{"id":2199,"date":"2024-12-23T15:53:52","date_gmt":"2024-12-23T07:53:52","guid":{"rendered":"https:\/\/www.haruhi.fans\/?p=2199"},"modified":"2024-12-30T11:19:19","modified_gmt":"2024-12-30T03:19:19","slug":"%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%e4%bd%9c%e4%b8%9aallinone","status":"publish","type":"post","link":"https:\/\/www.haruhi.fans\/?p=2199","title":{"rendered":"\u5927\u8bed\u8a00\u6a21\u578b\u4f5c\u4e1aAllInOne"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\" id=\"A1\">A1<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u7ec3\u4e60\u4ee5\u4e0b\u4e24\u4e2a Unix \u547d\u4ee4\u7684\u64cd\u4f5c\uff08\u6839\u636e Markus Dickinson \u7684\u8bfe\u7a0b\u6539\u7f16\uff09\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u4ece&nbsp;<code>dates_in_may.txt<\/code>&nbsp;\u6587\u4ef6\u4e2d\u521b\u5efa\u4e00\u4e2a\u5355\u8bcd\u5217\u8868\uff0c\u8be5\u5217\u8868\u6309\u5b57\u6bcd\u987a\u5e8f\u6392\u5e8f\uff0c\u4f46\u6392\u5e8f\u65b9\u5f0f\u662f<strong>\u4ece\u53f3\u5230\u5de6<\/strong>\u7684\u3002\u4f8b\u5982\uff0c<code>tina<\/code>&nbsp;\u5e94\u8be5\u6392\u5728&nbsp;<code>angst<\/code>&nbsp;\u4e4b\u524d\u3002\u63d0\u793a\uff1a\u547d\u4ee4&nbsp;<code>rev<\/code>&nbsp;\u53ef\u4ee5\u63a5\u53d7\u4e00\u4e2a\u6587\u4ef6\u4f5c\u4e3a\u53c2\u6570\u5e76\u53cd\u8f6c\u6bcf\u884c\u7684\u5b57\u7b26\u3002\u5c06\u6240\u6709\u547d\u4ee4\u5199\u5165\u4e00\u4e2a\u6587\u4ef6\uff0c\u8f93\u51fa\u7ed3\u679c\u5199\u5165\u53e6\u4e00\u4e2a\u6587\u4ef6\u3002<\/li>\n\n\n\n<li>\u81ea\u52a8\u4ece&nbsp;<code>vm.pos<\/code>&nbsp;\u6587\u4ef6\u4e2d\u521b\u5efa\u4e00\u4e2a\u5305\u542b\u8bcd\u6027\u6807\u6ce8\uff08POS tags\uff09\u7684\u201c\u5b57\u5178\u201d\uff0c\u5373\u751f\u6210\u4e00\u4e2a\u5217\u8868\uff0c\u6bcf\u884c\u6709\u4e00\u4e2a\u8bcd\u6027\u6807\u6ce8\u4ee5\u53ca\u5b83\u7684\u51fa\u73b0\u9891\u7387\u3002\u5047\u8bbe\u6240\u6709\u7684\u5927\u5199\u5b57\u6bcd\u5b57\u7b26\u4ee3\u8868\u8bcd\u6027\u6807\u6ce8\uff0c\u800c\u5c0f\u5199\u5b57\u6bcd\u5b57\u7b26\u4ee3\u8868\u5355\u8bcd\uff08\u56e0\u6b64\u53ef\u4ee5\u5220\u9664\u5c0f\u5199\u5b57\u6bcd\uff09\u3002<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">\u5b89\u88c5\u914d\u7f6e\uff1aMobaXterm\uff0c\u5b98\u7f51\u4e0b\u8f7d\u5373\u53ef<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4efb\u52a1\u4e00\uff1a\u96be\u5ea6\u2b50<\/h3>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\">\u65b0\u624b\u6751\u7b2c\u4e00\u4e2a\u5c0f\u602a<\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">\u7b80\u8981\u6982\u8ff0\uff1a\u9006\u5e8f\u5355\u8bcd\u8868\u3002\u601d\u8def\u662f\u5148\u628a\u6bcf\u4e2a\u5355\u8bcd\u53d8\u6210\u72ec\u7acb\u4e00\u884c\uff0c\u518d\u6bcf\u4e00\u884c\u7684\u5b57\u7b26\u53cd\u8f6c\uff0c\u6309\u7167\u5b57\u6bcd\u6392\u5e8f\uff0c\u518d\u53cd\u8f6c\u56de\u53bb\uff0c\u6700\u540e\u7ed3\u679c\u518d\u8f93\u51fa\u5230\u4e00\u4e2a\u6587\u4ef6\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u89e3\u7b54\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>cat dates_in_may.txt | tr ' ' '\\n'| tr 'A-Z' 'a-z'| tr -cd 'a-z\\n_'| sed  '\/^$\/d'  | rev | sort | rev &gt; a_result.txt<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u9010\u53e5\u89e3\u91ca\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><code>cat dates_in_may.txt<\/code><\/strong>\uff1a\u8bfb\u6587\u4ef6\uff0c\u5c06\u6587\u4ef6\u5185\u5bb9\u4f5c\u4e3a\u8f93\u5165\u6d41\u3002<\/li>\n\n\n\n<li><strong><code>tr ' ' '\\n'<\/code><\/strong>\uff1a\u628a\u6bcf\u4e2a\u5355\u8bcd\u53d8\u6210\u72ec\u7acb\u7684\u4e00\u884c<\/li>\n\n\n\n<li><code><strong>tr 'A-Z' 'a-z'<\/strong><\/code>\uff1a\u5ffd\u89c6\u5927\u5c0f\u5199\uff0c\u5168\u90e8\u53d8\u6210\u5c0f\u5199\uff0c\u53ea\u5173\u5fc3\u5177\u4f53\u7684\u5355\u8bcd<\/li>\n\n\n\n<li><code><strong>tr -cd 'a-z\\n_'<\/strong><\/code>\uff1a\u5220\u9664\u9664\u4e86\u5b57\u6bcd\u6362\u884c\u4e0b\u5212\u7ebf\u7684\u5b57\u7b26\uff0c\u56e0\u4e3a\u8003\u8651\u5230\u6570\u636e\u96c6\u4e2d\u6709_Sound_Pattern_of_English\u8fd9\u6837\u7684\u5355\u8bcd\u3002<\/li>\n\n\n\n<li><strong><code>sed '\/^$\/d'<\/code><\/strong>\uff1a\u5220\u9664\u7a7a\u884c<\/li>\n\n\n\n<li><strong><code>rev<\/code><\/strong>\uff1a\u53cd\u8f6c\u6bcf\u4e00\u884c\u5b57\u7b26<\/li>\n\n\n\n<li><strong><code>sort<\/code><\/strong>\uff1a\u5bf9\u4e8e\u53cd\u8f6c\u540e\u5185\u5bb9\u6392\u5e8f<\/li>\n\n\n\n<li><strong><code>rev<\/code><\/strong>\uff1a\u518d\u53cd\u8f6c\u56de\u6765\uff0c\u5b8c\u6210\u4efb\u52a1<\/li>\n\n\n\n<li><strong><code>&gt; a_result.txt<\/code><\/strong>\uff1a\u6700\u540e\u4e00\u6b65\uff0c\u5199\u5165\u6587\u4ef6\u4e2d<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u7ec8\u7ed3\u679c\u7b26\u5408\u9884\u671f\uff0c\u90e8\u5206\u7ed3\u679c\u5982\u4e0b\u3002\u53ef\u4ee5\u770b\u5230\u662f\u6309\u7167\u53f3\u4fa7cd\u6392\u5e8f\u7684<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-41.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"168\" height=\"248\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-41.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2201\"\/><\/div><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">\u4efb\u52a1\u4e8c\uff1a\u96be\u5ea6\u2b50\u2b50<\/h3>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\">\u7565\u5fae\u590d\u6742\u4e00\u70b9\uff0c\u4f46\u4ecd\u5c5e\u4e8e\u7b80\u5355\u7684\u8303\u7574<\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">\u7b80\u8981\u6982\u8ff0\uff1a\u8fc7\u6ee4\u51faTag\uff0c\u5e76\u7edf\u8ba1\u6392\u5e8f<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5206\u6790\uff1a\u6570\u636e\u5185\u5bb9RT\uff0c\u9700\u8981\u6392\u9664\u5404\u79cd\u5947\u5947\u602a\u602a\u7684\u7b26\u53f7\uff0c\u6700\u7ec8\u53ea\u7559\u4e0bWRB,VBZ\u8fd9\u6837\u7684\u3002\u6ce8\u610f\uff1a\u7b2c\u4e00\u884c\u4e2d\uff0cBOS\uff0cNNK\u4e4b\u7c7b\u7684\u7f16\u7801\u4e0d\u9700\u8981\u4fdd\u7559\uff0c\u6240\u4ee5\u9700\u8981\u5c0f\u5fc3\u7684\u62c6\u89e3\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-42.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"683\" height=\"174\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-42.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2203\"  sizes=\"auto, (max-width: 683px) 100vw, 683px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u89e3\u7b54\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>cat vm.pos | tr -d 'a-z0-9&#91;:punct:]' | sed 's\/^&#91; \\t]<em>\/\/;s\/&#91; \\t]<\/em>$\/\/' | sed '\/^$\/d' | grep '^&#91;A-Z]*$' | sort | uniq -c | sort -nr &gt; pos_frequency.txt<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code><strong>cat vm.pos<\/strong><\/code>\uff1a\u8bfb\u53d6\u6587\u4ef6\u7684\u5185\u5bb9\u3002<\/li>\n\n\n\n<li><code><strong>tr -d 'a-z0-9[:punct:]'<\/strong><\/code>\uff1a\u5220\u9664\u6240\u6709\u7684\u5c0f\u5199\u5b57\u6bcd\uff08\u9898\u76ee\u8bf4\u4e86\uff09\u3001\u6570\u5b57\u548c\u6807\u70b9\u7b26\u53f7\uff0c\u4fdd\u7559\u5927\u5199\u5b57\u6bcd\u3002<\/li>\n\n\n\n<li><code><strong>sed 's\/^[ \\t]*\/\/;s\/[ \\t]*$\/\/'<\/strong><\/code>\uff1a\u53bb\u9664\u6bcf\u884c\u7684\u524d\u540e\u7a7a\u683c\uff0c\u7531\u4e0a\u9762\u6570\u636e\u53ef\u89c1\uff0c\u7a7a\u683c\u7a7a\u683c\u975e\u5e38\u591a\u3002<\/li>\n\n\n\n<li><strong><code>sed '\/^$\/d'<\/code><\/strong>\uff1a\u5220\u9664\u7a7a\u884c\u3002<\/li>\n\n\n\n<li><code><strong>grep '^[A-Z]*$'<\/strong><\/code>\uff1a\u6b64\u65f6\u6211\u4eec\u9700\u8981\u7684\u6570\u636e\u884c\u5df2\u7ecf\u53ea\u5269\u4e0b\u7eaf\u5927\u5199\u5b57\u6bcd\uff0c\u800c\u7f16\u7801\u5185\u5bb9\u8fd8\u5f88\u6df7\u4e71\uff0c\u6211\u4eec\u7b5b\u9009\u5e76\u4fdd\u7559\u53ea\u5305\u542b\u5927\u5199\u5b57\u6bcd\u7684\u884c\uff0c\u5373\u8bcd\u6027\u6807\u6ce8\u3002<\/li>\n\n\n\n<li><code><strong>sort<\/strong><\/code>\uff1a\u5bf9\u8f93\u51fa\u7684\u8bcd\u6027\u6807\u6ce8\u6309\u5b57\u5178\u5e8f\u6392\u5e8f\uff0c<strong>\u56e0\u4e3auniq -c\u53ea\u80fd\u7edf\u8ba1\u8fde\u7eed\u91cd\u590d\u7684\u884c<\/strong>\u3002<\/li>\n\n\n\n<li><code><strong>uniq -c<\/strong><\/code>\uff1a\u7edf\u8ba1\u6bcf\u4e2a\u8bcd\u6027\u6807\u6ce8\u7684\u51fa\u73b0\u6b21\u6570\u3002<\/li>\n\n\n\n<li><code><strong>sort -nr<\/strong><\/code>\uff1a\u6839\u636e\u9891\u7387\u4ece\u9ad8\u5230\u4f4e\u6392\u5e8f\u3002<\/li>\n\n\n\n<li><strong><code>&gt; pos_frequency.txt<\/code><\/strong>\uff1a\u4fdd\u5b58\uff0c\u5b8c\u6210\u4efb\u52a1<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u7ec8\u7ed3\u679c\u7b26\u5408\u9884\u671f\uff0c\u90e8\u5206\u7ed3\u679c\u5982\u4e0b\uff0cBOS\uff0cNNK\u4e4b\u7c7b\u7684\u7f16\u7801\u6ca1\u6709\u4fdd\u7559\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-43.