2018-12-12 词频统计

Hamlet词频统计（含Hamlet原文文本）

#CalHamletV1.py

defgetText():

    txt =open("hamlet.txt", "r").read()

    txt =txt.lower()

    forch in'!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':

        txt =txt.replace(ch, " ")   #将文本中特殊字符替换为空格

    returntxt

hamletTxt =getText()

words  =hamletTxt.split()

counts ={}

forword inwords:          

    counts[word] =counts.get(word,0) +1

items =list(counts.items())

items.sort(key=lambdax:x[1], reverse=True) 

fori inrange(10):

    word, count =items[i]

    print("{0:<10}{1:>5}".format(word, count))

《三国演义》人物出场统计（上）（含《三国演义》原文文本）

#CalThreeKingdomsV1.py

importjieba

txt =open("threekingdoms.txt", "r", encoding='utf-8').read()

words  =jieba.lcut(txt)

counts ={}

forword inwords:

    iflen(word) ==1:

        continue

    else:

        counts[word] =counts.get(word,0) +1

items =list(counts.items())

items.sort(key=lambdax:x[1], reverse=True) 

fori inrange(15):

    word, count =items[i]

    print("{0:<10}{1:>5}".format(word, count))

《三国演义》人物出场统计（下）（含《三国演义》原文文本）

#CalThreeKingdomsV2.py

importjieba

excludes ={"将军","却说","荆州","二人","不可","不能","如此"}

txt =open("threekingdoms.txt", "r", encoding='utf-8').read()

words  =jieba.lcut(txt)

counts ={}

forword inwords:

    iflen(word) ==1:

        continue

    elifword =="诸葛亮"orword =="孔明曰":

        rword ="孔明"

    elifword =="关公"orword =="云长":

        rword ="关羽"

    elifword =="玄德"orword =="玄德曰":

        rword ="刘备"

    elifword =="孟德"orword =="丞相":

        rword ="曹操"

    else:

        rword =word

    counts[rword] =counts.get(rword,0) +1

forword inexcludes:

    delcounts[word]

items =list(counts.items())

items.sort(key=lambdax:x[1], reverse=True) 

fori inrange(10):

    word, count =items[i]

    print("{0:<10}{1:>5}".format(word, count))