{"id":1162073,"date":"2025-01-13T19:24:07","date_gmt":"2025-01-13T11:24:07","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1162073.html"},"modified":"2025-01-13T19:24:10","modified_gmt":"2025-01-13T11:24:10","slug":"python%e5%a6%82%e4%bd%95%e5%a4%84%e7%90%86%e4%b8%bb%e9%a2%98%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1162073.html","title":{"rendered":"python\u5982\u4f55\u5904\u7406\u4e3b\u9898\u6a21\u578b"},"content":{"rendered":"

\"python\u5982\u4f55\u5904\u7406\u4e3b\u9898\u6a21\u578b\"<\/p>\n

Python\u5904\u7406\u4e3b\u9898\u6a21\u578b\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528gensim\u5e93\u3001\u4f7f\u7528scikit-learn\u5e93\u3001\u4f7f\u7528spaCy\u5e93\u3001\u7ed3\u5408LDA\u7b97\u6cd5\u4e0eNMF\u7b97\u6cd5<\/strong>\u3002\u5176\u4e2d\uff0c\u4f7f\u7528gensim\u5e93\u662f\u6700\u5e38\u89c1\u7684\u65b9\u6cd5\u4e4b\u4e00\u3002Gensim\u5e93\u662f\u4e00\u6b3e\u4e13\u95e8\u7528\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684Python\u5e93\uff0c\u7279\u522b\u64c5\u957f\u5904\u7406\u4e3b\u9898\u6a21\u578b\u3002\u901a\u8fc7Gensim\u5e93\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u4f7f\u7528LDA\uff08Latent Dirichlet Allocation\uff09\u7b97\u6cd5\u6765\u63d0\u53d6\u6587\u6863\u4e2d\u7684\u4e3b\u9898\u3002\u4e0b\u9762\u5c31\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528gensim\u5e93\u6765\u5904\u7406\u4e3b\u9898\u6a21\u578b\u3002<\/p>\n<\/p>\n

\u4e00\u3001Gensim\u5e93\u7684\u5b89\u88c5\u4e0e\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n

1\u3001\u5b89\u88c5Gensim\u5e93<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5Gensim\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install gensim<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n
\u5728\u4f7f\u7528Gensim\u8fdb\u884c\u4e3b\u9898\u6a21\u578b\u5904\u7406\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165\u4e00\u4e9b\u5fc5\u8981\u7684\u5e93\uff0c\u5305\u62ecgensim\u3001nltk\u3001\u4ee5\u53ca\u4e00\u4e9b\u6587\u672c\u9884\u5904\u7406\u5e93\uff1a<\/p>\n<\/p>\n
import gensim<\/p>\n
from gensim import corpora<\/p>\n
from nltk.corpus import stopwords<\/p>\n
from nltk.tokenize import word_tokenize<\/p>\n
import string<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u6570\u636e\u9884\u5904\u7406<\/h3>\n<\/p>\n
\u6570\u636e\u9884\u5904\u7406\u662f\u4e3b\u9898\u6a21\u578b\u5904\u7406\u7684\u91cd\u8981\u6b65\u9aa4\u3002\u6211\u4eec\u9700\u8981\u5bf9\u6587\u672c\u8fdb\u884c\u5206\u8bcd\u3001\u53bb\u9664\u505c\u7528\u8bcd\u3001\u53bb\u9664\u6807\u70b9\u7b26\u53f7\u7b49\u64cd\u4f5c\u3002<\/p>\n<\/p>\n
1\u3001\u52a0\u8f7d\u6570\u636e<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u52a0\u8f7d\u6570\u636e\u3002\u8fd9\u91cc\u6211\u4eec\u4ee5\u4e00\u4e2a\u7b80\u5355\u7684\u6587\u672c\u5217\u8868\u4e3a\u4f8b\uff1a<\/p>\n<\/p>\n
documents = [<\/p>\n
    "Machine learning is great.",<\/p>\n
    "Natural language processing is a complex field.",<\/p>\n
    "Deep learning models are powerful.",<\/p>\n
