gensim\u306f\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u30bf\u30b9\u30af\u3092\u624b\u8efd\u306b\u5b9f\u88c5\u3067\u304d\u308bPython\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u3053\u306e\u8a18\u4e8b\u3067\u306f\u3001\u521d\u5fc3\u8005\u3067\u3082gensim\u3092\u4f7f\u3044\u3053\u306a\u305b\u308b\u3088\u3046\u306b\u306a\u308b\u305f\u3081\u306e\u57fa\u790e\u77e5\u8b58\u3084Tips\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3084\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306e\u5b9f\u88c5\u65b9\u6cd5\u3001\u4e8b\u524d\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u6d3b\u7528\u65b9\u6cd5\u306a\u3069\u3001\u5b9f\u8df5\u7684\u306a\u5185\u5bb9\u304c\u6e80\u8f09\u3067\u3059\u3002\u30b3\u30fc\u30c9\u30b5\u30f3\u30d7\u30eb\u3092\u4ea4\u3048\u306a\u304c\u3089\u3001gensim\u306e\u9b45\u529b\u3092\u5b58\u5206\u306b\u4f1d\u3048\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u76ee\u6b21 <\/p>\n
gensim\u306f\u3001\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3084\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306b\u7279\u5316\u3057\u305fPython\u306e\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u5927\u898f\u6a21\u306a\u30c6\u30ad\u30b9\u30c8\u30b3\u30fc\u30d1\u30b9\u3092\u52b9\u7387\u7684\u306b\u51e6\u7406\u3067\u304d\u308b\u6700\u9069\u5316\u3055\u308c\u305f\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u63d0\u4f9b\u3057\u3066\u304a\u308a\u3001Latent Dirichlet Allocation (LDA)\u3001Latent Semantic Analysis (LSA)\u3001Doc2Vec\u306a\u3069\u306e\u624b\u6cd5\u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001FastText\u3084word2vec\u306e\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u3092\u8aad\u307f\u8fbc\u3093\u3067\u6d3b\u7528\u3059\u308b\u3053\u3068\u3082\u53ef\u80fd\u3067\u3059\u3002<\/p>\n\n\n\n
gensim\u306e\u5927\u304d\u306a\u7279\u5fb4\u306f\u3001\u30b7\u30f3\u30d7\u30eb\u3067\u76f4\u611f\u7684\u306aAPI\u3092\u5099\u3048\u3066\u3044\u308b\u3053\u3068\u3067\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306e\u8907\u96d1\u306a\u30bf\u30b9\u30af\u3092\u624b\u8efd\u306b\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002\u307e\u305f\u3001\u30e1\u30e2\u30ea\u52b9\u7387\u304c\u9ad8\u304f\u3001\u5927\u898f\u6a21\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u6271\u3046\u3053\u3068\u304c\u3067\u304d\u308b\u307b\u304b\u3001\u4e26\u5217\u51e6\u7406\u306b\u3088\u3063\u3066\u9ad8\u901f\u306b\u52d5\u4f5c\u3057\u307e\u3059\u3002\u3055\u3089\u306b\u3001scikit-learn\u306a\u3069\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u306e\u9023\u643a\u3082\u5bb9\u6613\u3067\u3042\u308b\u305f\u3081\u3001\u69d8\u3005\u306a\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3067\u6d3b\u7528\u3057\u3084\u3059\u3044\u3068\u3044\u3046\u5229\u70b9\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
\u5b9f\u969b\u306e\u30d3\u30b8\u30cd\u30b9\u3084\u7814\u7a76\u306e\u73fe\u5834\u3067\u306f\u3001gensim\u3092\u4f7f\u3063\u3066\u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u306e\u81ea\u52d5\u30ab\u30c6\u30b4\u30ea\u5206\u985e\u3001\u9867\u5ba2\u30ec\u30d3\u30e5\u30fc\u306e\u611f\u60c5\u5206\u6790\u3068\u30c8\u30d4\u30c3\u30af\u62bd\u51fa\u3001\u6587\u66f8\u306e\u985e\u4f3c\u5ea6\u306b\u57fa\u3065\u304f\u63a8\u85a6\u30b7\u30b9\u30c6\u30e0\u306e\u69cb\u7bc9\u3001\u7814\u7a76\u8ad6\u6587\u306e\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3068\u53ef\u8996\u5316\u306a\u3069\u3001\u69d8\u3005\u306a\u30e6\u30fc\u30b9\u30b1\u30fc\u30b9\u3067\u6210\u679c\u3092\u4e0a\u3052\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
\u305d\u308c\u3067\u306f\u3001gensim\u3092\u4f7f\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u307e\u305a\u306f\u3001\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3067gensim\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
!pip install gensim<\/pre>\n\n\n\n\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5b8c\u4e86\u3057\u305f\u3089\u3001\u6b21\u306e\u3088\u3046\u306bgensim\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