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"209\" height=\"215\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-43.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2204\"\/><\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">A2<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f5c\u4e1a\u8981\u6c42\uff1a<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7528&nbsp;<strong>Unix \u547d\u4ee4<\/strong>&nbsp;\u6765\u5b8c\u6210\u4ee5\u4e0b\u4efb\u52a1\uff0c\u5e76\u6d89\u53ca\u4e24\u4e2a\u8bed\u6599\u5e93\u7684\u6bd4\u8f83\u5206\u6790\uff1a<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>\u7edf\u8ba1\u201c\u7684\u201d\u7684\u9891\u7387<\/strong>\uff1a\n<ul class=\"wp-block-list\">\n<li>\u6bd4\u8f83&nbsp;<strong>\u7ffb\u8bd1\u6c49\u8bed\u6587\u672c\uff08ZCTC_raw\uff09<\/strong>&nbsp;\u548c&nbsp;<strong>\u539f\u751f\u6c49\u8bed\u6587\u672c\uff08LCMC_raw\uff09<\/strong>&nbsp;\u4e2d\u201c\u7684\u201d\u51fa\u73b0\u7684\u9891\u7387\u3002<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>\u5206\u6790\u201c\u662f\u2026\u7684\u201d\u7ed3\u6784\u7684\u9891\u7387<\/strong>\uff1a\n<ul class=\"wp-block-list\">\n<li>\u6bd4\u8f83&nbsp;<strong>\u7ffb\u8bd1\u65b0\u95fb\u6587\u672c\uff08ZCTC \u4e2d\u7684 A B C \u7c7b\uff09<\/strong>&nbsp;\u548c&nbsp;<strong>\u539f\u751f\u65b0\u95fb\u6587\u672c\uff08LCMC \u4e2d\u7684 A B C \u7c7b\uff09<\/strong>&nbsp;\u4e2d\u201c\u662f\u2026\u7684\u201d\u7ed3\u6784\u7684\u9891\u7387\u3002<\/li>\n\n\n\n<li><strong>\u63d0\u793a<\/strong>\uff1a\n<ul class=\"wp-block-list\">\n<li>\u9700\u8981\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5339\u914d\u201c\u662f\u2026\u7684\u201d\u7ed3\u6784\uff0c\u4f8b\u5982\u201c\u6211\u662f\u4ea4\u5927\u7684\u201d\u201c\u4ed6\u662f\u590d\u65e6\u7684\u201d\u3002<\/li>\n\n\n\n<li>\u4f7f\u7528\u5206\u8bcd\u540e\u7684\u6587\u672c\u6587\u4ef6\uff08LCMC_seg \u548c ZCTC_seg\uff09\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>\u7edf\u8ba1\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784<\/strong>\uff1a\n<ul class=\"wp-block-list\">\n<li>\u6839\u636e\u6587\u732e\uff08\u5982 Hu and Kuebler 2021\uff09\u7684\u7814\u7a76\uff0c<strong>\u7ffb\u8bd1\u6c49\u8bed<\/strong>\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u9891\u7387\u9ad8\u4e8e\u539f\u751f\u6c49\u8bed\u3002<\/li>\n\n\n\n<li>\u9a8c\u8bc1\u8fd9\u4e00\u8bf4\u6cd5\uff1a\n<ol class=\"wp-block-list\">\n<li>\u5206\u522b\u7edf\u8ba1 LCMC \u548c ZCTC \u4e2d\u6700\u5e38\u89c1\u7684 10 \u4e2a\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u53ca\u5176\u9891\u7387\u3002<\/li>\n\n\n\n<li>\u7edf\u8ba1\u6bcf\u4e2a\u8bed\u6599\u5e93\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u603b\u9891\u6570\u3002<\/li>\n<\/ol>\n<\/li>\n\n\n\n<li>\u4f7f\u7528\u5e26\u6709\u8bcd\u6027\u6807\u7b7e\u7684\u6587\u672c\u6587\u4ef6\uff08LCMC_wordnpos \u548c ZCTC_wordnpos\uff09\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">\u5206\u6790\u4efb\u52a1\uff1a<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5bf9\u4e8e\u6211\u4eec\u6765\u8bf4\uff0c\u6838\u5fc3\u4efb\u52a1\u5c31\u662f\u4f7f\u7528 Unix \u547d\u4ee4\u6765\u5b8c\u6210\u6587\u672c\u641c\u7d22\u3001\u5339\u914d\u3001\u8ba1\u6570\u7b49\u64cd\u4f5c\uff0c\u5e76\u8bb0\u5f55\u6bcf\u6761\u547d\u4ee4\u7684\u4f5c\u7528\u3002\u5206\u6790\u64cd\u4f5c\u7684\u7ed3\u679c\uff0c\u5e76\u8ba8\u8bba\u4ec5\u4f7f\u7528 Unix \u547d\u4ee4\u5b8c\u6210\u8fd9\u4e9b\u4efb\u52a1\u53ef\u80fd\u5b58\u5728\u7684\u5c40\u9650\u6027\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u4efb\u52a1\u4e00\uff1a\u96be\u5ea6\u2b50<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u4efb\u52a1\u8981\u6c42\uff1a\u53bb\u7edf\u8ba1\u6587\u4ef6\u5939<strong>ZCTC_raw<\/strong>\u548c<strong>LCMC_raw<\/strong>\u4e0b\u9762\u6240\u6709\u6587\u4ef6\u4e2d\u201c\u7684\u201d\u51fa\u73b0\u9891\u7387\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u89e3\u7b54\u601d\u8def\uff1a\u6587\u672c\u5185\u5bb9\u5982\u4e0b\u56fe\u6240\u793a\uff0c\u6211\u4eec\u53ef\u7528grep -o\u53ea\u5339\u914d\u7684\u90e8\u5206\uff0c\u5373\u4e00\u4e2a\u201c\u7684\u201d\uff0c\u5355\u5185\u5bb9\u72ec\u6210\u884c\uff0c\u7136\u540e\u518d\u7edf\u8ba1\u884c\u6570\u5373\u53ef\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-46-1024x210.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"210\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-46-1024x210.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2209\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ee3\u7801\u5b9e\u73b0\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u5728 LCMC_raw \u6587\u4ef6\u5939\u4e2d\u7edf\u8ba1\u201c\u7684\u201d\u7684\u9891\u7387\ngrep -o '\u7684' LCMC_raw\/* | wc -l\n\n# \u5728 ZCTC_raw \u6587\u4ef6\u5939\u4e2d\u7edf\u8ba1\u201c\u7684\u201d\u7684\u9891\u7387\n\ngrep -o '\u7684' ZCTC_raw\/* | wc -l<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u7ec8\u7ed3\u679c\u5982\u4e0b\uff0c\u53ef\u4ee5\u770b\u51fa<strong>\u7ffb\u8bd1\u6587\u672c<\/strong>\u4e2d\u201c\u7684\u201d\u6570\u76ee\u663e\u8457\u9ad8\u4e8e<strong>\u539f\u751f\u6c49\u8bed<\/strong>\u4e2d\u201c\u7684\u201d\u6570\u76ee<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-44.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"989\" height=\"158\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-44.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2206\"  sizes=\"auto, (max-width: 989px) 100vw, 989px\" \/><\/div><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>grep -o &#8216;\u7684&#8217; LCMC_raw\/*\uff1a\u5339\u914d LCMC_raw \u6587\u4ef6\u5939\u4e2d\u6240\u6709\u6587\u4ef6\u4e2d\u7684\u201c\u7684\u201d\u3002<\/li>\n\n\n\n<li>wc -l\uff1a\u7edf\u8ba1\u603b\u9891\u7387\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f46\u662f\u8fd9\u5e76\u4e0d\u4e25\u8c28\uff0c\u5f88\u663e\u7136\u6211\u4eec\u5e76\u4e0d\u6e05\u695a\u603b\u6570\uff0c\u6b64\u65f6\u7684\u9891\u7387\u663e\u5f97\u6ca1\u6709\u610f\u4e49\u3002\u4e8e\u662f\u4f7f\u7528\u4e0b\u9762\u6307\u4ee4\u7edf\u8ba1\u603b\u6587\u672c\u6570\uff0c\u53d1\u73b0\u4e8c\u8005\u6570\u76ee\u57fa\u672c\u76f8\u5f53\u3002\u6240\u4ee5\u6b64\u65f6\u8ba4\u4e3a<strong>\u7ffb\u8bd1\u6587\u672c<\/strong>\u4e2d\u201c\u7684\u201d\u6570\u76ee\u663e\u8457\u9ad8\u4e8e<strong>\u539f\u751f\u6c49\u8bed<\/strong>\u4e2d\u201c\u7684\u201d\u6570\u76ee<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-45.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"948\" height=\"166\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-45.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2207\"  sizes=\"auto, (max-width: 948px) 100vw, 948px\" \/><\/div><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>wc -m LCMC_raw\/*\uff1a\u7edf\u8ba1\u6bcf\u4e2a\u6587\u4ef6\u7684\u5b57\u7b26\u6570\uff0c\u5e76\u5217\u51fa\u6bcf\u4e2a\u6587\u4ef6\u7684\u7ed3\u679c\u3002<\/li>\n\n\n\n<li>tail -n 1\uff1a\u53ea\u53d6\u6700\u540e\u4e00\u884c\u7684\u603b\u8ba1\uff08total\uff09\u5b57\u7b26\u6570\u3002<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u4efb\u52a1\u4e8c\uff1a<\/strong>\u96be\u5ea6\u2b50\uff08\u2b50\u2b50\u2b50\u2b50\uff09<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u4efb\u52a1\u8981\u6c42\uff1a\u5728LCMC_seg \u548c ZCTC_seg\u6587\u4ef6\u5939\u4e0b\uff0c\u7edf\u8ba1\u201d\u662f\u2026\u7684\u201d\u7ed3\u6784\u7684\u9891\u7387<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4efb\u52a1\u5206\u6790\uff1a\u6587\u672c\u5df2\u7ecf\u88ab\u5206\u5f00\uff0c\u76ee\u7684\u8fd8\u662f\u6b63\u5219\u5339\u914d\u3002\u793a\u4f8b\u5185\u5bb9\u6982\u8ff0\u4e3a A \u662f B \u7684\u3002\u5982\u679c\u53ea\u5b9e\u73b0\u8fd9\u6837\u7684\u5185\u5bb9\u5f88\u7b80\u5355\u3002\u4f46\u5982\u4f55\u533a\u5206 A \u662f B \u548c C \u7684 \uff1b A \u662f B \uff0cC \u548c D \u7684\u3002\u8fd9\u4ec5\u4ec5\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u65e0\u6cd5\u63d0\u53d6\u51fa\u6765\uff0c\u5177\u4f53\u6765\u8bf4\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u4ea4\u5927 <strong>\u662f \u81ea\u7531 \uff0c\u7f8e\u4e3d \u548c \u548c\u8c10 \u7684<\/strong><\/li>\n\n\n\n<li>\u4f60 <strong>\u662f \u8c01 \uff0c \u6211 \u7684<\/strong> \u670b\u53cb \uff1f<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f88\u663e\u7136\uff0c\u7b2c\u4e00\u53e5\u7b26\u5408\u8981\u6c42\uff0c\u7b2c\u4e8c\u53e5\u4e0d\u7b26\u5408\u8981\u6c42\u3002\u8fd9\u4e24\u53e5\u6ca1\u6709\u529e\u6cd5\u901a\u8fc7\u7b80\u5355\u7684\u903b\u8f91\u5c31\u533a\u522b\u51fa\u6765\uff0c\u5fc5\u987b\u8981\u6bd4\u5982\u8bcd\u4e49\u5206\u6790\u540e\uff0c\u624d\u6709\u53ef\u80fd\u533a\u5206\u51fa\u6765\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-47-1024x147.