{"id":1076185,"date":"2025-01-08T11:51:10","date_gmt":"2025-01-08T03:51:10","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1076185.html"},"modified":"2025-01-08T11:51:12","modified_gmt":"2025-01-08T03:51:12","slug":"python-%e5%a6%82%e4%bd%95%e5%88%97%e8%a1%a8%e4%b8%ad%e6%8f%90%e5%8f%96%e5%85%b3%e9%94%ae%e8%af%8d-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1076185.html","title":{"rendered":"python \u5982\u4f55\u5217\u8868\u4e2d\u63d0\u53d6\u5173\u952e\u8bcd"},"content":{"rendered":"

\"python<\/p>\n

\u5728Python\u4e2d\u63d0\u53d6\u5217\u8868\u4e2d\u7684\u5173\u952e\u8bcd\u6709\u591a\u79cd\u65b9\u6cd5<\/strong>\uff0c\u5305\u62ec\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u4f7f\u7528NLP\u5e93\u7b49\u3002\u4f60\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4e2d\u4e00\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u5173\u952e\u8bcd\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5217\u8868\u63a8\u5bfc\u5f0f\u63d0\u53d6\u5173\u952e\u8bcd<\/h3>\n<\/p>\n

\u5217\u8868\u63a8\u5bfc\u5f0f\u662f\u4e00\u79cd\u7b80\u6d01\u4e14\u9ad8\u6548\u7684\u65b9\u6cd5\uff0c\u9002\u7528\u4e8e\u7b80\u5355\u7684\u5173\u952e\u8bcd\u63d0\u53d6\u4efb\u52a1\u3002\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u5305\u542b\u591a\u4e2a\u5b57\u7b26\u4e32\u7684\u5217\u8868\uff0c\u5e76\u5e0c\u671b\u4ece\u4e2d\u63d0\u53d6\u7279\u5b9a\u7684\u5173\u952e\u8bcd\u3002<\/p>\n<\/p>\n

# \u793a\u4f8b\u5217\u8868<\/p>\n
data = ["Python is great", "I love programming", "Data science with Python"]<\/p>\n
\u8981\u63d0\u53d6\u7684\u5173\u952e\u8bcd\u5217\u8868<\/strong><\/h2>\n
keywords = ["Python", "programming"]<\/p>\n
\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u63d0\u53d6\u5173\u952e\u8bcd<\/strong><\/h2>\n
extracted_keywords = [word for sentence in data for word in sentence.split() if word in keywords]<\/p>\n
print(extracted_keywords)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u79cd\u65b9\u6cd5\u975e\u5e38\u9002\u5408\u5904\u7406\u7b80\u5355\u7684\u63d0\u53d6\u4efb\u52a1\uff0c\u5c24\u5176\u662f\u5f53\u5173\u952e\u8bcd\u5217\u8868\u8f83\u5c0f\u65f6<\/strong>\u3002\u7136\u800c\uff0c\u5bf9\u4e8e\u66f4\u590d\u6742\u7684\u4efb\u52a1\uff0c\u4f8b\u5982\u4ece\u672a\u6807\u6ce8\u7684\u6570\u636e\u4e2d\u63d0\u53d6\u5173\u952e\u8bcd\u6216\u5904\u7406\u66f4\u5927\u7684\u6587\u672c\u6570\u636e\u96c6\u65f6\uff0c\u8fd9\u79cd\u65b9\u6cd5\u53ef\u80fd\u5c31\u663e\u5f97\u4e0d\u591f\u4e86\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u5173\u952e\u8bcd<\/h3>\n<\/p>\n
\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u4f9b\u4e86\u4e00\u79cd\u5f3a\u5927\u7684\u6587\u672c\u5904\u7406\u65b9\u6cd5\uff0c\u53ef\u4ee5\u7528\u4e8e\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u590d\u6742\u7684\u6a21\u5f0f\u548c\u5173\u952e\u8bcd\u3002Python \u7684 re<\/code> \u6a21\u5757\u63d0\u4f9b\u4e86\u5bf9\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u652f\u6301\u3002<\/p>\n<\/p>\n
import re<\/p>\n
\u793a\u4f8b\u5217\u8868<\/strong><\/h2>\n
data = ["Python is great", "I love programming", "Data science with Python"]<\/p>\n
\u8981\u63d0\u53d6\u7684\u5173\u952e\u8bcd\u5217\u8868<\/strong><\/h2>\n
keywords = ["Python", "programming"]<\/p>\n
\u521b\u5efa\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f<\/strong><\/h2>\n
