simplify all scripts and Snakefile

.gitignore

@@ -1,6 +1,2 @@
-*~
-__pycache__/
-venv/
-results/*.png
-results/*.txt
-processed_data/*.dat
+.snakemake
+*/*.log

Snakefile

@@ -1,49 +1,27 @@
 # 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'
+        expand('statistics/{book}.data', book=DATA),
+        expand('plot/{book}.png', book=DATA)
 
 # count words in one of our books
-# logfiles from each run are put in .log files"
 rule count_words:
     input:
-        wc='source/wordcount.py',
+        script='statistics/count.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
-        '''
+    output: 'statistics/{file}.data'
+    conda: 'environment.yml'
+    log: 'statistics/{file}.log'
+    shell: 'python {input.script} {input.book} > {output}'
 
 # 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}'
+        script='plot/plot.py',
+        book='statistics/{file}.data'
+    output: 'plot/{file}.png'
+    conda: 'environment.yml'
+    log: 'plot/{file}.log'
+    shell: 'python {input.script} --data-file {input.book} --plot-file {output}'

environment.yml

@@ -1,22 +1,9 @@
-name: coderefinery
+name: word-count
 channels:
   - conda-forge
-  - defaults
   - bioconda
 dependencies:
-  - python>3.7
-  - click=7.1.2
-  - ipywidgets=7.6.3
-  - jupyterlab=3.0.14
-  - jupyterlab-git=0.30.0
-  - matplotlib=3.4.1
-  - numpy=1.20.2
-  - pandas=1.2.4
-  - pytest=6.2.3
-  - seaborn=0.11.1
-  - snakemake-minimal=6.2.1
-  - sphinx=3.5.4
-  - sphinx_rtd_theme=0.5.2
-  - pip
-#  - pip:
-#    - jupyterlab-github==2.0.0
+  - python>3.9
+  - click=8.1.3
+  - matplotlib=3.7.0
+  - snakemake-minimal=7.22.0

plot/plot.py

@@ -0,0 +1,31 @@
+import matplotlib.pyplot as plt
+import click
+
+
+def plot_bar_chart(x_values, y_values, title, plot_file):
+    plt.figure(figsize=(10, 5))
+    plt.bar(x_values, y_values)
+    plt.title(title)
+    plt.savefig(plot_file)
+
+
+@click.command()
+@click.option(
+    "--data-file", required=True, help="Input data file", type=click.Path(exists=True)
+)
+@click.option("--plot-file", required=True, help="Output plot file")
+def main(data_file, plot_file):
+    # read data from input_file
+    x_values = []
+    y_values = []
+    for line in open(data_file, "r").readlines():
+        word, count = line.split()
+        x_values.append(word)
+        y_values.append(int(count))
+
+    # now plot the data
+    plot_bar_chart(x_values, y_values, "10 most common words", plot_file)
+
+
+if __name__ == "__main__":
+    main()

statistics/abyss.data

@@ -0,0 +1,10 @@
+the 4044
+and 2807
+of 1907
+a 1594
+to 1515
+in 1221
+i 974
+was 695
+it 680
+for 675

statistics/isles.data

@@ -0,0 +1,10 @@
+the 3822
+of 2460
+and 1723
+to 1479
+a 1308
+in 997
+is 894
+that 652
+by 607
+it 573

statistics/last.data

@@ -0,0 +1,10 @@
+the 12244
+and 5566
+to 5073
+of 4952
+a 4015
+in 2699
+we 2649
+is 2302
+it 2102
+on 1861

statistics/sierra.data

@@ -0,0 +1,10 @@
+the 4242
+and 2469
+of 2190
+a 1319
+to 1292
+in 1175
+i 621
+is 564
+as 524
+on 513