267 lines
11 KiB
R
267 lines
11 KiB
R
# 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 (with check.names=FALSE to preserve original column names)
|
|
# na.strings="" keeps empty cells as empty strings instead of converting to NA
|
|
df <- read.csv("eohi2.csv", stringsAsFactors = FALSE, check.names = FALSE, na.strings = NULL)
|
|
|
|
# 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"
|
|
)
|
|
|
|
# ============= TROUBLESHOOTING: CHECK COLUMN EXISTENCE =============
|
|
cat("\n=== COLUMN EXISTENCE CHECK ===\n\n")
|
|
|
|
# Get actual column names from dataframe (trimmed)
|
|
df_cols <- trimws(names(df))
|
|
|
|
# Print first 30 actual column names for debugging
|
|
cat("First 30 actual column names in CSV:\n")
|
|
for (i in 1:min(30, length(df_cols))) {
|
|
cat(sprintf(" %2d. '%s' (length: %d)\n", i, df_cols[i], nchar(df_cols[i])))
|
|
}
|
|
cat("\n")
|
|
|
|
# Check Source A columns
|
|
missing_A <- source_cols_A[!source_cols_A %in% df_cols]
|
|
existing_A <- source_cols_A[source_cols_A %in% df_cols]
|
|
|
|
cat("Source Set A:\n")
|
|
cat(" Expected: 60 columns\n")
|
|
cat(" Found:", length(existing_A), "columns\n")
|
|
cat(" Missing:", length(missing_A), "columns\n")
|
|
|
|
if (length(missing_A) > 0) {
|
|
cat("\n Missing columns from Set A:\n")
|
|
for (col in missing_A) {
|
|
cat(" -", col, "\n")
|
|
}
|
|
}
|
|
|
|
# Check Source B columns
|
|
missing_B <- source_cols_B[!source_cols_B %in% df_cols]
|
|
existing_B <- source_cols_B[source_cols_B %in% df_cols]
|
|
|
|
cat("\nSource Set B:\n")
|
|
cat(" Expected: 60 columns\n")
|
|
cat(" Found:", length(existing_B), "columns\n")
|
|
cat(" Missing:", length(missing_B), "columns\n")
|
|
|
|
if (length(missing_B) > 0) {
|
|
cat("\n Missing columns from Set B:\n")
|
|
for (col in missing_B) {
|
|
cat(" -", col, "\n")
|
|
}
|
|
}
|
|
|
|
# Check for columns with similar names (potential typos/spaces)
|
|
if (length(missing_A) > 0 || length(missing_B) > 0) {
|
|
cat("\n\n=== CHECKING FOR SIMILAR COLUMN NAMES ===\n")
|
|
all_missing <- c(missing_A, missing_B)
|
|
for (miss_col in all_missing) {
|
|
# Find columns that start with similar pattern
|
|
pattern <- substr(miss_col, 1, 10)
|
|
similar <- grep(pattern, df_cols, value = TRUE, ignore.case = TRUE)
|
|
if (length(similar) > 0) {
|
|
cat("\nLooking for:", miss_col)
|
|
cat("\n Similar columns found:\n")
|
|
for (sim in similar) {
|
|
cat(" - '", sim, "' (length:", nchar(sim), ")\n", sep = "")
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
cat("\n=== END CHECK ===\n\n")
|
|
|
|
# Stop if critical columns are missing
|
|
if (length(missing_A) > 30 || length(missing_B) > 30) {
|
|
stop("ERROR: Too many columns missing! Please check column names in CSV file.")