pattern = re.compile(r'\\b(?:' + '|'.join(keywords) + r')\\b')<\/p>\n
\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u5173\u952e\u8bcd<\/strong><\/h2>\n
extracted_keywords = [pattern.findall(sentence) for sentence in data]<\/p>\n
print(extracted_keywords)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u6b63\u5219\u8868\u8fbe\u5f0f\u65b9\u6cd5\u975e\u5e38\u7075\u6d3b<\/strong>\uff0c\u53ef\u4ee5\u5904\u7406\u66f4\u590d\u6742\u7684\u63d0\u53d6\u4efb\u52a1\uff0c\u4f8b\u5982\u5339\u914d\u8bcd\u7684\u53d8\u4f53\u5f62\u5f0f\u6216\u5ffd\u7565\u5927\u5c0f\u5199\u7b49\u3002\u5bf9\u4e8e\u5927\u578b\u6587\u672c\u6570\u636e\u96c6\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u80fd\u4f1a\u66f4\u9ad8\u6548\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528NLP\u5e93\u63d0\u53d6\u5173\u952e\u8bcd<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u66f4\u590d\u6742\u7684\u5173\u952e\u8bcd\u63d0\u53d6\u4efb\u52a1\uff0c\u4f8b\u5982\u4ece\u957f\u6587\u672c\u4e2d\u63d0\u53d6\u4e3b\u9898\u8bcd\u6216\u5904\u7406\u81ea\u7136\u8bed\u8a00\u8bed\u4e49\uff0c\u4f7f\u7528\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\u5e93\u53ef\u80fd\u66f4\u4e3a\u5408\u9002\u3002Python \u63d0\u4f9b\u4e86\u591a\u79cdNLP\u5e93\uff0c\u5982 NLTK\u3001SpaCy \u548c Gensim\u3002<\/p>\n<\/p>\n
1\u3001\u4f7f\u7528NLTK\u63d0\u53d6\u5173\u952e\u8bcd<\/h4>\n<\/p>\n
NLTK \u662f\u4e00\u4e2a\u6d41\u884c\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5e93\uff0c\u63d0\u4f9b\u4e86\u591a\u79cd\u6587\u672c\u5904\u7406\u5de5\u5177\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u5b83\u6765\u63d0\u53d6\u5173\u952e\u8bcd\u3002<\/p>\n<\/p>\n
import nltk<\/p>\n
from nltk.corpus import stopwords<\/p>\n
from nltk.tokenize import word_tokenize<\/p>\n
\u786e\u4fdd\u5df2\u7ecf\u4e0b\u8f7d\u505c\u7528\u8bcd<\/strong><\/h2>\n
nltk.download('punkt')<\/p>\n
nltk.download('stopwords')<\/p>\n
\u793a\u4f8b\u6587\u672c<\/strong><\/h2>\n
data = "Python is great for programming and data science"<\/p>\n
\u505c\u7528\u8bcd\u5217\u8868<\/strong><\/h2>\n
stop_words = set(stopwords.words('english'))<\/p>\n
\u5206\u8bcd<\/strong><\/h2>\n
word_tokens = word_tokenize(data)<\/p>\n
\u63d0\u53d6\u5173\u952e\u8bcd<\/strong><\/h2>\n
keywords = [word for word in word_tokens if word.isalpha() and word not in stop_words]<\/p>\n
print(keywords)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u79cd\u65b9\u6cd5\u53ef\u4ee5\u6709\u6548\u5730\u53bb\u9664\u505c\u7528\u8bcd\uff0c\u53ea\u4fdd\u7559\u6709\u610f\u4e49\u7684\u5173\u952e\u8bcd\u3002\u9002\u7528\u4e8e\u9700\u8981\u5904\u7406\u81ea\u7136\u8bed\u8a00\u6587\u672c\u7684\u4efb\u52a1<\/strong>\u3002<\/p>\n<\/p>\n
2\u3001\u4f7f\u7528SpaCy\u63d0\u53d6\u5173\u952e\u8bcd<\/h4>\n<\/p>\n
SpaCy \u662f\u53e6\u4e00\u4e2a\u5f3a\u5927\u7684NLP\u5e93\uff0c\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u529f\u80fd\u3002<\/p>\n<\/p>\n
import spacy<\/p>\n
\u52a0\u8f7dSpaCy\u6a21\u578b<\/strong><\/h2>\n
nlp = spacy.load('en_core_web_sm')<\/p>\n
\u793a\u4f8b\u6587\u672c<\/strong><\/h2>\n
data = "Python is great for programming and data science"<\/p>\n
\u5904\u7406\u6587\u672c<\/strong><\/h2>\n
doc = nlp(data)<\/p>\n
\u63d0\u53d6\u5173\u952e\u8bcd<\/strong><\/h2>\n
