From e9c81f9f40187bc4701ac539d110003e92b9ca69 Mon Sep 17 00:00:00 2001
From: Mohammad Akhlaghi <mohammad@akhlaghi.org>
Date: Mon, 2 Mar 2020 02:55:00 +0000
Subject: Described the first analysis phase with a demo subMakefile
Until now, there was no explanation on an actual analysis phase, therefore
with this commit an example scenario with a readable Makefile is included.
The Data lineage graph was also simplified to both be more readable, and
also to correspond to this new explanation and subMakefile.
Some random edits/typos were also corrected and some references added for
discussion.
---
reproduce/analysis/config/INPUTS.mk | 2 +-
reproduce/analysis/make/analysis-1.mk | 78 +++++++++++++++++++++++++++++++++++
reproduce/analysis/make/download.mk | 8 ++--
reproduce/analysis/make/menke2020.mk | 78 -----------------------------------
reproduce/analysis/make/top-make.mk | 2 +-
5 files changed, 84 insertions(+), 84 deletions(-)
create mode 100644 reproduce/analysis/make/analysis-1.mk
delete mode 100644 reproduce/analysis/make/menke2020.mk
(limited to 'reproduce/analysis')
diff --git a/reproduce/analysis/config/INPUTS.mk b/reproduce/analysis/config/INPUTS.mk
index 9332df3..b1cf546 100644
--- a/reproduce/analysis/config/INPUTS.mk
+++ b/reproduce/analysis/config/INPUTS.mk
@@ -9,7 +9,7 @@
# this notice are preserved. This file is offered as-is, without any
# warranty.
-MK20DATA = menke-etal-2020.xlsx
+MK20DATA = menke20.xlsx
MK20MD5 = 8e4eee64791f351fec58680126d558a0
MK20SIZE = 1.9MB
MK20URL = https://www.biorxiv.org/content/biorxiv/early/2020/01/18/2020.01.15.908111/DC1/embed/media-1.xlsx
diff --git a/reproduce/analysis/make/analysis-1.mk b/reproduce/analysis/make/analysis-1.mk
new file mode 100644
index 0000000..9d0018e
--- /dev/null
+++ b/reproduce/analysis/make/analysis-1.mk
@@ -0,0 +1,78 @@
+# Use the data from Menke 2020 (DOI:10.1101/2020.01.15.908111) as a
+# demonstration analysis for this paper. This is a relevant paper because
+# it provides good statistics about the status of reproducibility in
+# scientific publications.
+#
+# Copyright (C) 2020 Mohammad Akhlaghi <mohammad@akhlaghi.org>
+#
+# This Makefile is free software: you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the
+# Free Software Foundation, either version 3 of the License, or (at your
+# option) any later version.
+#
+# This Makefile is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General
+# Public License for more details. See <http://www.gnu.org/licenses/>.
+
+
+
+
+# Save the "Table 3" spreadsheet from the downloaded `.xlsx' file into a
+# simple plain-text file that is easy to use.
+a1dir = $(BDIR)/analysis-1
+mk20tab3 = $(a1dir)/menke20-table-3.txt
+$(a1dir):; mkdir $@
+$(mk20tab3): $(indir)/menke20.xlsx | $(a1dir)
+
+ # Set a base-name for the table-3 data.
+ base=$(basename $(notdir $<))-table-3
+
+ # Unfortunately XLSX I/O only works when the input and output are
+ # in the directory it is running. So first, we need to switch to
+ # the input directory, run it, then put our desired output where we
+ # want and delete the extra files.
+ topdir=$$(pwd)
+ cd $(indir)
+ xlsxio_xlsx2csv $(notdir $<)
+ cp $(notdir $<)."Table 3 All by journal by year".csv $$base.csv
+ rm $(notdir $<).*.csv
+ cd $$topdir
+
+ # Read the necessary information. Note that we are dealing with a
+ # CSV (comma-separated value) file. But when there are commas in a
+ # string, quotation signs are put around it. The `FPAT' values is
+ # fully described in the GNU AWK manual. In short, it ensures that
+ # if there is a comma in the middle of double-quotes, it doesn't
+ # count as a delimter.
