Initial commit

.gitignore

@@ -0,0 +1,7 @@
+*~
+__pycache__/
+_build/
+venv/
+results/*.png
+results/*.txt
+processed_data/*.dat

.readthedocs.yml

@@ -0,0 +1,13 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: doc/conf.py
+
+# Optionally build your docs in additional formats such as PDF and ePub
+formats: all

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019, CodeRefinery
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Makefile

@@ -0,0 +1,34 @@
+# directory containing source data
+SRCDIR := data
+
+# directory containing intermediate data
+TMPDIR := processed_data
+
+# results directory
+RESDIR := results
+
+# all source files (book texts)
+SRCS = $(wildcard $(SRCDIR)/*.txt)
+
+# all intermediate data files
+DATA = $(patsubst $(SRCDIR)/%.txt,$(TMPDIR)/%.dat,$(SRCS))
+
+# all images
+IMAGES = $(patsubst $(SRCDIR)/%.txt,$(RESDIR)/%.png,$(SRCS))
+
+all: $(DATA) $(IMAGES) $(RESDIR)/results.txt
+
+$(TMPDIR)/%.dat: $(SRCDIR)/%.txt source/wordcount.py
+	python source/wordcount.py $< $@
+
+$(RESDIR)/%.png: $(TMPDIR)/%.dat source/plotcount.py
+	python source/plotcount.py $< $@
+
+$(RESDIR)/results.txt: $(DATA) source/zipf_test.py
+	python source/zipf_test.py $(DATA) > $@
+
+clean:
+	@$(RM) $(TMPDIR)/*
+	@$(RM) $(RESDIR)/*
+
+.PHONY: clean directories

README.md

@@ -0,0 +1,16 @@
+[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/coderefinery/word-count/HEAD)
+
+# Word count example
+
+These programs will count words in a given text, plot a bar chart of the 10
+most common words, and test [Zipf's
+law](https://en.wikipedia.org/wiki/Zipf%27s_law) on the two most common words.
+
+- Inspired by and derived from https://hpc-carpentry.github.io/hpc-python/
+  which is distributed under
+  [Creative Commons Attribution license (CC-BY 4.0)](https://creativecommons.org/licenses/by/4.0/).
+- Documentation: https://word-count.readthedocs.io
+
+We use this example in two [CodeRefinery](https://coderefinery.org/) lessons:
+- https://coderefinery.github.io/reproducible-research/
+- https://coderefinery.github.io/documentation/

Snakefile

@@ -0,0 +1,49 @@
+# a list of all the books we are analyzing
+DATA = glob_wildcards('data/{book}.txt').book
+
+# this is for running on HPC resources
+localrules: all, make_archive
+
+# the default rule
+rule all:
+    input:
+        'zipf_analysis.tar.gz'
+
+# count words in one of our books
+# logfiles from each run are put in .log files"
+rule count_words:
+    input:
+        wc='source/wordcount.py',
+        book='data/{file}.txt'
+    output: 'processed_data/{file}.dat'
+    threads: 4
+    log: 'processed_data/{file}.log'
+    shell:
+        '''
+            python {input.wc} {input.book} {output} >> {log} 2>&1
+        '''
+
+# create a plot for each book
+rule make_plot:
+    input:
+        plotcount='source/plotcount.py',
+	book='processed_data/{file}.dat'
+    output: 'results/{file}.png'
+    shell: 'python {input.plotcount} {input.book} {output}'
+
+# generate summary table
+rule zipf_test:
+    input:
+        zipf='source/zipf_test.py',
+        books=expand('processed_data/{book}.dat', book=DATA)
+    output: 'results/results.txt'
+    shell:  'python {input.zipf} {input.books} > {output}'
+
+# create an archive with all of our results
+rule make_archive:
+    input:
+        expand('results/{book}.png', book=DATA),
+        expand('processed_data/{book}.dat', book=DATA),
+        'results/results.txt'
+    output: 'zipf_analysis.tar.gz'
+    shell: 'tar -czvf {output} {input}'

binder/environment.yml

@@ -0,0 +1 @@
+../environment.yml