import gensim\nfrom gensim import corpora, models, similarities<\/pre>\n\n\n\n\u3053\u308c\u3067\u3001gensim\u306e\u4e3b\u8981\u306a\u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u4f7f\u3046\u6e96\u5099\u304c\u6574\u3044\u307e\u3057\u305f\u3002\u6b21\u7bc0\u4ee5\u964d\u3067\u3001\u5b9f\u969b\u306bgensim\u3092\u4f7f\u3063\u305f\u30b3\u30fc\u30c9\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
gensim\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3068\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9 \u2013 \u521d\u5fc3\u8005\u3067\u3082\u7c21\u5358\u306b\u59cb\u3081\u3089\u308c\u308b<\/h2>\n\n\n\n
gensim\u3092\u4f7f\u3044\u59cb\u3081\u308b\u306b\u306f\u3001\u307e\u305aPython\u74b0\u5883\u306b\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3001pip\u3092\u4f7f\u3063\u3066\u7c21\u5358\u306b\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
!pip install gensim<\/pre>\n\n\n\n\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5b8c\u4e86\u3057\u305f\u3089\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bgensim\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u307e\u3059\u3002\u4e3b\u8981\u306a\u30e2\u30b8\u30e5\u30fc\u30eb\u3068\u3057\u3066\u3001corpora\u3001models\u3001similarities\u3092\u899a\u3048\u3066\u304a\u304f\u3068\u826f\u3044\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
import gensim\nfrom gensim import corpora, models, similarities<\/pre>\n\n\n\n\u6b21\u306b\u3001gensim\u3092\u4f7f\u3063\u305f\u57fa\u672c\u7684\u306a\u6d41\u308c\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002\u4ee5\u4e0b\u306e\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u3067\u306f\u3001\u3044\u304f\u3064\u304b\u306e\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u4f8b\u306b\u3001\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u524d\u51e6\u7406\u304b\u3089\u3001\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3001\u985e\u4f3c\u5ea6\u8a08\u7b97\u307e\u3067\u3092\u884c\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
# \u30b5\u30f3\u30d7\u30eb\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\ndocuments = [\n \"Human machine interface for lab abc computer applications\",\n \"A survey of user opinion of computer system response time\",\n \"The EPS user interface management system\",\n \"System and human system engineering testing of EPS\",\n \"Relation of user perceived response time to error measurement\",\n \"The generation of random binary unordered trees\",\n \"The intersection graph of paths in trees\",\n \"Graph minors IV Widths of trees and well quasi ordering\",\n \"Graph minors A survey\",\n]\n\n# \u524d\u51e6\u7406\uff1a\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u306e\u9664\u53bb\u3068\u30c8\u30fc\u30af\u30f3\u5316\nstop_words = ['for', 'a', 'of', 'the', 'and', 'to', 'in', 'on', 'is']\ntexts = [[word for word in document.lower().split() if word not in stop_words] for document in documents]\n\n# \u5358\u8a9e\u8f9e\u66f8\u306e\u4f5c\u6210\u3068BOW\u8868\u73fe\u3078\u306e\u5909\u63db\ndictionary = corpora.Dictionary(texts)\ncorpus = [dictionary.doc2bow(text) for text in texts]\n\n# TF-IDF\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\ntfidf = models.TfidfModel(corpus)\ncorpus_tfidf = tfidf[corpus]\n\n# LDA\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\nlda_model = models.LdaModel(corpus=corpus_tfidf, id2word=dictionary, num_topics=2)<\/pre>\n\n\n\n\u30b3\u30fc\u30c9\u306e\u6d41\u308c\u3092\u8aac\u660e\u3059\u308b\u3068\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
\n
- \u524d\u51e6\u7406\uff1a\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\uff08\u4e00\u822c\u7684\u3059\u304e\u308b\u5358\u8a9e\uff09\u3092\u9664\u53bb\u3057\u3001\u5404\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u30c8\u30fc\u30af\u30f3\u5316\u3057\u307e\u3059\u3002<\/li>\n\n\n\n
- \u5358\u8a9e\u8f9e\u66f8\u306e\u4f5c\u6210\u3068BOW\uff08Bag of Words\uff09\u8868\u73fe\u3078\u306e\u5909\u63db\uff1a\u5358\u8a9eID\u3068\u51fa\u73fe\u983b\u5ea6\u3092\u8a18\u9332\u3057\u307e\u3059\u3002<\/li>\n\n\n\n
- TF-IDF\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\uff1a\u5358\u8a9e\u306e\u91cd\u8981\u5ea6\u3092\u8003\u616e\u3057\u305f\u30d9\u30af\u30c8\u30eb\u8868\u73fe\u3092\u4f5c\u6210\u3057\u307e\u3059\u3002<\/li>\n\n\n\n
