{"id":45085,"date":"2023-12-11T15:04:49","date_gmt":"2023-12-11T07:04:49","guid":{"rendered":"https:\/\/wx.kaifamiao.info\/?p=45085"},"modified":"2023-12-11T15:04:49","modified_gmt":"2023-12-11T07:04:49","slug":"%e7%bb%99%e4%ba%86%e4%b8%aa%e9%93%be%e6%8e%a5%e7%ba%bf%e4%b8%8a%e5%86%99%e4%bb%a3%e7%a0%81%ef%bc%8c%e8%a6%81%e6%b1%82%e5%86%99%e8%af%bb%e6%96%87%e6%9c%ac%e3%80%81%e6%96%87%e6%9c%ac%e9%a2%84%e5%a4%84-2","status":"publish","type":"post","link":"http:\/\/wx.kaifamiao.info\/index.php\/2023\/12\/11\/%e7%bb%99%e4%ba%86%e4%b8%aa%e9%93%be%e6%8e%a5%e7%ba%bf%e4%b8%8a%e5%86%99%e4%bb%a3%e7%a0%81%ef%bc%8c%e8%a6%81%e6%b1%82%e5%86%99%e8%af%bb%e6%96%87%e6%9c%ac%e3%80%81%e6%96%87%e6%9c%ac%e9%a2%84%e5%a4%84-2\/","title":{"rendered":"\u7ed9\u4e86\u4e2a\u94fe\u63a5\u7ebf\u4e0a\u5199\u4ee3\u7801\uff0c\u8981\u6c42\u5199\u8bfb\u6587\u672c\u3001\u6587\u672c\u9884\u5904\u7406\u3001\u7279\u5f81\u63d0\u53d6\u548c\u5efa\u6a21\u7684\u57fa\u672c\u8fc7\u7a0b\uff0c\u4e0d\u8fc7\u5199\u5230\u7279\u5f81\u5c31\u6ca1\u5199\u4e86"},"content":{"rendered":"

“`” \u53c2\u8003\u56de\u7b54\uff1a<\/p>\n

\u6536\u96c6\u6570\u636e<\/p>\n

\u603b\u6240\u5468\u77e5\uff0c\u6570\u636e\u6316\u6398\u6a21\u578b\u4e2d\u975e\u5e38\u91cd\u8981\u7684\u90e8\u5206\u662f\u8bad\u7ec3\u6a21\u578b\uff0c\u8bad\u7ec3\u96c6\u4e0e\u6d4b\u8bd5\u96c6\u4fbf\u662f\u6574\u4e2a\u6570\u636e\u6316\u6398\u8fc7\u7a0b\u4e2d\u82b1\u8d39\u65f6\u95f4\u6700\u591a\u7684\u8fc7\u7a0b\u3002\u6570\u636e\u96c6\u901a\u8fc7\u6709\u5982\u4e0b\u7684\u4e00\u4e9b\u9014\u5f84\u83b7\u5f97\uff1a<\/p>\n

\u7ecf\u5178\u6570\u636e\u96c6\uff1aPython NLTK \u4fbf\u63d0\u4f9b\u4e86\u975e\u5e38\u591a\u7ecf\u5178\u7684\u6570\u636e\u96c6\u3002\u5f88\u591a\u6570\u636e\u96c6\u90fd\u662f\u624b\u5de5\u6807\u6ce8\u800c\u6210\uff0c\u6240\u4ee5\u4f7f\u7528\u7684\u65f6\u5019\u4e0d\u5f97\u4e0d\u611f\u53f9\u5de5\u7a0b\u7684\u6d69\u5927\u3002\u4f8b\u5982NLP\u4e2d\u4f7f\u7528\u7684Penn TreeBank\uff0c\u6709\u5174\u8da3\u7684\u540c\u5b66\u53ef\u4ee5\u770b\u770b\u4ed6\u4eec\u7684\u8bba\u6587\u300aBuilding a Large Annotated Corpus of English: The Penn TreeBank\u300b\uff0c\u90a3\u7b80\u76f4\u5c31\u662f\u4e00\u90e8\u8f9b\u9178\u53f2\u554a\uff01<\/p>\n