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"147\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-47-1024x147.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2210\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd9\u91cc\u6211\u4e0d\u59a8\u5927\u80c6\u5047\u8bbe\uff0c\u9700\u8981\u7684\u5c31\u662f\u5f62\u5982\u201cA \u662f B \u7684\u201d\u8fd9\u79cd\u7b80\u5355\u53e5\uff0c\u8fd9\u5728\u4e00\u5b9a\u7a0b\u5ea6\u4e0a\u662f\u53ef\u4ee5\u8bf4\u660e\u8d8b\u52bf\u7684\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u89e3\u7b54\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u5728 ZCTC_seg \u6587\u4ef6\u5939\u4e2d\u7edf\u8ba1ABC\u7c7b\u4e2d\u201c\u662f...\u7684\u201d\u7684\u9891\u7387\ngrep -Eo '\u662f &#91;^ ]+ \u7684' ZCTC_seg\/ZCTC_A* ZCTC_seg\/ZCTC_B* ZCTC_seg\/ZCTC_C* | wc -l\n\n# \u5728 LCMC_seg \u6587\u4ef6\u5939\u4e2d\u7edf\u8ba1ABC\u7c7b\u4e2d\u201c\u662f...\u7684\u201d\u7684\u9891\u7387\ngrep -Eo '\u662f &#91;^ ]+ \u7684' LCMC_seg\/LCMC_A* LCMC_seg\/LCMC_B* LCMC_seg\/LCMC_C* | wc -l<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li>grep -Eo &#8216;\u662f [^ ]+ \u7684&#8217;\uff1a\u6b63\u5219\u5339\u914d\u7b26\u5408\u8981\u6c42\u7684\uff0c\u8868\u8fbe\u5f0f\u8868\u793a\u4e2d\u95f4\u9664\u4e86\u5f00\u59cb\u7a7a\u7684\u4e00\u683c\uff0c\u91cc\u9762\u5fc5\u987b\u662f\u975e\u7a7a\u683c\uff0c\u8fd9\u6837\u4fdd\u8bc1\u662f \u7684\u8fd9\u79cd\u8bcd\u88ab\u8bef\u5165\u3002-E\u662f\u4e3a\u4e86\u4f7f\u7528\u6269\u5c55\u6b63\u5219\u8868\u8fbe\u5f0f\u8bed\u6cd5\uff0c-o\u4e3a\u4e86\u5206\u884c\u7edf\u8ba1<\/li>\n\n\n\n<li>LCMC_seg\/LCMC_A* LCMC_seg\/LCMC_B* LCMC_seg\/LCMC_C*\uff1a\u89c2\u5bdf\u6587\u4ef6\u683c\u5f0f\u5f97\u5230\u7684\u3002\u53bbLCMC_seg\u6587\u4ef6\u5939\u4e0b\uff0c\u5f97\u5230\u4e09\u79cd\u6587\u4ef6\uff0c\u4ed6\u4eec\u90fd\u4ee5\u81ea\u5df1\u7684\u7c7b\u522b\u6253\u5934<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">wc -l\uff1a\u7edf\u8ba1\u884c\u6570\uff0c\u5f97\u5230\u9891\u7387\u6570\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7ed3\u679c\u5982\u4e0b\uff0c\u8bf4\u660e\u539f\u751f\u65b0\u95fb\u4e2d\u201c\u662f&#8230;\u7684\u201d\u51fa\u73b0\u8bc4\u7387\u4f4e\u4e8e\u7ffb\u8bd1\u6587\u672c\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-50-1024x98.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"98\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-50-1024x98.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2214\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">\u4f5c\u4e1a\u4e09<strong>\uff1a<\/strong>\u96be\u5ea6\u2b50\u2b50<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u5728LCMC_wordnpos \u548c ZCTC_wordnpos\u6587\u4ef6\u5939\u4e0b\uff0c\u5b8c\u6210\u4e24\u4ef6\u4e8b<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>\u5206\u522b\u7edf\u8ba1 LCMC \u548c ZCTC \u4e2d\u6700\u5e38\u89c1\u7684 10 \u4e2a\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u53ca\u5176\u9891\u7387\u3002<\/li>\n\n\n\n<li>\u7edf\u8ba1\u6bcf\u4e2a\u8bed\u6599\u5e93\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u603b\u9891\u6570\u3002<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">\u4efb\u52a1\u5206\u6790\uff1a\u53ef\u4ee5\u770b\u5230\uff0c\u5728\u8fd9\u4e24\u4e2a\u6587\u4ef6\u5939\u4e0b\u7684\u6587\u4ef6\uff0c\u5df2\u7ecf\u505a\u597d\u4e86\u8bcd\u6027\u6807\u6ce8\uff0c\u6240\u4ee5\u53ef\u4ee5\u5148\u53bb\u7f51\u7ad9\u67e5\u51fa\u4e00\u548c\u91cf\u8bcd\u5206\u522b\u5bf9\u5e94\u7684POS tags\uff08\u4f5c\u4e1a\u6587\u6863\u4e2d\u6709\uff09\uff0c\u7136\u540e\u6b63\u5219\u5373\u53ef\u3002\u7edf\u8ba1\u603b\u6570\u5219\u7b80\u5355\u4e86\uff0c\u76f4\u63a5\u770b\u884c\u6570\u5c31\u662f\u7ed3\u679c\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-49-1024x480.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"480\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-49-1024x480.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2213\" style=\"width:620px;height:auto\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u89e3\u7b54\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># \u63d0\u53d6\u539f\u751f\u6587\u672c\u4e2d\u7684\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u4e2d\u6700\u5e38\u89c1\u768410\u4e2a\ngrep -Eho \" \u4e00\/m &#91;^ ]+\/q\" LCMC_wordnpos\/* | sort | uniq -c | sort -nr | head -n 10\n# \u63d0\u53d6\u7ffb\u8bd1\u6587\u672c\u4e2d\u7684\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u4e2d\u6700\u5e38\u89c1\u768410\u4e2a\ngrep -Eho \" \u4e00\/m &#91;^ ]+\/q\" ZCTC_wordnpos\/* | sort | uniq -c | sort -nr | head -n 10\n\n# \u7edf\u8ba1\u539f\u751f\u6587\u672c\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u603b\u9891\u6570\ngrep -Eho \" \u4e00\/m &#91;^ ]+\/q\" LCMC_wordnpos\/* | wc -l\n# \u7edf\u8ba1\u7ffb\u8bd1\u6587\u672c\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u603b\u9891\u6570\ngrep -Eho \" \u4e00\/m &#91;^ ]+\/q\" ZCTC_wordnpos\/* | wc -l<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li>grep -Eho\uff1a-h\u5ffd\u7565\u6587\u4ef6\u540d\u79f0\uff0c-E\u6269\u5c55\u6b63\u5219\u8868\u8fbe\u5f0f\u8bed\u6cd5\uff0c-o\u4e3a\u4e86\u5206\u884c\u7edf\u8ba1<\/li>\n\n\n\n<li>&#8221; \u4e00\/m [^ ]+\/q&#8221;\uff1a\u6309\u7167\u8bcd\u4e49\uff0c\u91cf\u8bcd\u4e3a\/q\uff0c\u4e3a\u4e86\u4fdd\u8bc1\u7b2c\u4e00\u4e4b\u7c7b\u7684\u8bcd\u5e72\u6270\uff0c\u52a0\u4e86\u4e00\u4e2a\u7a7a\u683c\u8868\u793a\u533a\u5206\u3002<\/li>\n\n\n\n<li>LCMC_wordnpos\/*\uff1a\u76ee\u5f55\u4e0b\u5168\u90e8\u6587\u4ef6\u3002<\/li>\n\n\n\n<li>sort | uniq -c | sort -nr\uff1a\u7edf\u8ba1\u6bcf\u79cd\u7ed3\u6784\u7684\u9891\u7387\uff0c\u5e76\u6309\u964d\u5e8f\u6392\u5217\u3002<\/li>\n\n\n\n<li>head -n 10\uff1a\u7edf\u8ba1\u524d\u5341\u4e2a<\/li>\n\n\n\n<li>wc -l\uff1a\u7edf\u8ba1\u884c\u6570\uff0c\u4e5f\u5c31\u662f\u603b\u6570<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u5982\u4e0b\u56fe\u6240\u793a\uff0cTOP10\u51fa\u73b0\u7684\u7ec4\u5408\u5982\u4e0b\uff0c\u53ef\u4ee5\u770b\u5230\u57fa\u672c\u8d8b\u52bf\u662f\u5dee\u4e0d\u591a\u7684\uff0c\u4f46\u662f\u7ffb\u8bd1\u6587\u672c \u4e00\u79cd \u51fa\u73b0\u7684\u9891\u7387\u660e\u663e\u8981\u66f4\u9ad8\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-53-1024x378.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"378\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-53-1024x378.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2217\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u6240\u6709\u51fa\u73b0\u7684\u7ec4\u5408\u5185\u5bb9\u5982\u4e0b<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-54-1024x137.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"137\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-54-1024x137.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2218\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u6240\u4ee5\u7ffb\u8bd1\u6c49\u8bed\u4e2d\u201c\u4e00 + \u91cf\u8bcd\u201d\u7ed3\u6784\u7684\u9891\u7387\u9ad8\u4e8e\u539f\u751f\u6c49\u8bed\uff0c\u57fa\u672c\u5f97\u5230\u9a8c\u8bc1\uff08\u603b\u6570\u4e4b\u524d\u5df2\u5b8c\u6210\u7edf\u8ba1\uff0c\u5e76\u65e0\u660e\u663e\u5dee\u5f02\uff09<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">A3<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u96be\u5ea6\uff1a\u2b50\u2b50\u2b50\u2b50<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">SJTU\u8d85\u7b97\u4e0d\u77e5\u9053\u4e3a\u4ec0\u4e48\u4e0d\u53ef\u4ee5\u4f7f\u7528\u4e86\uff1f\u6211\u7684\u6570\u636e\u8fd8\u5728\u91cc\u9762\u5462\uff01\uff1f<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e00\u4e2a\u597d\u6d88\u606f\u662f\u4e4b\u524d\u5199\u4e86\u4e00\u70b9\u8bb0\u5f55<a href=\"https:\/\/www.haruhi.fans\/?p=1108\">https:\/\/www.haruhi.fans\/?p=1108<\/a>\uff0c\u574f\u6d88\u606f\u662f\u4e0d\u7b26\u5408\u62a5\u544a\u683c\u5f0f\uff0c\u5c11\u6d4b\u4e86\u5f88\u591a\u5f88\u591a\u4e1c\u897f\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u70bc\u4e39\uff0c\u4f46\u662f\u5206\u4e3a3\u4e2a\u90e8\u5206\uff1a\uff081\uff09\u6570\u636e\u9884\u5904\u7406\uff1b\uff082\uff09\u6a21\u578b\u8bad\u7ec3\uff1b\uff083\uff09\u6a21\u578b\u8bc4\u6d4b<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\uff081\uff09\u6570\u636e\u9884\u5904\u7406<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f00\u59cb\u662f\u4e00\u4e2a\u6570\u636e\u7684\u6e05\u6d17\u3002\u6e05\u6d17\u8fc7\u540e\u7684\u6570\u636e\u683c\u5f0f\u5927\u6982\u662f\u6bcf\u4e00\u4e2a\u6c49\u5b57\u4e4b\u95f4\u90fd\u6709\u4e00\u4e2a\u7a7a\u683c\u3002\u81f3\u4e8e\u82f1\u6587\u5355\u8bcd\uff0c\u6211\u4e5f\u662f\u5982\u6b64\uff0c\u56e0\u4e3a\u6d4b\u8bd5\u6570\u636e\u96c6\u5982\u6b64\u3002\u4e3a\u4e86\u53d6\u5f97\u66f4\u9ad8\u7684\u5206\u6570\uff0c\u81ea\u7136\u8981\u9762\u5411\u6570\u636e\u96c6\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/11\/image-2.