- LDA\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\uff1a\u30c8\u30d4\u30c3\u30af\u5206\u6790\u3092\u884c\u3044\u3001\u5404\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u306e\u30c8\u30d4\u30c3\u30af\u5206\u5e03\u3092\u5f97\u307e\u3059\u3002<\/li>\n<\/ol>\n\n\n\n
\u3053\u306e\u3088\u3046\u306bgensim\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u5c11\u306a\u3044\u30b3\u30fc\u30c9\u91cf\u3067\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306e\u30bf\u30b9\u30af\u3092\u5b9f\u884c\u3067\u304d\u307e\u3059\u3002\u6b21\u7bc0\u4ee5\u964d\u3067\u306f\u3001\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3068\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306e\u8a73\u7d30\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
gensim\u3067\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5 \u2013 LDA\u306b\u3088\u308b\u30c8\u30d4\u30c3\u30af\u62bd\u51fa\u306e\u624b\u9806<\/h2>\n\n\n\n
\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u306f\u3001\u5927\u91cf\u306e\u6587\u66f8\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u304b\u3089\u6f5c\u5728\u7684\u306a\u30c8\u30d4\u30c3\u30af\uff08\u8a71\u984c\uff09\u3092\u767a\u898b\u3059\u308b\u6559\u5e2b\u306a\u3057\u5b66\u7fd2\u306e\u624b\u6cd5\u3067\u3059\u3002\u6587\u66f8\u3092\u7279\u5b9a\u306e\u30c8\u30d4\u30c3\u30af\u306e\u6df7\u5408\u7269\u3068\u3057\u3066\u8868\u73fe\u3057\u3001\u5404\u30c8\u30d4\u30c3\u30af\u3092\u7279\u5fb4\u7684\u306a\u5358\u8a9e\u306e\u78ba\u7387\u5206\u5e03\u3068\u3057\u3066\u8868\u73fe\u3057\u307e\u3059\u3002gensim\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u3053\u306e\u3088\u3046\u306a\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u7c21\u5358\u306b\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u306f\u3001\u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u3084\u9867\u5ba2\u30ec\u30d3\u30e5\u30fc\u306a\u3069\u306e\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u81ea\u52d5\u7684\u306b\u5206\u985e\u30fb\u8981\u7d04\u3059\u308b\u305f\u3081\u306b\u5229\u7528\u3055\u308c\u307e\u3059\u3002\u30de\u30fc\u30b1\u30c6\u30a3\u30f3\u30b0\u306b\u304a\u3051\u308b\u9867\u5ba2\u306e\u95a2\u5fc3\u4e8b\u306e\u628a\u63e1\u3084\u3001\u7814\u7a76\u5206\u91ce\u306b\u304a\u3051\u308b\u6587\u732e\u306e\u6574\u7406\u306a\u3069\u306b\u6d3b\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
gensim\u3067\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5\u3059\u308b\u624b\u9806\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002<\/p>\n\n\n\n
\n
- \u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u524d\u51e6\u7406\uff08\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u3001\u30c8\u30fc\u30af\u30f3\u5316\u3001\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u9664\u53bb\u306a\u3069\uff09<\/li>\n\n\n\n
- \u5358\u8a9e\u8f9e\u66f8\u306e\u4f5c\u6210\u3068BOW\u8868\u73fe\u3078\u306e\u5909\u63db<\/li>\n\n\n\n
- TF-IDF\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\uff08\u30aa\u30d7\u30b7\u30e7\u30f3\uff09<\/li>\n\n\n\n
- LDA\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3068\u30c8\u30d4\u30c3\u30af\u6570\u306e\u8a2d\u5b9a<\/li>\n\n\n\n
- \u30c8\u30d4\u30c3\u30af\u306e\u89e3\u91c8\u3068\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1<\/li>\n<\/ol>\n\n\n\n
\u4ee5\u4e0b\u306f\u3001gensim\u3092\u4f7f\u3063\u305f\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u5b9f\u88c5\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
import gensim\nfrom gensim import corpora, models\n\n# \u524d\u51e6\u7406\u3068BOW\u8868\u73fe\u3078\u306e\u5909\u63db\uff08\u7701\u7565\uff09\n\n# LDA\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\nnum_topics = 5\nlda_model = models.LdaModel(corpus=corpus_tfidf, id2word=dictionary, num_topics=num_topics, passes=20, alpha='auto', eta='auto')\n\n# \u30c8\u30d4\u30c3\u30af\u306e\u89e3\u91c8\nfor topic_id, topic in lda_model.print_topics(num_topics=num_topics, num_words=10):\n print(f\"Topic #{topic_id}: {topic}\")<\/pre>\n\n\n\n\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001