\u4ece\u7f51\u9875\u4e0a\u6293\u53d6\uff1a\u76f4\u63a5\u52a8\u624b\u5199\u4e00\u4e2a\u722c\u866b\u722c\u53d6\u7279\u5b9a\u7684\u7f51\u9875\u4e0d\u96be\uff0c\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u5c31\u80fd\u591f\u5c06\u6709\u6548\u7684\u5185\u5bb9\u63d0\u53d6\u51fa\u6765\uff1b\u5f53\u7136\uff0c\u53d1\u626c\u62ff\u6765\u4e3b\u4e49\u7cbe\u795e\u7684\u8bdd\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u4e00\u4e9b\u4f18\u79c0\u7684\u5e93\uff0c\u6bd4\u5982scrapy\uff0cbeautifulsoup \u7b49\u7b49\u3002<\/p>\n

\u4ece\u65e5\u5fd7\u3001\u5df2\u6709\u6587\u4ef6\u4e2d\u5206\u6790\uff1a\u5982\u679c\u662f\u6d77\u91cf\u6570\u636e\u7684\u8bdd\u53ef\u4ee5\u4f7f\u7528hadoop\u8fd9\u6837\u7684\u7cfb\u7edf\u3002\u7ed3\u5408\u4f20\u7edfSQL\u4e2d\u7684\u4e00\u4e9b\u7279\u6b8a\u529f\u80fd\uff0c\u4f8b\u5982Partition\uff0c\u6709\u65f6\u4f1a\u6709\u4e0d\u9519\u7684\u6548\u679c\uff0c\u4e0d\u8fc7\u6700\u591a\u538b\u7f29\u7a7a\u95f4\u3001\u7f29\u51cf\u7279\u5f81\u518d\u7528SQL\u5904\u7406\u3002<\/p>\n

\u5176\u4ed6\u7f51\u7edc\u6570\u636e\u96c6\uff1aStanford Large Network Dataset Collectionm\uff0c100+ Interesting Data Sets for Statistics<\/a><\/p>\n

 <\/p>\n

\u9884\u5904\u7406<\/p>\n

\u5982\u679c\u662f\u7f51\u9875\u5185\u5bb9\uff0c\u9996\u5148\u9700\u8981\u53bb\u6389Html Tag\uff0clxml\u548chtml5lib\u662f\u6bd4\u8f83\u6709\u540d\u7684Python\u5e93\uff0cbeautifulsoup\u4e5f\u5bf9\u4ed6\u4eec\u505a\u4e86\u4e00\u5c42\u5c01\u88c5\u3002\u4e0d\u8fc7\u522b\u5fd8\u4e86\uff0cPython\u672c\u8eab\u4e5f\u81ea\u5e26\u4e86sgmllib\u8fd9\u6837\u7684\u57fa\u672c\u53ef\u6269\u5c55\u7684\u89e3\u6790\u5668\u3002\u5982\u679c\u662f\u6709\u7279\u522b\u7684\u5904\u7406\uff0c\u5176\u5b9e\u6b63\u5219\u8868\u8fbe\u5f0f\u4e5f\u662f\u4e0d\u9519\u7684\u9009\u62e9\u3002<\/p>\n

\u5904\u7406\u7f16\u7801\uff0c\u7531\u4e8e\u6211\u4e3b\u8981\u662f\u5904\u7406\u82f1\u6587\u7684\u6570\u636e\uff0c\u8fd9\u4e00\u6b65\u57fa\u672c\u4e5f\u8df3\u8fc7\u4e86\u3002<\/p>\n