    "Text mining involves extracting information from text."<\/p>\n
]<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5206\u8bcd\u4e0e\u53bb\u9664\u505c\u7528\u8bcd<\/h4>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5bf9\u6587\u672c\u8fdb\u884c\u5206\u8bcd\uff0c\u5e76\u53bb\u9664\u505c\u7528\u8bcd\u548c\u6807\u70b9\u7b26\u53f7\uff1a<\/p>\n<\/p>\n
stop_words = set(stopwords.words('english'))<\/p>\n
punctuations = set(string.punctuation)<\/p>\n
def preprocess(text):<\/p>\n
    tokens = word_tokenize(text.lower())<\/p>\n
    tokens = [word for word in tokens if word not in stop_words and word not in punctuations]<\/p>\n
    return tokens<\/p>\n
texts = [preprocess(document) for document in documents]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u6784\u5efa\u8bcd\u5178\u4e0e\u8bed\u6599\u5e93<\/h3>\n<\/p>\n
\u5728\u5b8c\u6210\u6570\u636e\u9884\u5904\u7406\u4e4b\u540e\uff0c\u6211\u4eec\u9700\u8981\u6784\u5efa\u8bcd\u5178\u548c\u8bed\u6599\u5e93\u3002\u8bcd\u5178\u662f\u5c06\u6bcf\u4e2a\u5355\u8bcd\u6620\u5c04\u5230\u4e00\u4e2a\u552f\u4e00\u7684ID\uff0c\u8bed\u6599\u5e93\u662f\u5c06\u6bcf\u4e2a\u6587\u6863\u8f6c\u6362\u6210\u5355\u8bcdID\u53ca\u5176\u51fa\u73b0\u9891\u7387\u7684\u8868\u793a\u3002<\/p>\n<\/p>\n
1\u3001\u6784\u5efa\u8bcd\u5178<\/h4>\n<\/p>\n
\u4f7f\u7528gensim.corpora.Dictionary\u6765\u6784\u5efa\u8bcd\u5178\uff1a<\/p>\n<\/p>\n
dictionary = corpora.Dictionary(texts)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u6784\u5efa\u8bed\u6599\u5e93<\/h4>\n<\/p>\n
\u4f7f\u7528\u8bcd\u5178\u5c06\u6587\u672c\u8f6c\u6362\u4e3a\u5411\u91cf\u8868\u793a\uff1a<\/p>\n<\/p>\n
corpus = [dictionary.doc2bow(text) for text in texts]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u8bad\u7ec3LDA\u6a21\u578b<\/h3>\n<\/p>\n
\u4f7f\u7528Gensim\u5e93\u4e2d\u7684LdaModel\u6765\u8bad\u7ec3LDA\u6a21\u578b\uff1a<\/p>\n<\/p>\n
lda_model = gensim.models.LdaModel(corpus, num_topics=3, id2word=dictionary, passes=15)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5176\u4e2d\uff0cnum_topics\u8868\u793a\u4e3b\u9898\u7684\u6570\u91cf\uff0cpasses\u8868\u793a\u8bad\u7ec3\u7684\u8fed\u4ee3\u6b21\u6570\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u67e5\u770b\u4e3b\u9898<\/h3>\n<\/p>\n
\u8bad\u7ec3\u5b8c\u6210\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u67e5\u770b\u6bcf\u4e2a\u4e3b\u9898\u53ca\u5176\u5bf9\u5e94\u7684\u5355\u8bcd\uff1a<\/p>\n<\/p>\n
for idx, topic in lda_model.print_topics(-1):<\/p>\n
    print(f"Topic: {idx} \\nWords: {topic}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u63a8\u65ad\u65b0\u6587\u6863\u7684\u4e3b\u9898\u5206\u5e03<\/h3>\n<\/p>\n
\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528\u8bad\u7ec3\u597d\u7684LDA\u6a21\u578b\u6765\u63a8\u65ad\u65b0\u6587\u6863\u7684\u4e3b\u9898\u5206\u5e03\uff1a<\/p>\n<\/p>\n
new_document = "Machine learning and natural language processing are closely related."<\/p>\n
new_bow = dictionary.doc2bow(preprocess(new_document))<\/p>\n
