python词云小程序

•  pip install -i https://mirrors.aliyun.com/pypi/simple/ jieba wordcloud matplotlib
• pip install wordcloud matplotlib
• 这里需要安装的库

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


def read_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        text = file.read()
    return text


def extract_words(text):
    # 使用结巴分词进行分词
    words = jieba.lcut(text)
    # 可以选择过滤掉一些停用词或单个字符的词
    filtered_words = [word for word in words if len(word.strip()) > 1 and not word.isdigit()]
    return filtered_words


def count_word_frequency(words):
    return Counter(words)


def top_n_words(word_counts, n=10):   #这里可以改提取的词的个数
    return word_counts.most_common(n)


def generate_wordcloud(word_frequencies, width=800, height=400):  #这里可以改变生成的图片的大小
    wordcloud = WordCloud(width=width, height=height, background_color='white',
                          font_path='simhei.ttf').generate_from_frequencies(word_frequencies)
    plt.figure(figsize=(10, 5))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')  # 不显示坐标轴
    plt.show()


# 主程序
if __name__ == "__main__":
    file_path = 'E:\\我的作品\\djangoWeb\\pythonProject_Web_text\\message.txt'  # 替换为你的文本文件路径
    text = read_file(file_path)
    words = extract_words(text)
    word_counts = count_word_frequency(words)
    top_10_words = top_n_words(word_counts)

    # 将top 10的词频转换为字典，以便传递给WordCloud
    top_10_dict = dict(top_10_words)

    # 生成并显示词云
    generate_wordcloud(top_10_dict, width=1200, height=600)  # 可以根据需要调整宽度和高度