python计算机二级综合应用，红楼梦统计人物词频。

问题描述：

python计算机二级综合应用，红楼梦统计人物词频。

问题解答：本人这道题代码写的有点拙劣，仅提供另一种思路的参考。

# 以下代码为提示框架
# 请在...处使用一行或多行代码替换
# 请在______处使用一行代码替换
#
# 注意：提示框架代码可以任意修改，以完成程序功能为准

import jieba

f = open("红楼梦.txt","r",encoding="utf-8")
sf = open("停用词.txt","r",encoding="utf-8")

s_fengjie = ["凤姐","凤姐儿","凤丫头"]
s_baoyu = ["宝玉","二爷","宝二爷"]
s_daiyu = ["黛玉","颦儿","林妹妹","黛玉道"]
s_baochai=["宝钗","宝丫头"]
s_jiamu=["贾母","老祖宗"]
s_xiren=["袭人","袭人道"]
s_jiazheng=["贾政","贾政道"]
s_jialian=["贾琏","琏二爷"]
ssf=[]
lines1=sf.readlines()
for line in lines1:
    line=line.strip("\n")
    ssf.append(line)


ls1=[]

lines2=f.readlines()    
for line in lines2:
    line=line.strip()
    line=jieba.lcut(line)
    for word in line:
        ls1.append(word)  
for i in range(len(ls1)):
    if ls1[i] in s_fengjie:
        ls1[i]= "凤姐"
    elif ls1[i] in s_baoyu:
         ls1[i]= "宝玉"
    elif ls1[i] in s_daiyu:
        ls1[i]= "黛玉"
    elif ls1[i] in s_baochai:
         ls1[i]= "宝钗"
    elif ls1[i] in s_jiamu:
        ls1[i]= "贾母"
    elif ls1[i] in s_xiren:
         ls1[i]= "袭人"   
    elif ls1[i] in s_jiazheng:
        ls1[i]= "贾政"
    elif ls1[i] in s_jialian:
         ls1[i]= "贾琏"
    else:
        pass
d={}

for i in ls1:
    if i not in ssf:
        d[i]=d.get(i,0)+1
ls2=list(d.items())
ls2.sort(key=lambda x:x[1], reverse=True)
ls3=[]
for i in ls2:
    if i[1]>=40:
        if len(i[0])>=2:
            ls3.append(i)
print(ls3)
import csv
# 打开一个新的 csv 文件，准备写入
with open('result.csv', 'w', newline='', encoding='utf-8') as csvfile:
    csvwriter = csv.writer(csvfile)
    
    # 遍历列表，将每个元组写入文件
    for item in ls3:
        csvwriter.writerow(item)


  

个人觉得难点，在于如何写入.csv文件中，个人对.csv文件不如.txt文件的写入操作熟悉，所以，.csv文件的写入操作还需要练习。 

下面是系统给出的准确答案。

# 以下代码为提示框架
# 请在...处使用一行或多行代码替换
# 请在______处使用一行代码替换
#
# 注意：提示框架代码可以任意修改，以完成程序功能为准

import jieba

f = "红楼梦.txt"
sf = "停用词.txt"

txt = jieba.lcut(open(f, 'r', encoding = 'utf-8').read())
stop_words = []
with open(sf, 'r', encoding = 'utf-8') as f:
    for i in f.read().splitlines():
        stop_words.append(i)
#剔除停用词
txt0 = [x for x in txt if x not in stop_words]

#统计词频
counts = {}
for word in txt0:
    if len(word) == 1:
        continue
    elif word == '凤姐儿' or word == '凤丫头':
        rword = '凤姐'
    elif word == '二爷' or word == '宝二爷':
        rword = '宝玉'
    elif word == '颦儿' or word == '林妹妹' or word == '黛玉道':
        rword = '黛玉'
    elif word == '宝丫头':
        rword = '宝钗'
    elif word == '老祖宗':
        rword = '贾母'
    elif word == '袭人道':
        rword = '袭人'
    elif word == '贾政道':
        rword = '贾政'
    elif word == '琏二爷':
        rword = '贾琏'
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1

li = list(counts.items())
li.sort(key=lambda x:x[1], reverse=True)
print(li)

#列出词频超过40的结果
with open(r'result.csv','a', encoding = 'gbk') as f:
  for i in li:
    key,value = i
    if value < 40:
        break
    f.write(key + ',' + str(value) + '\n')
    print(key + ',' + str(value))