{"id":3395,"date":"2022-02-27T15:41:47","date_gmt":"2022-02-27T07:41:47","guid":{"rendered":"https:\/\/egonlin.com\/?p=3395"},"modified":"2022-02-27T15:46:02","modified_gmt":"2022-02-27T07:46:02","slug":"%e7%ac%ac%e4%ba%8c%e7%af%87%ef%bc%9a%e6%8e%a8%e8%8d%90%e7%b3%bb%e7%bb%9f","status":"publish","type":"post","link":"https:\/\/egonlin.com\/?p=3395","title":{"rendered":"\u7b2c\u4e8c\u7bc7\uff1a\u63a8\u8350\u7cfb\u7edf"},"content":{"rendered":"<h1>\u63a8\u8350\u7cfb\u7edf<\/h1>\n<p>&emsp;&emsp;\u76ee\u524d\u63a8\u8350\u7cfb\u7edf\u88ab\u5e94\u7528\u4e8e\u5404\u4e2a\u9886\u57df\uff0c\u4f8b\u5982\u6dd8\u5b9d\u7684\u5546\u54c1\u63a8\u8350\u3001b\u7ad9\u7684\u89c6\u9891\u63a8\u8350\u3001\u7f51\u6613\u4e91\u97f3\u4e50\u7684\u6bcf\u65e5\u63a8\u8350\u7b49\u7b49\uff0c\u8fd9\u4e9b\u90fd\u662f\u57fa\u4e8e\u7528\u4e8e\u5f80\u65e5\u5728\u5e73\u53f0\u7684\u884c\u4e3a\u6a21\u5f0f\u7ed9\u7528\u6237\u63a8\u8350\u4ed6\u4eec\u53ef\u80fd\u559c\u6b22\u7684\u5546\u54c1\u3001\u89c6\u9891\u3001\u97f3\u4e50\u3002<\/p>\n<p>&emsp;&emsp;\u4e0b\u9762\u6211\u4eec\u5c06\u4ee5\u7535\u5f71\u63a8\u8350\u7cfb\u7edf\u4e3e\u4f8b\uff0c\u4e00\u6b65\u4e00\u6b65\u901a\u8fc7Python\u5b9e\u73b0\u4e00\u4e2a\u7b80\u5355\u7684\u7535\u5f71\u63a8\u8350\u7cfb\u7edf\u3002<\/p>\n<p>&emsp;&emsp;\u7531\u4e8e\u6570\u636e\u91cf\u7684\u539f\u56e0\uff0c\u6211\u4eec\u53ef\u80fd\u65e0\u6cd5\u505a\u5230\u7cbe\u5ea6\u8f83\u9ad8\u7684\u63a8\u8350\u7cfb\u7edf\uff0c\u4f46\u662f\u505a\u4e00\u4e2a\u5dee\u4e0d\u591a\u80fd\u5b9e\u73b0\u63a8\u8350\u529f\u80fd\u7684\u7535\u5f71\u63a8\u8350\u7cfb\u7edf\u662f\u5b8c\u5168\u6ca1\u6709\u95ee\u9898\u7684\u3002<\/p>\n<h1>\u5bfc\u5165\u6a21\u5757<\/h1>\n<pre><code class=\"language-python\">import io\nimport os\nimport sys\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom matplotlib.font_manager import FontProperties\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.metrics.pairwise import cosine_similarity\n%matplotlib inline\nfont = FontProperties(fname=&#039;\/Library\/Fonts\/Heiti.ttc&#039;)<\/code><\/pre>\n<h1>\u6536\u96c6\u6570\u636e<\/h1>\n<p>&emsp;&emsp;\u65e9\u671f\u8bb2\u6784\u9020\u673a\u5668\u5b66\u4e60\u7cfb\u7edf\u7684\u65f6\u5019\u8bf4\u5230\uff0c\u6211\u4eec\u7b2c\u4e00\u6b65\u5f80\u5f80\u662f\u9700\u8981\u6536\u96c6\u6570\u636e\u3002<\/p>\n<p>&emsp;&emsp;\u7531\u4e8e\u672c\u6b21\u8981\u505a\u7684\u63a8\u8350\u7cfb\u7edf\u662f\u548c\u7535\u5f71\u6709\u5173\u7684\uff0c\u800c\u4e3a\u4e86\u7ed9\u7528\u6237\u63a8\u8350\u4ed6\u559