基于python实现分析识别文章/内容中的高频词和关键词

pip install nltk
pip install collections

import nltk
nltk.download('stopwords')
nltk.download('punkt')

import collections
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
# 读取文章
with open('article.txt', 'r',encoding='utf-8') as f:
    article = f.read()
# 分词
tokens = word_tokenize(article)
# 去除停用词
stop_words = set(stopwords.words('english'))
filtered_tokens = [token for token in tokens if token.lower() not in stop_words]
# 统计词频
word_freq = collections.Counter(filtered_tokens)
# 输出高频词
print('Top 10 frequent words:')
for word, freq in word_freq.most_common(10):
    print(f'{word}: {freq}')
# 提取关键词
keywords = nltk.FreqDist(filtered_tokens).keys()
# 输出关键词
print('Keywords:')
for keyword in keywords:
    print(keyword)

# 导入必要的库
import jieba
import jieba.analyse
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as plt
# 读取文章
with open('./data/2.txt', 'r', encoding='utf-8') as f:
    article = f.read()
# 分词
words = jieba.cut(article)
# 统计词频
word_counts = Counter(words)
# 输出高频词
print('高频词：')
for word, count in word_counts.most_common(10):
    print(word, count)
# 输出关键词
print('关键词：')
keywords = jieba.analyse.extract_tags(article, topK=10, withWeight=True, allowPOS=('n', 'nr', 'ns'))
for keyword, weight in keywords:
    print(keyword, weight)
# 生成词云
wordcloud = WordCloud(font_path='msyh.ttc', background_color='white', width=800, height=600).generate(article)
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()