|
|
}
|
|
|
|
cat("Proceeding with processing...\n\n")
|
|
|
|
# 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")
|
|
}
|
|
|
|
# ============= VERIFY TARGET COLUMNS WERE CREATED =============
|
|
cat("\n\n=== VERIFYING TARGET COLUMNS ===\n\n")
|
|
|
|
# Get updated column names
|
|
df_cols_after <- trimws(names(df))
|
|
|
|
# Check which target columns exist
|
|
existing_targets <- target_cols[target_cols %in% df_cols_after]
|
|
missing_targets <- target_cols[!target_cols %in% df_cols_after]
|
|
|
|
cat("Target Columns:\n")
|
|
cat(" Expected: 60 columns\n")
|
|
cat(" Created:", length(existing_targets), "columns\n")
|
|
cat(" Missing:", length(missing_targets), "columns\n")
|
|
|
|
if (length(missing_targets) > 0) {
|
|
cat("\n WARNING: The following target columns were NOT created:\n")
|
|
for (col in missing_targets) {
|
|
cat(" -", col, "\n")
|
|
}
|
|
stop("\nERROR: Not all target columns were created successfully!")
|
|
} else {
|
|
cat("\n SUCCESS: All 60 target columns created successfully!\n")
|
|
}
|
|
|
|
cat("\n=== END VERIFICATION ===\n\n")
|
|
|
|
|
|
# ============= QUALITY ASSURANCE: RANDOM ROW CHECK =============
|
|
# This function can be run multiple times to check different random rows
|
|
|
|
qa_check_random_row <- function() {
|
|
# Pick a random row
|
|
random_row <- sample(1:nrow(df), 1)
|
|
|
|
cat("\n========================================\n")
|
|
cat("QA CHECK: Random Row #", random_row, "\n")
|
|
cat("========================================\n\n")
|
|
|
|
# Check each of the 60 pairs
|
|
for (i in 1:60) {
|
|
col_A <- source_cols_A[i]
|
|
col_B <- source_cols_B[i]
|
|
target_col <- target_cols[i]
|
|
|
|
# Get values
|
|
val_A <- if (col_A %in% names(df)) df[random_row, col_A] else ""
|
|
val_B <- if (col_B %in% names(df)) df[random_row, col_B] else ""
|
|
target_val <- df[random_row, target_col]
|
|
|
|
# Determine which source had the value
|
|
has_val_A <- !is.na(val_A) && val_A != ""
|
|
has_val_B <- !is.na(val_B) && val_B != ""
|
|
|
|
if (has_val_A) {
|
|
source_used <- "A"
|
|
original_text <- val_A
|
|
} else if (has_val_B) {
|
|
source_used <- "B"
|
|
original_text <- val_B
|
|
} else {
|
|
source_used <- "NONE"
|
|
original_text <- "(empty)"
|
|
}
|
|
|
|
# Print the info
|
|
cat(sprintf("Pair %2d:\n", i))
|
|
cat(sprintf(" Source A: %-30s\n", col_A))
|
|
cat(sprintf(" Source B: %-30s\n", col_B))
|
|
cat(sprintf(" Target: %-30s\n", target_col))
|
|
cat(sprintf(" Value found in: Source %s\n", source_used))
|
|
cat(sprintf(" Original text: '%s'\n", original_text))
|
|
cat(sprintf(" Numeric value: %s\n", ifelse(is.na(target_val), "NA", as.character(target_val))))
|
|
cat("\n")
|
|
}
|
|
|
|
cat("========================================\n")
|
|
cat("END QA CHECK\n")
|
|
cat("========================================\n\n")
|
|
}
|
|
|
|
# Run QA check on first random row
|
|
cat("\n\n")
|
|
qa_check_random_row()
|
|
|
|
# Instructions for running additional checks
|
|
cat("\n")
|
|
cat("*** TO CHECK ANOTHER RANDOM ROW ***\n")
|
|
cat("Run this command in R console:\n")
|
|
cat(" qa_check_random_row()\n")
|
|
cat("\n")
|
|
|
|
|
|
# Save the modified dataframe back to CSV
|
|
# na="" writes NA values as empty cells instead of "NA" text
|
|
write.csv(df, "eohi2.csv", row.names = FALSE, na = "")
|
|
|
|
cat("\nProcessing complete! 60 new columns added to eohi2.csv\n")
|
|
|