\u5c06\u6587\u6863\u5206\u5272\u6210\u53e5\u5b50\uff08\u53ef\u9009\uff09\u3002\u5f88\u591a\u65f6\u5019\u6211\u4eec\u91c7\u7528\u7684\u662f\u8bcd\u888b\u6a21\u578b\uff08bag of words\uff09\uff0c\u6240\u4ee5\u662f\u5426\u5206\u5272\u6210\u53e5\u5b50\u4e5f\u65e0\u6240\u8c13\u3002\u6bd4\u8f83\u7b80\u5355\u7684\u65b9\u6cd5\u5c31\u662fPython NLTK\u4e2d\u7684sent_tokenize()\u51fd\u6570\uff0c\u7528\u7684\u662fpunkt\u7b97\u6cd5\uff0c\u8bba\u6587\u5728\u8fd9\u91cc<\/a>\u3002<\/p>\n

\u5c06\u53e5\u5b50\u5206\u5272\u6210\u8bcd\u3002\u9996\u5148\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u81ea\u5df1\u5b8c\u6210\uff1b\u5982\u679c\u8981\u5229\u7528\u5df2\u6709\u5de5\u5177\uff0cPython NLTK\u4e2d\u7684word_tokenize()\uff0c\u8fd9\u4e2a\u65b9\u5f0f\u5c31\u662f\u524d\u6587\u63d0\u5230\u7684Penn TreeBank\u8bed\u6599\u5e93\u6240\u4f7f\u7528\u7684\u5206\u8bcd\u65b9\u6cd5\u3002\u542c\u8d77\u6765\u662f\u4e0d\u662f\u5f88\u9ad8\u5927\u4e0a\uff0c\u6211\u662f\u4e0d\u4f1a\u544a\u8bc9\u4f60\u5176\u5b9e\u5b83\u4e5f\u662f\u6b63\u5219\u8868\u8fbe\u5f0f\u5b9e\u73b0\u7684\uff0c\u60f3\u77e5\u9053\u5177\u4f53\u5b9e\u73b0\uff0c\u6233\u8fd9\u91cc<\/a>\u3002\u5206\u8bcd\u5176\u5b9e\u4e3b\u8981\u5e72\u4e86\u8fd9\u4e48\u51e0\u4e2a\u4e8b\uff1a1\uff09\u5c06’\u5206\u5f00. don’t -> do n’t, they’ll -> they ‘ll; 2\uff09\u5c06\u5927\u90e8\u5206\u6807\u70b9\u5f53\u4f5c\u5355\u72ec\u7684\u4e00\u4e2a\u8bcd; 3\uff09\u5c06\u540e\u4e00\u4f4d\u662f\u9017\u53f7\u6216\u8005\u5f15\u53f7\u7684\u8bcd\u5206\u5f00; 4\uff09\u5355\u72ec\u51fa\u73b0\u5728\u4e00\u884c\u7684\u53e5\u53f7\u5206\u5f00\u3002\u4e2d\u6587\u5206\u8bcd\u533a\u522b\u6bd4\u8f83\u5927\uff0c\u53ef\u4ee5\u91c7\u7528\u65af\u5766\u798f<\/a>\u6216\u8005ICTCLAS\uff08\u4e2d\u79d1\u9662\u80cc\u666f\uff09\u7684\u65b9\u6848\u3002<\/p>\n

\u62fc\u5199\u9519\u8bef\u7ea0\u6b63\u3002\u63a8\u8350pyenchant\uff0c\u975e\u5e38\u559c\u6b22\uff0c\u56e0\u4e3a\u7b80\u6d01\u5230\u56db\u53e5\u8bed\u53e5\u5c31\u80fd\u5b8c\u6210\u3002Windows 8\u4e2d\u64cd\u4f5c\u7cfb\u7edf\u4e5f\u76f4\u63a5\u63d0\u4f9b\u4e86\u62fc\u5199\u68c0\u67e5\u7684COM\u7aef\u53e3\uff0c\u4e0d\u8fc7\u5c31\u5f97\u591a\u82b1\u65f6\u95f4\u7814\u7a76\u5566\u3002<\/p>\n