num_topics<\/code>\u3067\u30c8\u30d4\u30c3\u30af\u6570\u3092\u8a2d\u5b9a\u3057\u3001passes<\/code>\u3067\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u53cd\u5fa9\u56de\u6570\u3092\u6307\u5b9a\u3057\u3066\u3044\u307e\u3059\u3002alpha<\/code>\u3068eta<\/code>\u306f\u30c8\u30d4\u30c3\u30af\u5206\u5e03\u3068\u5358\u8a9e\u5206\u5e03\u306e\u4e8b\u524d\u5206\u5e03\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3067\u3001\u2019auto\u2019\u306b\u8a2d\u5b9a\u3059\u308b\u3053\u3068\u3067\u6700\u9069\u5024\u304c\u81ea\u52d5\u7684\u306b\u63a8\u5b9a\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5\u3059\u308b\u969b\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a\u306e\u30b3\u30c4\u3092\u62bc\u3055\u3048\u3066\u304a\u304f\u3068\u826f\u3044\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\n
- num_topics\uff1a\u30c8\u30d4\u30c3\u30af\u6570\u306e\u8a2d\u5b9a\u3002\u8907\u6570\u306e\u5024\u3092\u8a66\u3057\u3066\u3001\u89e3\u91c8\u53ef\u80fd\u3067\u6709\u7528\u306a\u30c8\u30d4\u30c3\u30af\u304c\u5f97\u3089\u308c\u308b\u3082\u306e\u3092\u9078\u3076\u3002<\/li>\n\n\n\n
- passes\uff1a\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u53cd\u5fa9\u56de\u6570\u3002\u5927\u304d\u306a\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3068\u53ce\u675f\u3057\u3084\u3059\u304f\u306a\u308b\u304c\u3001\u8a08\u7b97\u6642\u9593\u304c\u9577\u304f\u306a\u308b\u3002<\/li>\n\n\n\n
- alpha\uff1a\u30c8\u30d4\u30c3\u30af\u5206\u5e03\u306e\u4e8b\u524d\u5206\u5e03\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3002\u5c0f\u3055\u306a\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3068\u3001\u5404\u6587\u66f8\u306b\u542b\u307e\u308c\u308b\u30c8\u30d4\u30c3\u30af\u6570\u304c\u5c11\u306a\u304f\u306a\u308b\u3002<\/li>\n\n\n\n
- eta\uff1a\u5358\u8a9e\u5206\u5e03\u306e\u4e8b\u524d\u5206\u5e03\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3002\u5c0f\u3055\u306a\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3068\u3001\u5404\u30c8\u30d4\u30c3\u30af\u306b\u542b\u307e\u308c\u308b\u5358\u8a9e\u6570\u304c\u5c11\u306a\u304f\u306a\u308b\u3002<\/li>\n<\/ul>\n\n\n\n
gensim\u3092\u4f7f\u3048\u3070\u3001\u5c11\u306a\u3044\u30b3\u30fc\u30c9\u91cf\u3067\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002\u305f\u3060\u3057\u3001\u9069\u5207\u306a\u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a\u3092\u898b\u3064\u3051\u308b\u306b\u306f\u3001\u8a66\u884c\u932f\u8aa4\u304c\u5fc5\u8981\u3067\u3059\u3002\u6b21\u7bc0\u3067\u306f\u3001\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306e\u5b9f\u88c5\u65b9\u6cd5\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
gensim\u3067\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u3092\u5b9f\u88c5 \u2013 Doc2Vec\u306b\u3088\u308b\u6587\u66f8\u57cb\u3081\u8fbc\u307f\u306e\u624b\u6cd5<\/h2>\n\n\n\n
\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306f\u3001\u6587\u66f8\u9593\u306e\u985e\u4f3c\u6027\u3092\u5b9a\u91cf\u7684\u306b\u8a55\u4fa1\u3059\u308b\u624b\u6cd5\u3067\u3059\u3002\u6587\u66f8\u3092\u30d9\u30af\u30c8\u30eb\u8868\u73fe\u306b\u5909\u63db\u3057\u3001\u30d9\u30af\u30c8\u30eb\u9593\u306e\u8ddd\u96e2\uff08\u30b3\u30b5\u30a4\u30f3\u985e\u4f3c\u5ea6\u306a\u3069\uff09\u3092\u8a08\u7b97\u3059\u308b\u3053\u3068\u3067\u985e\u4f3c\u5ea6\u3092\u6c42\u3081\u307e\u3059\u3002gensim\u306eDoc2Vec\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u3053\u306e\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u3092\u7c21\u5358\u306b\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306f\u3001\u63a8\u85a6\u30b7\u30b9\u30c6\u30e0\u306b\u304a\u3051\u308b\u95a2\u9023\u30b3\u30f3\u30c6\u30f3\u30c4\u306e\u63d0\u793a\u3084\u3001\u91cd\u8907\u30b3\u30f3\u30c6\u30f3\u30c4\u306e\u691c\u77e5\u306a\u3069\u306b\u6d3b\u7528\u3055\u308c\u307e\u3059\u3002\u307e\u305f\u3001\u6587\u66f8\u5206\u985e\u3084\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306e\u30bf\u30b9\u30af\u306b\u3082\u5fdc\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n
gensim\u3092\u4f7f\u3063\u3066\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u3092\u5b9f\u88c5\u3059\u308b\u624b\u9806\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\u3002<\/p>\n\n\n\n
\n
- \u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u306e\u524d\u51e6\u7406\uff08\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u3001\u30c8\u30fc\u30af\u30f3\u5316\u3001\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u9664\u53bb\u306a\u3069\uff09<\/li>\n\n\n\n
- Doc2Vec\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\n
