对斗破苍穹进行python文本分析

Posted 2023-03-21 宣哲

对斗破苍穹进行python文本分析

用python分析该小说的分词，词频，词云，小说人物出场次数排序等等。

1、分词

对文本进行分词，将分词结果输出到文本文件中。

自己创建一个txt文本文件，形成自定义词库，如下

import jieba
import re
import string

# 使用 load_userdict 方法加载自定义词库
jieba.load_userdict("1.txt")

with open(\'doupo.txt\',\'r\',encoding=\'gbk\') as f:    #读取文件
    text = f.read()

# 使用正则表达式去掉标点符号和空格
text = re.sub(\'[\\s+\\.\\!\\/_,$%^*(+\\"\\\']+|[+——！，。？、~@#￥%……&*（）：；《）《》“”()»〔〕-]+\', \'\', text)

# 对文本进行分词
words = jieba.cut(text)

# 去掉无意义的空字符串
result = \' \'.join(word for word in words if word.strip())

# 将分词结果保存到txt文档中
with open(\'output.txt\', \'w\', encoding=\'utf-8\') as f:
    f.write(result)

结果显示：

2、词频

import jieba
import jieba.posseg as pseg
from wordcloud import WordCloud
from collections import Counter
import matplotlib.pyplot as plt
import re

with open(\'output.txt\',\'r\',encoding=\'utf-8\') as f:    #读取文件
    text = f.read()

# 对文本进行分词
words = jieba.lcut(text)

# 统计词频
word_count = 
for word in words:
    if len(word) > 1:  # 只统计长度大于1的词
        word_count[word] = word_count.get(word, 0) + 1

# 按照词频排序
sorted_word_count = sorted(word_count.items(), key=lambda x: x[1], reverse=True)

# 打印结果
for word, count in sorted_word_count:
  print(word, count)

结果显示：

由于分词太多就不一一展示

3、绘制词云

import jieba
import jieba.posseg as pseg
from wordcloud import WordCloud
from collections import Counter
import matplotlib.pyplot as plt
import re

with open(\'doupo.txt\',\'r\',encoding=\'gbk\') as f:    #读取文件
    text = f.read()

# 对文本进行分词
words = jieba.lcut(text)

# 统计词频
word_count = 
for word in words:
    if len(word) > 1:  # 只统计长度大于1的词
        word_count[word] = word_count.get(word, 0) + 1

# 按照词频排序
sorted_word_count = sorted(word_count.items(), key=lambda x: x[1], reverse=True)

#创建词云对象
wc = WordCloud(
    font_path=\'云峰静龙行书.ttf\',
    background_color= \'white\',
    max_words=500,
    max_font_size=200,
    width=1000,
    margin=5,
    height=800
).generate_from_frequencies(word_count)

plt.imshow(wc)
plt.axis(\'off\')
plt.show()

结果显示：

4、画饼状图

注：小说前10人物出场次数排序的饼状图

import jieba
import matplotlib.pyplot as plt
from collections import Counter
import re

# 打开人物姓名词库文件
with open(\'person_names.txt\', \'r\', encoding=\'utf-8\') as f:
    person_names = f.read().splitlines()

# 添加人物姓名词库到结巴分词器
jieba.load_userdict(\'person_names.txt\')

# 打开文本文件
with open(\'doupo.txt\', \'r\', encoding=\'gbk\') as f:
    text = f.read()

# 对文本进行分词
words = jieba.lcut(text)

# 统计人物姓名词频
name_freq = 
for word in words:
    if word in person_names:
        if word in name_freq:
            name_freq[word] += 1
        else:
            name_freq[word] = 1

# 输出人物姓名及其词频
#for name, freq in name_freq.items():
    #print(name, freq)

sorted_dict = sorted(name_freq.items(), key=lambda x: x[1], reverse=True)
top_words = sorted_dict[:10] # 取出前 10 个值
labels = [word[0] for word in top_words]
sizes = [word[1] for word in top_words]

# 画图
fig, ax = plt.subplots()
plt.rcParams[\'font.sans-serif\'] = [\'SimHei\']  # 设置字体为黑体
plt.pie(sizes, labels=labels, autopct=\'%1.1f%%\', startangle=150)
plt.rcParams[\'font.size\'] = 16

# 调整图形大小
fig.set_size_inches(8, 8)
# 添加标题
plt.title(\'斗破苍穹人物出场次数饼状图\')

# 显示图表
plt.show()

结果显示：