1.<beautiful data>中的例子，由于没有中文语料库，故用英文串代替，思路一样（如将finallylast）切分成['finally','last']
2.代码切分模块
代码
import operator
def segment(text):
"Return a list of words that is the best segmentation of text."
if not text: return []
candidates = ([first]+segment(rem) for first,rem in splits(text))
return max(candidates, key=Pwords)
def splits(text, L=20):
"Return a list of all possible (first, rem) pairs, len(first)<=L."
return [(text[:i+1], text[i+1:])
for i in range(min(len(text), L))]
def Pwords(words):
"The Naive Bayes probability of a sequence of words."
return product(Pw(w) for w in words)
def product(nums):
"Return the product of a sequence of numbers."
return reduce(operator.mul, nums, 1)
class Pdist(dict):
"A probability distribution estimated from counts in datafile."
def __init__(self, data=[], N=None, missingfn=None):
for key,count in data:
self[key] = self.get(key, 0) + int(count)
self.N = float(N or sum(self.itervalues()))
self.missingfn = missingfn or (lambda k, N: 1./N)
def __call__(self, key):
if key in self: return self[key]/self.N
else: return self.missingfn(key, self.N)
def datafile(name, sep='\t'):
"Read key,value pairs from file."
for line in file(name):
yield line.split(sep)
def avoid_long_words(key, N):
"Estimate the probability of an unknown word."
return 10./(N * 10**len(key))
N = 1024908267229 ## Number of tokens
Pw = Pdist(datafile(r'C:\Python26\Myngrams\count_1w.txt'), N, avoid_long_words)
def segment(text):
"Return a list of words that is the best segmentation of text."
if not text: return []
candidates = ([first]+segment(rem) for first,rem in splits(text))
return max(candidates, key=Pwords)
def splits(text, L=20):
"Return a list of all possible (first, rem) pairs, len(first)<=L."
return [(text[:i+1], text[i+1:])
for i in range(min(len(text), L))]
def Pwords(words):
"The Naive Bayes probability of a sequence of words."
return product(Pw(w) for w in words)
def product(nums):
"Return the product of a sequence of numbers."
return reduce(operator.mul, nums, 1)
class Pdist(dict):
"A probability distribution estimated from counts in datafile."
def __init__(self, data=[], N=None, missingfn=None):
for key,count in data:
self[key] = self.get(key, 0) + int(count)
self.N = float(N or sum(self.itervalues()))
self.missingfn = missingfn or (lambda k, N: 1./N)
def __call__(self, key):
if key in self: return self[key]/self.N
else: return self.missingfn(key, self.N)
def datafile(name, sep='\t'):
"Read key,value pairs from file."
for line in file(name):
yield line.split(sep)
def avoid_long_words(key, N):
"Estimate the probability of an unknown word."
return 10./(N * 10**len(key))
N = 1024908267229 ## Number of tokens
Pw = Pdist(datafile(r'C:\Python26\Myngrams\count_1w.txt'), N, avoid_long_words)
2.注意：在Myngrams 添加一个空的__init__.py
3.验证
from Myngrams import Mysegment
Mysegment.segment('finallylast')
['finally', 'last']
Mysegment.segment('unregardedsitdown')
['un', 'regarded', 'sitdown']
由于训练语料中没有unregarded这个词，加上sitdown当成一个词的概率》P(sit)P(down)所以这个结果分错了。考虑采用二元语法分词
