第八章马尔科夫链 -将演讲内容生成链长为100的markov组成的句子

本文介绍了一个使用Python编写的马尔科夫链文本生成器，该生成器从网上获取文本，构建词典并生成新的文本链。通过剔除标点符号和特殊字符，将文本分割成单词，并利用字典结构存储单词及其后续单词的概率，最终生成长度为100的文本链。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#!/usr/bin/env python
# _*_ coding:utf-8 _*_
from random import randint
from urllib.request import urlopen


def wordListSum(wordList):
    sum=0
    for word ,value in wordList.items():
        sum+=value
    return sum
def retrieveRandomWord(wordList):
    randomIndex=randint(1,wordListSum(wordList))
    for word,value in wordList:
        randomIndex-=value
        if value<=0:
            return word
def buildWordDict(text):
    #剔除换行符和引号
    text=text.replace("\n"," ")
    text=text.replace("\"","")
    punctuation=[',','.',';',':']
    for symbol in punctuation:
        text=text.replace(symbol," "+symbol+" ")
    words=text.split(" ")
    words=[word for word in words if word!=""]
    wordDict={}
    for i in range(0,len(words)):
        if words[i-1] not in wordDict:
            #新建一个字典
            wordDict[words[i-1]]={}
        if words[i] not in wordDict[words[i-1]]:
            wordDict[words[i-1]][words[i]]=wordDict[words[i-1]][words[i]]+1
    return wordDict
text=str(urlopen("https://pythonscraping.com/files/inaugurationSpeech.txt").read(),'utf-8')
wordDict=buildWordDict(text)
#生成链长为100的马尔科夫链
length=100
chain=""
currentWord="I"
for i in range(0,length):
    chain+=currentWord
    currentWord=retrieveRandomWord(wordDict[currentWord])
print(chain)