{"id":1175908,"date":"2025-01-15T17:38:17","date_gmt":"2025-01-15T09:38:17","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1175908.html"},"modified":"2025-01-15T17:38:19","modified_gmt":"2025-01-15T09:38:19","slug":"%e5%a6%82%e4%bd%95%e5%8e%bb%e6%8e%89python%e7%9a%84%e5%81%9c%e7%94%a8%e8%af%8d","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1175908.html","title":{"rendered":"\u5982\u4f55\u53bb\u6389python\u7684\u505c\u7528\u8bcd"},"content":{"rendered":"

\"\u5982\u4f55\u53bb\u6389python\u7684\u505c\u7528\u8bcd\"<\/p>\n

\u4f7f\u7528NLTK\u5e93\u3001\u4f7f\u7528SpaCy\u5e93\u3001\u4f7f\u7528gensim\u5e93\u3001\u4f7f\u7528\u81ea\u5b9a\u4e49\u505c\u7528\u8bcd\u5217\u8868<\/strong>\u3002\u5176\u4e2d\uff0c\u4f7f\u7528NLTK\u5e93\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u7b80\u4fbf\u7684\u65b9\u6cd5\u3002NLTK\uff08Natural Language Toolkit\uff09\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684Python\u5e93\uff0c\u53ef\u4ee5\u7528\u4e8e\u5904\u7406\u548c\u5206\u6790\u81ea\u7136\u8bed\u8a00\u6570\u636e\u3002\u901a\u8fc7NLTK\u5e93\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u53bb\u9664\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5\u5e76\u5bfc\u5165NLTK\u5e93\uff0c\u7136\u540e\u4e0b\u8f7d\u505c\u7528\u8bcd\u5217\u8868\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u6587\u672c\u8fdb\u884c\u5206\u8bcd\u64cd\u4f5c\uff0c\u5e76\u53bb\u9664\u505c\u7528\u8bcd\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u7684\u6b65\u9aa4\u3002<\/p>\n<\/p>\n

import nltk<\/p>\n
from nltk.corpus import stopwords<\/p>\n
from nltk.tokenize import word_tokenize<\/p>\n
\u4e0b\u8f7d\u505c\u7528\u8bcd\u5217\u8868<\/strong><\/h2>\n
nltk.download('stopwords')<\/p>\n
nltk.download('punkt')<\/p>\n
\u83b7\u53d6\u82f1\u8bed\u7684\u505c\u7528\u8bcd\u5217\u8868<\/strong><\/h2>\n
stop_words = set(stopwords.words('english'))<\/p>\n
\u793a\u4f8b\u6587\u672c<\/strong><\/h2>\n
text = "This is a sample sentence, showing off the stop words filtration."<\/p>\n
\u5206\u8bcd<\/strong><\/h2>\n
word_tokens = word_tokenize(text)<\/p>\n
\u53bb\u9664\u505c\u7528\u8bcd<\/strong><\/h2>\n
filtered_sentence = [w for w in word_tokens if not w.lower() in stop_words]<\/p>\n
print(filtered_sentence)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86\u6240\u9700\u7684NLTK\u6a21\u5757\uff0c\u5e76\u4e0b\u8f7d\u4e86\u505c\u7528\u8bcd\u5217\u8868\u548cpunkt\u5206\u8bcd\u5668\u3002\u7136\u540e\uff0c\u6211\u4eec\u5b9a\u4e49\u4e86\u4e00\u6bb5\u793a\u4f8b\u6587\u672c\uff0c\u5e76\u5c06\u5176\u8fdb\u884c\u5206\u8bcd\u64cd\u4f5c\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u901a\u8fc7\u5217\u8868\u63a8\u5bfc\u5f0f\u5c06\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u53bb\u9664\uff0c\u5f97\u5230\u8fc7\u6ee4\u540e\u7684\u53e5\u5b50\u3002<\/p>\n<\/p>\n
\u4e00\u3001\u4f7f\u7528NLTK\u5e93\u53bb\u9664\u505c\u7528\u8bcd<\/h3>\n<\/p>\n
NLTK\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5e93\u4e4b\u4e00\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\u548c\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u53bb\u9664\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5\u548c\u5bfc\u5165NLTK\u5e93<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528NLTK\u5e93\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u5b89\u88c5NLTK\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install nltk<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165NLTK\u5e93\uff1a<\/p>\n<\/p>\n