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"534\" height=\"257\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/11\/image-2.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-1111\" style=\"width:425px;height:auto\"  sizes=\"auto, (max-width: 534px) 100vw, 534px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd9\u6837\u5c31\u5b8c\u6210\u4e86\u4e00\u4e2a\u7b80\u5355\u7684\u6e05\u6d17<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\uff082\uff09\u6a21\u578b\u8bad\u7ec3<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6211\u5f00\u59cb\u4fbf\u662f\u60f3\u8981\u505a\u4e00\u4e2a\u6700\u597d\u7684\u6a21\u578b\uff0c\u8bb0\u5f97\u8001\u5e08\u63d0\u5230\u56f0\u60d1\u5ea6\u6700\u4f4e\u7684\u4f1a\u7ed9\u4e2a\u5c0f\u793c\u7269\uff08\u8001\u5e08\u8c8c\u4f3c\u5fd8\u4e86\uff0c\u90a3\u4e48\u6700\u597d\u80af\u5b9a\u662f\u8981\u6709\u6700\u5927\u7684\u6570\u636e\u91cf\uff0c\u6700\u9ad8\u7684\u5c42\u6b21\uff0c\u5360\u7528\u66f4\u5927\u5185\u5b58\u3002\u4f46\u662f\u5185\u5b58\u8fc7\u5927\u4f1a\u88ab\u4ea4\u6211\u7b97\u6740\u4e86\uff0c\u5c42\u8fc7\u591a\u4f1a\u5bfc\u81f4\u975e\u5e38\u6162\u3002\u7ecf\u8fc7\u4e00\u4e2atrade-off\u6700\u7ec8\u5982\u4e0b\u9762\u6240\u793a\uff0c\u4ea4\u6211\u529e40\u6838\u673a\u566840-50\u5206\u949f\u53ef\u4ee5\u8dd1\u5b8c\u8bad\u7ec3\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">cat data\/full\/*.txt | .\/build\/bin\/lmplz -o 5 -S 15G &gt; models\/full\/full2.arpa<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\uff083\uff09\u6a21\u578b\u8bc4\u6d4b<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5bf9\u4e8e\u8fd9\u6837\u5927\u7684\u4e00\u4e2a\u6a21\u578b\uff0c\u8bc4\u6d4b\u4e5f\u662f\u8981\u82b1\u975e\u5e38\u591a\u65f6\u95f4\u7684\u3002\u8bc4\u6d4b\u4e00\u6b21\u4e5f\u8981\u5c06\u8fd11h\u7684\u65f6\u95f4\uff0c\u6700\u7ec8\u56f0\u60d1\u5ea6\u5927\u698256.\u591a\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-55.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"172\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-55.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2230\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u5982\u679c\u76ee\u6807\u662f\u51b2\u51fb\u6700\u9ad8\u7684\u5206\u6570\uff0c\u90a3\u4e48\u8fd9\u4e2a\u8bed\u6599\u5e93\u548c\u6a21\u578b\u7684\u80fd\u529b\u4e0a\u9650\u5c31\u8fd9\u4e2a\u6c34\u5e73\u4e86\uff0c\u6700\u591a\u56f0\u60d1\u5ea6\u4f4e1-2\u30024\u5c42\u52305\u5c42\u6a21\u578b\u5e76\u6ca1\u6709\u53d8\u597d\u591a\u5c11\uff0c\u4f46\u82b1\u8d39\u65f6\u95f4\u5374\u591a\u4e86\u975e\u5e38\u591a\uff0c\u6a21\u578b\u4e5f\u5927\u4e86\u597d\u51e0\u500d\uff0c\u8fbe\u5230\u4e86\u597d\u51e0\u5341\u4e2aG\u3002\u53ef\u4f9b\u8c03\u6574\u7684\u53c2\u6570\u4e5f\u4e0d\u591a\u3002\u800c\u4e14\u5982\u679c\u60f3\u8981\u51b2\u51fb\u66f4\u9ad8\u5206\u6570\uff0c\u6211\u5b8c\u5168\u53ef\u4ee5\u7528\u66f4\u591a\u6838\u670d\u52a1\u5668\uff0c\u66f4\u591a\u65f6\u95f4\u5728\u6211\u7684\u57fa\u7840\u4e0a\u4fee\u6539\uff0c\u8fd9\u4e0e\u6a21\u578b\u8bad\u7ec3\u4f18\u5316\u7684\u521d\u8877\u4f3c\u4e4e\u6709\u4e9b\u8fdd\u80cc\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"A4\">A4<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u96be\u5ea6\uff1a\u2b50\u2b50\u2b50\u2b50\u2b50<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5b8c\u6210\u4e00\u4e2a\u4e00\u4e2a\u4e00\u4e2a\u903b\u8f91\u56de\u5f52\u9879\u76ee\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u914d\u7f6e\u73af\u5883\u63a8\u8350\u8fd9\u4e00\u7bc7\uff0c\u8bb2\u7684\u5f88\u8be6\u7ec6\u3002\u6211\u8fd8\u662f\u63a8\u8350mnt\u6302\u5728\u5230\u7cfb\u7edf\u91cc\u9762\u4e00\u4e2a\u5177\u4f53\u4f4d\u7f6e\u53bb\uff0c\u8fd9\u6837\u65b9\u4fbf\u64cd\u4f5c\uff0c\u6bd4\u5982\u8bf4\u6211\u5728E\u7684cs124\u6587\u4ef6\u5939\u76ee\u5f55\u4e0b\uff0c\u91cc\u9762\u8be6\u7ec6\u6b65\u9aa4\u90fd\u6709\u4ecb\u7ecd\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/cs124\/pa0-jupyter-tutorial\/blob\/main\/platform\/Windows.md\">https:\/\/github.com\/cs124\/pa0-jupyter-tutorial\/blob\/main\/platform\/Windows.md<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4efb\u52a1\u4ecb\u7ecd\uff1a\u7b80\u5355\u6765\u8bf4\u5c31\u662f\u533a\u5206\u51fa\u4e00\u6761\u6d88\u606f\u662f\u5426aid\u7684\u4fe1\u606f\uff0c\u5e76\u4e14\u9700\u8981\u627e\u5230\u548c\u6551\u63f4\u6709\u5173\u7684\u4fe1\u606f\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e3a\u6b64\uff0c\u6211\u4eec\u8981\u505a\u7684\u662f\u5199\u516d\u4e2a\u51fd\u6570<strong>Sigmoid<\/strong>\uff0c<strong>Logistic Loss<\/strong> \u548c <strong>Logistic Regression Classifier<\/strong>\u4e2d\u56db\u4e2a\uff08__init__\uff0ctrain\uff0cclassify\uff0cget_weights\uff09\uff0c\u6700\u540e\u6a21\u578b\u8bc4\u4f30\uff0c\u8fdb\u884c\u51c6\u786e\u5ea6\u6d4b\u8bd5\uff08\u8bad\u7ec3\u96c6\u548c\u5f00\u53d1\u96c6\u4e0a\uff09\uff0c\u548c\u5408\u7406\u6027\u68c0\u67e5<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u51fd\u6570<\/h3>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Sigmoid<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u5c06\u6a21\u578b\u7684\u7ebf\u6027\u8f93\u51fa\uff08z = W * X + b\uff09\u6620\u5c04\u5230\u6982\u7387\u8303\u56f4 [0, 1]\uff0c\u6309\u7167\u63d0\u793a\u4f7f\u7528sigmoid\u5b8c\u6210\u4efb\u52a1\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def sigmoid(x: np.ndarray) -&gt; np.ndarray:\n  s = 1 \/ (1 + np.exp(-x))\n  return s<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Logistic Loss<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u8ba1\u7b97\u6a21\u578b\u9884\u6d4b\u503c\u4e0e\u771f\u5b9e\u6807\u7b7e\u4e4b\u95f4\u7684\u635f\u5931\uff08\u4ea4\u53c9\u71b5\u635f\u5931\uff09\u3002\u8fd9\u91cc\u4e3a\u4e86\u9632\u6b62log(0) \u7684\u95ee\u9898\uff0c\u6211\u4eec\u52a0\u5165\u4e00\u4e2a\u5f88\u5c0f\u7684epsilon\uff0c\u63a5\u7740\u6839\u636e\u4ea4\u53c9\u71b5\u5b9a\u4e49\u5b8c\u6210\u6b64\u51fd\u6570\uff0c\u6700\u540e\u8fd4\u56de\u4e00\u4e2a\u5e73\u5747\u503c\u3002\u4f7f\u7528np.clip\uff08\uff09\u662f\u4e3a\u4e86\u4e25\u683c\u4fdd\u8bc1\u6982\u7387\u5904\u4e8e(0, 1) \u4e4b\u95f4<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def logistic_loss(y_pred: np.ndarray, y_true: np.ndarray) -&gt; float:\n    epsilon = 1e-8\n    y_pred = np.clip(y_pred, epsilon, 1 - epsilon) \n    \n    # \u6839\u636e\u516c\u5f0f\u8ba1\u7b97\u903b\u8f91\u635f\u5931\n    losses = - (y_true * np.log(y_pred) + (1 - y_true) * np.log(1 - y_pred))\n    return np.mean(losses)<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e0b\u9762\u5c31\u53ef\u4ee5\u6d4b\u6d4b\u6211\u4eec\u7684\u635f\u5931\u4e86\uff0c\u9884\u8ba1\u503c\u4e0e\u771f\u5b9e\u503c\u8d8a\u63a5\u8fd1\uff0closs\u8d8a\u4f4e\uff0c\u53ef\u89c1\u8d8b\u52bf\u8fd8\u662f\u5f88\u660e\u663e\u7684\u3002\u53ef\u89c1\u54ea\u6015\u662f0\u548c1\u4e5f\u6ca1\u6709\u65e0\u7a77\u5927\u6216\u80050\uff0c\u56e0\u4e3a\u6211\u4eec\u4e4b\u524d\u505a\u4e86epsilon\u7684\u7f18\u6545\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-56.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"717\" height=\"264\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-56.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2236\"  sizes=\"auto, (max-width: 717px) 100vw, 717px\" \/><\/div><\/figure>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Logistic Regression Classifier<\/strong><\/h4>\n\n\n\n<h5 class=\"wp-block-heading\">__init__()<\/h5>\n\n\n\n<p class=\"wp-block-paragraph\">\u521d\u59cb\u5316\u5206\u7c7b\u5668\u7684\u53c2\u6570\uff08\u5982\u5b66\u4e60\u7387\u3001\u8fed\u4ee3\u6b21\u6570\u7b49\uff09\u548c\u7279\u5f81\u63d0\u53d6\u5668\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f46\u5b9e\u9645\u4e0a\u4ed6\u7ed9\u7684\u5df2\u7ecf\u5f88\u591f\u7528\u4e86\uff0c\u6211\u5e76\u6ca1\u6709\u4efb\u4f55\u7684\u6dfb\u52a0\u3002\u7531\u4e8e\u68af\u5ea6\u4e0b\u964d\u51fd\u6570\u662f\u4e0d\u8bb8\u53d8\u66f4\u7684\uff0c\u90a3\u6211\u4eec\u8fd9\u90e8\u5206\u5176\u5b9e\u81ea\u7531\u53d1\u6325\u7a7a\u95f4\u4e5f\u5e76\u4e0d\u591a\u3002<\/p>\n\n\n\n<h5 class=\"wp-block-heading\">train()<\/h5>\n\n\n\n<p class=\"wp-block-paragraph\">\u8bad\u7ec3\u903b\u8f91\u56de\u5f52\u6a21\u578b\u3002\u3002example\u5177\u4f53\u6837\u5b50\u5728\u4e0a\u6587\u63d0\u5230\u8fc7\uff0c\u53ef\u4ee5\u89c1\u5230\u662f\u4e00\u4e2aVec<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-57.