python实现朴素贝叶斯算法

本代码实现了朴素贝叶斯分类器（假设了条件独立的版本），常用于垃圾邮件分类，进行了拉普拉斯平滑。

关于朴素贝叶斯算法原理可以参考博客中原理部分的博文。

#!/usr/bin/python
# -*- coding: utf-8 -*-
from math import log
from numpy import*
import operator
import matplotlib
import matplotlib.pyplot as plt
from os import listdir
def loaddataset():
  postinglist=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
         ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
         ['my', 'dalmation', 'is', 'so', 'cute', 'i', 'love', 'him'],
         ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
         ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
         ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
  classvec = [0,1,0,1,0,1]
  return postinglist,classvec
def createvocablist(dataset):
  vocabset = set([]) #create empty set
  for document in dataset:
    vocabset = vocabset | set(document) #union of the two sets
  return list(vocabset)
 
def setofwords2vec(vocablist, inputset):
  returnvec = [0]*len(vocablist)
  for word in inputset:
    if word in vocablist:
      returnvec[vocablist.index(word)] = 1
    else: print "the word: %s is not in my vocabulary!" % word
  return returnvec
def trainnb0(trainmatrix,traincategory):  #训练模型
  numtraindocs = len(trainmatrix)
  numwords = len(trainmatrix[0])
  pabusive = sum(traincategory)/float(numtraindocs)
  p0num = ones(numwords); p1num = ones(numwords)  #拉普拉斯平滑
  p0denom = 0.0+2.0; p1denom = 0.0 +2.0      #拉普拉斯平滑
  for i in range(numtraindocs):
    if traincategory[i] == 1:
      p1num += trainmatrix[i]
      p1denom += sum(trainmatrix[i])
    else:
      p0num += trainmatrix[i]
      p0denom += sum(trainmatrix[i])
  p1vect = log(p1num/p1denom)    #用log()是为了避免概率乘积时浮点数下溢
  p0vect = log(p0num/p0denom)
  return p0vect,p1vect,pabusive
 
def classifynb(vec2classify, p0vec, p1vec, pclass1):
  p1 = sum(vec2classify * p1vec) + log(pclass1)
  p0 = sum(vec2classify * p0vec) + log(1.0 - pclass1)
  if p1 > p0:
    return 1
  else:
    return 0
 
def bagofwords2vecmn(vocablist, inputset):
  returnvec = [0] * len(vocablist)
  for word in inputset:
    if word in vocablist:
      returnvec[vocablist.index(word)] += 1
  return returnvec
 
def testingnb():  #测试训练结果
  listoposts, listclasses = loaddataset()
  myvocablist = createvocablist(listoposts)
  trainmat = []
  for postindoc in listoposts:
    trainmat.append(setofwords2vec(myvocablist, postindoc))
  p0v, p1v, pab = trainnb0(array(trainmat), array(listclasses))
  testentry = ['love', 'my', 'dalmation']
  thisdoc = array(setofwords2vec(myvocablist, testentry))
  print testentry, 'classified as: ', classifynb(thisdoc, p0v, p1v, pab)
  testentry = ['stupid', 'garbage']
  thisdoc = array(setofwords2vec(myvocablist, testentry))
  print testentry, 'classified as: ', classifynb(thisdoc, p0v, p1v, pab)
 
def textparse(bigstring): # 长字符转转单词列表
  import re
  listoftokens = re.split(r'\w*', bigstring)
  return [tok.lower() for tok in listoftokens if len(tok) > 2]
 
def spamtest():  #测试垃圾文件 需要数据
  doclist = [];
  classlist = [];
  fulltext = []
  for i in range(1, 26):
    wordlist = textparse(open('email/spam/%d.txt' % i).read())
    doclist.append(wordlist)
    fulltext.extend(wordlist)
    classlist.append(1)
    wordlist = textparse(open('email/ham/%d.txt' % i).read())
    doclist.append(wordlist)
    fulltext.extend(wordlist)
    classlist.append(0)
  vocablist = createvocablist(doclist) 
  trainingset = range(50);
  testset = [] 
  for i in range(10):
    randindex = int(random.uniform(0, len(trainingset)))
    testset.append(trainingset[randindex])
    del (trainingset[randindex])
  trainmat = [];
  trainclasses = []
  for docindex in trainingset: 
    trainmat.append(bagofwords2vecmn(vocablist, doclist[docindex]))
    trainclasses.append(classlist[docindex])
  p0v, p1v, pspam = trainnb0(array(trainmat), array(trainclasses))
  errorcount = 0
  for docindex in testset: 
    wordvector = bagofwords2vecmn(vocablist, doclist[docindex])
    if classifynb(array(wordvector), p0v, p1v, pspam) != classlist[docindex]:
      errorcount += 1
      print "classification error", doclist[docindex]
  print 'the error rate is: ', float(errorcount) / len(testset)
 
 
 
listoposts,listclasses=loaddataset()
myvocablist=createvocablist(listoposts)
print myvocablist,'\n'
# print setofwords2vec(myvocablist,listoposts[0]),'\n'
trainmat=[]
for postindoc in listoposts:
  trainmat.append(setofwords2vec(myvocablist,postindoc))
print trainmat
p0v,p1v,pab=trainnb0(trainmat,listclasses)
print pab
print p0v,'\n',p1v
testingnb()

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。