DSP Project first push, date: 29/01/2026

r_scripts/category_frequency.R

@@ -0,0 +1,79 @@
+#!/usr/bin/env Rscript
+
+`%||%` <- function(lhs, rhs) {
+  if (is.null(lhs) || is.na(lhs)) rhs else lhs
+}
+
+suppressPackageStartupMessages({
+  library(jsonlite)
+  library(readr)
+})
+
+args <- commandArgs(trailingOnly = TRUE)
+
+if (length(args) < 2) {
+  stop("Expected arguments: <data_file_path> <params_json>")
+}
+
+data_file_path <- args[1]
+params_json <- args[2]
+
+if (!file.exists(data_file_path)) {
+  stop(sprintf("Data file not found at %s", data_file_path))
+}
+
+params <- tryCatch(
+  fromJSON(params_json),
+  error = function(e) list()
+)
+
+target_column <- params$column
+if (is.null(target_column) || target_column == "") {
+  stop("Parameter 'column' is required for category_frequency.R")
+}
+
+top_n <- as.integer(params$top_n %||% 10)
+include_missing <- isTRUE(params$include_missing)
+
+data <- tryCatch(
+  read_csv(
+    file = data_file_path,
+    show_col_types = FALSE,
+    progress = FALSE,
+    locale = locale(encoding = params$encoding %||% "UTF-8")
+  ),
+  error = function(e) stop(sprintf("Failed to read CSV: %s", e$message))
+)
+
+if (!target_column %in% names(data)) {
+  stop(sprintf("Column '%s' not found in dataset", target_column))
+}
+
+column_vector <- data[[target_column]]
+
+if (!include_missing) {
+  column_vector <- column_vector[!is.na(column_vector)]
+}
+
+frequency_table <- sort(table(column_vector, useNA = if (include_missing) "always" else "no"), decreasing = TRUE)
+
+freq_df <- head(as.data.frame(frequency_table, stringsAsFactors = FALSE), top_n)
+names(freq_df) <- c("value", "count")
+
+output <- list(
+  message = sprintf("Top %s frequency distribution for '%s'.", top_n, target_column),
+  analyzed_column = target_column,
+  top_n = top_n,
+  include_missing = include_missing,
+  frequencies = freq_df
+)
+
+cat(
+  toJSON(
+    output,
+    pretty = TRUE,
+    auto_unbox = TRUE,
+    na = "null",
+    dataframe = "rows"
+  )
+)