\n
- TaggedDocument\u306e\u4f5c\u6210<\/li>\n\n\n\n
- \u30e2\u30c7\u30eb\u306e\u30cf\u30a4\u30d1\u30fc\u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a\uff08vector_size, min_count, epochs\u306a\u3069\uff09<\/li>\n\n\n\n
- \u30e2\u30c7\u30eb\u306e\u5b66\u7fd2<\/li>\n<\/ul>\n<\/li>\n\n\n\n
- \u985e\u4f3c\u5ea6\u8a08\u7b97\n
\n
- \u65b0\u3057\u3044\u6587\u66f8\u306e\u30d9\u30af\u30c8\u30eb\u8868\u73fe\u306e\u63a8\u8ad6<\/li>\n\n\n\n
- \u30e2\u30c7\u30eb\u5185\u306e\u4ed6\u306e\u6587\u66f8\u30d9\u30af\u30c8\u30eb\u3068\u306e\u30b3\u30b5\u30a4\u30f3\u985e\u4f3c\u5ea6\u8a08\u7b97<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n
\u4ee5\u4e0b\u306f\u3001gensim\u3092\u4f7f\u3063\u305f\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306e\u5b9f\u88c5\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
import gensim\nfrom gensim.models.doc2vec import Doc2Vec, TaggedDocument\n\n# \u30b5\u30f3\u30d7\u30eb\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\nraw_documents = [\n \"I love machine learning. Its awesome.\",\n \"I love coding in python. I love building chatbots.\",\n \"I love building chatbots. I love conversational AI.\",\n \"I love python. I love building NLP projects.\",\n]\n\n# \u524d\u51e6\u7406\u3068TaggedDocument\u306e\u4f5c\u6210\ntagged_docs = [TaggedDocument(doc.lower().split(), [i]) for i, doc in enumerate(raw_documents)]\n\n# Doc2Vec\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\nmodel = Doc2Vec(tagged_docs, vector_size=20, min_count=1, epochs=50)\n\n# \u985e\u4f3c\u5ea6\u8a08\u7b97\ninferred_vector = model.infer_vector([\"machine\", \"learning\"])\nsims = model.dv.most_similar([inferred_vector])\n\nprint(f\"Most similar documents:\")\nfor doc_id, similarity in sims:\n print(f\"Document #{doc_id}: {similarity}\")<\/pre>\n\n\n\n\u3053\u306e\u30b3\u30fc\u30c9\u3067\u306f\u3001
vector_size<\/code>\u3067\u6587\u66f8\u30d9\u30af\u30c8\u30eb\u306e\u6b21\u5143\u6570\u3092\u8a2d\u5b9a\u3057\u3001min_count<\/code>\u3067\u5b66\u7fd2\u306b\u4f7f\u3046\u5358\u8a9e\u306e\u6700\u5c0f\u51fa\u73fe\u56de\u6570\u3092\u6307\u5b9a\u3057\u3066\u3044\u307e\u3059\u3002epochs<\/code>\u306f\u5b66\u7fd2\u306e\u53cd\u5fa9\u56de\u6570\u3067\u3059\u3002<\/p>\n\n\n\nDoc2Vec\u3092\u5b9f\u88c5\u3059\u308b\u969b\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a\u306e\u30b3\u30c4\u3092\u62bc\u3055\u3048\u3066\u304a\u304f\u3068\u826f\u3044\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\n
- vector_size\uff1a\u6587\u66f8\u30d9\u30af\u30c8\u30eb\u306e\u6b21\u5143\u6570\u3002\u5927\u304d\u306a\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3068\u8868\u73fe\u529b\u304c\u4e0a\u304c\u308b\u304c\u3001\u5b66\u7fd2\u306b\u6642\u9593\u304c\u304b\u304b\u308b\u3002<\/li>\n\n\n\n
- min_count\uff1a\u5b66\u7fd2\u306b\u4f7f\u3046\u5358\u8a9e\u306e\u6700\u5c0f\u51fa\u73fe\u56de\u6570\u3002\u983b\u5ea6\u306e\u4f4e\u3044\u5358\u8a9e\u3092\u7121\u8996\u3059\u308b\u3053\u3068\u3067\u3001\u5b66\u7fd2\u3092\u9ad8\u901f\u5316\u3067\u304d\u308b\u3002<\/li>\n\n\n\n
- epochs\uff1a\u5b66\u7fd2\u306e\u53cd\u5fa9\u56de\u6570\u3002\u5927\u304d\u306a\u5024\u3092\u8a2d\u5b9a\u3059\u308b\u3068\u6027\u80fd\u304c\u5411\u4e0a\u3059\u308b\u304c\u3001\u5b66\u7fd2\u6642\u9593\u304c\u9577\u304f\u306a\u308b\u3002<\/li>\n\n\n\n
- dm\uff1a\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u9078\u629e\u3002dm=1\u3067PV-DM\uff08\u5206\u6563\u30e1\u30e2\u30ea\uff09\u3001dm=0\u3067PV-DBOW\uff08\u5206\u6563\u30d0\u30c3\u30b0\u30fb\u30aa\u30d6\u30fb\u30ef\u30fc\u30c9\uff09\u3092\u4f7f\u7528\u3059\u308b\u3002<\/li>\n<\/ul>\n\n\n\n
gensim\u306eDoc2Vec\u3092\u4f7f\u3048\u3070\u3001\u5c11\u306a\u3044\u30b3\u30fc\u30c9\u91cf\u3067\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u3092\u5b9f\u88c5\u3067\u304d\u307e\u3059\u3002\u305f\u3060\u3057\u3001\u9069\u5207\u306a\u30d1\u30e9\u30e1\u30fc\u30bf\u8a2d\u5b9a\u3092\u898b\u3064\u3051\u308b\u306b\u306f\u3001\u8a66\u884c\u932f\u8aa4\u304c\u5fc5\u8981\u3067\u3059\u3002\u6b21\u7bc0\u3067\u306f\u3001gensim\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306eTips\u3092\u898b\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
gensim\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306e\u8c46\u77e5\u8b58\u3068Tips<\/h2>\n\n\n\n
