{"id":1384,"date":"2022-05-22T14:55:34","date_gmt":"2022-05-22T06:55:34","guid":{"rendered":"http:\/\/www.eait.co\/?p=1384"},"modified":"2022-05-22T18:26:27","modified_gmt":"2022-05-22T10:26:27","slug":"nlp%e5%88%9d%e6%ad%a5-jieba","status":"publish","type":"post","link":"https:\/\/notes.coremix.net\/?p=1384","title":{"rendered":"NLP\u521d\u6b65\u2014\u2014jieba"},"content":{"rendered":"<p>pip install jieba<\/p>\n<p>jieba\u6709\u4e00\u5b9a\u8bc6\u522b\u65b0\u8bcd\u7684\u80fd\u529b<\/p>\n<p>&nbsp;<\/p>\n<pre class=\"brush: python; title: ; notranslate\" title=\"\">\r\n#-*- coding:utf-8 -*-\r\n\r\nimport jieba\r\nimport jieba.analyse as anls\r\n# \u5206\u8bcd\u5168\u6a21\u5f0f \uff08\u5c3d\u53ef\u80fd\u591a\u7684\u5206\u8bcd\uff09\r\ntext = '\u6211\u4eec\u518d\u7075\u5c71\u5b66\u9662\u5b66\u4e60\u5927\u6570\u636e\u4e0e\u4eba\u5de5\u667a\u80fdNLP\u5904\u7406\uff0c\u7136\u540e\u53d8\u6210\u653b\u57ce\u72ee'\r\nprint(&quot;\u5168\u6a21\u5f0f&quot;+'\/'.join(jieba.cut(text,cut_all = True)))\r\n\r\n# \u7cbe\u786e\u6a21\u5f0f\uff08\u7528\u7684\u6bd4\u8f83\u591a\uff09\r\nprint(&quot;\u7cbe\u786e\u6a21\u5f0f&quot;+'\/'.join(jieba.cut(text,cut_all = False)))\r\n\r\n# \u641c\u7d22\u5f15\u64ce\u6a21\u5f0f  HMM\u6a21\u578b\r\nprint(&quot;\u641c\u7d22\u5f15\u64ce\u6a21\u5f0f&quot;+'\/'.join(jieba.cut(text)))\r\n# \u652f\u6301\u7e41\u4f53\u6a21\u5f0f \u7565\r\njieba.add_word('\u7075\u5c71\u5b66\u9662')\r\nprint(&quot;\u641c\u7d22\u5f15\u64ce\u6a21\u5f0f&quot;+'\/'.join(jieba.cut(text)))\r\n# \u652f\u6301\u7528\u6237\u5b57\u5178 \u7565 jieba.load_userdict(path)\r\n\r\n# \u5173\u952e\u8bcd\u62bd\u53d6\r\ns = &quot;&quot;&quot;\u65e9\u671f\u5927\u90e8\u5206\u7684\u95e8\u6237\u7f51\u7ad9\u90fd\u662f\u6309\u7167\u4e13\u9898\u9891\u9053\u7b49\u5212\u5206\uff0c\u901a\u8fc7\u4e13\u4e1a\u7684\u4eba\u5de5\u7f16\u8f91\u6765\u7ef4\u62a4\u4fe1\u606f\u7684\u66f4\u65b0\uff0c\u6240\u6709\u4eba\u5728\u540c\u4e00\u65f6\u523b\u770b\u5230\u7684\u95e8\u6237\u65b0\u95fb\u90fd\u662f\u4e00\u6837\u7684\u3002\r\n\u800c\u968f\u7740\u4fe1\u606f\u7684\u7206\u70b8\uff0c\u4e92\u8054\u7f51\u4e0a\u6e90\u6e90\u4e0d\u65ad\u751f\u4ea7\u51fa\u6d77\u91cf\u5185\u5bb9\uff0c\u901a\u8fc7\u4eba\u5de5\u7684\u65b9\u5f0f\u5df2\u7ecf\u5f88\u96be\u53bb\u7ef4\u62a4\u548c\u66f4\u65b0\u3002\u9664\u6b64\u4e4b\u5916\uff0c\u968f\u7740\u4e92\u8054\u7f51\u7684\u7528\u6237\u7206\u53d1\u6027\u7684\u589e\u957f\uff0c\u6bcf\u4e2a\u7528\u6237\u5bf9\u4fe1\u606f\u7684\u559c\u597d\u4ea6\u6709\u6240\u4e0d\u540c\uff0c\u8fd9\u5c31\u5bfc\u81f4\u4e86\u5343\u4eba\u4e00\u9762\u7684\u95e8\u6237\u7f51\u7ad9\u96be\u4ee5\u6ee1\u8db3\u7528\u6237\u7684\u9700\u6c42\u3002\r\n\u63a8\u8350\u7cfb\u7edf\u5728\u8fd9\u4e2a\u573a\u666f\u4e0b\u5f97\u5230\u4e86\u5feb\u901f\u7684\u53d1\u5c55\uff0c\u6bcf\u4e2a\u4eba\u5728\u6253\u5f00 App \u6216\u8005\u7f51\u9875\u65f6\uff0c\u770b\u5230\u7684\u90fd\u662f\u548c\u81ea\u8eab\u5174\u8da3\u76f8\u5173\u7684\u5185\u5bb9\uff0c\u4ece\u800c\u5b9e\u73b0\u4e86\u5343\u4eba\u5343\u9762\uff0c\u63d0\u5347\u4e86\u4fe1\u606f\u7684\u5206\u53d1\u6548\u7387\u3002&quot;&quot;&quot;\r\nkeywords = anls.extract_tags(s,topK=5,withWeight=True)\r\nfor