第四次作业

小说词频统计：

代码：

# usr/bin/env/python
#  -*- coding:utf-8 -*-

import jieba
import jieba.posseg as psg

with open("NotTrustAnyone.txt", 'r') as f:
    NotTrustAnyone = f.read()

# 去掉非汉字的字符
for ch in NotTrustAnyone:
    if ch.isalpha() is False:
        NotTrustAnyone = NotTrustAnyone.replace(ch, "")


# 分词并转成一个列表
NotTrustAnyOneList = [x.word for x in psg.cut(NotTrustAnyone) if x.flag.startswith('n')]

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

keyList = []
valueList = []

for word in mySet:
    keyList.append(word)
    valueList.append(NotTrustAnyOneList.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])

截图（Top20）：

 

英文歌曲频次统计：

代码：

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])

截图（Top20）：

歌曲和小说文件见附件1