c\u6b22\u7684\u7535\u5f71\uff0c\u4e00\u822c\u4f1a\u6536\u96c6\u6bcf\u4e2a\u7528\u6237\u5bf9\u81ea\u5df1\u770b\u8fc7\u7684\u7535\u5f71\u7684\u8bc4\u5206\u3002\u8fd9\u91cc\u6211\u4eec\u5047\u8bbe\u7528\u6237\u770b\u5b8c\u7535\u5f71\u4e00\u5b9a\u4f1a\u7ed9\u7535\u5f71\u8bc4\u5206\uff0c\u5e76\u4e14\u8bc4\u5206\u8303\u56f4\u4e3a${1,2,3,4,5}$\uff0c\u5373\u8bc4\u5206\u6700\u4f4e\u4e3a1\u5206\uff0c\u6700\u9ad8\u4e3a5\u5206\u3002\u5982\u679c\u7528\u6237\u6ca1\u6709\u8bc4\u5206\u5219\u610f\u5473\u7740\u7528\u6237\u6ca1\u6709\u770b\u8fc7\u8be5\u7535\u5f71\u3002<\/p>\n<p>&emsp;&emsp;\u5982\u679c\u662f\u5927\u578b\u7684\u63a8\u8350\u7cfb\u7edf\uff0c\u5f80\u5f80\u9700\u8981\u901a\u8fc7\u5f88\u591a\u9014\u5f84\u83b7\u5f97\u5404\u79cd\u6570\u636e\uff0c\u5982\u722c\u866b\u3001\u5e73\u53f0\u5408\u4f5c\uff0c\u5e76\u4e14\u53ef\u80fd\u8fd8\u4f1a\u8003\u8651\u7528\u6237\u672c\u8eab\u7684\u5404\u79cd\u4fe1\u606f\uff0c\u5982\u8eab\u9ad8\u3001\u4f53\u91cd\u3001\u5e74\u9f84\u3001\u5174\u8da3\u7231\u597d\u2026\u2026\u548c\u7535\u5f71\u7684\u5404\u79cd\u4fe1\u606f\uff0c\u5982\u7bc7\u540d\u3001\u5bfc\u6f14\u3001\u6f14\u5458\u9635\u5bb9\u3001\u4e0a\u6620\u65f6\u95f4\u2026\u2026\uff0c\u901a\u5e38\u8fd9\u79cd\u5927\u578b\u7cfb\u7edf\u9488\u5bf9\u7684\u6570\u636e\u7ef4\u5ea6\u5f80\u5f80\u90fd\u662f\u4e0a\u4e07\uff0c\u4e0a\u5341\u4e07\u7684\u3002\u7531\u4e8e\u6570\u636e\u9650\u5236\uff0c\u56e0\u6b64\u8fd9\u91cc\u53ea\u5047\u8bbe\u7528\u6237\u559c\u6b22\u770b\u7684\u7535\u5f71\u548c\u4ed6\u5bf9\u7535\u5f71\u7684\u8bc4\u5206\u6709\u5173\u3002<\/p>\n<p>&emsp;&emsp;\u7531\u4e8e\u8fd9\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u63a8\u8350\u7cfb\u7edf\u7248\u672c\uff0c\u6240\u4ee5\u6211\u4eec\u5047\u8bbe\u6211\u4eec\u5df2\u7ecf\u83b7\u53d6\u4e86\u7528\u6237\u5bf9\u81ea\u5df1\u770b\u8fc7\u7684\u7535\u5f71\u7684\u8bc4\u5206\uff0c\u5373\u6570\u636e\u5728<code>movie.xlsx<\/code>\u8868\u683c\u4e2d\u3002<\/p>\n<pre><code class=\"language-python\"># \u6536\u96c6\u6570\u636e\n# \u6ca1\u6709\u8868\u683c\u6587\u4ef6\u65f6\u81ea\u5b9a\u4e49\u6570\u636e\ncsv_data = &#039;&#039;&#039;\n\u300a\u8096\u7533\u514b\u7684\u6551\u8d4e\u300b,\u300a\u63a7\u65b9\u8bc1\u4eba\u300b,\u300a\u8fd9\u4e2a\u6740\u624b\u4e0d\u592a\u51b7\u300b,\u300a\u9738\u738b\u522b\u59ec\u300b,\u300a\u7f8e\u4e3d\u4eba\u751f\u300b,\u300a\u963f\u7518\u6b63\u4f20\u300b,\u300a\u8f9b\u5fb7\u52d2\u7684\u540d\u5355\u300b,\u59d3\u540d\n,4.0,,4.0,,5.0,,&#039;\u5218\u4e00&#039;\n4.0,,5.0,3.0,5.0,,,&#039;\u9