import nltk<\/p>\n
from nltk.corpus import stopwords<\/p>\n
from nltk.tokenize import word_tokenize<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4e0b\u8f7d\u505c\u7528\u8bcd\u5217\u8868<\/h4>\n<\/p>\n
NLTK\u5e93\u63d0\u4f9b\u4e86\u591a\u79cd\u8bed\u8a00\u7684\u505c\u7528\u8bcd\u5217\u8868\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u9700\u8981\u4e0b\u8f7d\u76f8\u5e94\u7684\u505c\u7528\u8bcd\u5217\u8868\u3002\u4ee5\u4e0b\u662f\u4e0b\u8f7d\u82f1\u8bed\u505c\u7528\u8bcd\u5217\u8868\u7684\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
nltk.download('stopwords')<\/p>\n
nltk.download('punkt')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u83b7\u53d6\u505c\u7528\u8bcd\u5217\u8868<\/h4>\n<\/p>\n
\u4e0b\u8f7d\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u83b7\u53d6\u505c\u7528\u8bcd\u5217\u8868\uff1a<\/p>\n<\/p>\n
stop_words = set(stopwords.words('english'))<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u5206\u8bcd\u64cd\u4f5c<\/h4>\n<\/p>\n
\u5728\u53bb\u9664\u505c\u7528\u8bcd\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u5c06\u6587\u672c\u8fdb\u884c\u5206\u8bcd\u64cd\u4f5c\u3002\u53ef\u4ee5\u4f7f\u7528NLTK\u5e93\u63d0\u4f9b\u7684word_tokenize\u51fd\u6570\u8fdb\u884c\u5206\u8bcd\uff1a<\/p>\n<\/p>\n
text = "This is a sample sentence, showing off the stop words filtration."<\/p>\n
word_tokens = word_tokenize(text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
5\u3001\u53bb\u9664\u505c\u7528\u8bcd<\/h4>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5217\u8868\u63a8\u5bfc\u5f0f\u5c06\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u53bb\u9664\uff0c\u5f97\u5230\u8fc7\u6ee4\u540e\u7684\u53e5\u5b50\uff1a<\/p>\n<\/p>\n
filtered_sentence = [w for w in word_tokens if not w.lower() in stop_words]<\/p>\n
print(filtered_sentence)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528SpaCy\u5e93\u53bb\u9664\u505c\u7528\u8bcd<\/h3>\n<\/p>\n
\u9664\u4e86NLTK\u5e93\uff0cSpaCy\u4e5f\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5e93\u3002\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u53bb\u9664\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5\u548c\u5bfc\u5165SpaCy\u5e93<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528SpaCy\u5e93\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u5b89\u88c5SpaCy\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install spacy<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u8fd8\u9700\u8981\u4e0b\u8f7dSpaCy\u7684\u6a21\u578b\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u4e0b\u8f7d\uff1a<\/p>\n<\/p>\n
python -m spacy download en_core_web_sm<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u548c\u4e0b\u8f7d\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165SpaCy\u5e93\uff1a<\/p>\n<\/p>\n
import spacy<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u52a0\u8f7d\u6a21\u578b<\/h4>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u52a0\u8f7dSpaCy\u7684\u6a21\u578b\uff1a<\/p>\n<\/p>\n
nlp = spacy.load('en_core_web_sm')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u53bb\u9664\u505c\u7528\u8bcd<\/h4>\n<\/p>\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528SpaCy\u5e93\u63d0\u4f9b\u7684\u505c\u7528\u8bcd\u5217\u8868\uff0c\u7ed3\u5408\u6a21\u578b\u5bf9\u6587\u672c\u8fdb\u884c\u5904\u7406\uff0c\u5e76\u53bb\u9664\u505c\u7528\u8bcd\uff1a<\/p>\n<\/p>\n
