第四次作业

 1 # usr/bin/env/python
 2 #  -*- coding:utf-8 -*-
 3 
 4 import jieba
 5 import jieba.posseg as psg
 6 
 7 with open("NotTrustAnyone.txt", ‘r‘) as f:
 8     NotTrustAnyone = f.read()
 9 
10 # 去掉非汉字的字符
11 for ch in NotTrustAnyone:
12     if ch.isalpha() is False:
13         NotTrustAnyone = NotTrustAnyone.replace(ch, "")
14 
15 
16 # 分词并转成一个列表
17 NotTrustAnyOneList = [x.word for x in psg.cut(NotTrustAnyone) if x.flag.startswith(‘n‘)]
18 
19 # 词频统计，用字典保存，并按出现次数降序排序
20 mySet = set(NotTrustAnyOneList)
21 
22 keyList = []
23 valueList = []
24 
25 for word in mySet:
26     keyList.append(word)
27     valueList.append(NotTrustAnyOneList.count(word))
28 
29 wordCount = dict(zip(keyList, valueList))
30 
31 # 字典排序函数(并取top20):
32 
33 
34 def sortDict(myDict):
35     tempList = list()
36     for i in myDict.items():
37         tempList.append(i)
38     tempList.sort(key=lambda x: x[1], reverse=True)
39     myDict = dict(tempList[0:21])
40     return myDict
41 
42 
43 wordCount = sortDict(wordCount)
44 
45 # 输出
46 print("     单词      出现次数".center(13))
47 for word in wordCount.keys():
48     print(word.center(13), wordCount[word])

with open("HallOfFame.txt", ‘r‘) as f:
    HallOfFame = f.read().lower()

# 去除标点符号，并按行分隔
sep = ",.!、!@#$%^‘"
for ch in sep:
    HallOfFame = HallOfFame.replace(ch, "")

HallOfFameList = HallOfFame.split("\n")

# 对每行用空格分隔
temp = []
for i in HallOfFameList:
    temp.extend(i.split(" "))
HallOfFameList = list(x for x in temp if x != ‘‘)
print(HallOfFameList)

# 词频统计，用字典保存，并按出现次数降序排序
mySet = set(HallOfFameList)

keyList = []
valueList = []

for word in mySet:
    keyList.append(word)
    valueList.append(HallOfFameList.count(word))

wordCount = dict(zip(keyList, valueList))

# 字典排序函数(并取top20):


def sortDict(myDict):
    tempList = list()
    for i in myDict.items():
        tempList.append(i)
    tempList.sort(key=lambda x:x[1], reverse=True)
    myDict = dict(tempList[0:21])
    return myDict


wordCount = sortDict(wordCount)

# 输出
print("     单词   出现次数".center(13))
for word in wordCount.keys():
    print(word.center(13),wordCount[word])