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1019\" height=\"312\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-57.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2239\"  sizes=\"auto, (max-width: 1019px) 100vw, 1019px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u90a3\u4e48\uff0c\u6211\u4eec\u9700\u8981\u505a\u7684\u662f\u8bcd\u5411\u91cf\u53d8\u6210\u53e5\u5b50\uff0c\u56e0\u4e3a<code>CountVectorizer<\/code>&nbsp;\u9700\u8981\u4ee5\u5b57\u7b26\u4e32\u5f62\u5f0f\u8f93\u5165\u6587\u672c\u6570\u636e\uff0c\u800c\u4e0d\u662f\u5355\u4e2a\u5355\u8bcd\u7684\u5217\u8868\u3002labels\u4e0a\u9762\u770b\u5230\u4e86\uff0c\u5c31\u662f0\u548c1\uff0c\u7b80\u5355\u7c97\u66b4\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">X\u6839\u636e\u4e0a\u9762\u68af\u5ea6\u4e0b\u964d\u51fd\u6570\u5b9a\u4e49\uff0c\u662f\u4e00\u4e2anumpy array\uff0c\u6211\u4eec\u8981toarray()\u628a\u4ed6\u8f6c\u53d8\u4e3a\u5bc6\u96c6\u77e9\u9635\uff0c\u4ee5\u4fbf\u6211\u4eec\u53ef\u4ee5\u7528\u5b83\u6765\u8fdb\u884c\u68af\u5ea6\u4e0b\u964d\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>    def train(self, examples: List&#91;Example]) -&gt; None:\n        \n        texts = &#91;\" \".join(example.words) for example in examples]  \n        labels = np.array(&#91;example.label for example in examples])\n\n        self.X = self.vectorizer.fit_transform(texts).toarray()\n        self.y = labels\n\n        self.weights, self.bias = gradient_descent(\n            X=self.X,\n            Y=self.y,\n            batch_size=self.batch_size,\n            alpha=self.alpha,\n            num_iterations=self.num_iterations,\n            print_every=self.print_every,\n            epsilon=self.epsilon\n        )<\/code><\/pre>\n\n\n\n<h5 class=\"wp-block-heading\">classify<\/h5>\n\n\n\n<p class=\"wp-block-paragraph\">\u7528\u8bad\u7ec3\u597d\u7684\u6743\u91cd\u548c\u504f\u7f6e\u5bf9\u65b0\u6837\u672c\u8fdb\u884c\u5206\u7c7b\uff080 \u6216 1\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5148\u540c\u7406\u8f6c\u6362\u4e3atexts,\u5c06\u6587\u672c\u8f6c\u5316\u4e3a\u7279\u5f81\u77e9\u9635,\u8ba1\u7b97\u7ebf\u6027\u6a21\u578b\u7684\u8f93\u51fa z = X * W + b,\u518dSigmoid \u51fd\u6570\u6620\u5c04\u5230\u5408\u7406\u8303\u56f4\uff0c\u8fd4\u56de\u7ed3\u679c\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def classify(self, examples: List&#91;Example],\n             return_scores: bool = False) -&gt; Union&#91;List&#91;int], List&#91;float]]:\n    \n    texts = &#91;\" \".join(example.words) for example in examples]\n    X = self.vectorizer.transform(texts).toarray() \n    z = np.dot(X, self.weights) + self.bias\n    scores = 1 \/ (1 + np.exp(-z))\n\n    if return_scores:\n        return scores.tolist()\n    else:\n        return &#91;1 if score &gt;= 0.5 else 0 for score in scores]<\/code><\/pre>\n\n\n\n<h5 class=\"wp-block-heading\"><strong>get_weights<\/strong><\/h5>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd4\u56de\u8bad\u7ec3\u597d\u7684\u6743\u91cd\u5411\u91cf\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def get_weights(self) -&gt; np.ndarray:\n  return self.weights<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u7ed3\u679c\uff1a\u8fd9\u4e9b\u8bcd\u90fd\u5f88\u7b26\u5408\u6211\u7684\u76f4\u89c9\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-58-1024x820.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"820\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-58-1024x820.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2240\" style=\"width:558px;height:auto\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8868\u73b0\u6765\u770b\u5012\u4e5f\u6b63\u5e38\uff0c\u8fd9\u4e2a\u51c6\u786e\u5ea6\u4e0d\u77e5\u9053\u662f\u5426\u591f\u597d\u3002\u8fd9\u548c\u4ed6\u7ed9\u6211\u7684\u7ed3\u679c\u5012\u662f\u975e\u5e38\u63a5\u8fd1<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">stop_word\uff0c\u4e00\u4e9b\u5e38\u89c1\u4f46\u610f\u4e49\u8f83\u5f31\u7684\u8bcd\u53ef\u80fd\u6709\u566a\u58f0\uff0c\u53bb\u6389\u3002\u4f46\u5bf9\u6211\u7684\u7ed3\u679c\u5e76\u6ca1\u6709\u4ec0\u4e48\u5f71\u54cd\u3002\u4f46\u662f\u5b9e\u8bdd\u8bf4\u5bf9\u6211\u53ef\u80fd\u8fd8\u662f\u526f\u4f5c\u7528\uff0c\u611f\u89c9\u53ef\u80fd\u662f\u56e0\u4e3a\u5982\u679c\u79fb\u9664\u4e86\u505c\u7528\u8bcd\uff0c\u53ef\u80fd\u4f1a\u4e22\u5931\u4e00\u4e9b\u4e0a\u4e0b\u6587\u4fe1\u606f\u3002\u4f8b\u5982\uff0c\u201clike\u201d \u6216 \u201cto\u201d \u7b49\u8bcd\u53ef\u80fd\u5728\u4e0a\u4e0b\u6587\u4e2d\u6709\u610f\u4e49\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-59.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"848\" height=\"667\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-59.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2241\"  sizes=\"auto, (max-width: 848px) 100vw, 848px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f46\u662f\u5047\u9633\u6027\u548c\u5047\u9634\u6027\u7ed3\u679c\u8fd8\u662f\u5b58\u5728\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ece\u9519\u8bef\u6837\u672c\u6765\u770b\uff0cFalse Negatives \u4e2d\u7684\u6587\u672c\u5f80\u5f80\u662f\u4e00\u4e9b\u8bed\u4e49\u4e0a\u590d\u6742\u7684\u53e5\u5b50\uff0c\u53ef\u80fd\u56e0\u4e3a\u7f3a\u4e4f\u5173\u952e\u7279\u5f81\uff08\u5982\u5173\u952e\u8bcd\uff09\u6216\u4e0a\u4e0b\u6587\u4fe1\u606f\uff0c\u5bfc\u81f4\u6a21\u578b\u672a\u80fd\u8bc6\u522b\u51fa\u5b83\u4eec\u5c5e\u4e8e\u6b63\u7c7b\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6bd4\u5982\u7b2c\u4e00\u6761 FN\uff1a<code>\"i'd like to get more information about the possibility of\"<\/code>\uff0c\u53ef\u80fd\u6bd4\u8f83\u6a21\u7cca\uff0c<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">False Positives \u4e2d\u7684\u6587\u672c\u901a\u5e38\u5305\u542b\u4e00\u4e9b\u5f3a\u76f8\u5173\u7684\u8bcd\u6c47\uff08\u5982 &#8220;food,&#8221; &#8220;water,&#8221; &#8220;help,&#8221; \u7b49\uff09\uff0c\u4f46\u8fd9\u4e9b\u8bcd\u6c47\u53ef\u80fd\u5728\u4e0a\u4e0b\u6587\u4e2d\u5e76\u672a\u771f\u6b63\u8868\u8fbe\u707e\u96be\u6216\u7d27\u6025\u60c5\u51b5\uff0c\u800c\u662f\u51fa\u73b0\u5728\u5176\u4ed6\u60c5\u5883\u4e2d\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7b2c\u4e00\u6761 FP\uff1a<code>\"these communities are in areas experiencing chronic food insecurity environmental problems and a general lack of basic services\"<\/code><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u63cf\u8ff0\u4e86\u67d0\u4e9b\u56f0\u5883\uff0c\u4f46\u662f\u5b9e\u9645\u662f\u8d1f\u7c7b\u3002\u6a21\u578b\u53ef\u80fd\u5b58\u5728\u67d0\u4e9b\u8fc7\u62df\u5408\uff1f\u5bfc\u81f4\u5c06\u8d1f\u7c7b\u6837\u672c\u8bef\u5224\u4e3a\u6b63\u7c7b<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e0b\u9762\u4fee\u6539\u53c2\u6570\u5c1d\u8bd5\u4f18\u5316\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5148\u662f\u5c1d\u8bd5\u5206\u7c7b\u6807\u51c6\u7ed9\u62100.4\uff0c\u5e76\u65e0\u663e\u8457\u5dee\u5f02\uff0c\u786c\u8981\u8bf4\u90a3\u5c31\u662f\u7565\u6709\u4e0a\u5347<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-60.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"422\" height=\"54\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-60.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2244\"  sizes=\"auto, (max-width: 422px) 100vw, 422px\" \/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-61.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"415\" height=\"64\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-61.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2245\"  sizes=\"auto, (max-width: 415px) 100vw, 415px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f53\u6211\u6539\u62100.6\u540e\uff0c\u751a\u81f3\u51fa\u73b0\u4e86\u4e00\u5b9a\u7684\u4e0b\u964d\u3002\u770b\u6765\u76ee\u524d0.5\u4ee5\u4e0b\u5904\u4e8e\u4e00\u4e2a\u6bd4\u8f83\u5408\u7406\u7684\u533a\u95f4<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-62.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"421\" height=\"59\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-62.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2246\" style=\"width:305px;height:auto\"  sizes=\"auto, (max-width: 421px) 100vw, 421px\" \/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-63.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"418\" height=\"55\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-63.