print(lda_model.get_document_topics(new_bow))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u4f7f\u7528scikit-learn\u5e93\u5904\u7406\u4e3b\u9898\u6a21\u578b<\/h3>\n<\/p>\n
\u9664\u4e86Gensim\u5e93\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528scikit-learn\u5e93\u6765\u5904\u7406\u4e3b\u9898\u6a21\u578b\u3002Scikit-learn\u5e93\u63d0\u4f9b\u4e86Latent Dirichlet Allocation (LDA)\u548cNon-negative Matrix Factorization (NMF)\u4e24\u79cd\u7b97\u6cd5\u6765\u8fdb\u884c\u4e3b\u9898\u6a21\u578b\u5904\u7406\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5scikit-learn\u5e93<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5scikit-learn\u5e93\uff1a<\/p>\n<\/p>\n
pip install scikit-learn<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer<\/p>\n
from sklearn.decomposition import LatentDirichletAllocation, NMF<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u6587\u672c\u9884\u5904\u7406<\/h4>\n<\/p>\n
\u4e0e\u4f7f\u7528Gensim\u5e93\u65f6\u7c7b\u4f3c\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u6587\u672c\u8fdb\u884c\u9884\u5904\u7406\u3002\u8fd9\u91cc\u6211\u4eec\u4f7f\u7528CountVectorizer\u6216TfidfVectorizer\u8fdb\u884c\u6587\u672c\u5411\u91cf\u5316\uff1a<\/p>\n<\/p>\n
vectorizer = CountVectorizer(stop_words='english')<\/p>\n
X = vectorizer.fit_transform(documents)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u8bad\u7ec3LDA\u6a21\u578b<\/h4>\n<\/p>\n
\u4f7f\u7528LatentDirichletAllocation\u6765\u8bad\u7ec3LDA\u6a21\u578b\uff1a<\/p>\n<\/p>\n
lda = LatentDirichletAllocation(n_components=3, random_state=0)<\/p>\n
lda.fit(X)<\/p>\n
<\/code><\/pre>\n<\/p>\n
5\u3001\u67e5\u770b\u4e3b\u9898<\/h4>\n<\/p>\n
\u6211\u4eec\u53ef\u4ee5\u67e5\u770b\u6bcf\u4e2a\u4e3b\u9898\u53ca\u5176\u5bf9\u5e94\u7684\u5355\u8bcd\uff1a<\/p>\n<\/p>\n
def print_topics(model, vectorizer, top_n=10):<\/p>\n
    for idx, topic in enumerate(model.components_):<\/p>\n
        print(f"Topic {idx}:")<\/p>\n
        print([(vectorizer.get_feature_names()[i], topic[i])<\/p>\n
                for i in topic.argsort()[:-top_n - 1:-1]])<\/p>\n
print_topics(lda, vectorizer)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u7ed3\u5408LDA\u548cNMF\u7b97\u6cd5<\/h3>\n<\/p>\n
\u6211\u4eec\u8fd8\u53ef\u4ee5\u7ed3\u5408LDA\u548cNMF\u7b97\u6cd5\u6765\u8fdb\u884c\u66f4\u590d\u6742\u7684\u4e3b\u9898\u6a21\u578b\u5904\u7406\u3002\u4f8b\u5982\uff0c\u6211\u4eec\u53ef\u4ee5\u5148\u4f7f\u7528TF-IDF\u5411\u91cf\u5316\u6587\u672c\uff0c\u7136\u540e\u4f7f\u7528NMF\u7b97\u6cd5\u6765\u63d0\u53d6\u4e3b\u9898\uff1a<\/p>\n<\/p>\n
1\u3001\u4f7f\u7528TF-IDF\u5411\u91cf\u5316\u6587\u672c<\/h4>\n<\/p>\n
tfidf_vectorizer = TfidfVectorizer(stop_words='english')<\/p>\n
X_tfidf = tfidf_vectorizer.fit_transform(documents)<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4f7f\u7528NMF\u7b97\u6cd5\u63d0\u53d6\u4e3b\u9898<\/h4>\n<\/p>\n
nmf = NMF(n_components=3, random_state=0)<\/p>\n
nmf.fit(X_tfidf)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u67e5\u770b\u4e3b\u9898<\/h4>\n<\/p>\n
