Python基于jieba和wordcloud绘制词云图

在这里插入图片描述

【Cesium】自定义材质，添加带有方向的滚动路线

🍖 前言
🎶一、实现过程
✨二、代码展示
🏀三、运行结果
🏆四、知识点提示

🍖 前言

Python基于jieba和wordcloud绘制词云图

🎶一、实现过程

读取文本信息，采用jieba进行分词统计
wordcloud配合matplotlib进行词云绘制（可以选择一张词云的背景轮廓图，本实例选择一张动物轮廓）
将词云图保存到本地、展示出来

✨二、代码展示

以下是组件源码（未包含自定义的材质类）：

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np


# 读取文本文件
def readText(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        text = f.read()
    return text


# 对文本进行分词
def segmentText(text):
    # 使用jieba进行分词，精确模式
    words = jieba.cut(text)
    # 过滤掉单个字符的词
    filtered_words = [word for word in words if len(word) > 1]
    return filtered_words


# 统计词频
def countWords(words):
    word_counts = {}
    for word in words:
        if word in word_counts:
            word_counts[word] += 1
        else:
            word_counts[word] = 1
    # 按词频降序排序
    word_counts = dict(sorted(word_counts.items(), key=lambda x: x[1], reverse=True))
    return word_counts


# 生成词云
def generateWordcloud(word_counts, background_image_path):
    # 读取背景图片
    background_image = Image.open(background_image_path)
    mask = np.array(background_image)
    # 创建WordCloud对象
    wordcloud = WordCloud(
        font_path='simhei.ttf',
        background_color='white',
        max_words=200,
        mask=mask
    )
    wordcloud.generate_from_frequencies(word_counts)
    return wordcloud


# 显示词云
def showWordcloud(wordcloud):
    plt.figure(figsize=(10, 6))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.savefig('wordcloud.png')
    plt.show()

# 输出词频前十名
def outputTop10(word_counts):
    top10 = dict(list(word_counts.items())[:10])
    for word, count in top10.items():
        print(f'{word}: {count}')

if __name__ == "__main__":
    text = readText('yourTxt.txt')
    words = segmentText(text)
    word_counts = countWords(words)
    background_image_path = 'yourImg.jpg'
    wordcloud = generateWordcloud(word_counts, background_image_path)
    showWordcloud(wordcloud)
    outputTop10(word_counts)