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2247\" style=\"width:317px;height:auto\"  sizes=\"auto, (max-width: 418px) 100vw, 418px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u90a3\u4e48\u518d\u67650.3\uff0c\u81ea\u7136\u663e\u8457\u4e0b\u964d\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-64.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"416\" height=\"55\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-64.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2248\" style=\"width:347px;height:auto\"  sizes=\"auto, (max-width: 416px) 100vw, 416px\" \/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-65.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"412\" height=\"54\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-65.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2249\" style=\"width:330px;height:auto\"  sizes=\"auto, (max-width: 412px) 100vw, 412px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u5c1d\u8bd5\u4ecemin_df\u7740\u624b\uff0c\u4e4b\u524dFN\u6709\u4e9b\u4e0d\u5c31\u662f\u770b\u4e0d\u51fa\u6765\uff0c\u5c1d\u8bd5\u53d8\u5927\u53d8\u5c0f\u770b\u770b\u3002\u8fd9\u4e2a\u8868\u793aCountVectorizer\u8003\u8651\u9891\u7387\u7684\u6700\u4f4e\u503c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">min_df\u8bbe\u7f6e\u4e3a10\uff0c\u4ece\u51c6\u786e\u5ea6\u6765\u770b\uff0cemm\uff0cno stopword removal\u7684\u8fd9\u4e24\u8005\u7684\u533a\u522b\u53d8\u5927\u4e86\u3002\u8bad\u7ec3\u901f\u5ea6\u53d8\u7684\u975e\u5e38\u611f\u4eba\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-66.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"426\" height=\"58\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-66.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2250\"  sizes=\"auto, (max-width: 426px) 100vw, 426px\" \/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-67.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"421\" height=\"50\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-67.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2251\"  sizes=\"auto, (max-width: 421px) 100vw, 421px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">min_df\u8bbe\u7f6e\u4e3a30\uff0c\u8089\u773c\u53ef\u89c1\u8bad\u7ec3\u901f\u5ea6\u5feb\u4e86\u4e0d\u5c11<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-68.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"430\" height=\"55\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-68.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2252\"  sizes=\"auto, (max-width: 430px) 100vw, 430px\" \/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-69.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"421\" height=\"55\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-69.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2253\"  sizes=\"auto, (max-width: 421px) 100vw, 421px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e5f\u5c1d\u8bd5\u8fc7\u8bb8\u591a\u5176\u5b83\u53c2\u6570\uff0c\u6bd4\u5982\u5b66\u4e60\u7387\uff0c\u8bad\u7ec3\u6570\u7b49\u7b49\u3002\u4f46\u662f\u5b9e\u9645\u611f\u89c9\u610f\u4e49\u4e0d\u5927\uff0cAccuracy\u548cLoss\u5e76\u6ca1\u6709\u663e\u8457\u53d8\u5316\uff0c\u5f53\u7136\u8bad\u7ec3\u8bba\u8ff0\u591a\uff0c\u53ef\u80fd\u4f1a\u66f4\u597d\u4e00\u70b9\u70b9\u3002\u4f46\u6ca1\u6709\u4ec0\u4e48\u672c\u8d28\u533a\u522b\uff0c\u533a\u522b\u53ea\u662f\u65f6\u95f4\u7684\u957f\u77ed\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6240\u4ee5\uff0c\u5982\u679c\u60f3\u8981\u5f97\u5230\u66f4\u597d\u7684\u7ed3\u679c\uff0c\u5c31\u5982\u4e0a\u9762\u5206\u6790\u4e00\u6837\uff0c\u90a3\u4e48\u9700\u8981\u7684\u5e94\u8be5\u662f\u66f4\u597d\u7684\u7279\u5f81\u6355\u6349\uff0c\u6355\u6349\u66f4\u6df1\u7684\u8bcd\u4e49\u3002\u6a21\u578b\u6240\u9650\uff0c\u4f18\u5316\u4e0a\u7ebf\u5982\u6b64\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">A5<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u96be\u5ea6\uff1a\u2b50\u2b50\u2b50\u2b50\u2b50\u2b50\u2b50<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Part1\uff1aSynonyms<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u540c\u4e49\u8bcd\u3002\u6211\u4eec\u7684\u4efb\u52a1\u662f\u5b8c\u6210\u7b54\u9898\uff0c\u6bd4\u5982\u8bf4\u627e\u5230\u6218\u58eb\u7684\u76f8\u4f3c\u7684\u8bcd\u3002\u539f\u7406\u5c31\u662f\u90a3\u51e0\u79cd\u8ddd\u79bb\u8868\u793a\u76f8\u4f3c\u5ea6\u3002\u8fd9\u91cc\u53ea\u9700\u8981\u5b8c\u6210\u56db\u4e2a\u51fd\u6570\uff0ceuclidean_distance\uff0ccosine_similarity\uff0cfind_synonym\uff0cpart1_written<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">euclidean_distance<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u8ba1\u7b97\u4e24\u4e2a\u5411\u91cf\u4e4b\u95f4\u7684\u6b27\u6c0f\u8ddd\u79bb\uff0c\u5c31\u662f\u7a7a\u95f4\u4e2d\u4e24\u70b9\u8ddd\u79bb\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">np.linalg.norm\u5c31\u662f\u7b97\u6cdb\u5f0f\uff0c\u9ed8\u8ba4\u662f\u7b2c\u4e8c\u6cdb\u5f0f\u4e5f\u5c31\u662f\u6b27\u6c0f\u8ddd\u79bb\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def euclidean_distance(v1, v2):\n    euclidean_dist = np.linalg.norm(v1 - v2)\n    return euclidean_dist    <\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>cosine_similarity<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u8ba1\u7b97\u4e24\u4e2a\u5411\u91cf\u4e4b\u95f4\u7684\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff0c\u8ba1\u7b97\u4e24\u4e2a\u5411\u91cf\u7684\u70b9\u79ef\uff0c\u7136\u540e\u9664\u4ee5\u5b83\u4eec\u7684\u6a21\uff08\u5373\u5411\u91cf\u7684\u957f\u5ea6\uff09\u6765\u5f97\u5230\u7684\u3002\u56fe\u4e0a\u5927\u6982\u5c31\u662f\u4e24\u4e2a\u5411\u91cf\u4e4b\u95f4\u7684\u5939\u89d2<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def cosine_similarity(v1, v2):\n    dot_product = np.dot(v1, v2)\n    magnitude_v1 = np.linalg.norm(v1)\n    magnitude_v2 = np.linalg.norm(v2)\n    cosine_sim = dot_product \/ (magnitude_v1 * magnitude_v2)\n    return cosine_sim  <\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>find_synonym<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u5c31\u662f\u5f00\u59cb\u505a\u9898\u4e86\uff0c\u53bb\u6839\u636e\u76f8\u4f3c\u5ea6\uff0c\u627e\u5230\u6b63\u786e\u7684\u7b54\u6848\u3002\u5982\u679c\u4f7f\u7528\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff0c\u9009\u62e9\u76f8\u4f3c\u5ea6\u6700\u9ad8\u7684\u8bcd\uff1b\u5982\u679c\u4f7f\u7528\u6b27\u6c0f\u8ddd\u79bb\uff0c\u9009\u62e9\u8ddd\u79bb\u6700\u5c0f\u7684\u8bcd\u3002\u5982\u679c\u4f7f\u7528\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff08&#8217;cosine_sim&#8217;\uff09\uff0c\u5c06 best_score \u8bbe\u4e3a\u8d1f\u65e0\u7a77\u5927\uff0c\u56e0\u4e3a\u6211\u4eec\u5e0c\u671b\u627e\u5230\u6700\u5927\u503c\u3002\u5982\u679c\u4f7f\u7528\u6b27\u51e0\u91cc\u5f97\u8ddd\u79bb\uff08&#8217;euc_dist&#8217;\uff09\uff0c\u5c06 best_score \u8bbe\u4e3a\u6b63\u65e0\u7a77\u5927\uff0c\u56e0\u4e3a\u6211\u4eec\u5e0c\u671b\u627e\u5230\u6700\u5c0f\u503c\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def find_synonym(word, choices, embeddings, comparison_metric):\n    answer = None\n    best_score = float('-inf') if comparison_metric == 'cosine_sim' else float('inf')\n  \n    for choice in choices:\n        if comparison_metric == 'cosine_sim':\n            score = cosine_similarity(embeddings&#91;word], embeddings&#91;choice])\n            if score &gt; best_score:\n                best_score = score\n                answer = choice\n        elif comparison_metric == 'euc_dist':\n            score = euclidean_distance(embeddings&#91;word], embeddings&#91;choice])\n            if score &lt; best_score:\n                best_score = score\n                answer = choice\n    return answer<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>part1_written<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u6a21\u578b\u53ef\u80fd\u4f1a\u9009\u62e9\u201c\u60b2\u89c2\u7684\u201d\u800c\u4e0d\u662f\u201c\u79ef\u6781\u7684\u201d\uff0c\u56e0\u4e3a\u5728\u8bad\u7ec3\u6570\u636e\u4e2d\uff0c\u201c\u4e50\u89c2\u7684\u201d\u548c\u201c\u60b2\u89c2\u7684\u201d\u53ef\u80fd\u5728\u5411\u91cf\u7a7a\u95f4\u4e2d\u66f4\u63a5\u8fd1\uff0c\u5c3d\u7ba1\u5b83\u4eec\u7684\u610f\u601d\u76f8\u53cd\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7b54\u6848\u4e0e\u9884\u671f\u4e00\u81f4\uff0c\u7b2c\u4e00\u90e8\u5206\u5b8c\u6210\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-70.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"771\" height=\"449\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-70.