gensim\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306b\u306f\u3001\u4e8b\u524d\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u6d3b\u7528\u65b9\u6cd5\u3084\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u306e\u9023\u643a\u65b9\u6cd5\u3092\u77e5\u3063\u3066\u304a\u304f\u3053\u3068\u304c\u91cd\u8981\u3067\u3059\u3002\u307e\u305f\u3001\u3064\u307e\u305a\u304d\u304c\u3061\u306a\u30dd\u30a4\u30f3\u30c8\u3092\u7406\u89e3\u3057\u3001\u9069\u5207\u306b\u30c7\u30d0\u30c3\u30b0\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308b\u3053\u3068\u304c\u6c42\u3081\u3089\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
gensim\u306b\u306f\u3001\u4e8b\u524d\u5b66\u7fd2\u6e08\u307f\u306eword2vec\u30e2\u30c7\u30eb\u3092\u8aad\u307f\u8fbc\u3080\u6a5f\u80fd\u304c\u3042\u308a\u307e\u3059\u3002\u65e5\u672c\u8a9e\u306e\u30e2\u30c7\u30eb\u3068\u3057\u3066\u306f\u3001\u300c\u6771\u5317\u5927\u5b66 \u65e5\u672c\u8a9e Wikipedia \u30a8\u30f3\u30c6\u30a3\u30c6\u30a3\u30d9\u30af\u30c8\u30eb\u300d\u306a\u3069\u304c\u5229\u7528\u53ef\u80fd\u3067\u3059\u3002\u30e2\u30c7\u30eb\u3092\u8aad\u307f\u8fbc\u3080\u3053\u3068\u3067\u3001\u5358\u8a9e\u306e\u985e\u4f3c\u5ea6\u8a08\u7b97\u3084\u8db3\u3057\u7b97\u30fb\u5f15\u304d\u7b97\u306a\u3069\u306e\u6f14\u7b97\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
\u4ee5\u4e0b\u306f\u3001\u4e8b\u524d\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u3092\u6d3b\u7528\u3059\u308b\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
from gensim.models import KeyedVectors\n\n# \u4e8b\u524d\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u8aad\u307f\u8fbc\u307f\nmodel_path = \"\/path\/to\/model\/jawiki.model\"\nmodel = KeyedVectors.load_word2vec_format(model_path, binary=True)\n\n# \u5358\u8a9e\u306e\u985e\u4f3c\u5ea6\u8a08\u7b97\nprint(model.similarity(\"\u6771\u4eac\", \"\u5927\u962a\"))\n\n# \u5358\u8a9e\u306e\u8db3\u3057\u7b97\u30fb\u5f15\u304d\u7b97\nresult = model.most_similar(positive=[\"\u738b\", \"\u5973\u6027\"], negative=[\"\u7537\u6027\"])\nprint(result)<\/pre>\n\n\n\n\u307e\u305f\u3001gensim\u3092\u4ed6\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3068\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u3001\u3055\u3089\u306b\u9ad8\u5ea6\u306a\u5206\u6790\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001scikit-learn\u3068\u9023\u643a\u3059\u308b\u3053\u3068\u3067\u3001gensim\u3067\u4f5c\u6210\u3057\u305f\u6587\u66f8\u30d9\u30af\u30c8\u30eb\u3092\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u306e\u5165\u529b\u3068\u3057\u3066\u4f7f\u7528\u3067\u304d\u307e\u3059\u3002FastText\u3067\u5b66\u7fd2\u3057\u305f\u5358\u8a9e\u30d9\u30af\u30c8\u30eb\u3092gensim\u3067\u8aad\u307f\u8fbc\u3093\u3067\u6d3b\u7528\u3059\u308b\u3053\u3068\u3082\u53ef\u80fd\u3067\u3059\u3002<\/p>\n\n\n\n
\u305f\u3060\u3057\u3001gensim\u3092\u4f7f\u3046\u969b\u306b\u306f\u3001\u3044\u304f\u3064\u304b\u306e\u3064\u307e\u305a\u304d\u304c\u3061\u306a\u30dd\u30a4\u30f3\u30c8\u304c\u3042\u308a\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001\u5927\u898f\u6a21\u306a\u30b3\u30fc\u30d1\u30b9\u3092\u51e6\u7406\u3059\u308b\u969b\u306b\u30e1\u30e2\u30ea\u4e0d\u8db3\u30a8\u30e9\u30fc\u304c\u767a\u751f\u3059\u308b\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u3002\u3053\u306e\u5834\u5408\u3001corpus_mm\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3092\u4f7f\u7528\u3059\u308b\u3053\u3068\u3067\u89e3\u6c7a\u3067\u304d\u307e\u3059\u3002\u307e\u305f\u3001\u5b66\u7fd2\u306b\u6642\u9593\u304c\u304b\u304b\u308a\u3059\u304e\u308b\u5834\u5408\u306f\u3001\u30d1\u30e9\u30e1\u30fc\u30bf\u8abf\u6574\uff08vector_size, min_count, epochs\u306e\u5024\u3092\u5c0f\u3055\u304f\u3059\u308b\uff09\u3067\u5bfe\u51e6\u3057\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\u4ee5\u4e0b\u306f\u3001\u30e1\u30e2\u30ea\u4e0d\u8db3\u30a8\u30e9\u30fc\u3092\u56de\u907f\u3059\u308b\u4f8b\u3067\u3059\u3002<\/p>\n\n\n\n