POS Tagging\uff08\u6839\u636e\u5b9e\u9645\u5e94\u7528\uff09\u3002\u8fd8\u662fNltk\uff0c\u9996\u9875<\/a>\u5c31\u6709\u4ecb\u7ecd\uff1b\u65af\u5766\u798f<\/a>\u4e5f\u63d0\u4f9b\u4e86\u8fd9\u7c7b\u5de5\u5177\u3002\u8fd9\u4e00\u5757\u5c5e\u4e8eNLP\u7684\u8303\u7574\uff0c\u8fd8\u662fParsing\u7b49\u5e94\u7528\uff0c\u8981\u4e86\u89e3NLP\u539f\u7406\u63a8\u8350Coursera\u4e0a\u4e00\u95e8\u4e0d\u9519\u7684\u8bfe\u7a0bNatural Language Processing<\/p>\n

\u53bb\u6389\u6807\u70b9\u3002\u6b63\u5219\u8868\u8fbe\u5f0f\u5373\u53ef\uff0c\u6709\u7684\u65f6\u95f4\u975e\u5e38\u77ed\u7684\u5355\u8bcd\u4e5f\u53ef\u4ee5\u4e00\u8d77\u53bb\u6389\uff0clen<3\u7684\u5e38\u89c1\u7684\u9009\u62e9<\/p>\n

\u53bb\u6389\u975e\u82f1\u6587\u5b57\u7b26\u7684\u8bcd\uff08\u6839\u636e\u5b9e\u9645\u5e94\u7528\u51b3\u5b9a\uff09\u3002<\/p>\n

\u8f6c\u6362\u6210\u5c0f\u5199\u3002<\/p>\n

\u53bb\u6389\u505c\u7528\u8bcd\u3002\u5c31\u662f\u5728\u5404\u79cd\u53e5\u5b50\u4e2d\u90fd\u7ecf\u5e38\u51fa\u73b0\u7684\u4e00\u4e9b\u8bcd\uff0cI\u3001and\u4ec0\u4e48\u7684\u3002NLTK\u6709\u4e00\u4e2aStopwords\u3002Matthew L. Jockers\u63d0\u4f9b\u4e86\u4e00\u4efd\u6bd4\u673a\u5668\u5b66\u4e60\u548c\u81ea\u7136\u8bed\u8a00\u5904\u7406\u4e2d\u5e38\u7528\u7684\u505c\u8bcd\u8868\u66f4\u957f\u7684\u505c\u8bcd\u8868\u3002\u4e2d\u6587\u505c\u7528\u8bcd\u6233\u8fd9\u91cc<\/a>\u3002\u4ec0\u4e48\uff1f\u4f60\u95ee\u6211\u505c\u7528\u8bcd\u600e\u4e48\u627e\u5230\u7684\uff0c\u6211\u60f3\u5927\u6982\u662fIDF\u8fd9\u6837\u7684\u7b97\u6cd5\u5427\u3002<\/p>\n

\u8bcd\u578b\u8f6c\u6362\u3002\u7b80\u5355\u6765\u8bb2\uff0c\u6211\u4eec\u5e0c\u671bdo\u3001did\u3001done\u90fd\u80fd\u7edf\u4e00\u7684\u8fd4\u56dedo\u3002\u7b2c\u4e00\u79cd\u65b9\u6cd5\u53ebstem\uff0cPorter\u662f\u6bd4\u8f83\u5e38\u89c1\u7684\u4e00\u79cd\u57fa\u4e8e\u89c4\u5219\u7684\u7b97\u6cd5\uff0c\u7f51\u9875\u6709snowball\u5de5\u5177\uff0c\u4e5f\u662f\u5b83\u7684\u8bba\u6587\u3002Porter\u7684\u7ed3\u679c\u5dee\u5f3a\u4eba\u610f\uff0c\u5355\u8bcd\u672b\u5c3e\u6709e\u3001y\u7684\uff0c\u57fa\u672c\u4e0astem\u4e4b\u540e\u90fd\u4e0d\u95f4\u4e86\uff0c\u4f8b\u5982replace->replac\uff1b\u672b\u5c3e\u6709\u91cd\u590d\u5355\u8bcd\u7684\uff0c\u57fa\u672c\u53ea\u5269\u4e00\u4e2a\u4e86\uff0c\u4f8b\u5982ill->il\u3002NLTK\u4e2d\u4e5f\u6709Stem\u5e93\uff0c\u7b97\u6cd5\u5e94\u8be5\u662f\u7c7b\u4f3c\u7684\u3002\u7b2c\u4e8c\u79cd\u65b9\u6cd5\u53eblemmatization\uff0c\u5c31\u662f\u57fa\u4e8e\u8bcd\u5178\u505a\u8bcd\u578b\u8f6c\u6362\uff0cNLTK\u7684Stem\u5e93\u4e2d\u4fbf\u6709WordNetLemmatizer\u53ef\u4ee5\u4f7f\u7528\u3002<\/p>\n

