這篇文章主要介紹了python實現中文分詞FMM算法,實例分析了Python基于FMM算法進行中文分詞的實現方法,涉及Python針對文件、字符串及正則匹配操作的相關技巧,需要的朋友可以參考下
本文實例講述了python實現中文分詞FMM算法。分享給大家供大家參考。具體分析如下:
FMM算法的最簡單思想是使用貪心算法向前找n個,如果這n個組成的詞在詞典中出現,就ok,如果沒有出現,那么找n-1個...然后繼續下去。假如n個詞在詞典中出現,那么從n+1位置繼續找下去,直到句子結束。
- import re
- def PreProcess(sentence,edcode="utf-8"):
- sentence = sentence.decode(edcode)
- sentence=re.sub(u"[。,,!……!《》<>/"'::?/?、/|“”‘';]"," ",sentence)
- return sentence
- def FMM(sentence,diction,result = [],maxwordLength = 4,edcode="utf-8"):
- i = 0
- sentence = PreProcess(sentence,edcode)
- length = len(sentence)
- while i < length:
- # find the ascii word
- tempi=i
- tok=sentence[i:i+1]
- while re.search("[0-9A-Za-z/-/+#@_/.]{1}",tok)<>None:
- i= i+1
- tok=sentence[i:i+1]
- if i-tempi>0:
- result.append(sentence[tempi:i].lower().encode(edcode))
- # find chinese word
- left = len(sentence[i:])
- if left == 1:
- """go to 4 step over the FMM"""
- """should we add the last one? Yes, if not blank"""
- if sentence[i:] <> " ":
- result.append(sentence[i:].encode(edcode))
- return result
- m = min(left,maxwordLength)
- for j in xrange(m,0,-1):
- leftword = sentence[i:j+i].encode(edcode)
- # print leftword.decode(edcode)
- if LookUp(leftword,diction):
- # find the left word in dictionary
- # it's the right one
- i = j+i
- result.append(leftword)
- break
- elif j == 1:
- """only one word, add into result, if not blank"""
- if leftword.decode(edcode) <> " ":
- result.append(leftword)
- i = i+1
- else:
- continue
- return result
- def LookUp(word,dictionary):
- if dictionary.has_key(word):
- return True
- return False
- def ConvertGBKtoUTF(sentence):
- return sentence.decode('gbk').encode('utf-8')
- dictions = {}
- dictions["ab"] = 1
- dictions["cd"] = 2
- dictions["abc"] = 1
- dictions["ss"] = 1
- dictions[ConvertGBKtoUTF("好的")] = 1
- dictions[ConvertGBKtoUTF("真的")] = 1
- sentence = "asdfa好的是這樣嗎vasdiw呀真的daf dasfiw asid是嗎?"
- s = FMM(ConvertGBKtoUTF(sentence),dictions)
- for i in s:
- print i.decode("utf-8")
- test = open("test.txt","r")
- for line in test:
- s = FMM(CovertGBKtoUTF(line),dictions)
- for i in s:
- print i.decode("utf-8")
運行結果如下:
asdfa
好的
是
這
樣
嗎
vasdiw
呀
真的
daf
dasfiw
asid
是
嗎
?
希望本文所述對大家的Python程序設計有所幫助。
新聞熱點
疑難解答