朴素贝叶斯算法Python实现

# -*- coding: cp936 -*-
#朴素贝叶斯分类器的实现
#运行
#reload(docclass)
#c1=docclass.naivebayes(docclass.getwords)
#docclass.sampletrain(c1)
#c1.classify('quick rabbit',default='unknown')
#构建训练样本
def sampletrain(c1):
    c1.train('Nobody owns the water.','good')
    c1.train('the quick rabbit jumps fences','good')
    c1.train('buy pharmaceuticals now','bad')
    c1.train('make quick money at the online casino','bad')
    c1.train('the quick brown fox jumps','good')
import re
import math
#从文本中提取特征
def getwords(doc):
    splitter=re.compile('\\W*')
    #根据非字母字典进行单词拆分
    words=[s.lower() for s in splitter.split(doc) if len(s)>2 and len(s)<20]
    #只返回一组不重复的单词
    return dict([(w,1) for w in words])

#分类器
class classifier:
    def __init__(self,getfeatures):
        self.fc={}
        self.cc={}
        self.getfeatures=getfeature