简单马尔可夫模型的实现（简单的机器学习）

#-*- coding:utf-8 -*-
from urllib2 import urlopen
from random import randint

#统计所有单词出现的次数总和
def wordListSum(wordList):
    sum=0
    for word,value in wordList.items():
        print word,value
        sum+=value
    return sum

def retrieveRandomWord(wordList):
    #在1到所有单词出现总和之间选着一个数字，保证每次输出句子不一样
    randIndex=randint(1,wordListSum(wordList))
    #通过randIndex随机选择一个字母返回
    for word,value in wordList.items():
        randIndex-=value
        if randIndex<=0:
            return word

def buildWordDic(text):
    #清洗\n和 "
    text=text.replace("\n"," ")
    text=text.replace("\"","")
    #保证标点符号和前面的单词在一起，不被剔除
    punctuation=[‘,‘,‘.‘,‘;‘,‘:‘]
    for symbol in punctuation:
        text=text.replace(symbol," "+symbol+" ")
    #切割文章
    words=text.split(" ")
    #除去空单词
    words=[word for word in words if word !=""]
    #定义一个总词典
    wordDict={}
    for i in range(1,len(words)):
        #为新单词再创一个新词典
        # 比如句子为：How do you do.
        if words[i-1] not in wordDict:
            #结果应该为：{‘How‘:{},‘do‘:{}}
            wordDict[words[i-1]]={}

        #将下一个单词加入前一个单词的词典中
        if words[i] not in wordDict[words[i - 1]]:
            # 结果应该为：{‘How‘:{‘do‘:0},‘do‘:{‘you‘:0,‘.‘:0}}
            wordDict[words[i-1]][words[i]]=0
        # 结果应该为：{‘How‘:{‘do‘:1},‘do‘:{‘you‘:1,‘.‘:1}}
        wordDict[words[i - 1]][words[i]]=wordDict[words[i-1]][words[i]]+1
    return wordDict

text=str(urlopen(‘http://pythonscraping.com/files/inaugurationSpeech.txt‘).read().decode(‘utf-8‘))
wordDict=buildWordDic(text)

length=100
chain=‘‘
#随便选择一个单词开头
currentword=‘I‘
for i in range(0,length):
    chain +=currentword+‘ ‘
    currentword=str(retrieveRandomWord(wordDict[currentword]))

print(chain)