import re
word_list = ["go", "walk", "run", "jump"] # list of all possible words
pattern = re.compile("|".join("%s" % word for word in word_list))
s = "gowalkrunjump"
result = re.findall(pattern, s)
from __future__ import division
from collections import Counter
import re, nltk
WORDS = nltk.corpus.brown.words()
COUNTS = Counter(WORDS)
def pdist(counter):
"Make a probability distribution, given evidence from a Counter."
N = sum(counter.values())
return lambda x: counter[x]/N
P = pdist(COUNTS)
def Pwords(words):
"Probability of words, assuming each word is independent of others."
return product(P(w) for w in words)
def product(nums):
"Multiply the numbers together. (Like `sum`, but with multiplication.)"
result = 1
for x in nums:
result *= x
return result
def splits(text, start=0, L=20):
"Return a list of all (first, rest) pairs; start <= len(first) <= L."
return [(text[:i], text[i:])
for i in range(start, min(len(text), L)+1)]
def segment(text):
"Return a list of words that is the most probable segmentation of text."
if not text:
return []
else:
candidates = ([first] + segment(rest)
for (first, rest) in splits(text, 1))
return max(candidates, key=Pwords)
print segment('acquirecustomerdata')
#['acquire', 'customer', 'data']
如果你有一个所有可能的单词的列表,你可以用这样的方法:
检查Word Segmentation Task来自Norvig的工作。在
为了获得更好的解决方案,可以使用bigram/trigram。在
更多示例:Word Segmentation Task
相关问题 更多 >
编程相关推荐