02 versions of items, then recodes text to numeric values

# Load necessary library
library(dplyr)

setwd("C:/Users/irina/Documents/DND/EOHI/eohi2")

# Read the data
df <- read.csv("eohi2.csv", stringsAsFactors = FALSE)

# Define the mapping function
recode_likert <- function(x) {
  case_when(
    tolower(x) == "strongly disagree" ~ -3,
    tolower(x) == "disagree" ~ -2,
    tolower(x) == "somewhat disagree" ~ -1,
    tolower(x) == "neither agree nor disagree" ~ 0,
    tolower(x) == "somewhat agree" ~ 1,
    tolower(x) == "agree" ~ 2,
    tolower(x) == "strongly agree" ~ 3,
    TRUE ~ NA_real_
  )
}

# Define source column pairs (Set A and Set B)
source_cols_A <- c(
  "01past5PrefItem_1", "01past5PrefItem_2", "01past5PrefItem_3", "01past5PrefItem_4", "01past5PrefItem_5",
  "01past5PersItem_1", "01past5PersItem_2", "01past5PersItem_3", "01past5PersItem_4", "01past5PersItem_5",
  "01past5ValItem_1", "01past5ValItem_2", "01past5ValItem_3", "01past5ValItem_4", "01past5ValItem_5",
  "01past10PrefItem_1", "01past10PrefItem_2", "01past10PrefItem_3", "01past10PrefItem_4", "01past10PrefItem_5",
  "01past10PersItem_1", "01past10PersItem_2", "01past10PersItem_3", "01past10PersItem_4", "01past10PersItem_5",
  "01past10ValItem_1", "01past10ValItem_2", "01past10ValItem_3", "01past10ValItem_4", "01past10ValItem_5",
  "01fut5PrefItem_1", "01fut5PrefItem_2", "01fut5PrefItem_3", "01fut5PrefItem_4", "01fut5PrefItem_5",
  "01fut5PersItem_1", "01fut5PersItem_2", "01fut5PersItem_3", "01fut5PersItem_4", "01fut5PersItem_5",
  "01fut5ValItem_1", "01fut5ValItem_2", "01fut5ValItem_3", "01fut5ValItem_4", "01fut5ValItem_5",
  "01fut10PrefItem_1", "01fut10PrefItem_2", "01fut10PrefItem_3", "01fut10PrefItem_4", "01fut10PrefItem_5",
  "01fut10PersItem_1", "01fut10PersItem_2", "01fut10PersItem_3", "01fut10PersItem_4", "01fut10PersItem_5",
  "01fut10ValItem_1", "01fut10ValItem_2", "01fut10ValItem_3", "01fut10ValItem_4", "01fut10ValItem_5"
)

source_cols_B <- c(
  "02past5PrefItem_1", "02past5PrefItem_2", "02past5PrefItem_3", "02past5PrefItem_4", "02past5PrefItem_5",
  "02past5PersItem_1", "02past5PersItem_2", "02past5PersItem_3", "02past5PersItem_4", "02past5PersItem_5",
  "02past5ValItem_1", "02past5ValItem_2", "02past5ValItem_3", "02past5ValItem_4", "02past5ValItem_5",
  "02past10PrefItem_1", "02past10PrefItem_2", "02past10PrefItem_3", "02past10PrefItem_4", "02past10PrefItem_5",
  "02past10PersItem_1", "02past10PersItem_2", "02past10PersItem_3", "02past10PersItem_4", "02past10PersItem_5",
  "02past10ValItem_1", "02past10ValItem_2", "02past10ValItem_3", "02past10ValItem_4", "02past10ValItem_5",
  "02fut5PrefItem_1", "02fut5PrefItem_2", "02fut5PrefItem_3", "02fut5PrefItem_4", "02fut5PrefItem_5",
  "02fut5PersItem_1", "02fut5PersItem_2", "02fut5PersItem_3", "02fut5PersItem_4", "02fut5PersItem_5",
  "02fut5ValItem_1", "02fut5ValItem_2", "02fut5ValItem_3", "02fut5ValItem_4", "02fut5ValItem_5",
  "02fut10PrefItem_1", "02fut10PrefItem_2", "02fut10PrefItem_3", "02fut10PrefItem_4", "02fut10PrefItem_5",
  "02fut10PersItem_1", "02fut10PersItem_2", "02fut10PersItem_3", "02fut10PersItem_4", "02fut10PersItem_5",
  "02fut10ValItem_1", "02fut10ValItem_2", "02fut10ValItem_3", "02fut10ValItem_4", "02fut10ValItem_5"
)

# Define target column names
target_cols <- c(
  "past_5_pref_read", "past_5_pref_music", "past_5_pref_TV", "past_5_pref_nap", "past_5_pref_travel",
  "past_5_pers_extravert", "past_5_pers_critical", "past_5_pers_dependable", "past_5_pers_anxious", "past_5_pers_complex",
  "past_5_val_obey", "past_5_val_trad", "past_5_val_opinion", "past_5_val_performance", "past_5_val_justice",
  "past_10_pref_read", "past_10_pref_music", "past_10_pref_TV", "past_10_pref_nap", "past_10_pref_travel",
  "past_10_pers_extravert", "past_10_pers_critical", "past_10_pers_dependable", "past_10_pers_anxious", "past_10_pers_complex",
  "past_10_val_obey", "past_10_val_trad", "past_10_val_opinion", "past_10_val_performance", "past_10_val_justice",
  "fut_5_pref_read", "fut_5_pref_music", "fut_5_pref_TV", "fut_5_pref_nap", "fut_5_pref_travel",
  "fut_5_pers_extravert", "fut_5_pers_critical", "fut_5_pers_dependable", "fut_5_pers_anxious", "fut_5_pers_complex",
  "fut_5_val_obey", "fut_5_val_trad", "fut_5_val_opinion", "fut_5_val_performance", "fut_5_val_justice",
  "fut_10_pref_read", "fut_10_pref_music", "fut_10_pref_TV", "fut_10_pref_nap", "fut_10_pref_travel",
  "fut_10_pers_extravert", "fut_10_pers_critical", "fut_10_pers_dependable", "fut_10_pers_anxious", "fut_10_pers_complex",
  "fut_10_val_obey", "fut_10_val_trad", "fut_10_val_opinion", "fut_10_val_performance", "fut_10_val_justice"
)

# Process each pair of columns
for (i in 1:60) {
  col_A <- source_cols_A[i]
  col_B <- source_cols_B[i]
  target_col <- target_cols[i]
  
  # Get values from columns, handling missing columns
  vals_A <- if (col_A %in% names(df)) df[[col_A]] else rep(NA, nrow(df))
  vals_B <- if (col_B %in% names(df)) df[[col_B]] else rep(NA, nrow(df))
  
  # Coalesce: take value from vals_A if present, otherwise from vals_B
  combined <- ifelse(!is.na(vals_A) & vals_A != "", 
                     vals_A, 
                     vals_B)
  
  # Recode to numeric
  df[[target_col]] <- recode_likert(combined)
  
  # Print progress
  cat("Processed:", target_col, "\n")
}

# Save the modified dataframe back to CSV
write.csv(df, "eohi3.csv", row.names = FALSE)

cat("\nProcessing complete! 60 new columns added to eohi3.csv\n")