+ echo "# Column 1: YEAR [counter, i16] Year of journal's publication." > $@.tmp
+ echo "# Column 2: NUM_PAPERS [counter, i16] Number of studied papers in that journal." >> $@.tmp
+ echo "# Column 3: NUM_ID_TOOLS [counter, i16] Number of software/tools that were identified." >> $@.tmp
+ echo "# Column 4: JOURNAL_NAME [string, str150] Name of journal." >> $@.tmp
+ awk 'NR>1{printf("%-10d%-10d%-10d %s\n", $$2, $$3, $$(NF-1)*$$NF, $$1)}' \
+ FPAT='([^,]+)|("[^"]+")' $(indir)/$$base.csv >> $@.tmp
+
+ # Set the temporary file as the final target. This was done so if
+ # there is any possible crash in the steps above, this rule is
+ # re-run (its final target isn't rebuilt).
+ mv $@.tmp $@
+
+
+
+
+
+# Main LaTeX macro file
+$(mtexdir)/analysis-1.tex: $(mk20tab3) | $(mtexdir)
+
+ # Count the total number of papers in their study.
+ v=$$(awk '!/^#/{c+=$$2} END{print c}' $(mk20tab3))
+ echo "\newcommand{\menkenumpapers}{$$v}" > $@
+
+ # Count how many unique journals there were in the study. Note that
+ # the `31' comes because we put 10 characters for each numeric
+ # column and separated the last numeric column from the string
+ # column with a space. If the number of numeric columns change in
+ # the future, the `31' also has to change.
+ v=$$(awk 'BEGIN{FIELDWIDTHS="31 10000"} !/^#/{print $$2}' \
+ $(mk20tab3) | uniq | wc -l)
+ echo "\newcommand{\menkenumjournals}{$$v}" >> $@
diff --git a/reproduce/analysis/make/download.mk b/reproduce/analysis/make/download.mk
index 7e61cb8..e4f2ccd 100644
--- a/reproduce/analysis/make/download.mk
+++ b/reproduce/analysis/make/download.mk
@@ -49,11 +49,11 @@
# progress at every moment.
$(indir):; mkdir $@
downloadwrapper = $(bashdir)/download-multi-try
-inputdatasets = $(indir)/menke-etal-2020.xlsx
+inputdatasets = $(indir)/menke20.xlsx
$(inputdatasets): $(indir)/%: | $(indir) $(lockdir)
# Set the necessary parameters for this input file.
- if [ $* = menke-etal-2020.xlsx ]; then
+ if [ $* = menke20.xlsx ]; then
origname=$(MK20DATA); fullurl=$(MK20URL); mdf=$(MK20MD5);
else
echo; echo; echo "Not recognized input dataset: '$*.fits'."
@@ -93,5 +93,5 @@ $(inputdatasets): $(indir)/%: | $(indir) $(lockdir)
#
# It is very important to mention the address where the data were
# downloaded in the final report.
-$(mtexdir)/download.tex: $(pconfdir)/INPUTS.mk | $(mtexdir)
- echo > $@
+$(mtexdir)/download.tex: $(indir)/menke20.xlsx | $(mtexdir)
+ echo "\newcommand{\menketwentyurl}{$(MK20URL)}" > $@
diff --git a/reproduce/analysis/make/menke2020.mk b/reproduce/analysis/make/menke2020.mk
deleted file mode 100644
index 4dd9897..0000000
--- a/reproduce/analysis/make/menke2020.mk
+++ /dev/null
@@ -1,78 +0,0 @@
-# Use the data from Menke 2020 (DOI:10.1101/2020.01.15.908111) as a
-# demonstration analysis for this paper. This is a relevant paper because
-# it provides good statistics about the status of reproducibility in
-# scientific publications.
