词云语义分割

最新推荐文章于 2025-08-23 10:40:11 发布

原创

最新推荐文章于 2025-08-23 10:40:11 发布 · 245 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python

import collections
import os

import jieba  # 词语切割
import matplotlib.pyplot as plt  # 数据可视化
import numpy as np  # 科学计算
import wordcloud  # 分词
from PIL import Image  # 处理图片
from wordcloud import STOPWORDS, ImageColorGenerator, WordCloud  # 词云，颜色生成器，停止词


def read_stopword(fpath):
    # 读取中文停用词表
    with open(fpath, 'r', encoding='utf-8') as file:
        stopword = file.readlines()
    return [word.replace('\n', '') for word in stopword]


def ciyun():
    with open('C:\\Users\\算法.txt', 'r', encoding='utf-8') as f:  # 打开新的文本转码为gbk
        textfile = f.read()  # 读取文本内容

    # 加载多个停用词表
    path = 'F:\\pythonProject2\\stopwords-master'
    # 两个停用词表是网上下载的
    name_list = ['中文停用词表.txt', '哈工大停用词表.txt']

    stop_word = []
    for fname in name_list:
        stop_word += read_stopword(os.path.join(path, fname))
        # print(stop_word)

    stop_word += 'U'
    stop_word += 'E'
    stop_word += 'D'
    sto