\u53bb\u6389\u957f\u5ea6\u8fc7\u5c0f\u7684\u8bcd\uff08\u53ef\u9009\uff09\u3002\u5982\u679c\u4e4b\u524d\u505a\u4e86\uff0c\u8fd9\u91cc\u8981\u518d\u505a\u4e00\u6b21\uff0c\u56e0\u4e3astem\u4f1a\u6539\u53d8\u8bcd\u578b\u3002<\/p>\n

\u91cd\u65b0\u53bb\u505c\u7528\u8bcd\u3002\u7406\u7531\u540c\u4e0a\u3002<\/p>\n

\u7279\u5f81\u63d0\u53d6\uff1a<\/p>\n

1\u3001TF-IDF\uff1a<\/p>\n

2\u3001\u8bcd\u9891\u65b9\u6cd5(Word Frequency)\uff1a<\/p>\n

3\u3001\u6587\u6863\u9891\u6b21\u65b9\u6cd5(Document Frequency)\uff1a<\/p>\n

4\u3001\u4e92\u4fe1\u606f(Mutual Information)\uff1a<\/p>\n

5\u3001\u671f\u671b\u4ea4\u53c9\u71b5(Expected Cross Entropy)\uff1a<\/p>\n

6\u3001\u4e8c\u6b21\u4fe1\u606f\u71b5(QEMI)\uff1a<\/p>\n

7\u3001\u4fe1\u606f\u589e\u76ca\u65b9\u6cd5(Information Gain)\uff1a<\/p>\n

8\u3001x2\u7edf\u8ba1\u91cf\u65b9\u6cd5\uff1a<\/p>\n

9\u3001\u6587\u672c\u8bc1\u636e\u6743(The Weight of Evidence forText)\uff1a<\/p>\n

10\u3001\u4f18\u52bf\u7387(Odds Ratio)\uff1a<\/p>\n

11\u3001\u9057\u4f20\u7b97\u6cd5(Genetic Algorithm, GA)\uff1a<\/p>\n

12\u3001\u4e3b\u6210\u5206\u5206\u6790\u6cd5(Principal Component Analysis\uff0cPCA)\uff1a<\/p>\n

13\u3001\u6a21\u62df\u9000\u706b\u7b97\u6cd5(Simulating Anneal\uff0cSA)\uff1a<\/p>\n

14\u3001N—Gram\u7b97\u6cd5<\/p>\n

\u6587\u672c\u5efa\u6a21\uff1a<\/p>\n

LDA\u3001pLSA\u3001LSA<\/p>\n

            \"```\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
“`” \u53c2\u8003\u56de\u7b54\uff1a \u6536\u96c6\u6570\u636e \u603b\u6240\u5468\u77e5\uff0c\u6570\u636e\u6316\u6398\u6a21\u578b\u4e2d\u975e\u5e38\u91cd\u8981\u7684\u90e8\u5206\u662f\u8bad\u7ec3\u6a21\u578b\uff0c\u8bad\u7ec3\u96c6 […]<\/p>\n","protected":false},"author":7,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-45085","post","type-post","status-publish","format-standard","hentry","category-c"],"_links":{"self":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/45085","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/comments?post=45085"}],"version-history":[{"count":1,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/45085\/revisions"}],"predecessor-version":[{"id":45086,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/45085\/revisions\/45086"}],"wp:attachment":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/media?parent=45085"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/categories?post=45085"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/tags?post=45085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}