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2258\" style=\"width:493px;height:auto\"  sizes=\"auto, (max-width: 771px) 100vw, 771px\" \/><\/div><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">Part2\uff1aAnalogies<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u7c7b\u6bd4\uff0ca:b \u2192 aa:bb\uff0c\u6211\u4eec\u8fd9\u91cc\u5b8c\u6210\u4e00\u4e2a\u7c7b\u6bd4\u7684\u63a8\u6f14\uff0c\u539f\u7406\u7c7b\u4f3c\u4e8e\u5e73\u884c\u56db\u8fb9\u5f62\u3002\u6bd4\u5982\u8bf4\u201c\u7537\u4eba\uff1a\u56fd\u738b \u2192 \u5973\u4eba\uff1a\u5973\u738b\u201d<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">find_analogy_word()<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">a , b , aa\uff0c\u6211\u4eec\u53bb\u627e\u6253\u90a3\u4e2a\u6700\u597d\u7684bb\uff0c\u5728\u5019\u9009\u8bcd\u5217\u8868\u4e2d\u627e\u5230\u6700\u80fd\u5b8c\u6210\u7c7b\u6bd4\u7684\u8bcd\uff08\u5229\u7528\u4f59\u5f26\u76f8\u4f3c\u5ea6\u4f5c\u4e3a\u76f8\u4f3c\u6027\u5ea6\u91cf\uff09\u3002\u5c31\u662f\u5148\u5e73\u884c\u56db\u8fb9\u5f62\uff0c\u7b97\u51fa\u671f\u671b\u7684\u8fb9\uff0c\u518d\u6bd4\u8f83\u76f8\u4f3c\u5ea6\uff0c\u9009\u62e9\u4f59\u5f26\u76f8\u4f3c\u5ea6\u6700\u5927\u7684\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def find_analogy_word(a, b, aa, choices, embeddings):\n    answer = None\n    best_score = float('-inf')\n    analogy_vector = embeddings&#91;b] - embeddings&#91;a] + embeddings&#91;aa]\n    for choice in choices:\n        choice_vector = embeddings&#91;choice]\n        cosine_sim = np.dot(analogy_vector, choice_vector) \/ (\n            np.linalg.norm(analogy_vector) * np.linalg.norm(choice_vector)\n        )\n        if cosine_sim &gt; best_score:\n            best_score = cosine_sim\n            answer = choice\n    return answer<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u6700\u7ec8\u7ed3\u679c\u5982\u4e0b\uff0c\u4e0e\u9884\u671f\u4e00\u81f4\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-71-1024x717.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"717\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-71-1024x717.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2263\" style=\"width:571px;height:auto\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">Part 3: Sentence Similarity<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u8bed\u53e5\u76f8\u4f3c\u3002\u7b80\u5355\u6765\u8bf4\uff0c\u7ed9\u4f60\u4e24\u4e2a\u53e5\u5b50\uff0c\u75280 or 1,\u6765\u8bf4\u660e\u4e24\u4e2a\u53e5\u5b50\u8bed\u4e49\u662f\u5426\u63a5\u8fd1\u3002\u6bd4\u5982\u8bf4\u201c\u6211\u5403\u4e86\u996d\u201d\u548c\u201c\u996d\u88ab\u6211\u5403\u4e86\u201d\u8fd9\u6837\u76f8\u4f3c\u3002\u5177\u4f53\u5b9e\u73b0\u6765\u8bf4\u5c31\u662f\u901a\u8fc7\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff08cosine similarity\uff09\u8ba1\u7b97\u4e24\u4e2a\u53e5\u5b50\u5d4c\u5165\u5411\u91cf\u4e4b\u95f4\u7684\u76f8\u4f3c\u5ea6\uff0c\u5982\u679c\u8d85\u8fc7\u4e00\u5b9a\u9608\u503c\uff0c\u5c31\u8ba4\u4e3a\u4ed6\u4eec\u76f8\u4f3c\u3002\u8fd9\u91cc\u662f\u5b9e\u73b0\u4e24\u4e2a\u51fd\u6570\uff0cget_embedding\u548cget_similarity\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5c06\u53e5\u5b50\u8f6c\u5316\u4e3a\u5355\u4e2a\u5411\u91cf\u5d4c\u5165\u7684\u6b65\u9aa4\u6709\u4ee5\u4e0b\u4e24\u79cd\u65b9\u5f0f\uff0c\u8981\u4e48\u7b80\u5355\u6c42\u548c\uff0c\u628a\u5b50\u4e2d\u6bcf\u4e2a\u5355\u8bcd\u7684\u5d4c\u5165\u5411\u91cf\u76f8\u52a0\uff0c\u5f97\u5230\u4e00\u4e2a\u603b\u7684\u53e5\u5b50\u5411\u91cf\u3002\u8981\u4e48\u57fa\u4e8e\u8bcd\u6027\u52a0\u6743\u6c42\u548c<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">get_embedding<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u5c06\u8f93\u5165\u7684\u53e5\u5b50\u8f6c\u5316\u4e3a\u4e00\u4e2a\u53e5\u5b50\u5d4c\u5165\uff08\u5411\u91cf\u8868\u793a\uff09\u3002\u521d\u59cb\u53160\u5411\u91cf\uff0c\u5bf9\u4e8ewords\u5206\u8bcd\uff0c\u5224\u65ad\u662f\u5426\u5f00\u6717\u6839\u636e\u8bed\u4e49\u5206\u8bcd\uff0c\u662f\u7684\u8bdd\u5148\u83b7\u53d6\u6bcf\u4e00\u4e2a\u7684\u8bcd\u6027\uff0c\u52a0\u6743\u6c42\u548c\uff0c\u6700\u540e\u5f52\u4e00\u5316\u3002\u4e0d\u662f\u7684\u8bdd\u6bcf\u4e2a\u8bcd\u90fd\u4e00\u6837\uff0c\u6700\u540e\u8fd8\u662f\u52a0\u6743\u6c42\u548c\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def get_embedding(s, embeddings, use_POS=False, POS_weights=None):\n  embed = np.zeros(embeddings.vector_size)\n  words = word_tokenize(s)\n  if use_POS:\n      tagged_tokens = nltk.pos_tag(words)\n      total_weight = 0.0\n      for word, tag in tagged_tokens:\n          if word in embeddings and tag in POS_weights:\n              embed += embeddings&#91;word] * POS_weights&#91;tag]\n              total_weight += POS_weights&#91;tag]\n      if total_weight &gt; 0:\n          embed \/= total_weight\n  else:\n      count = 0\n      for word in words:\n          if word in embeddings:\n              embed += embeddings&#91;word]\n              count += 1\n      if count &gt; 0:\n          embed \/= count\n  return embed<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">get_similarity<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u8ba1\u7b97\u4e24\u4e2a\u53e5\u5b50\u7684\u4f59\u5f26\u76f8\u4f3c\u5ea6\u3002s1,s2\u5c31\u662f\u6211\u4eec\u90a3\u4e24\u4e2a\u53e5\u5b50\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f00\u59cb\u5c06\u53e5\u5b50&nbsp;<code>s1<\/code>&nbsp;\u548c&nbsp;<code>s2<\/code>&nbsp;\u8f6c\u6362\u4e3a\u56fa\u5b9a\u7ef4\u5ea6\u7684\u5d4c\u5165\u5411\u91cf&nbsp;<code>embed1<\/code>&nbsp;\u548c&nbsp;<code>embed2<\/code>\u3002\u68c0\u67e5\u4e0b\u4fdd\u8bc1\u4e0d\u662f\u7a7a\u5411\u91cf\uff0c\u8ba1\u7b97\u6211\u4eec\u7684\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff0c\u8fd4\u56de\u5373\u53ef\u3002\u662f\u7a7a\u5411\u91cf\u5c31\u76f4\u63a50.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def get_similarity(s1, s2, embeddings, use_POS, POS_weights=None):\n    similarity = 0\n    embed1 = get_embedding(s1, embeddings, use_POS, POS_weights)\n    embed2 = get_embedding(s2, embeddings, use_POS, POS_weights)\n\n    if np.linalg.norm(embed1) &gt; 0 and np.linalg.norm(embed2) &gt; 0:\n        similarity = np.dot(embed1, embed2) \/ (np.linalg.norm(embed1) * np.linalg.norm(embed2))\n    else:\n        similarity = 0.0\n    return similarity<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u53ef\u4ee5\u770b\u5230\uff0c\u7ed3\u679c\u4e0e\u9884\u671f\u5b8c\u5168\u4e00\u81f4\uff0c\u8868\u660e\u7ecf\u8fc7\u52a0\u6743\u6c42\u548c\u5f97\u5230\u7684\u6548\u679c\u66f4\u597d\uff0c\u51c6\u786e\u5ea6\u66f4\u9ad8\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-72-1024x644.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"644\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-72-1024x644.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2270\" style=\"width:690px;height:auto\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"Part-4:-Exploration\">Part 4: Exploration<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u6709\u4e86\u524d\u9762\u7684\u79ef\u7d2f\uff0c\u73b0\u5728\u5c31\u53ef\u4ee5\u6765\u89e3\u51b3\u5b9e\u9645\u95ee\u9898\u4e86<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>occupation_exploration<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u9700\u8981\u5b9e\u73b0\u4e00\u4e2a\u51fd\u6570\uff0c\u6839\u636e\u804c\u4e1a\u540d\u79f0\u5217\u8868\u548c\u8bcd\u5d4c\u5165\u6a21\u578b\uff0c\u627e\u5230\u4e0e\u5355\u8bcd &#8220;man&#8221; \u4ee5\u53ca &#8220;woman&#8221; \u6700\u76f8\u4f3c\u76845\u4e2a\u804c\u4e1a\u3002\u804c\u4e1a\u4e4b\u95f4\u7684\u76f8\u4f3c\u5ea6\u4f7f\u7528\u4f59\u5f26\u76f8\u4f3c\u5ea6\u8fdb\u884c\u8861\u91cf\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5148\u68c0\u67e5\u662f\u5426\u662fman\u548cwoman\uff0c\u662f\u7684\u8bdd\u7ee7\u7eed\u63d0\u53d6\u8bcd\u5411\u91cf\u3002\u7136\u540e\u5bf9\u4e8e\u5408\u89c4\u7684\u804c\u4e1a\uff0c\u5206\u522b\u8ba1\u7b97\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff0c\u6dfb\u52a0\u5230\u76f8\u4f3c\u5ea6\u5217\u8868\uff0c\u6700\u540e\u6392\u5e8f\u5f97\u5230\u4e86\u524d5\u7684\u804c\u4e1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def occupation_exploration(occupations, embeddings):\n    top_man_occs = &#91;]\n    top_woman_occs = &#91;]\n    if 'man' not in embeddings or 'woman' not in embeddings:\n        raise ValueError(\"Embeddings for 'man' and 'woman' are required.