-#
-# Copyright (C) 2020 Mohammad Akhlaghi <mohammad@akhlaghi.org>
-#
-# This Makefile is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the
-# Free Software Foundation, either version 3 of the License, or (at your
-# option) any later version.
-#
-# This Makefile is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General
-# Public License for more details. See <http://www.gnu.org/licenses/>.
-
-
-
-
-# Save the "Table 3" spreadsheet from the downloaded `.xlsx' file into a
-# simple plain-text file that is easy to use.
-mk20dir = $(BDIR)/menke2020
-mk20tab3 = $(mk20dir)/table-3.txt
-$(mk20dir):; mkdir $@
-$(mk20tab3): $(indir)/menke-etal-2020.xlsx | $(mk20dir)
-
- # Set a base-name for the table-3 data.
- base=$(basename $(notdir $<))-table-3
-
- # Unfortunately XLSX I/O only works when the input and output are
- # in the directory it is running. So first, we need to switch to
- # the input directory, run it, then put our desired output where we
- # want and delete the extra files.
- topdir=$$(pwd)
- cd $(indir)
- xlsxio_xlsx2csv $(notdir $<)
- cp $(notdir $<)."Table 3 All by journal by year".csv $$base.csv
- rm $(notdir $<).*.csv
- cd $$topdir
-
- # Read the necessary information. Note that we are dealing with a
- # CSV (comma-separated value) file. But when there are commas in a
- # string, quotation signs are put around it. The `FPAT' values is
- # fully described in the GNU AWK manual. In short, it ensures that
- # if there is a comma in the middle of double-quotes, it doesn't
- # count as a delimter.
- echo "# Column 1: YEAR [counter, i16] Year of journal's publication." > $@.tmp
- echo "# Column 2: NUM_PAPERS [counter, i16] Number of studied papers in that journal." >> $@.tmp
- echo "# Column 3: NUM_ID_TOOLS [counter, i16] Number of software/tools that were identified." >> $@.tmp
- echo "# Column 4: JOURNAL_NAME [string, str150] Name of journal." >> $@.tmp
- awk 'NR>1{printf("%-10d%-10d%-10d %s\n", $$2, $$3, $$(NF-1)*$$NF, $$1)}' \
- FPAT='([^,]+)|("[^"]+")' $(indir)/$$base.csv >> $@.tmp
-
- # Set the temporary file as the final target. This was done so if
- # there is any possible crash in the steps above, this rule is
- # re-run (its final target isn't rebuilt).
- mv $@.tmp $@
-
-
-
-
-
-# Main LaTeX macro file
-$(mtexdir)/menke2020.tex: $(mk20tab3) | $(mtexdir)
-
- # Count the total number of papers in their study.
- v=$$(awk '!/^#/{c+=$$2} END{print c}' $(mk20tab3))
- echo "\newcommand{\menkenumpapers}{$$v}" > $@
-
- # Count how many unique journals there were in the study. Note that
- # the `31' comes because we put 10 characters for each numeric
- # column and separated the last numeric column from the string
- # column with a space. If the number of numeric columns change in
- # the future, the `31' also has to change.
- v=$$(awk 'BEGIN{FIELDWIDTHS="31 10000"} !/^#/{print $$2}' \
- $(mk20tab3) | uniq | wc -l)
- echo "\newcommand{\menkenumjournals}{$$v}" >> $@
diff --git a/reproduce/analysis/make/top-make.mk b/reproduce/analysis/make/top-make.mk
index 29bcd83..6dd322f 100644
--- a/reproduce/analysis/make/top-make.mk
+++ b/reproduce/analysis/make/top-make.mk
@@ -113,7 +113,7 @@ endif
makesrc = initialize \
download \
verify \
- menke2020 \
+ analysis-1 \
paper
--
cgit v1.2.1