退火算法

 w

# -*- coding: utf-8 -*-
def segment(text, segs):
    words = []
    last = 0
    for i in range(len(segs)):
        if segs[i] == '1':
            words.append(text[last:i+1])
            last = i+1
    words.append(text[last:])
    return words

def evaluate(text, segs):
    words = segment(text, segs)
    print words
    text_size = len(words)
    print text_size
    lexicon_size = len(' '.join(list(set(words))))
    print set(words)
    print list(set(words))
    print ' '.join(list(set(words)))
    print lexicon_size
    size = text_size + lexicon_size
    print size
    return size

text = "doyouseethekittyseethedoggydoyoulikethekittylikethedoggy"
seg1 = "0000000000000001000000000010000000000000000100000000000"
seg2 = "0100100100100001001001000010100100010010000100010010000"
seg3 = "0000100100000011001000000110000100010000001100010000001"

#evaluate(text, seg1)
evaluate(text, seg2)
#evaluate(text, seg3)