{"id":1386,"date":"2022-05-22T15:44:52","date_gmt":"2022-05-22T07:44:52","guid":{"rendered":"http:\/\/www.eait.co\/?p=1386"},"modified":"2022-05-22T18:27:07","modified_gmt":"2022-05-22T10:27:07","slug":"%e5%88%9d%e6%ad%a5-pkuseg","status":"publish","type":"post","link":"https:\/\/notes.coremix.net\/?p=1386","title":{"rendered":"\u521d\u6b65\u2014\u2014PKUseg"},"content":{"rendered":"<p>\u5b89\u88c5\uff1apip install pkuseg<\/p>\n<p><span class=\"md-line md-end-block md-focus\" contenteditable=\"true\"><span class=\"md-expand\"> \u5317\u5927\u7684\u5206\u8bcd\u5de5\u5177\u3002<\/span><\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\"><span class=\"\">\uff081)\u591a\u9886\u57df\u5206\u8bcd\u3002\u65b0\u95fb\u3001\u79d1\u7814\u3001\u7f51\u7edc\u3001\u533b\u836f\u3001\u65c5\u6e38\u3001\u91d1\u878d\u3001\u5de5\u4e1a\u3002<\/span><\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\">\uff082\uff09\u8ddf\u9ad8\u7684\u5206\u8bcd\u51c6\u786e\u7387<\/span><\/p>\n<p><span class=\"md-line md-end-block\" contenteditable=\"true\">\uff083\uff09\u652f\u6301\u7528\u6237\u81ea\u8bad\u7ec3\u6a21\u578b\u3002\u652f\u6301\u7528\u6237\u4f7f\u7528\u5168\u65b0\u7684\u6807\u6ce8\u6570\u636e\u8fdb\u884c\u8bad\u7ec3\u3002<\/span><\/p>\n<p>\u7f3a\u70b9\uff0c\u8fdb\u884c\u6587\u4ef6\u5206\u8bcd\u7684\u65f6\u5019\u901f\u5ea6\u7565\u6162\uff0c\u5185\u5b58CPU\u5360\u7528\u8f83\u9ad8<\/p>\n<pre class=\"brush: python; title: ; notranslate\" title=\"\">\r\n#-*- coding:utf-8 -*-\r\nimport pkuseg\r\nseg = pkuseg.pkuseg()\r\ntext = seg.cut('\u8fd9\u662f\u4e00\u6bb5\u6d4b\u8bd5\u7528\u7684\u6587\u672c')\r\nprint(text)\r\n\r\nseg_med = pkuseg.pkuseg(model_name='medicine')\r\ntext2 = seg_med.cut('\u6211\u60f3\u4e70\u70b9\u675c\u4ef2\u548c\u67b8\u675e\u5b50\u4ee5\u53ca\u82f9\u679c\u76ae\uff0c\u8fd8\u6709\u83df\u4e1d\u5b50')\r\nprint('\u533b\u836f\u9886\u57df',text2)   #\r\n\r\n# \u8bcd\u6027\u6807\u6ce8\r\nseg_med = pkuseg.pkuseg(model_name='medicine',postag=True)\r\ntext2 = seg_med.cut('\u6211\u60f3\u4e70\u70b9\u675c\u4ef2\u548c\u67b8\u675e\u5b50\u4ee5\u53ca\u82f9\u679c\u76ae\uff0c\u8fd8\u6709\u83df\u4e1d\u5b50')\r\nprint('\u8bcd\u6027\u6807\u6ce8',text2)   #\r\n\r\n# \u6587\u4ef6\u5206\u8bcd\r\ninpath = r&quot;D:\\win7\u8fdc\u7a0b\\NLP \u5927\u6570\u636e\u4eba\u5de5\u667a\u80fd\u81ea\u7136\u8bed\u8a00\u5904\u7406&#92;&#48;630-\u4e2d\u6587\u6807\u6ce8-BIOES\\day4\\input.txt&quot;\r\noutpath = 'ddd.txt'\r\npkuseg.test(inpath,outpath)   # \u6709\u4e2a\u5751\uff0c\u5bb9\u6613\u6b7b\u673a\uff0cCPU100%\uff0c\u5185\u5b58\u98d9\u53476\u4e2aG\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n<\/pre>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5b89\u88c5\uff1apip install pkuseg \u5317\u5927\u7684\u5206\u8bcd\u5de5\u5177\u3002 \uff081)\u591a\u9886\u57df\u5206\u8bcd\u3002\u65b0\u95fb\u3001\u79d1\u7814\u3001\u7f51\u7edc\u3001\u533b\u836f\u3001\u65c5\u6e38\u3001 [&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-1386","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\/1386","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=1386"}],"version-history":[{"count":3,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1386\/revisions"}],"predecessor-version":[{"id":1397,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1386\/revisions\/1397"}],"wp:attachment":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1386"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1386"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1386"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}