Bugfix plotting of jobs. More details in paper.
This commit is contained in:
parent
c2e3353420
commit
8364582785
211
paper/main.tex
211
paper/main.tex
|
|
@ -239,12 +239,219 @@ Potentially, analyze how the rankings of different similarities look like.
|
|||
\end{subfigure}
|
||||
\centering
|
||||
\caption{Histogram for the number of jobs (bin width: 2.5\%, numbers are the actual job counts)}
|
||||
\label{fig:ecdf}
|
||||
\label{fig:hist}
|
||||
\end{figure}
|
||||
|
||||
\subsection{Quantitative Analysis of Selected Jobs}
|
||||
|
||||
\begin{table}
|
||||
\caption{User and Group Information}
|
||||
\end{table}
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/jobs-nodes}
|
||||
\caption{Job-S} \label{fig:nodes-job-S}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/jobs-nodes}
|
||||
\caption{Job-M} \label{fig:nodes-job-M}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_7488914-out/jobs-nodes}
|
||||
\caption{Job-L} \label{fig:nodes-job-L}
|
||||
\end{subfigure}
|
||||
\centering
|
||||
\caption{Distribution of node counts}
|
||||
\label{fig:nodes-job}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/jobs-elapsed}
|
||||
\caption{Job-S} \label{fig:runtime-job-S}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/jobs-elapsed}
|
||||
\caption{Job-M} \label{fig:runtime-job-M}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_7488914-out/jobs-elapsed}
|
||||
\caption{Job-L} \label{fig:runtime-job-L}
|
||||
\end{subfigure}
|
||||
\centering
|
||||
\caption{Distribution of elapsed runtime}
|
||||
\label{fig:runtime-job}
|
||||
\end{figure}
|
||||
|
||||
Different algorithms ...
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/intersection-heatmap}
|
||||
\caption{Job-S} \label{fig:heatmap-job-S}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/intersection-heatmap}
|
||||
\caption{Job-M} \label{fig:heatmap-job-M}
|
||||
\end{subfigure}
|
||||
|
||||
\begin{subfigure}{0.5\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_7488914-out/intersection-heatmap}
|
||||
\caption{Job-L} \label{fig:heatmap-job-L}
|
||||
\end{subfigure}
|
||||
\centering
|
||||
\caption{Intersection of the top 100 jobs for the different algorithms}
|
||||
\label{fig:heatmap-job}
|
||||
\end{figure}
|
||||
|
||||
\section{Assessing Timelines for Similar Jobs}
|
||||
|
||||
\subsection{Job-S}
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_lev-0.9615-timeseries4297102}
|
||||
\caption{Rank 2, SIM=0.9615}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_lev-0.9017-timeseries4570701}
|
||||
\caption{Rank 15, SIM=0.9017}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_lev-0.7901-timeseries4693267}
|
||||
\caption{Rank\,100, SIM=0.790}
|
||||
\end{subfigure}
|
||||
|
||||
\caption{Job-S with Hex-Lev, selection of similar jobs}
|
||||
\label{fig:job-S-hex-lev}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_native-0.9808-timeseries4567314}
|
||||
\caption{Rank 2, SIM=}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_native-0.9375-timeseries4709700}
|
||||
\caption{Rank 15, SIM=}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_native-0.9001-timeseries4527630}
|
||||
\caption{Rank\,100, SIM=}
|
||||
\end{subfigure}
|
||||
|
||||
\caption{Job-S with Hex-Native, selection of similar jobs}
|
||||
\label{fig:job-S-hex-native}
|
||||
\end{figure}
|
||||
|
||||
|
||||
|
||||
\section{Summary and Conclusion}
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_phases-0.9153-timeseries4567314}
|
||||
\caption{Rank 2, $SIM=$ (same job as hex native Top1)}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_native-0.9268-timeseries4557849}
|
||||
\caption{Rank 15, $SIM=$}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_4296426-out/hex_phases-0.7382-timeseries4693267}
|
||||
\caption{Rank\,100, $SIM=$ }
|
||||
\end{subfigure}
|
||||
|
||||
\caption{Job-S with Hex-Phases, selection of similar jobs}
|
||||
\label{fig:job-S-hex-phases}
|
||||
\end{figure}
|
||||
|
||||
% \ContinuedFloat
|
||||
|
||||
Bin aggzeros works quite well here too.