648\u4e8c&#039;\n3.0,4.0,,3.0,2.0,3.0,3.0,&#039;\u5f20\u4e09&#039;\n2.0,3.0,,3.0,,,,&#039;\u674e\u56db&#039;\n3.0,4.0,,5.0,3.0,3.0,,&#039;\u738b\u4e94&#039;\n,,4.0,,4.0,2.0,,&#039;\u8d75\u516d&#039;\n3.0,,1.0,5.0,3.0,3.0,2.0,&#039;\u5b59\u4e03&#039;\n2.0,,2.0,,1.0,,,&#039;\u5468\u516b&#039;\n1.0,2.0,,,,2.0,,&#039;\u5434\u4e5d&#039;\n,5.0,,4.0,,3.0,3.0,&#039;\u90d1\u5341&#039;\n&#039;&#039;&#039;\nif not os.path.exists(&#039;datasets\/movie.xlsx&#039;):\n    # \u5c06\u6587\u4ef6\u8bfb\u5165\u5185\u5b58\n    csv_data = io.StringIO(csv_data)\n    df = pd.read_csv(csv_data, header=0)\n    df.index = df[&#039;\u59d3\u540d&#039;].tolist()\nelse:\n    # \u4ece\u8868\u683c\u4e2d\u83b7\u53d6\u6570\u636e\n    df = pd.read_excel(&#039;datasets\/movie.xlsx&#039;, header=0)\n    df.index = df[&#039;\u59d3\u540d&#039;].tolist()\ndf<\/code><\/pre>\n<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }<\/p>\n<p>    .dataframe tbody tr th {\n        vertical-align: top;\n    }<\/p>\n<p>    .dataframe thead th {\n        text-align: right;\n    }\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>\u300a\u8096\u7533\u514b\u7684\u6551\u8d4e\u300b<\/th>\n<th>\u300a\u63a7\u65b9\u8bc1\u4eba\u300b<\/th>\n<th>\u300a\u8fd9\u4e2a\u6740\u624b\u4e0d\u592a\u51b7\u300b<\/th>\n<th>\u300a\u9738\u738b\u522b\u59ec\u300b<\/th>\n<th>\u300a\u7f8e\u4e3d\u4eba\u751f\u300b<\/th>\n<th>\u300a\u963f\u7518\u6b63\u4f20\u300b<\/th>\n<th>\u300a\u8f9b\u5fb7\u52d2\u7684\u540d\u5355\u300b<\/th>\n<th>\u59d3\u540d<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>\u5218\u4e00<\/th>\n<td>NaN<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>5.0<\/td>\n<td>NaN<\/td>\n<td>\u5218\u4e00<\/td>\n<\/tr>\n<tr>\n<th>\u9648\u4e8c<\/th>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>5.0<\/td>\n<td>3.0<\/td>\n<td>5.0<\/td>\n<td>NaN<\/td>\n<td>NaN<\/td>\n<td>\u9648\u4e8c<\/td>\n<\/tr>\n<tr>\n<th>\u5f20\u4e09<\/th>\n<td>3.0<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>3.0<\/td>\n<td>2.0<\/td>\n<td>3.0<\/td>\n<td>3.0<\/td>\n<td>\u5f20\u4e09<\/td>\n<\/tr>\n<tr>\n<th>\u674e\u56db<\/th>\n<td>2.0<\/td>\n<td>3.0<\/td>\n<td>NaN<\/td>\n<td>3.0<\/td>\n<td>3.0<\/td>\n<td>2.0<\/td>\n<td>NaN<\/td>\n<td>\u674e\u56db<\/td>\n<\/tr>\n<tr>\n<th>\u738b\u4e94<\/th>\n<td>3.0<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>5.0<\/td>\n<td>3.0<\/td>\n<td>3.0<\/td>\n<td>NaN<\/td>\n<td>\u738b\u4e94<\/td>\n<\/tr>\n<tr>\n<th>\u8d75\u516d<\/th>\n<td>NaN<\/td>\n<td>NaN<