Python自然语言分析（第四期）：第2课书面作业

#  -*- coding: UTF-8 -*-
import nltk
from nltk.book import  *

len_text2 = len(text2)
len_dis_text2 = len(set(text2))
print("在text2中有" + str(len_text2) + "个词")
print("在text2中有" + str(len_dis_text2) + "个不同的词")

print("因为言情小说词汇多样性得分是8.3，幽默小的词汇多样性得分是4.3，所以是幽默小说文体中的词汇更丰富")

text5.collocations()

word_li = [w for w in text5 if len(w) == 4]
fdist = FreqDist(word_li)
sorted_word_li = sorted(fdist.keys(), key=lambda x: fdist[x], reverse=True)
for w in sorted_word_li:
    print "%s\t%d; " % (w, fdist[w]),

print ("")

def percent(word,text):
    freq = len([w for w in text if w == word]) * 1.0 / len(text)*100
    return freq


print (str(round(percent("JOIN",text5),3))+"%")