text = "This is a sample sentence, showing off the stop words filtration."<\/p>\n
doc = nlp(text)<\/p>\n
filtered_sentence = [token.text for token in doc if not token.is_stop]<\/p>\n
print(filtered_sentence)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528gensim\u5e93\u53bb\u9664\u505c\u7528\u8bcd<\/h3>\n<\/p>\n
gensim\u662f\u53e6\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u53bb\u9664\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5\u548c\u5bfc\u5165gensim\u5e93<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528gensim\u5e93\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u5b89\u88c5gensim\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install gensim<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165gensim\u5e93\uff1a<\/p>\n<\/p>\n
from gensim.parsing.preprocessing import remove_stopwords<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u53bb\u9664\u505c\u7528\u8bcd<\/h4>\n<\/p>\n
gensim\u5e93\u63d0\u4f9b\u4e86remove_stopwords\u51fd\u6570\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u53bb\u9664\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\uff1a<\/p>\n<\/p>\n
text = "This is a sample sentence, showing off the stop words filtration."<\/p>\n
filtered_sentence = remove_stopwords(text)<\/p>\n
print(filtered_sentence)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4f7f\u7528\u81ea\u5b9a\u4e49\u505c\u7528\u8bcd\u5217\u8868\u53bb\u9664\u505c\u7528\u8bcd<\/h3>\n<\/p>\n
\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u6211\u4eec\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u81ea\u5b9a\u4e49\u7684\u505c\u7528\u8bcd\u5217\u8868\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528\u81ea\u5b9a\u4e49\u505c\u7528\u8bcd\u5217\u8868\u53bb\u9664\u505c\u7528\u8bcd\u7684\u793a\u4f8b\u4ee3\u7801\u3002<\/p>\n<\/p>\n
1\u3001\u5b9a\u4e49\u81ea\u5b9a\u4e49\u505c\u7528\u8bcd\u5217\u8868<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b9a\u4e49\u4e00\u4e2a\u81ea\u5b9a\u4e49\u7684\u505c\u7528\u8bcd\u5217\u8868\uff1a<\/p>\n<\/p>\n
custom_stop_words = {"is", "a", "the"}<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5206\u8bcd\u64cd\u4f5c<\/h4>\n<\/p>\n
\u4e0e\u4e4b\u524d\u7684\u65b9\u6cd5\u4e00\u6837\uff0c\u6211\u4eec\u9700\u8981\u5148\u5c06\u6587\u672c\u8fdb\u884c\u5206\u8bcd\u64cd\u4f5c\uff1a<\/p>\n<\/p>\n
text = "This is a sample sentence, showing off the stop words filtration."<\/p>\n
word_tokens = word_tokenize(text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u53bb\u9664\u505c\u7528\u8bcd<\/h4>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5217\u8868\u63a8\u5bfc\u5f0f\u5c06\u6587\u672c\u4e2d\u7684\u505c\u7528\u8bcd\u53bb\u9664\uff0c\u5f97\u5230\u8fc7\u6ee4\u540e\u7684\u53e5\u5b50\uff1a<\/p>\n<\/p>\n
filtered_sentence = [w for w in word_tokens if not w.lower() in custom_stop_words]<\/p>\n
print(filtered_sentence)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u6bd4\u8f83\u4e0d\u540c\u65b9\u6cd5\u7684\u4f18\u7f3a\u70b9<\/h3>\n<\/p>\n
\u5728\u53bb\u9664\u505c\u7528\u8bcd\u65f6\uff0c\u4e0d\u540c\u7684\u65b9\u6cd5\u5404\u6709\u4f18\u7f3a\u70b9\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
1\u3001NLTK\u5e93\u7684\u4f18\u7f3a\u70b9<\/h4>\n<\/p>\n
\u4f18\u70b9\uff1a<\/strong><\/p>\n<\/p>\n