keyword, weight in keywords:\r\n    print(keyword,weight)  #\u6548\u679c\u8f83\u5dee\uff0c\u4fe1\u606f\u7206\u70b8\uff0c\u63a8\u8350\u7cfb\u7edf\uff0c\u5343\u4eba\u5343\u9762\uff0c\u4e92\u8054\u7f51\uff0c\u7206\u53d1\u6027 \u7b49\u5173\u952e\u8bcd\u6ca1\u627e\u5230\r\nkeywords = anls.textrank(s,topK=5,withWeight=True)\r\nfor keyword, weight in keywords:\r\n    print('textrank',keyword,weight)  #\u6548\u679c\u8f83\u5dee\uff0c\u4fe1\u606f\u7206\u70b8\uff0c\u63a8\u8350\u7cfb\u7edf\uff0c\u5343\u4eba\u5343\u9762\uff0c\u4e92\u8054\u7f51\uff0c\u7206\u53d1\u6027 \u7b49\u5173\u952e\u8bcd\u6ca1\u627e\u5230\r\n# \u8bcd\u6027\u6807\u6ce8 \u7565\r\n\r\n\r\n\r\n\r\n<\/pre>\n<p>\u5176\u5b83\uff1a<\/p>\n<p><span class=\"md-line md-end-block md-focus\" contenteditable=\"true\"><span class=\"md-expand\">4\u3001jieba<\/span><\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"> \uff081\uff09\u76ee\u524d\u6700\u597d\u7684Python\u4e2d\u6587\u5206\u8bcd\u7ec4\u4ef6\uff0c\u4e3b\u8981\u67093\u4e2a\u7279\u6027\uff1a<\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\"> 1\uff09\u652f\u6301\u7e41\u4f53\u5206\u8bcd<\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\"><span class=\"\">2\uff09\u652f\u6301\u81ea\u5b9a\u4e49\u8bcd\u5178\u3002<\/span><\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\"> 3\uff09\u652f\u63013\u79cd\u5206\u8bcd\u65b9\u5f0f<\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"><span class=\"\"> \u7cbe\u786e\u6a21\u5f0f\uff1a\u8bd5\u56fe\u5c06\u53e5\u5b50\u6700\u7cbe\u786e\u7684\u5207\u5f00\uff0c\u9002\u5408\u6587\u672c\u5206\u6790\u3002<\/span><\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"> \u5168\u6a21\u5f0f\uff1a\u628a\u53e5\u5b50\u4e2d\u6240\u6709\u53ef\u80fd\u7684\u8bcd\u90fd\u626b\u63cf\u8bf4\u51fa\u6765\uff0c\u901f\u5ea6\u975e\u5e38\u5feb\uff0c\u4e0d\u80fd\u89e3\u51b3\u6b67\u4e49\uff1b<\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"> \u641c\u7d22\u5f15\u64ce\u6a21\u578b\uff1a\u5728\u7cbe\u786e\u6a21\u5f0f\u7684\u57fa\u7840\u4e0a\uff0c\u9002\u7528\u4e8e\u641c\u7d22\u5f15\u64ce\uff0c\u5bf9\u957f\u8bcd\u518d\u6b21\u5207\u5206<\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"> \u7ed3\u5df4\u6709\u81ea\u5df1\u8bc6\u522b\u65b0\u8bcd\u7684\u80fd\u529b\u3002<\/span><span class=\"md-line md-end-block\" contenteditable=\"true\"> HMM<\/span><\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>pip install jieba jieba\u6709\u4e00\u5b9a\u8bc6\u522b\u65b0\u8bcd\u7684\u80fd\u529b &nbsp; #-*- coding:ut [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[32,20],"class_list":["post-1384","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-nlp","tag-python"],"blocksy_meta":[],"_links":{"self":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1384","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1384"}],"version-history":[{"count":3,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1384\/revisions"}],"predecessor-version":[{"id":1396,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1384\/revisions\/1396"}],"wp:attachment":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}