133 lines
3.4 KiB
R
133 lines
3.4 KiB
R
library(ggplot2)
|
|
library(dplyr)
|
|
library(readr)
|
|
|
|
# Usage: Rscript combined_instr_fault_correlation.r exp_abspath1 exp_abspath2 ... [faults_file]
|
|
|
|
args <- commandArgs(trailingOnly = TRUE)
|
|
if (length(args) < 1) {
|
|
stop("Need at least 1 experiment")
|
|
}
|
|
|
|
# TODO: I should probably stop duplicating this each time
|
|
csv_suffix <- if (grepl("\\.csv$", args[length(args)])) {
|
|
args[length(args)]
|
|
} else {
|
|
"faults.csv"
|
|
}
|
|
exp_args <- if (grepl("\\.csv$", args[length(args)])) {
|
|
args[-length(args)]
|
|
} else {
|
|
args
|
|
}
|
|
|
|
# Don't use counts from faults.csv, as that would correlate completely
|
|
# because only mnemonics with faults are listed there
|
|
# NOTE: Doesn't match selected filters for faults.csv
|
|
mnemonics_file <- "mnemonics.csv"
|
|
|
|
freq_data <- data.frame()
|
|
faults_data <- data.frame()
|
|
|
|
# TODO: I should probably stop duplicating this each time
|
|
for (arg in exp_args) {
|
|
mnem_path <- file.path(arg, mnemonics_file)
|
|
faults_path <- file.path(arg, csv_suffix)
|
|
|
|
if (!file.exists(mnem_path)) {
|
|
warning(paste("Missing:", mnem_path))
|
|
next
|
|
}
|
|
if (!file.exists(faults_path)) {
|
|
warning(paste("Missing:", faults_path))
|
|
next
|
|
}
|
|
|
|
mdf <- read_csv(mnem_path, col_types = cols())
|
|
mdf$experiment <- basename(arg)
|
|
freq_data <- bind_rows(freq_data, mdf)
|
|
|
|
fdf <- read_csv(faults_path, col_types = cols())
|
|
fdf$experiment <- basename(arg)
|
|
faults_data <- bind_rows(faults_data, fdf)
|
|
}
|
|
|
|
if (nrow(freq_data) == 0 || nrow(faults_data) == 0) {
|
|
stop("No data loaded")
|
|
}
|
|
|
|
# x-axis: mnemonics.csv counts
|
|
instr_freq <- freq_data |>
|
|
filter(!is.na(mnemonic), mnemonic != "NULL") |>
|
|
group_by(mnemonic) |>
|
|
summarise(instr_count = sum(count, na.rm = TRUE), .groups = "drop")
|
|
|
|
# y-axis: no OK_MARKERs, sum GROUP1_MARKER + TRAP.
|
|
marker_count <- faults_data |>
|
|
filter(!is.na(mnemonic), mnemonic != "NULL") |>
|
|
filter(resulttype != "OK_MARKER") |>
|
|
mutate(
|
|
resulttype = ifelse(resulttype == "GROUP1_MARKER", "TRAP", resulttype)
|
|
) |>
|
|
group_by(mnemonic) |>
|
|
summarise(marker_count = sum(faults, na.rm = TRUE), .groups = "drop")
|
|
|
|
correlation <- instr_freq |>
|
|
inner_join(marker_count, by = "mnemonic") |>
|
|
filter(instr_count > 0, marker_count > 0)
|
|
|
|
if (nrow(correlation) < 2) {
|
|
stop("Not enough mnemonics to compute a correlation")
|
|
}
|
|
|
|
cor_raw <- cor(
|
|
correlation$instr_count,
|
|
correlation$marker_count,
|
|
method = "pearson"
|
|
)
|
|
cor_log <- cor(
|
|
log10(correlation$instr_count),
|
|
log10(correlation$marker_count),
|
|
method = "pearson"
|
|
)
|
|
cat(sprintf("Pearson correlation (raw): %.4f\n", cor_raw))
|
|
cat(sprintf("Pearson correlation (log10): %.4f\n", cor_log))
|
|
|
|
plot <- ggplot(
|
|
correlation,
|
|
aes(x = instr_count, y = marker_count)
|
|
) +
|
|
geom_smooth(
|
|
method = "lm",
|
|
se = FALSE,
|
|
colour = "grey50",
|
|
linetype = "dashed"
|
|
) +
|
|
geom_point(aes(colour = mnemonic), size = 3, alpha = 0.8) +
|
|
geom_text(
|
|
aes(label = mnemonic),
|
|
size = 3,
|
|
vjust = -0.8,
|
|
check_overlap = TRUE
|
|
) +
|
|
scale_x_log10(name = "Instruction Execution Frequency") +
|
|
scale_y_log10(name = "Failure-Marker Occurrences") +
|
|
labs(
|
|
title = sprintf(
|
|
"Instruction / Fault Correlation (r_raw = %.4f, r_log = %.4f)",
|
|
cor_raw,
|
|
cor_log
|
|
),
|
|
colour = "Mnemonic"
|
|
) +
|
|
theme_minimal() +
|
|
theme(
|
|
legend.position = "none",
|
|
plot.title = element_text(size = 14, face = "bold")
|
|
)
|
|
|
|
suffix <- gsub("^faults|\\.csv$", "", csv_suffix)
|
|
outfile <- paste0("injections/instr_fault_correlation", suffix, ".svg")
|
|
ggsave(outfile, plot = plot, width = 10, height = 8)
|
|
print(paste("Saved", outfile))
|