julian.kunkel/mistral-io-datasets
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Nai

Browse Source
This commit is contained in:
Julian M. Kunkel 2020-08-20 12:23:32 +01:00
parent 58709e01e6
commit 40fdb0a01e
2 changed files with 69 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
paper/main.tex
View File

@ -45,7 +45,8 @@
\usepackage{graphicx}
\graphicspath{
{./pictures/},
{../fig/}
{../fig/},
{../}
}
\usepackage[backend=bibtex, style=numeric]{biblatex}
@ -159,9 +160,11 @@ Potentially, analyze how the rankings of different similarities look like.
\begin{figure}
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job-timeseries4296426}
\caption{Job-S} \label{fig:job-S}
\end{subfigure}
\centering
\caption{Reference jobs: timeline of mean IO activity}
\label{fig:refJobs}
@ -171,19 +174,76 @@ Potentially, analyze how the rankings of different similarities look like.
\begin{figure}\ContinuedFloat
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job-timeseries5024292}
\caption{Job-M} \label{fig:job-M}
\end{subfigure}
\centering
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job-timeseries7488914-30.pdf}
\caption{Job-L (first 30 segments of 400; remaining segments are similar)}
\label{fig:job-L}
\end{subfigure}
\centering
\caption{Reference jobs: timeline of mean IO activity; non-shown timelines are 0}
\end{figure}
\begin{figure}
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_4296426-out/ecdf.png}
\caption{Job-S} \label{fig:ecdf-job-S}
\end{subfigure}
\centering
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_5024292-out/ecdf.png}
\caption{Job-M} \label{fig:ecdf-job-M}
\end{subfigure}
\centering
\begin{subfigure}{0.8\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_7488914-out/ecdf.png}
\caption{Job-L} \label{fig:ecdf-job-L}
\end{subfigure}
\centering
\caption{Empirical cumulative density function}
\label{fig:ecdf}
\end{figure}
\begin{figure}
\begin{subfigure}{0.5\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hist-sim}
\caption{Job-S} \label{fig:hist-job-S}
\end{subfigure}
\begin{subfigure}{0.5\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_5024292-out/hist-sim}
\caption{Job-M} \label{fig:hist-job-M}
\end{subfigure}
\begin{subfigure}{0.5\textwidth}
\centering
\includegraphics[width=\textwidth]{job_similarities_7488914-out/hist-sim}
\caption{Job-L} \label{fig:hist-job-L}
\end{subfigure}
\centering
\caption{Histogram for the number of jobs (bin width: 2.5\%, numbers are the actual job counts)}
\label{fig:ecdf}
\end{figure}
\section{Summary and Conclusion}
\label{sec:summary}

14
scripts/plot.R
View File

@ -3,16 +3,15 @@
library(ggplot2)
library(dplyr)
require(scales)
#library(hrbrthemes)
file = "job_similarities_5024292.csv"
file = "job_similarities_7488914.csv"
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)
@ -22,7 +21,7 @@ data$alg_id = as.factor(data$alg_id)
cat("Job count:")
cat(nrow(data))
# empirical cummulative density function (ECDF)
# 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)
@ -52,8 +51,11 @@ plotJobs = function(jobs){
# print the job timelines
r = e[ordered, ]
#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=",")))
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