compute_frequency_duplicate_nodes.py
No OneTemporary
Actions

Subscribers

None

File Metadata

	#!/usr/bin/env python

	from __future__ import print_function
	from collections import defaultdict
	import re
	import sys

	def parse_file(filename):
	counter = defaultdict(int)
	pattern = re.compile('^<Piece NumberOfPoints= "(\d+)', re.MULTILINE)
	with open(filename, 'r') as fh:
	match = None
	while not match:
	line = fh.next()
	match = re.match(pattern,line)
	if match:
	nb_points = int(match.groups()[0])
	fh.next()
	for i in range(nb_points):
	curr_pt = tuple((float(num) for num in fh.next().strip().split()))
	counter[curr_pt] +=1
	return counter


	def main():
	filename = sys.argv[1]
	counter = parse_file(filename)
	histo = defaultdict(list)
	for point, nb_occurences in counter.items():
	histo[nb_occurences].append(point)
	print("nb_duplicates: nb_occurences")
	for key, value in histo.items():
	print("{0:>13}: {1:>4}".format(key, len(value)))
	for point in histo[4]:
	print(point)

	if __name__ == "__main__":
	main()