counts.py

   1 import norms
   2 import itertools
   3 import random
   4 import bisect
   5 import collections
   6
   7 english_counts = collections.defaultdict(int)
   8 with open('count_1l.txt', 'r') as f:
   9     for line in f:
  10         (letter, count) = line.split("\t")
  11         english_counts[letter] = int(count)
  12 normalised_english_counts = norms.normalise(english_counts)
  13
  14 english_bigram_counts = collections.defaultdict(int)
  15 with open('count_2l.txt', 'r') as f:
  16     for line in f:
  17         (bigram, count) = line.split("\t")
  18         english_bigram_counts[bigram] = int(count)
  19 normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
  20
  21 english_trigram_counts = collections.defaultdict(int)
  22 with open('count_3l.txt', 'r') as f:
  23     for line in f:
  24         (trigram, count) = line.split("\t")
  25         english_trigram_counts[trigram] = int(count)
  26 normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
  27
  28
  29 # choices, weights = zip(*weighted_choices)
  30 # cumdist = list(itertools.accumulate(weights))
  31 # x = random.random() * cumdist[-1]
  32 # choices[bisect.bisect(cumdist, x)]