Add fault composition chart

2026-08-10 22:12:30 +02:00
parent 76a8fb4c4a
commit 836197a6ee
2 changed files with 103 additions and 120 deletions
@@ -0,0 +1,103 @@
+library(ggplot2)
+library(dplyr)
+library(readr)
+library(stringr)
+library(tidyr)
+
+# Usage: Rscript marker_composition.r exp_abspath1 ... resultsdata_file
+
+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)
+}
+
+# Load data
+all_data <- data.frame()
+weight_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$variant
+  all_data <- bind_rows(all_data, df)
+}
+
+if (nrow(all_data) == 0) {
+  stop("No data loaded")
+}
+
+# Skip OK_MARKERs, sum GROUP1 + TRAP.
+all_data <- all_data |>
+  filter(resulttype != "OK_MARKER") |>
+  mutate(
+    resulttype = ifelse(resulttype == "GROUP1_MARKER", "TRAP", resulttype)
+  ) |>
+  group_by(base_name, variant, benchmark, resulttype) |>
+  summarise(faults = sum(faults), .groups = "drop")
+
+out_suffix <- gsub("^resultsdata|\\.csv$", "", csv_suffix)
+
+# Calculate percentages
+composition <- all_data |>
+  group_by(base_name, variant, benchmark) |>
+  mutate(frac = faults / sum(faults)) |>
+  ungroup()
+
+plot <- ggplot(
+  composition |> filter(variant %in% c("aot", "interp")),
+  aes(x = variant, y = frac, fill = resulttype)
+) +
+  geom_col() +
+  facet_grid(benchmark ~ base_name) +
+  labs(
+    title = "Marker Composition (AOT vs Interp)",
+    x = NULL,
+    y = "Percentage of Faults",
+    fill = "Fault Type"
+  ) +
+  theme_minimal() +
+  theme(
+    plot.title = element_text(size = 13, face = "bold"),
+    axis.text.x = element_text(angle = 45, hjust = 1)
+  )
+
+filename <- paste0(
+  "injections/fault_composition",
+  out_suffix,
+  ".svg"
+)
+ggsave(filename, plot = plot, width = 13, height = 8)