diff options
Diffstat (limited to 'slides-intro.tex')
| -rw-r--r-- | slides-intro.tex | 63 |
1 files changed, 34 insertions, 29 deletions
diff --git a/slides-intro.tex b/slides-intro.tex index f4fcf97..3ffedf9 100644 --- a/slides-intro.tex +++ b/slides-intro.tex @@ -383,8 +383,7 @@ for computational reproducibility] \vspace{3mm}\tiny From ``Attributing and Referencing (Research) Software: Best Practices and Outlook from Inria'' (Alliez et - al. 2019, - \textcolor{blue}{\href{https://hal.archives-ouvertes.fr/hal-02135891}{hal-02135891}}) + al. 2020, CiSE, DOI:\textcolor{blue}{\href{https://doi.org/10.1109/MCSE.2019.2949413}{10.1109/MCSE.2019.2949413}}). } \end{frame} \begin{frame}{Impact of ``Dependency hell'' on native building in various hardware (CPU architectures)} @@ -1048,10 +1047,29 @@ for computational reproducibility] %% Make demo. - \begin{frame} - \LARGE - \vspace{1cm} - \hfill Let's see how the analysis is managed in a hypothetical project... + \begin{frame}{Let's look at the data lineage to replicate Figure 1C (green/tool) of Menke+2020 \\(DOI:\href{https://doi.org/10.1101/2020.01.15.908111}{10.1101/2020.01.15.908111})} + \begin{columns} + \column{0.55\linewidth} + \textcolor{blue}{ORIGINAL PLOT} + + The Green plot shows the fraction of papers mentioning software tools from 1997 to 2019. + \column{0.45\linewidth} + \includegraphics[width=\linewidth]{img/tools-per-year-orig.jpg} + \end{columns} + + \rule{\textwidth}{1pt} + + \begin{columns} + \column{0.4\linewidth} + \textcolor{green!70!black}{OUR enhanced REPLICATION} + + The green line is same as above but over their full historical range. + + Red histogram is the number of papers studied in each year + \column{0.6\linewidth} + \vspace{1cm} + \includegraphics[width=\linewidth]{img/tools-per-year.pdf} + \end{columns} \end{frame} \makedemoslide{img/data-lineage-1.pdf} {Makefiles (\texttt{\*.mk}) keep contextually separate parts of the project, all imported into \texttt{top-make.mk}} @@ -1066,37 +1084,24 @@ for computational reproducibility] \makedemoslide{img/data-lineage-6.pdf} {Basic project info comes from \texttt{initialize.tex}.} \makedemoslide{img/data-lineage-7.pdf} - {Reported values about the downloaded inputs come from \texttt{download.tex}.} + {The paper includes some information about the plot.} \makedemoslide{img/data-lineage-8.pdf} - {... for example the number of rows in the second input (a catalog) of the project.} + {The final plotted data are calculated and stored in \texttt{tools-per-year.txt}.} \makedemoslide{img/data-lineage-9.pdf} - {The URL to download \texttt{input2.dat}, and a checksum to validate it, are stored in \texttt{INPUTS.conf}.} + {The plot's calculation is done on a formatted sub-set of the raw input data.} \makedemoslide{img/data-lineage-10.pdf} - {Reported values from first analysis steps stored in \texttt{analysis1.tex}.} + {The raw data that were downloaded are stored in XLSX format.} \makedemoslide{img/data-lineage-11.pdf} - {... for example the average of the numbers in \texttt{out-1b.dat}.} + {The download URL \emph{and} a \alert{checksum to validate} the raw inputs, are stored in \texttt{INPUTS.conf}.} \makedemoslide{img/data-lineage-12.pdf} - {But \texttt{out-1b.dat} itself depends on other files and a paramter (for example a multiple of sigma).} + {We also need to report the URL in the paper...} \makedemoslide{img/data-lineage-13.pdf} - {\texttt{out-1a.dat} is built from a downloaded dataset.} + {Some general info about the full dataset may also be reported.} \makedemoslide{img/data-lineage-14.pdf} - {Download URL and checksum of \texttt{input1.dat} also stored in \texttt{INPUTS.conf}.} + {We report the number of papers studied in a special year, desired year is stored in \texttt{.conf} file.} + \makedemoslide{img/data-lineage-15.pdf} - {Reported values from second analysis steps stored in \texttt{analysis2.tex}.} - \makedemoslide{img/data-lineage-16.pdf} - {... for example the number of selected rows in \texttt{out-2b.dat}.} - \makedemoslide{img/data-lineage-17.pdf} - {\texttt{out-2b.dat} is derived from \texttt{out-1b.dat} (for example, rejected some of \texttt{out-1b.dat}'s rows).} - \makedemoslide{img/data-lineage-18.pdf} - {Reported values from third analysis steps stored in \texttt{analysis3.tex}.} - \makedemoslide{img/data-lineage-19.pdf} - {... for example measurements from both \texttt{out-3a.dat} and \texttt{out-3b.dat}.} - \makedemoslide{img/data-lineage-20.pdf} - {\texttt{out-3b.dat} is generated from an analysis on \texttt{out-2a.dat}.} - \makedemoslide{img/data-lineage-21.pdf} - {But \texttt{out-2a.dat} itself is generated from \texttt{input1.dat} and an analysis which has two settings.} - \makedemoslide{img/data-lineage-22.pdf} - {\texttt{out-3a.dat} also depends on \texttt{out-1a.dat} and an analysis with needs one parameter.} + {It is very easy to expand the project and add new analysis steps (this solution is scalable)} |