keywords = [token.text for token in doc if not token.is_stop and token.is_alpha]<\/p>\n
print(keywords)<\/p>\n
<\/code><\/pre>\n<\/p>\n
SpaCy \u63d0\u4f9b\u4e86\u66f4\u9ad8\u7ea7\u7684\u6587\u672c\u5904\u7406\u529f\u80fd<\/strong>\uff0c\u5982\u8bcd\u6027\u6807\u6ce8\u3001\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u7b49\uff0c\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u4efb\u52a1\u3002<\/p>\n<\/p>\n
\u56db\u3001\u4f7f\u7528Gensim\u63d0\u53d6\u5173\u952e\u8bcd<\/h3>\n<\/p>\n
Gensim \u662f\u4e00\u4e2a\u7528\u4e8e\u4e3b\u9898\u5efa\u6a21\u548c\u6587\u6863\u76f8\u4f3c\u6027\u5206\u6790\u7684\u5e93\uff0c\u53ef\u4ee5\u7528\u4e8e\u4ece\u6587\u672c\u4e2d\u63d0\u53d6\u4e3b\u9898\u8bcd\u3002<\/p>\n<\/p>\n
from gensim.summarization import keywords<\/p>\n
\u793a\u4f8b\u6587\u672c<\/strong><\/h2>\n
data = "Python is great for programming and data science. Python can be used for machine learning, data analysis, and web development."<\/p>\n
\u63d0\u53d6\u5173\u952e\u8bcd<\/strong><\/h2>\n
extracted_keywords = keywords(data, words=5, split=True)<\/p>\n
print(extracted_keywords)<\/p>\n
<\/code><\/pre>\n<\/p>\n
Gensim \u7684 keywords<\/code> \u65b9\u6cd5\u4f7f\u7528\u4e86 TextRank \u7b97\u6cd5\uff0c\u9002\u7528\u4e8e\u4ece\u957f\u6587\u672c\u4e2d\u63d0\u53d6\u91cd\u8981\u5173\u952e\u8bcd<\/strong>\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u6bd4\u8f83\u548c\u603b\u7ed3<\/h3>\n<\/p>\n
\u4e0d\u540c\u7684\u65b9\u6cd5\u9002\u7528\u4e8e\u4e0d\u540c\u7684\u573a\u666f\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53ef\u4ee5\u63d0\u9ad8\u5173\u952e\u8bcd\u63d0\u53d6\u7684\u6548\u679c\u548c\u6548\u7387\u3002<\/p>\n<\/p>\n
    \n
  • \u5217\u8868\u63a8\u5bfc\u5f0f<\/strong>\uff1a\u9002\u7528\u4e8e\u7b80\u5355\u7684\u5173\u952e\u8bcd\u63d0\u53d6\u4efb\u52a1\uff0c\u4ee3\u7801\u7b80\u6d01\u9ad8\u6548\u3002<\/li>\n
  • \u6b63\u5219\u8868\u8fbe\u5f0f<\/strong>\uff1a\u9002\u7528\u4e8e\u9700\u8981\u5339\u914d\u590d\u6742\u6a21\u5f0f\u7684\u4efb\u52a1\uff0c\u7075\u6d3b\u4e14\u9ad8\u6548\u3002<\/li>\n
  • NLTK\u3001SpaCy<\/strong>\uff1a\u9002\u7528\u4e8e\u5904\u7406\u81ea\u7136\u8bed\u8a00\u6587\u672c\uff0c\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u6587\u672c\u5904\u7406\u5de5\u5177\u3002<\/li>\n
  • Gensim<\/strong>\uff1a\u9002\u7528\u4e8e\u4ece\u957f\u6587\u672c\u4e2d\u63d0\u53d6\u4e3b\u9898\u8bcd\uff0c\u4f7f\u7528\u4e86\u5148\u8fdb\u7684\u7b97\u6cd5\u3002<\/li>\n<\/ul>\n
    \u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5<\/strong>\uff0c\u6839\u636e\u5177\u4f53\u9700\u6c42\u548c\u6570\u636e\u7279\u70b9\u9009\u62e9\u6700\u4f18\u89e3\u3002\u5728\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u65f6\uff0c\u8003\u8651\u6027\u80fd\u4f18\u5316\u548c\u5e76\u884c\u5904\u7406\u4e5f\u975e\u5e38\u91cd\u8981\u3002\u5e0c\u671b\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u80fd\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u638c\u63e1Python\u4e2d\u63d0\u53d6\u5217\u8868\u5173\u952e\u8bcd\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u5728Python\u4e2d\u4ece\u5217\u8868\u4e2d\u63d0\u53d6\u7279\u5b9a\u5173\u952e\u8bcd\uff1f<\/strong>