from gensim import corpora\n\n# \u5927\u898f\u6a21\u30b3\u30fc\u30d1\u30b9\u306e\u8aad\u307f\u8fbc\u307f\ncorpus = [[\"document\", \"one\"], [\"document\", \"two\"], ...]\n\n# corpus_mm\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3067\u4fdd\u5b58\ncorpora.MmCorpus.serialize(\"\/path\/to\/corpus.mm\", corpus)\n\n# corpus_mm\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3067\u8aad\u307f\u8fbc\u307f\nmm_corpus = corpora.MmCorpus(\"\/path\/to\/corpus.mm\")<\/pre>\n\n\n\ngensim\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306b\u306f\u3001\u3053\u306e\u3088\u3046\u306a\u8c46\u77e5\u8b58\u3084Tips\u3092\u8eab\u306b\u3064\u3051\u308b\u3053\u3068\u304c\u5927\u5207\u3067\u3059\u3002\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3084\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u53c2\u8003\u306b\u3001\u7d99\u7d9a\u7684\u306b\u5b66\u7fd2\u3059\u308b\u3053\u3068\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
\u307e\u3068\u3081\uff1agensim\u30de\u30b9\u30bf\u30fc\u3092\u76ee\u6307\u3059\u305f\u3081\u306e\u4eca\u5f8c\u306e\u5b66\u7fd2\u30ed\u30fc\u30c9\u30de\u30c3\u30d7<\/h2>\n\n\n\n
gensim\u3092\u4f7f\u3044\u3053\u306a\u3059\u305f\u3081\u306b\u306f\u3001\u7d99\u7d9a\u7684\u306a\u5b66\u7fd2\u304c\u6b20\u304b\u305b\u307e\u305b\u3093\u3002\u3053\u3053\u3067\u306f\u3001gensim\u30de\u30b9\u30bf\u30fc\u3092\u76ee\u6307\u3059\u521d\u5fc3\u8005\u306e\u305f\u3081\u306e\u5b66\u7fd2\u30ed\u30fc\u30c9\u30de\u30c3\u30d7\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
gensim\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3068\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u7406\u89e3\u3092\u6df1\u3081\u308b<\/h3>\n\n\n\n
gensim\u306e\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\uff08https:\/\/radimrehurek.com\/gensim\/<\/a>\uff09\u3067\u306f\u3001API\u30ea\u30d5\u30a1\u30ec\u30f3\u30b9\u3084\u5404\u30e2\u30b8\u30e5\u30fc\u30eb\u306e\u8aac\u660e\u304c\u5145\u5b9f\u3057\u3066\u3044\u307e\u3059\u3002\u7279\u306b\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\uff08Tutorials\uff09\u30bb\u30af\u30b7\u30e7\u30f3\u3067\u306f\u3001\u5177\u4f53\u7684\u306a\u4f7f\u7528\u65b9\u6cd5\u3092\u5b66\u3076\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u307e\u305f\u3001Jupyter Notebook\u3067\u5b9f\u884c\u53ef\u80fd\u306a\u30b5\u30f3\u30d7\u30eb\u30b3\u30fc\u30c9\u304c\u8c4a\u5bcc\u306b\u63d0\u4f9b\u3055\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u5b9f\u969b\u306b\u30b3\u30fc\u30c9\u3092\u52d5\u304b\u3057\u306a\u304c\u3089\u7406\u89e3\u3092\u6df1\u3081\u308b\u3053\u3068\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
gensim\u3092\u4f7f\u3063\u305f\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u30b9\u30ad\u30eb\u5411\u4e0a\u306e\u3059\u3059\u3081 \u2013 \u5b9f\u8df5\u3042\u308b\u306e\u307f\uff01<\/h3>\n\n\n\n
gensim\u306e\u30b9\u30ad\u30eb\u3092\u5411\u4e0a\u3055\u305b\u308b\u306b\u306f\u3001\u5b9f\u8df5\u3042\u308b\u306e\u307f\u3067\u3059\u3002\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u65b9\u6cd5\u3067\u3001\u7d99\u7d9a\u7684\u306b\u5b66\u7fd2\u3092\u9032\u3081\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n
\n
- \u5b9f\u969b\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f7f\u3063\u305f\u6f14\u7fd2\u306b\u53d6\u308a\u7d44\u3080\n
\n
- kaggle\u3084Google Dataset\u306a\u3069\u304b\u3089\u3001\u8208\u5473\u306e\u3042\u308b\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u3092\u5165\u624b\u3059\u308b<\/li>\n\n\n\n
- gensim\u306e\u5404\u6a5f\u80fd\u3092\u4f7f\u3063\u3066\u30c7\u30fc\u30bf\u5206\u6790\u3092\u884c\u3044\u3001\u8003\u5bdf\u3059\u308b<\/li>\n<\/ul>\n<\/li>\n\n\n\n
- \u4ed6\u306e\u958b\u767a\u8005\u304c\u66f8\u3044\u305f\u30b3\u30fc\u30c9\u3092\u8aad\u3080\n
\n
- GitHub\u306a\u3069\u3067\u3001gensim\u3092\u4f7f\u3063\u305f\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306e\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3092\u63a2\u3059<\/li>\n\n\n\n
- \u30b3\u30fc\u30c9\u30ea\u30fc\u30c7\u30a3\u30f3\u30b0\u3092\u901a\u3058\u3066\u3001\u5b9f\u88c5\u306e\u30b3\u30c4\u3092\u5b66\u3076<\/li>\n<\/ul>\n<\/li>\n\n\n\n
- \u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306b\u53c2\u52a0\u3059\u308b\n
\n
- gensim\u306e\u516c\u5f0f\u30d5\u30a9\u30fc\u30e9\u30e0: https:\/\/groups.google.com\/g\/gensim<\/a><\/li>\n\n\n\n
- Stack Overflow\u306e\u95a2\u9023\u30bf\u30b0: https:\/\/stackoverflow.com\/questions\/tagged\/gensim<\/a><\/li>\n\n\n\n
