diff --git a/fig/runtime-cummulative.png b/fig/runtime-cummulative.png new file mode 100644 index 0000000..b3eb44d Binary files /dev/null and b/fig/runtime-cummulative.png differ diff --git a/fig/runtime-overview.png b/fig/runtime-overview.png new file mode 100644 index 0000000..5b8cbb7 Binary files /dev/null and b/fig/runtime-overview.png differ diff --git a/paper/main.tex b/paper/main.tex index 104f36d..e8aac59 100644 --- a/paper/main.tex +++ b/paper/main.tex @@ -149,8 +149,24 @@ We chose several reference jobs with different compute and IO characteristics vi For each reference job and algorithm, we created a CSV files with the computed similarity for all other jobs. +\begin{figure} +\centering + \begin{subfigure}{0.8\textwidth} + \centering + \includegraphics[width=\textwidth]{runtime-overview} + \caption{Overview to process all jobs} \label{fig:runtime-overview} + \end{subfigure} + + \begin{subfigure}{0.8\textwidth} + \centering + \includegraphics[width=\textwidth]{runtime-cummulative} + \caption{Cumulative} \label{fig:runtime-cummulative} + \end{subfigure} + + \caption{Performance of the algorithms} + \label{fig:performance} +\end{figure} -Sollte man was zur Laufzeit der Algorithmen sagen? Denke Daten zu haben wäre sinnvoll. Create histograms + cumulative job distribution for all algorithms. Insert job profiles for closest 10 jobs. @@ -414,12 +430,12 @@ Bin aggzeros works quite well here too. The jobs are a bit more diverse. \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_4296426-out/bin_aggzeros-0.7778--14timeseries4296191} +\includegraphics[width=\textwidth]{job_similarities_4296426-out/bin_aggzeros-0.7778--14timeseries4555405} \caption{Rank 15, SIM=} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_4296426-out/bin_aggzeros-0.6923--99timeseries4692693} +\includegraphics[width=\textwidth]{job_similarities_4296426-out/bin_aggzeros-0.6923--99timeseries4687419} \caption{Rank\,100, SIM=} \end{subfigure} @@ -442,7 +458,7 @@ Bin aggzero liefert Mist zurück. \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7347--14timeseries7753375} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/bin_aggzeros-0.7347--14timeseries4498983} \caption{$SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} @@ -474,7 +490,7 @@ Bin aggzero liefert Mist zurück. \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_lev-0.7007--99timeseries4371263} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_lev-0.7007--99timeseries8201967} \caption{$SIM=$ } \end{subfigure} @@ -513,21 +529,21 @@ Bin aggzero liefert Mist zurück. \begin{figure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.8974--1timeseries4851096} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.8831--1timeseries7826634} \caption{Rank 2, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.8974--2timeseries4756527} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.7963--2timeseries5240733} \caption{Rank 3, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} -\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.7963--14timeseries5240733} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.4583--14timeseries4244400} \caption{$SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.6863--99timeseries8073368} +\includegraphics[width=\textwidth]{job_similarities_5024292-out/hex_phases-0.2397--99timeseries7644009} \caption{$SIM=$ } \end{subfigure} @@ -541,21 +557,21 @@ Bin aggzero liefert Mist zurück. \begin{figure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1671--1timeseries8017954} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1671--1timeseries7869050} \caption{Rank 2, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1671--2timeseries7869050} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1671--2timeseries7990497} \caption{Rank 3, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} -\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1521--14timeseries8375617} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1521--14timeseries8363584} \caption{$SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1097--99timeseries5129989} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/bin_aggzeros-0.1097--97timeseries4262983} \caption{$SIM=$ } \end{subfigure} @@ -607,7 +623,7 @@ Bin aggzero liefert Mist zurück. \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_native-0.1695--99timeseries4365829} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_native-0.1695--99timeseries7942052} \caption{$SIM=$ } \end{subfigure} @@ -618,21 +634,21 @@ Bin aggzero liefert Mist zurück. \begin{figure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--1timeseries4400632} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--14timeseries4577917} \caption{Rank 2, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--2timeseries4454488} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--1timeseries4405671} \caption{Rank 3, $SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} -\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--14timeseries4395405} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--2timeseries4621422} \caption{$SIM=$} \end{subfigure} \begin{subfigure}{0.3\textwidth} \centering -\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--99timeseries4526720} +\includegraphics[width=\textwidth]{job_similarities_7488914-out/hex_phases-1.0000--99timeseries4232293} \caption{$SIM=$ } \end{subfigure} diff --git a/scripts/plot-performance.R b/scripts/plot-performance.R new file mode 100755 index 0000000..9315e33 --- /dev/null +++ b/scripts/plot-performance.R @@ -0,0 +1,21 @@ +#!/usr/bin/env Rscript +library(ggplot2) +library(dplyr) +require(scales) + +# Plot the performance numbers of the clustering + +data = read.csv("datasets/clustering_progress.csv") + +e = data %>% filter(min_sim %in% c(0.1, 0.5, 0.99)) +e$percent = paste("SIM =", as.factor(round(e$min_sim*100,0)), " %") + +# Development when adding more jobs +ggplot(e, aes(x=jobs_done, y=elapsed, color=alg_name)) + geom_point() + facet_grid(percent ~ .) + ylab("Cummulative runtime in s") + xlab("Jobs processed") + scale_y_log10() + theme(legend.position = "bottom") +ggsave("fig/runtime-cummulative.png", width=6, height=4.5) + +# Bar chart for the maximum +e = data %>% filter(jobs_done >= (jobs_total - 9998)) +e$percent = as.factor(round(e$min_sim*100,0)) +ggplot(e, aes(y=elapsed, x=percent, fill=alg_name)) + geom_bar(stat="identity") + facet_grid(. ~ alg_name, switch = 'y') + scale_y_log10() + theme(legend.position = "none") + ylab("Runtime in s") + xlab("Minimum similarity in %") + geom_text(aes(label = round(elapsed,0), angle = 90, y=0*(elapsed)+20)) +ggsave("fig/runtime-overview.png", width=7, height=2) diff --git a/scripts/plot.R b/scripts/plot.R index 923ae2a..642c61b 100755 --- a/scripts/plot.R +++ b/scripts/plot.R @@ -4,7 +4,7 @@ library(ggplot2) library(dplyr) require(scales) -plotjobs = FALSE +plotjobs = TRUE # Color scheme plotcolors <- c("#CC0000", "#FFA500", "#FFFF00", "#008000", "#9999ff", "#000066")