mistral-io-datasets/scripts/plot.R

120 lines
4.6 KiB
R
Executable File

#!/usr/bin/env Rscript
library(ggplot2)
library(dplyr)
require(scales)
plotjobs = FALSE
# Color scheme
plotcolors <- c("#CC0000", "#FFA500", "#FFFF00", "#008000", "#9999ff", "#000066")
# Parse job from command line
args = commandArgs(trailingOnly = TRUE)
file = "job_similarities_5024292.csv" # for manual execution
file = args[1]
data = read.csv(file)
# Columns are: jobid alg_id alg_name similarity
data$alg_id = as.factor(data$alg_id)
cat("Job count:")
cat(nrow(data))
# empirical cumulative density function (ECDF)
ggplot(data, aes(similarity, color=alg_name, group=alg_name)) + stat_ecdf(geom = "step") + xlab("SIM") + ylab("Fraction of jobs") + theme(legend.position=c(0.9, 0.4)) + scale_color_brewer(palette = "Set2")
ggsave("ecdf.png", width=8, height=3)
ggplot(data, aes(similarity, color=alg_name, group=alg_name)) + stat_ecdf(geom = "step") + xlab("SIM") + ylab("Fraction of jobs") + theme(legend.position=c(0.9, 0.4)) + scale_color_brewer(palette = "Set2") + xlim(0.5, 1.0)
ggsave("ecdf-0.5.png", width=8, height=3)
e = data %>% filter(similarity >= 0.5)
print(summary(e))
# histogram for the jobs
ggplot(data, aes(similarity), group=alg_name) + geom_histogram(color="black", binwidth=0.025) + aes(fill = alg_name) + facet_grid(alg_name ~ ., switch = 'y') + scale_y_continuous(limits=c(0, 100), oob=squish) + scale_color_brewer(palette = "Set2") + ylab("Count (cropped at 100)") + theme(legend.position = "none") + stat_bin(binwidth=0.025, geom="text", angle = 90, colour="black", size=3, aes(label=..count.., y=0*(..count..)+20))
ggsave("hist-sim.png")
# load job information, i.e., the time series per job
jobData = read.csv("job-io-datasets/datasets/job_codings.csv")
metadata = read.csv("job-io-datasets/datasets/job_metadata.csv")
metadata$user_id = as.factor(metadata$user_id)
metadata$group_id = as.factor(metadata$group_id)
plotJobs = function(jobs){
# plot details about the jobs of a given algorithm
tbl = jobData[jobData$jobid %in% jobs,]
print(summary(tbl))
#print(tbl)
md = metadata[metadata$jobid %in% jobs,]
print(summary(md))
# print the job timelines
r = e[ordered, ]
if (plotjobs) {
prefix = do.call("sprintf", list("%s-%.0f-", level, r$similarity))
system(sprintf("scripts/plot-single-job.py %s %s", paste(r$jobid, collapse=","), paste(prefix, collapse=",")))
}
}
# Store the job ids in a table, each column is one algorithm
dim = length(levels(data$alg_name))
count = 100
result = matrix(1:(dim*count), nrow=count, ncol=dim)
colnames(result) = levels(data$alg_name)
# Extract the 100 most similar jobs into the table
for (level in levels(data$alg_name)){
e = data %>% filter(alg_name == level)
print(level)
print(summary(e))
ordered = order(e$similarity, decreasing=TRUE)[1:count]
print(e[ordered,])
# Extract the data for the jobs
jobs = e[ordered,"jobid"]
result[, level] = jobs
plotJobs(jobs)
}
# Compute intersection in a new table
res.intersect = matrix(1:(dim*dim), nrow=dim, ncol=dim)
colnames(res.intersect) = levels(data$alg_name)
rownames(res.intersect) = levels(data$alg_name)
tbl.intersect = expand.grid(first=levels(data$alg_name), second=levels(data$alg_name))
tbl.intersect$intersect = 0
for (l1 in levels(data$alg_name)){
for (l2 in levels(data$alg_name)){
res = length(intersect(result[,l1], result[,l2]))
res.intersect[l1,l2] = res
tbl.intersect[tbl.intersect$first == l1 & tbl.intersect$second == l2, ]$intersect = res
}
}
print(res.intersect)
# Plot heatmap about intersection
ggplot(tbl.intersect, aes(first, second, fill=intersect)) + geom_tile() + geom_text(aes(label = round(intersect, 1))) + scale_fill_gradientn(colours = rev(plotcolors))
ggsave("intersection-heatmap.png", width=6, height=5)
# Collect the metadata of all jobs in a new table
res.jobs = tibble()
for (alg_name in levels(data$alg_name)){
res.jobs = rbind(res.jobs, cbind(alg_name, metadata[metadata$jobid %in% result[, alg_name],]))
}
ggplot(res.jobs, aes(alg_name, total_nodes, fill=alg_name)) + geom_boxplot() + scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log2", function(x) 2^x), labels = trans_format("log2", math_format(2^.x)))
ggsave("jobs-nodes.png")
ggplot(res.jobs, aes(alg_name, elapsed, fill=alg_name)) + geom_boxplot() + scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log10", function(x) 10^x), labels = trans_format("log10", math_format(10^.x))) + ylab("Runtime in s") + xlab("Algorithm")
ggsave("jobs-elapsed.png")
# scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log2", function(x) 2^x), labels = trans_format("log2", math_format(2^.x)))
# stat_summary(aes(linetype = alg_id), fun.y=mean, geom="line")