print_topics(nmf, tfidf_vectorizer)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e5d\u3001\u603b\u7ed3\u4e0e\u5c55\u671b<\/h3>\n<\/p>\n
\u4e3b\u9898\u6a21\u578b\u5904\u7406\u662f\u81ea\u7136\u8bed\u8a00\u5904\u7406\u4e2d\u7684\u4e00\u4e2a\u91cd\u8981\u4efb\u52a1\uff0c\u901a\u8fc7\u4e3b\u9898\u6a21\u578b\uff0c\u6211\u4eec\u53ef\u4ee5\u4ece\u5927\u91cf\u7684\u6587\u6863\u4e2d\u63d0\u53d6\u51fa\u4e3b\u8981\u7684\u4e3b\u9898\uff0c\u4ece\u800c\u66f4\u597d\u5730\u7406\u89e3\u548c\u5206\u6790\u6587\u672c\u6570\u636e\u3002\u672c\u6587\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528Python\u4e2d\u7684Gensim\u5e93\u548cscikit-learn\u5e93\u6765\u5904\u7406\u4e3b\u9898\u6a21\u578b\uff0c\u8be6\u7ec6\u8bb2\u89e3\u4e86\u4ece\u6570\u636e\u9884\u5904\u7406\u3001\u6784\u5efa\u8bcd\u5178\u4e0e\u8bed\u6599\u5e93\u3001\u8bad\u7ec3LDA\u6a21\u578b\u5230\u67e5\u770b\u4e3b\u9898\u7684\u5168\u8fc7\u7a0b\u3002\u6b64\u5916\uff0c\u8fd8\u4ecb\u7ecd\u4e86\u7ed3\u5408LDA\u548cNMF\u7b97\u6cd5\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u7684\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u7b97\u6cd5\u548c\u5de5\u5177\u3002\u4f8b\u5982\uff0c\u5bf9\u4e8e\u8f83\u5927\u7684\u6570\u636e\u96c6\uff0cGensim\u5e93\u7684LDA\u7b97\u6cd5\u53ef\u80fd\u66f4\u4e3a\u5408\u9002\uff0c\u800c\u5bf9\u4e8e\u9700\u8981\u66f4\u9ad8\u7ef4\u5ea6\u7279\u5f81\u7684\u6587\u672c\u6570\u636e\uff0cNMF\u7b97\u6cd5\u53ef\u80fd\u4f1a\u8868\u73b0\u66f4\u597d\u3002\u901a\u8fc7\u4e0d\u65ad\u5c1d\u8bd5\u548c\u4f18\u5316\uff0c\u6211\u4eec\u53ef\u4ee5\u627e\u5230\u6700\u9002\u5408\u81ea\u5df1\u6570\u636e\u7684\u4e3b\u9898\u6a21\u578b\u5904\u7406\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
\u603b\u4e4b\uff0cPython\u4e3a\u6211\u4eec\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5de5\u5177\u548c\u5e93\uff0c\u4f7f\u5f97\u4e3b\u9898\u6a21\u578b\u5904\u7406\u53d8\u5f97\u66f4\u52a0\u7b80\u5355\u548c\u9ad8\u6548\u3002\u5e0c\u671b\u672c\u6587\u7684\u4ecb\u7ecd\u80fd\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff0c\u795d\u60a8\u5728\u4e3b\u9898\u6a21\u578b\u5904\u7406\u7684\u9053\u8def\u4e0a\u53d6\u5f97\u66f4\u5927\u7684\u8fdb\u5c55\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u4e3b\u9898\u6a21\u578b\u662f\u4ec0\u4e48\uff0c\u5b83\u5728\u6570\u636e\u5206\u6790\u4e2d\u7684\u4f5c\u7528\u662f\u4ec0\u4e48\uff1f<\/strong>
\u4e3b\u9898\u6a21\u578b\u662f\u4e00\u79cd\u6587\u672c\u6316\u6398\u6280\u672f\uff0c\u65e8\u5728\u4ece\u5927\u91cf\u6587\u6863\u4e2d\u53d1\u73b0\u6f5c\u5728\u7684\u4e3b\u9898\u6216\u9690\u85cf\u7684\u7ed3\u6784\u3002\u5b83\u80fd\u591f\u5e2e\u52a9\u5206\u6790\u5e08\u7406\u89e3\u548c\u603b\u7ed3\u6587\u672c\u6570\u636e\u7684\u4e3b\u8981\u5185\u5bb9\uff0c\u8bc6\u522b\u4e0d\u540c\u6587\u6863\u4e4b\u95f4\u7684\u76f8\u4f3c\u6027\uff0c\u5e76\u4e3a\u4fe1\u606f\u68c0\u7d22\u63d0\u4f9b\u652f\u6301\u3002\u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u4e3b\u9898\u6a21\u578b\u53ef\u4ee5\u7528\u4e8e\u793e\u4ea4\u5a92\u4f53\u5206\u6790\u3001\u5ba2\u6237\u53cd\u9988\u6574\u7406\u3001\u6587\u732e\u7efc\u8ff0\u7b49\u591a\u4e2a\u9886\u57df\u3002<\/p>\n