- \u8cea\u554f\u3084\u30c7\u30a3\u30b9\u30ab\u30c3\u30b7\u30e7\u30f3\u306b\u53c2\u52a0\u3057\u3001\u77e5\u898b\u3092\u6df1\u3081\u308b<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n
\u6700\u5f8c\u306b\u3001gensim\u3092\u4f7f\u3063\u305f\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306e\u5b9f\u8df5\u4f8b\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002\u4ee5\u4e0b\u306e\u30b3\u30fc\u30c9\u306f\u3001\u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u306e\u30c8\u30d4\u30c3\u30af\u5206\u6790\u3092\u884c\u3046\u4e00\u9023\u306e\u6d41\u308c\u3092\u793a\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
import requests\nfrom bs4 import BeautifulSoup\nfrom gensim import corpora, models\n\n# \u30cb\u30e5\u30fc\u30b9\u8a18\u4e8b\u306e\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\uff08URL\u306f\u9069\u5b9c\u5909\u66f4\uff09\nurl = \"https:\/\/www.example.com\/news\/\"\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, \"html.parser\")\narticles = soup.find_all(\"div\", class_=\"article\")\n\n# \u524d\u51e6\u7406\ndef preprocess(text):\n # \u3053\u3053\u306b\u524d\u51e6\u7406\u306e\u51e6\u7406\u3092\u8a18\u8ff0\uff08\u5f62\u614b\u7d20\u89e3\u6790\u3001\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u9664\u53bb\u306a\u3069\uff09\n return processed_text\n\n# \u8a18\u4e8b\u306e\u5185\u5bb9\u3092\u62bd\u51fa\ntexts = [preprocess(article.get_text()) for article in articles]\n\n# \u8f9e\u66f8\u306e\u4f5c\u6210\u3068\u30b3\u30fc\u30d1\u30b9\u306e\u5909\u63db\ndictionary = corpora.Dictionary(texts)\ncorpus = [dictionary.doc2bow(text) for text in texts]\n\n# LDA\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\nlda_model = models.LdaModel(corpus=corpus, id2word=dictionary, num_topics=5)\n\n# \u30c8\u30d4\u30c3\u30af\u306e\u8868\u793a\nfor topic_id, topic in lda_model.print_topics(num_topics=5, num_words=5):\n print(f\"Topic #{topic_id}: {topic}\")<\/pre>\n\n\n\n\u3053\u306e\u3088\u3046\u306b\u3001\u5b9f\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u305f\u5206\u6790\u3092\u901a\u3058\u3066\u3001gensim\u306e\u4f7f\u3044\u65b9\u3092\u4f53\u5f97\u3057\u3066\u3044\u304d\u307e\u3057\u3087\u3046\u3002\u516c\u5f0f\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3084\u53c2\u8003\u66f8\u7c4d\u3001\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u3092\u6d3b\u7528\u3057\u306a\u304c\u3089\u3001\u7d99\u7d9a\u7684\u306b\u5b66\u7fd2\u3092\u91cd\u306d\u308b\u3053\u3068\u3067\u3001gensim\u30de\u30b9\u30bf\u30fc\u3078\u306e\u9053\u3092\u7740\u5b9f\u306b\u6b69\u3093\u3067\u3044\u304f\u3053\u3068\u304c\u3067\u304d\u308b\u306f\u305a\u3067\u3059\u3002\u304c\u3093\u3070\u3063\u3066\u304f\u3060\u3055\u3044\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"
gensim\u306f\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u30bf\u30b9\u30af\u3092\u624b\u8efd\u306b\u5b9f\u88c5\u3067\u304d\u308bPython\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u3053\u306e\u8a18\u4e8b\u3067\u306f\u3001\u521d\u5fc3\u8005\u3067\u3082gensim\u3092\u4f7f\u3044\u3053\u306a\u305b\u308b\u3088\u3046\u306b\u306a\u308b\u305f\u3081\u306e\u57fa\u790e\u77e5\u8b58\u3084Tips\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002\u30c8\u30d4\u30c3\u30af\u30e2\u30c7\u30ea\u30f3\u30b0\u3084\u6587\u66f8\u985e\u4f3c\u5ea6\u5206\u6790\u306e\u5b9f\u88c5\u65b9 … <\/p>\n","protected":false},"author":1,"featured_media":659,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":{"0":"post-658","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-python"},"_links":{"self":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/658","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=658"}],"version-history":[{"count":1,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/658\/revisions"}],"predecessor-version":[{"id":660,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/posts\/658\/revisions\/660"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=\/wp\/v2\/media\/659"}],"wp:attachment":[{"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=658"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=658"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/chocottopro.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=658"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}