X-Git-Url: https://projects.mako.cc/source/matplotlib-cdsw/blobdiff_plain/6e94163bfc436e165e143cbc6259054537f554a9..f53e20bf3dc31dc78d0cce4426f74057521f8e68:/wikibios/edits.py diff --git a/wikibios/edits.py b/wikibios/edits.py new file mode 100644 index 0000000..9744f90 --- /dev/null +++ b/wikibios/edits.py @@ -0,0 +1,48 @@ +"""Plot the number of edits vs. article creation date, for male and female bios.""" +import wikibios +from matplotlib import pyplot +from operator import itemgetter + +figure = pyplot.figure() + +rows_female_by_firstedit = sorted(wikibios.rows_female, key=itemgetter('firstedit')) +firstedit_female_medians = [] +mean_edits_female_by_firstedit = [] +N = 1000 +i = 0 +while i + N <= len(rows_female_by_firstedit): + chunk = rows_female_by_firstedit[i:i+N] + i = i + N + + firstedit_female_medians.append(chunk[N / 2]['firstedit']) + + total_edits = 0.0 + for row in chunk: + total_edits = total_edits + row['edits'] + mean_edits = total_edits / N + mean_edits_female_by_firstedit.append(mean_edits) + +rows_male_by_firstedit = sorted(wikibios.rows_male, key=itemgetter('firstedit')) +firstedit_male_medians = [] +mean_edits_male_by_firstedit = [] +i = 0 +while i + N <= len(rows_male_by_firstedit): + chunk = rows_male_by_firstedit[i:i+N] + i = i + N + + firstedit_male_medians.append(chunk[N / 2]['firstedit']) + + total_edits = 0.0 + for row in chunk: + total_edits = total_edits + row['edits'] + mean_edits = total_edits / N + mean_edits_male_by_firstedit.append(mean_edits) + +axes = figure.gca() +axes.plot(firstedit_female_medians, mean_edits_female_by_firstedit, label='Female') +axes.plot(firstedit_male_medians, mean_edits_male_by_firstedit, label='Male') +axes.set_xlabel('First Edit Date') +axes.set_ylabel('Mean Number of Edits') +axes.legend() + +figure.savefig('edits.pdf')