用python实现小说的平均句长，词性占比，关键词，标点符号，词形统计-CSDN博客

本文链接：https://blog.csdn.net/qq_42338771/article/details/113060547

本文介绍了如何使用Python进行小说分析，包括计算平均句长、统计词性占比、提取关键词并展示词云图、分析标点符号使用以及词形统计，帮助理解文本特征。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

用python实现小说的平均句长，词性占比，关键词，标点符号，词形统计

需求如下

在这里插入图片描述

代码：

词性占比

import jieba
from wordcloud import WordCloud
import re

from PIL import Image

import matplotlib.pyplot as plt

def read_file_gbk(filename):
    with open(filename,'r',encoding='GBK') as f:
        s = f.read()
        s = re.sub('/C', '', s)
        s = re.sub('\r|\n|\s','',s)
    return s
import jieba
import numpy as np


#打开词典文件，返回列表
def open_dict(Dict = 'hahah', path=r''):
    path = path + '%s.txt' % Dict
    dictionary = open(path, 'r', encoding='utf-8')
    dict = []
    for word in dictionary:
        word = word.strip(' ,\n')
        dict.append(word)
    return dict



def judgeodd(num):
    if (num % 2) == 0:
        return 'even'
    else:
        return 'odd'


#注意，这里你要修改path路径。
deny_word = open_dict(Dict = '否定词', path= r'')
posdict = open_dict(Dict = 'positive', path= r'')
negdict = open_dict(Dict = 'negative', path= r'')
degree_word = open_dict(Dict = '程度级别词语', path= r'')
mostdict = degree_word[degree_word.index('extreme')+1 : degree_word.index('very')]#权重4，即在情感词前乘以4
verydict = degree_word[degree_word.index('very')+1 : degree_word.index('more')]#权重3
moredict = degree_word[degree_word.index('more')+1 : degree_word.index('ish')]#权重2
ishdict = degree_word[degree_word.index('ish')+1 : degree_word.index('last')]#权重0.5



def sentiment_score_list(dataset):
    seg_sentence = dataset.split('。|！|？')
    count1 = []
    count2 = []
    for sen in seg_sentence: #循环遍历每一个评论
        segtmp = jieba.lcut(sen, cut_all=False,HMM=False)  #把句子进行分词，以列表的形式返回
        i = 0 #记录扫描到的词的位置
        a = 0 #记录情感词的位置
        poscount = 0 #积极词的第一次分值
        poscount2 = 0 #积极词反转后的分值
        poscount3 = 0 #积极词的最后分值（包括叹号的分值）
        negcount = 0
        negcount2 = 0
        negcount3 = 0
        for word in segtmp:
            poscount = 0
            neg_count = 0
            poscount2 = 0
            neg_count2 = 0
            poscount3 = 0
            neg_count3 = 0
            if word in posdict:  # 判断词语是否是情感词
                poscount += 1
                c = 0
                for w in segtmp[a:i]:  # 扫描情感词前的程度词
                    if w in mostdict:
                        poscount *= 4.0
                    elif w in verydict:
                        poscount *= 3.0
                    elif w in moredict:
                        poscount *= 2.0
                    elif w in ishdict:
                        poscount *= 0.5
                    elif w in deny_word:
                        c += 1
                if judgeodd(c) == 'odd':  # 扫描情感词前的否定词数，如果为奇数：
                    poscount *= -1.0
                    poscount2 += poscount
                    poscount = 0
                    poscount3 = poscount + poscount2 + poscount3
                    poscount2 =