def handle(self, *args, **options):
std_arrays = defaultdict(list)
doclist = []
canned_loader = CannedLoader()
for doc in canned_loader.iterate():
# Process this document
tm = TextManager(doc.text, doc.year)
# Trace progress message
self.stdout.write(doc.title + " " + doc.author)
for key, value in sorted(tm.profile_stats().items()):
std_arrays[key].append(value)
doclist.append((doc.author + ", " + doc.title, tm.profile_stats()))
mean_averages = {key: numpy.mean(values) for key, values in std_arrays.items()}
standard_deviations = {key: numpy.std(values) for key, values in std_arrays.items()}
doclist = [(title, _convert_to_zscores(stats, mean_averages, standard_deviations)) for title, stats in doclist]
for i, doc in enumerate(doclist):
title, stats = doc
rankings = []
for j, doc2 in enumerate(doclist):
if j == i:
continue
distance = _measure_distance(doc, doc2)
rankings.append((doc2[0], doc2[1], distance))
rankings.sort(key=lambda d: d[2])
self.stdout.write("\n\n" + title)
self.stdout.write(repr(stats))
for d in rankings[0:10]:
self.stdout.write("\t%s\t%f" % (d[0], d[2]))
self.stdout.write("\t\t" + repr(d[1]))