    \u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u6216\u5faa\u73af\u7ed3\u6784\u6765\u63d0\u53d6\u7279\u5b9a\u5173\u952e\u8bcd\u3002\u9996\u5148\uff0c\u5b9a\u4e49\u4e00\u4e2a\u5305\u542b\u591a\u4e2a\u5b57\u7b26\u4e32\u7684\u5217\u8868\uff0c\u7136\u540e\u4f7f\u7528\u6761\u4ef6\u8bed\u53e5\u68c0\u67e5\u6bcf\u4e2a\u5b57\u7b26\u4e32\u4e2d\u662f\u5426\u5305\u542b\u6240\u9700\u7684\u5173\u952e\u8bcd\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n
    keywords = ["python", "\u6570\u636e", "\u63d0\u53d6", "\u5173\u952e\u8bcd"]\ntext_list = ["python \u662f\u4e00\u79cd\u7f16\u7a0b\u8bed\u8a00", "\u6570\u636e\u5206\u6790\u662f\u6570\u636e\u79d1\u5b66\u7684\u91cd\u8981\u90e8\u5206", "\u5982\u4f55\u63d0\u53d6\u5173\u952e\u8bcd"]\n\nextracted_keywords = [text for text in text_list if any(keyword in text for keyword in keywords)]\nprint(extracted_keywords)\n<\/code><\/pre>\n
    \u8be5\u4ee3\u7801\u5c06\u8fd4\u56de\u5305\u542b\u5173\u952e\u8bcd\u7684\u6240\u6709\u6587\u672c\u3002<\/p>\n
    \u6709\u54ea\u4e9b\u5de5\u5177\u6216\u5e93\u53ef\u4ee5\u5e2e\u52a9\u63d0\u53d6\u5217\u8868\u4e2d\u7684\u5173\u952e\u8bcd\uff1f<\/strong>
    Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u5e93\u6765\u5e2e\u52a9\u63d0\u53d6\u5173\u952e\u8bcd\u3002\u5176\u4e2d\uff0cre<\/code>\u5e93\u53ef\u4ee5\u7528\u4e8e\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\uff0cnltk<\/code>\u5e93\u9002\u5408\u8fdb\u884c\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff0csklearn<\/code>\u5e93\u5219\u652f\u6301\u7279\u5f81\u63d0\u53d6\u548c\u6587\u672c\u5206\u6790\u3002\u4f7f\u7528\u8fd9\u4e9b\u5de5\u5177\uff0c\u60a8\u53ef\u4ee5\u66f4\u9ad8\u6548\u5730\u63d0\u53d6\u548c\u5904\u7406\u5217\u8868\u4e2d\u7684\u5173\u952e\u8bcd\u3002<\/p>\n
    \u5982\u4f55\u63d0\u9ad8\u5173\u952e\u8bcd\u63d0\u53d6\u7684\u51c6\u786e\u6027\uff1f<\/strong>
    \u4e3a\u4e86\u63d0\u9ad8\u5173\u952e\u8bcd\u63d0\u53d6\u7684\u51c6\u786e\u6027\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u6587\u672c\u9884\u5904\u7406\u6280\u672f\uff0c\u5982\u53bb\u9664\u505c\u7528\u8bcd\u3001\u8bcd\u5e72\u63d0\u53d6\u548c\u8bcd\u5f62\u8fd8\u539f\u3002\u8fd9\u4e9b\u6b65\u9aa4\u53ef\u4ee5\u5e2e\u52a9\u51cf\u5c11\u566a\u58f0\uff0c\u63d0\u9ad8\u5173\u952e\u8bcd\u63d0\u53d6\u7684\u8d28\u91cf\u3002\u6b64\u5916\uff0c\u4f7f\u7528TF-IDF\uff08\u8bcd\u9891-\u9006\u6587\u6863\u9891\u7387\uff09\u7b97\u6cd5\u53ef\u4ee5\u66f4\u597d\u5730\u8861\u91cf\u5173\u952e\u8bcd\u7684\u91cd\u8981\u6027\uff0c\u4ece\u800c\u4f18\u5316\u63d0\u53d6\u7ed3\u679c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u63d0\u53d6\u5217\u8868\u4e2d\u7684\u5173\u952e\u8bcd\u6709\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u4f7f\u7528NLP\u5e93\u7b49\u3002\u4f60\u53ef\u4ee5\u6839\u636e\u5177 […]","protected":false},"author":3,"featured_media":1076192,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1076185"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1076185"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1076185\/revisions"}],"predecessor-version":[{"id":1076193,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1076185\/revisions\/1076193"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1076192"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1076185"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1076185"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1076185"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}