\")\n\n    man_embedding = embeddings&#91;'man']\n    woman_embedding = embeddings&#91;'woman']\n\n    man_similarities = &#91;]\n    woman_similarities = &#91;]\n\n    for occ in occupations:\n        if occ in embeddings:\n            occ_embedding = embeddings&#91;occ]\n            similarity_to_man = np.dot(man_embedding, occ_embedding) \/ (np.linalg.norm(man_embedding) * np.linalg.norm(occ_embedding))\n            similarity_to_woman = np.dot(woman_embedding, occ_embedding) \/ (np.linalg.norm(woman_embedding) * np.linalg.norm(occ_embedding))\n            man_similarities.append((similarity_to_man, occ))\n            woman_similarities.append((similarity_to_woman, occ))\n\n    man_similarities.sort(key=lambda x: x&#91;0], reverse=True)\n    woman_similarities.sort(key=lambda x: x&#91;0], reverse=True)\n\n    top_man_occs = &#91;occ for _, occ in man_similarities&#91;:5]]\n    top_woman_occs = &#91;occ for _, occ in woman_similarities&#91;:5]]\n    return top_man_occs, top_woman_occs<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">part4_written<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e00\u4e9b\u804c\u4e1a\u66f4\u63a5\u8fd1\u201c\u7537\u4eba\u201d\uff0c\u800c\u53e6\u4e00\u4e9b\u804c\u4e1a\u66f4\u63a5\u8fd1\u201c\u5973\u4eba\u201d\uff0c\u8fd9\u53cd\u6620\u4e86\u793e\u4f1a\u4e2d\u5b58\u5728\u7684\u6027\u522b\u523b\u677f\u5370\u8c61\u3002\u53ef\u80fd\u662f\u56e0\u4e3a\u7528\u4e8e\u8bad\u7ec3\u8bcd\u5411\u91cf\u7684\u6570\u636e\u4e2d\u5305\u542b\u4e86\u8fd9\u4e9b\u504f\u89c1\uff0c\u5bfc\u81f4\u6a21\u578b\u5b66\u4e60\u5230\u4e86\u8fd9\u4e9b\u5173\u8054\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Part 5: Entity Representation<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f7f\u7528 \u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u6a21\u578b (NER Model) \u4ece Wikipedia \u7684\u6587\u6863\u4e2d\u63d0\u53d6\u547d\u540d\u5b9e\u4f53 (Named Entities)\u3002\u4f8b\u5982\uff0cBarack Obama \u662f\u4e00\u4e2a\u547d\u540d\u5b9e\u4f53\uff0c\u7c7b\u522b\u4e3a\u201c\u4eba\u540d\u201d\u3002\u63d0\u53d6\u547d\u540d\u5b9e\u4f53\u540e\uff0c\u7814\u7a76\u54ea\u4e9b\u5b9e\u4f53\u5f7c\u6b64\u76f8\u4f3c\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">extract_named_entities<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u7ed9\u4e00\u6bb5\u6587\u672c\uff0c\u4f7f\u7528 SpaCy \u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u529f\u80fd\u63d0\u53d6\u547d\u540d\u5b9e\u4f53\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7528nlp\u5bf9\u8c61\uff0c\u628a\u6211\u4eec\u7684\u6bb5\u843d\u8f6c\u5316\u4e3aSpaCy\u6587\u6863\uff0c\u6587\u6863\u63d0\u53d6\u6587\u6863\u4e2d\u7684\u547d\u540d\u5b9e\u4f53\u5e76\u8fd4\u56de\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def extract_named_entities(paragraph):\n    global nlp\n    spacy_paragraph = nlp(paragraph)\n    named_entities = list(spacy_paragraph.ents)\n    return named_entities, spacy_paragraph<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">compute_entity_representation<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e3a\u6bcf\u4e2a\u5b9e\u4f53\u6784\u5efa\u4e00\u4e2a\u8868\u793a\u5411\u91cf\uff0c\u4f7f\u7528\u63cf\u8ff0\u4e2d\u7684\u8bcd\u5d4c\u5165\u8ba1\u7b97\u5b9e\u4f53\u7684\u5e73\u5747\u5411\u91cf\uff0c\u6536\u96c6\u6240\u6709\u7b26\u5408\u6761\u4ef6\u7684\u8bcd\u7684\u5d4c\u5165\u5411\u91cf\uff0c\u5e76\u8ba1\u7b97\u5b83\u4eec\u7684\u5e73\u5747\u503c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u904d\u5386\u63cf\u8ff0\u4e2d\u7684\u6bcf\u4e2a\u8bcd\uff0c\u68c0\u67e5\u5176\u662f\u5426\u4e3a\u505c\u7528\u8bcd\uff0c\u5e76\u5728\u5d4c\u5165\u5b57\u5178\u4e2d\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def compute_entity_representation(description, embeddings):\n    vector = None\n    word_vectors = &#91;]\n    for token in description:\n        if not token.is_stop and token.text.lower() in embeddings:\n            word_vectors.append(embeddings&#91;token.text.lower()])\n\n    if word_vectors:\n        vector = np.mean(np.array(word_vectors), axis=0)\n    return vector<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">get_top_k_similar<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">\u8ba1\u7b97\u7ed9\u5b9a\u5b9e\u4f53\u5d4c\u5165\u4e0e\u4e00\u7ec4\u5019\u9009\u5b9e\u4f53\u5d4c\u5165\u4e4b\u95f4\u7684\u76f8\u4f3c\u6027\uff0c\u8fd4\u56de\u6700\u76f8\u4f3c\u7684\u524d k \u4e2a\u5b9e\u4f53\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u9996\u5148\u5bf9\u5b9e\u4f53\u5d4c\u5165\u548c\u5019\u9009\u5d4c\u5165\u8fdb\u884c\u5f52\u4e00\u5316\uff0c\u4f7f\u7528 NumPy \u7684\u77e9\u9635\u4e58\u6cd5\u8ba1\u7b97\u4f59\u5f26\u76f8\u4f3c\u5ea6\uff0c\u6700\u540e\u6839\u636e\u76f8\u4f3c\u5ea6\u6392\u5e8f\u5e76\u9009\u62e9\u524d k \u4e2a\u6700\u76f8\u4f3c\u7684\u5b9e\u4f53\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def get_top_k_similar(entity_embedding, choices, top_k):\n    similar_entities = &#91;]\n    if not choices:\n        return similar_entities\n    choice_names = list(choices.keys())\n    choice_embeddings = np.array(list(choices.values()))\n    entity_embedding_norm = entity_embedding \/ np.linalg.norm(entity_embedding)\n    choice_embeddings_norm = choice_embeddings \/ np.linalg.norm(choice_embeddings, axis=1, keepdims=True)\n    similarities = np.matmul(choice_embeddings_norm, entity_embedding_norm)\n    top_k_indices = np.argsort(similarities)&#91;::-1]&#91;:top_k]\n    similar_entities = &#91;choice_names&#91;i] for i in top_k_indices]\n    return similar_entities<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u7ed3\u679c\u975e\u5e38\u597d\uff0c\u7b26\u5408\u8981\u6c42\u3002\u5927\u4e8e\u4e86\u4ed6\u7684\u8981\u6c42<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-73-1024x316.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"316\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-73-1024x316.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2280\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e0b\u9762\u7684\u51c6\u786e\u5ea6\u548c\u5206\u6570\u4e5f\u90fd\u9065\u9065\u9886\u5148\uff0c\u4efb\u52a1\u6210\u529f\u843d\u4e0b\u5e37\u5e55\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-74-1024x720.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"720\" data-original=\"https:\/\/www.haruhi.fans\/wp-content\/uploads\/2024\/12\/image-74-1024x720.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-2282\" style=\"width:676px;height:auto\"  sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u5927\u8bba\u6587<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u96be\u5ea6\uff1a\u2b50\u2b50\uff08\u2b50\u2b50\u2b50\u2b50\u2b50\u2b50\u2b50\u2b50\uff09<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u91c7\u7528\u4e86\u661f\u706b\u5927\u6a21\u578b\uff0c\u4e3a\u4ec0\u4e48\u5462\uff1f\u56e0\u4e3a\u4ed6\u514d\u8d39\u989d\u5ea6\u6700\u591a\u4e86\uff0c\u6a21\u578b\u8fd8\u6bd4\u8f83\u597d\u7528\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6211\u7684\u8ba1\u5212\u662f\u5bf9\u4e8e\u4e09\u79cd\u4e0d\u540c\u7684\u4efb\u52a1\uff0c\u4e00\u79cd\u662f\u6587\u7ae0\u5185\u5bb9\u6897\u6982\uff0c\u4e00\u79cd\u662f\u5c0f\u7ea2\u4e66\u6587\u6848\u751f\u6210\uff0c\u4e00\u79cd\u662f\u6d3b\u52a8\u7b56\u5212\u3002\u4e3a\u4ec0\u4e48\u9009\u62e9\u8fd9\u4e09\u79cd\u5462\uff0c\u662f\u56e0\u4e3a\u8fd9\u4e09\u79cd\u5bf9\u5e94\u7684\u6587\u672c\u751f\u6210\u7b56\u7565\u3002\u6587\u7ae0\u5185\u5bb9\u6897\u6982\u8981\u6c42\u5185\u5bb9\u7cbe\u786e\uff0c\u9075\u5faa\u539f\u6587\uff1b\u5c0f\u7ea2\u4e66\u6587\u6848\u751f\u6210\u9700\u8981\u4e00\u5b9a\u7684\u6269\u5c55\uff0c\u4f46\u4e5f\u8981\u4fdd\u8bc1\u539f\u6709\u5185\u5bb9\u7684\u8986\u76d6\uff1b\u6d3b\u52a8\u7b56\u5212\u63d0\u793a\u5185\u5bb9\u8f83\u5c11\uff0c\u5927\u90e8\u5206\u4e3a\u81ea\u7531\u53d1\u6325\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A1 \u7ec3\u4e60\u4ee5\u4e0b\u4e24\u4e2a Unix \u547d\u4ee4\u7684\u64cd\u4f5c\uff08\u6839\u636e Markus Dickinson \u7684\u8bfe\u7a0b\u6539\u7f16\uff09\uff1a \u5b89\u88c5\u914d\u7f6e\uff1aM [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-2199","post","type-post","status-publish","format-standard","hentry","category-note"],"_links":{"self":[{"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/posts\/2199","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2199"}],"version-history":[{"count":36,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/posts\/2199\/revisions"}],"predecessor-version":[{"id":2392,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=\/wp\/v2\/posts\/2199\/revisions\/2392"}],"wp:attachment":[{"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2199"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2199"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.haruhi.fans\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2199"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}