\u5728Python\u4e2d\u6709\u54ea\u4e9b\u5e93\u53ef\u4ee5\u7528\u4e8e\u6784\u5efa\u4e3b\u9898\u6a21\u578b\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u6709\u591a\u4e2a\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6784\u5efa\u4e3b\u9898\u6a21\u578b\u3002\u5176\u4e2d\u8f83\u4e3a\u5e38\u7528\u7684\u5305\u62ecGensim\u3001Scikit-learn\u548cspaCy\u3002Gensim\u63d0\u4f9b\u4e86\u9ad8\u6548\u7684LDA\uff08Latent Dirichlet Allocation\uff09\u5b9e\u73b0\uff0c\u9002\u5408\u5904\u7406\u5927\u89c4\u6a21\u6587\u672c\u6570\u636e\u3002Scikit-learn\u5219\u63d0\u4f9b\u4e86\u591a\u79cd\u6a21\u578b\u548c\u5de5\u5177\uff0c\u4fbf\u4e8e\u7528\u6237\u8fdb\u884c\u673a\u5668\u5b66\u4e60<\/a>\u548c\u6570\u636e\u6316\u6398\u3002spaCy\u5219\u4ee5\u5176\u9ad8\u6548\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u529f\u80fd\u800c\u8457\u79f0\uff0c\u9002\u5408\u8fdb\u884c\u6587\u672c\u9884\u5904\u7406\u548c\u7279\u5f81\u63d0\u53d6\u3002<\/p>\n
\u5982\u4f55\u51c6\u5907\u6587\u672c\u6570\u636e\u4ee5\u4fbf\u8fdb\u884c\u4e3b\u9898\u5efa\u6a21\uff1f<\/strong>
\u5728\u8fdb\u884c\u4e3b\u9898\u5efa\u6a21\u4e4b\u524d\uff0c\u6587\u672c\u6570\u636e\u9700\u8981\u7ecf\u8fc7\u4e00\u7cfb\u5217\u9884\u5904\u7406\u6b65\u9aa4\u3002\u9996\u5148\uff0c\u5e94\u6e05\u6d17\u6587\u672c\u6570\u636e\uff0c\u5305\u62ec\u53bb\u9664\u6807\u70b9\u7b26\u53f7\u3001\u6570\u5b57\u548c\u505c\u7528\u8bcd\u3002\u63a5\u4e0b\u6765\uff0c\u8fdb\u884c\u8bcd\u5e72\u63d0\u53d6\u6216\u8bcd\u5f62\u8fd8\u539f\uff0c\u4ee5\u4fbf\u7edf\u4e00\u8bcd\u8bed\u5f62\u5f0f\u3002\u6b64\u5916\uff0c\u53ef\u4ee5\u4f7f\u7528TF-IDF\uff08Term Frequency-Inverse Document Frequency\uff09\u6216\u8bcd\u888b\u6a21\u578b\u5c06\u6587\u672c\u8f6c\u6362\u4e3a\u6570\u503c\u7279\u5f81\uff0c\u8fd9\u6709\u52a9\u4e8e\u6a21\u578b\u7684\u6709\u6548\u8bad\u7ec3\u3002\u8fd9\u4e9b\u9884\u5904\u7406\u6b65\u9aa4\u5bf9\u63d0\u9ad8\u4e3b\u9898\u6a21\u578b\u7684\u51c6\u786e\u6027\u548c\u53ef\u89e3\u91ca\u6027\u81f3\u5173\u91cd\u8981\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5904\u7406\u4e3b\u9898\u6a21\u578b\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528gensim\u5e93\u3001\u4f7f\u7528scikit-learn\u5e93\u3001\u4f7f\u7528spaCy\u5e93\u3001\u7ed3 […]","protected":false},"author":3,"featured_media":1162081,"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\/1162073"}],"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=1162073"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1162073\/revisions"}],"predecessor-version":[{"id":1162082,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1162073\/revisions\/1162082"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1162081"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1162073"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1162073"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1162073"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}