|
||||
|
||||
|
||||
\subsection{Job-M}
|
||||
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7755-timeseries7907734}
|
||||
\caption{Rank 2, $SIM=$}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7347-timeseries4244400}
|
||||
\caption{$SIM=$}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.5306-timeseries8038026}
|
||||
\caption{$SIM=$ }
|
||||
\end{subfigure}
|
||||
|
||||
\caption{Job-M with Bin-Aggzero, selection of similar jobs}
|
||||
\label{fig:job-M-bin-aggzero}
|
||||
\end{figure}
|
||||
|
||||
|
||||
|
||||
\begin{figure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7755-timeseries7907734}
|
||||
\caption{Rank 2, $SIM=$}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7347-timeseries4244400}
|
||||
\caption{$SIM=$}
|
||||
\end{subfigure}
|
||||
\begin{subfigure}{0.3\textwidth}
|
||||
\centering
|
||||
\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.5306-timeseries8038026}
|
||||
\caption{$SIM=$ }
|
||||
\end{subfigure}
|
||||
|
||||
\caption{Job-M with Bin-Aggzero, selection of similar jobs}
|
||||
\label{fig:job-M-bin-aggzero}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\subsection{Job-L}
|
||||
|
||||
|
||||
|
||||
|
||||
\section{Conclusion}
|
||||
\label{sec:summary}
|
||||
|
||||
%\printbibliography
|
||||
|
|
|
|||
|
|
@ -1,7 +1,23 @@
|
|||
#!/bin/bash
|
||||
|
||||
# call me from the parent directory
|
||||
|
||||
echo "This script performs the complete analysis steps"
|
||||
|
||||
function prepare(){
|
||||
pushd datasets
|
||||
./decompress.sh
|
||||
popd
|
||||
|
||||
for I in datasets/*.csv ; do
|
||||
ln -s $I
|
||||
done
|
||||
}
|
||||
|
||||
# prepare
|
||||
|
||||
for I in job_similarities_*.csv ; do
|
||||
rm *.png *.pdf
|
||||
./scripts/plot.R $I > description.txt
|
||||
OUT=${I%%.csv}-out
|
||||
mkdir $OUT
|
||||
|
|
|
|||
|
|
@ -12,7 +12,9 @@ prefix = sys.argv[2].split(",")
|
|||
|
||||
fileformat = ".png"
|
||||
|
||||
print("Plotting the job: " + str(jobs))
|
||||
print("Plotting the job: " + str(sys.argv[1]))
|
||||
print("Plotting with prefix: " + str(sys.argv[2]))
|
||||
|
||||
|
||||
# Color map
|
||||
colorMap = { "md_file_create": cm.tab10(0),
|
||||
|
|
@ -120,15 +122,14 @@ def plot(prefix, header, row):
|
|||
with open('job-io-datasets/datasets/job_codings.csv') as csv_file:
|
||||
csv_reader = csv.reader(csv_file, delimiter=',')
|
||||
line_count = 0
|
||||
job = 0
|
||||
for row in csv_reader:
|
||||
if line_count == 0:
|
||||
header = row
|
||||
line_count += 1
|
||||
continue
|
||||
|
||||
if not row[0].strip() in jobs:
|
||||
job = row[0].strip()
|
||||
if not job in jobs:
|
||||
continue
|
||||
else:
|
||||
plot(prefix[job], header, row)
|
||||
job += 1
|
||||
index = jobs.index(job)
|
||||
plot(prefix[index] + "-" + str(index), header, row)
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ library(ggplot2)
|
|||
library(dplyr)
|
||||
require(scales)
|
||||
|
||||
plotjobs = FALSE
|
||||
plotjobs = TRUE
|
||||
|
||||
# Color scheme
|
||||
plotcolors <- c("#CC0000", "#FFA500", "#FFFF00", "#008000", "#9999ff", "#000066")
|
||||
|
|
@ -53,7 +53,7 @@ plotJobs = function(jobs){
|
|||
r = e[ordered, ]
|
||||
|
||||
if (plotjobs) {
|
||||
prefix = do.call("sprintf", list("%s-%.0f-", level, r$similarity))
|
||||
prefix = do.call("sprintf", list("%s-%.4f-", level, r$similarity))
|
||||
system(sprintf("scripts/plot-single-job.py %s %s", paste(r$jobid, collapse=","), paste(prefix, collapse=",")))
|
||||
}
|
||||
}
|
||||
|
|
@ -96,7 +96,7 @@ for (l1 in levels(data$alg_name)){
|
|||
print(res.intersect)
|
||||
|
||||
# Plot heatmap about intersection
|
||||
ggplot(tbl.intersect, aes(first, second, fill=intersect)) + geom_tile() + geom_text(aes(label = round(intersect, 1))) + scale_fill_gradientn(colours = rev(plotcolors))
|
||||
ggplot(tbl.intersect, aes(first, second, fill=intersect)) + geom_tile() + geom_text(aes(label = round(intersect, 1))) + scale_fill_gradientn(colours = rev(plotcolors)) + xlab("") + ylab("")
|
||||
ggsave("intersection-heatmap.png", width=6, height=5)
|
||||
|
||||
# Collect the metadata of all jobs in a new table
|
||||
|
|
@ -105,11 +105,11 @@ for (alg_name in levels(data$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, 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))) + theme(legend.position = "none")
|
||||
ggsave("jobs-nodes.png", width=6, height=4)
|
||||
|
||||
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")
|
||||
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") + theme(legend.position = "none")
|
||||
ggsave("jobs-elapsed.png", width=6, height=4)
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue