Make chart naming consistent + simplify menu datafile selection

2026-07-25 17:50:26 +02:00
parent 062644ab17
commit fec9b32df1
6 changed files with 28 additions and 12 deletions
@@ -0,0 +1,102 @@
+library(ggplot2)
+library(dplyr)
+library(readr)
+library(stringr)
+
+# Usage: Rscript ratio_comparison_merged.r exp_abspath1 exp_abspath2 ... [resultsdata_file]
+# Sums all benchmarks
+
+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")
+}
+
+# Add all benchs together (per marker type)
+merged_data <- all_data |>
+  group_by(base_name, variant, resulttype) |>
+  summarise(faults = sum(faults), .groups = "drop")
+
+baseline <- merged_data |> filter(variant == "c")
+comparisons <- merged_data |> filter(variant != "c")
+
+ratios <- comparisons |>
+  left_join(
+    baseline |> select(base_name, resulttype, faults),
+    by = c("base_name", "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)")
+}
+
+plot <- ggplot(
+  ratios,
+  aes(x = resulttype, y = ratio, color = variant, group = variant)
+) +
+  geom_point(size = 2) +
+  geom_line() +
+  facet_wrap(~base_name) +
+  scale_y_log10(name = "Ratio (to C)") +
+  scale_x_discrete(name = "Marker") +
+  labs(color = "Variant") +
+  theme_minimal() +
+  theme(axis.text.x = element_text(angle = 45, hjust = 1))
+
+ggsave(
+  "injections/ratio_comparison_merged.svg",
+  plot = plot,
+  width = 12,
+  height = 8
+)
+print("Saved ratio_comparison_merged.svg")