From d3a68abf5619fb3e99f2858dd5592b5795139619 Mon Sep 17 00:00:00 2001
From: Christoph Urlacher <christoph.urlacher@protonmail.com>
Date: Sat, 25 Jul 2026 15:29:49 +0200
Subject: [PATCH] Custom ratio correlation plot

---
 scripts/charts/ratio_correlation_customized.r | 129 ++++++++++++++++++
 scripts/menu.pl                               |  11 +-
 2 files changed, 136 insertions(+), 4 deletions(-)
 create mode 100644 scripts/charts/ratio_correlation_customized.r

diff --git a/scripts/charts/ratio_correlation_customized.r b/scripts/charts/ratio_correlation_customized.r
new file mode 100644
index 0000000..be7021d
--- /dev/null
+++ b/scripts/charts/ratio_correlation_customized.r
@@ -0,0 +1,129 @@
+library(ggplot2)
+library(dplyr)
+library(readr)
+library(stringr)
+library(tidyr)
+
+# Usage: Rscript ratio_correlation_no_mem.r exp_abspath1 exp_abspath2 ... [resultsdata_file]
+# Plots correlation between aot/c and interp/c ratios, ignoring mem benchmark
+# NOTE: Just a copy of the ratio_correlation.r script where I've changed the filter in line 67
+
+args <- commandArgs(trailingOnly = TRUE)
+if (length(args) < 2) {
+  stop("Need at least 2 experiments")
+}
+
+csv_suffix <- if (grepl("\\.csv$", args[length(args)])) {
+  args[length(args)]
+} else {
+  "resultsdata.csv"
+}
+exp_args <- if (grepl("\\.csv$", args[length(args)])) {
+  args[-length(args)]
+} else {
+  args
+}
+
+extract_info <- function(path) {
+  dir_name <- basename(path)
+  match <- str_match(
+    dir_name,
+    "^\\d{2}-\\d{2}_\\d{2}-\\d{2}-\\d{2}_(.+?)_(c|aot|interp)_"
+  )
+  if (is.na(match[1, 1])) {
+    warning(paste("Could not parse:", dir_name))
+    return(NULL)
+  }
+  list(base_name = match[1, 2], variant = match[1, 3], path = path)
+}
+
+all_data <- data.frame()
+
+for (arg in exp_args) {
+  info <- extract_info(arg)
+  if (is.null(info)) {
+    next
+  }
+
+  csv_file <- file.path(info$path, csv_suffix)
+  if (!file.exists(csv_file)) {
+    warning(paste("Missing:", csv_file))
+    next
+  }
+
+  df <- read_csv(csv_file, col_types = cols())
+  df$base_name <- info$base_name
+  df$variant <- info$variant
+  all_data <- bind_rows(all_data, df)
+}
+
+if (nrow(all_data) == 0) {
+  stop("No data loaded")
+}
+
+# Ignore OK_MARKER (only plot failures) and sum GROUP1_MARKER with TRAP
+# Also ignore mem benchmark
+all_data <- all_data |>
+  filter(resulttype %in% c("TRAP", "GROUP1_MARKER"), benchmark == "ip") |>
+  mutate(resulttype = ifelse(resulttype == "GROUP1_MARKER", "TRAP", resulttype))
+
+all_data <- all_data |>
+  group_by(base_name, variant, benchmark, resulttype) |>
+  summarise(faults = sum(faults), .groups = "drop")
+
+baseline <- all_data |> filter(variant == "c")
+comparisons <- all_data |> filter(variant != "c")
+
+ratios <- comparisons |>
+  left_join(
+    baseline |> select(base_name, benchmark, resulttype, faults),
+    by = c("base_name", "benchmark", "resulttype"),
+    suffix = c("", "_baseline")
+  ) |>
+  filter(!is.na(faults_baseline), faults_baseline > 0) |>
+  mutate(ratio = faults / faults_baseline)
+
+if (nrow(ratios) == 0) {
+  stop("No ratios computed (missing baseline or zero values)")
+}
+
+# Pivot to get aot and interp ratios side by side
+ratio_wide <- ratios |>
+  select(base_name, benchmark, resulttype, variant, ratio) |>
+  pivot_wider(names_from = variant, values_from = ratio) |>
+  filter(!is.na(aot), !is.na(interp))
+
+if (nrow(ratio_wide) == 0) {
+  stop("No paired aot/interp ratios found")
+}
+
+# Compute correlation
+cor_result <- cor(ratio_wide$aot, ratio_wide$interp, method = "pearson")
+cat(sprintf("Pearson correlation: %.4f\n", cor_result))
+
+# Create plot
+plot <- ggplot(
+  ratio_wide,
+  aes(x = aot, y = interp, color = base_name, shape = resulttype)
+) +
+  geom_point(size = 3, alpha = 0.7) +
+  scale_x_log10(name = "AOT / C Ratio") +
+  scale_y_log10(name = "Interpreter / C Ratio") +
+  labs(
+    title = sprintf("Ratio Correlation (r = %.4f)", cor_result),
+    color = "Experiment",
+    shape = "Marker"
+  ) +
+  theme_minimal() +
+  theme(
+    legend.position = "right",
+    plot.title = element_text(size = 14, face = "bold")
+  )
+
+ggsave(
+  "injections/ratio_correlation_customized.svg",
+  plot = plot,
+  width = 10,
+  height = 8
+)
+print("Saved ratio_correlation_customized.svg")
diff --git a/scripts/menu.pl b/scripts/menu.pl
index 12ffabd..565d9e5 100644
--- a/scripts/menu.pl
+++ b/scripts/menu.pl
@@ -575,8 +575,9 @@ my %handlers = (
         # Need to know which chart uses which datafile
         my @faults_charts = grep { /heatmap|scatter|sankey/ } @selected_charts;
         my @resultsdata_charts =
-          grep { /result$|combined_comparison|ratio_comparison|ratio_correlation/ }
-          @selected_charts;
+          grep {
+            /result$|combined_comparison|ratio_comparison|ratio_correlation/
+          } @selected_charts;
 
         my $faults_csv;
         my $resultsdata_csv;
@@ -609,7 +610,8 @@ my %handlers = (
         }
 
         my @combined_charts =
-          grep { /combined|ratio_comparison|ratio_correlation/ } @selected_charts;
+          grep { /combined|ratio_comparison|ratio_correlation/ }
+          @selected_charts;
         my $print_experiments = join " ", @selected_experiments;
         my @path_experiments =
           map { "$local_archive_dir/$_" } @selected_experiments;
@@ -621,7 +623,8 @@ my %handlers = (
               if defined $faults_csv && $chart =~ /heatmap|scatter|sankey/;
             push @r_args, $resultsdata_csv
               if defined $resultsdata_csv
-              && $chart =~ /result$|combined_comparison|ratio_comparison|ratio_correlation/;
+              && $chart =~
+              /result$|combined_comparison|ratio_comparison|ratio_correlation/;
             system(@r_args);
         }
     },