IBM model1

#-*- encoding:utf-8 -*-

import operator
CORPUS_CH = [ ['一本','書'], ['一本','雜誌'], ['這本','書'], ['這本','雜誌'], ]
CORPUS_EN = [ ['a','book'], ['a','magazine'], ['this','book'], ['this','magazine'], ]
f_word = list(set(reduce(operator.add,CORPUS_CH)))
e_word = list(set(reduce(operator.add,CORPUS_EN)))
T = {}

for k in range(5) :
  C = {}
  for m,l in zip(CORPUS_CH,CORPUS_EN):
    if k == 0:
      for fi in m:
        for ej in l:
          if "%s|%s"%(fi,ej) not in T:
            T["%s|%s"%(fi,ej)]  =  1.0/len(e_word)
    for i, fi in enumerate(m):  
      sum_t = sum([ T["%s|%s"%(fi,ej)] for ej in l]) * 1.0
      for j, ej in enumerate(l):
        delta = T["%s|%s"%(fi,ej)] / sum_t
        C["%s %s"%(ej, fi)] =  C.get("%s %s"%(ej, fi), 0)