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>4.0<\/td>\n<td>2.0<\/td>\n<td>NaN<\/td>\n<td>\u8d75\u516d<\/td>\n<\/tr>\n<tr>\n<th>\u5b59\u4e03<\/th>\n<td>3.0<\/td>\n<td>NaN<\/td>\n<td>1.0<\/td>\n<td>5.0<\/td>\n<td>3.0<\/td>\n<td>3.0<\/td>\n<td>2.0<\/td>\n<td>\u5b59\u4e03<\/td>\n<\/tr>\n<tr>\n<th>\u5468\u516b<\/th>\n<td>2.0<\/td>\n<td>NaN<\/td>\n<td>2.0<\/td>\n<td>NaN<\/td>\n<td>1.0<\/td>\n<td>NaN<\/td>\n<td>2.0<\/td>\n<td>\u5468\u516b<\/td>\n<\/tr>\n<tr>\n<th>\u5434\u4e5d<\/th>\n<td>1.0<\/td>\n<td>2.0<\/td>\n<td>2.0<\/td>\n<td>NaN<\/td>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<td>NaN<\/td>\n<td>\u5434\u4e5d<\/td>\n<\/tr>\n<tr>\n<th>\u90d1\u5341<\/th>\n<td>NaN<\/td>\n<td>5.0<\/td>\n<td>NaN<\/td>\n<td>4.0<\/td>\n<td>NaN<\/td>\n<td>3.0<\/td>\n<td>3.0<\/td>\n<td>\u90d1\u5341<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h1>\u6570\u636e\u9884\u5904\u7406<\/h1>\n<h2>\u65e0\u8bc4\u5206\u7535\u5f71\u5904\u7406<\/h2>\n<p><\/p><div id=\"rml_readmorelogin_placeholder\" style=\"position:relative;\"><div id=\"rml_fade_content\" style=\"position: absolute;\r\ntop:-10em;\r\nwidth:100%;\r\nheight:10em;\r\nbackground: -webkit-linear-gradient(rgba(255, 255, 255, 0) 0%,#ffffff 100%);\r\nbackground-image: -moz-linear-gradient(rgba(255, 255, 255, 0) 0%,#ffffff 100%);\r\nbackground-image: -o-linear-gradient(rgba(255, 255, 255, 0) 0%,#ffffff 100%);\r\nbackground-image: linear-gradient(rgba(255, 255, 255, 0) 0%,#ffffff 100%);\r\nbackground-image: -ms-linear-gradient(rgba(255, 255, 255, 0) 0%,#ffffff 100%);\"><\/div><div class=\"wpf-controller aru_rml_from_in_post\" style=\"background-color:#eeeeee;border:5px solid #cce6ff;\" id=\"ARU_ReadMoreLogin_ReadMoreLoginController\"><h2 id=\"Header\">\u67e5\u770b\u66f4\u591a<\/h2><div id=\"Message\"><p>\u8054\u7cfb\u7ba1\u7406\u5458\u5fae\u4fe1tutu19192010\uff0c\u6ce8\u518c\u8d26\u53f7<\/p>\n<\/div><div id=\"StatusBarHeader\"><\/div><form id=\"ARU_ReadMoreLogin_ReadMoreLoginController\"><input name=\"post_id\" value=\"3395\" type=\"hidden\"\/><input name=\"_init_callback\" value=\"InitLogin\" type=\"hidden\"\/><input name=\"post_id\" value=\"3395\" type=\"hidden\"\/><input name=\"rt_ype\" value=\"1\" type=\"hidden\"\/><input name=\"nonce\" value=\"cc28897ddc\" type=\"hidden\"\/><input name=\"_wpnonce\" value=\"c9a2cc77e1\" type=\"hidden\"\/><input name=\"_controller\" value=\"ARU_ReadMoreLogin\\ReadMoreLoginController\" type=\"hidden\"\/><input name=\"_proxy_controller\" value=\"ARU_ReadMoreLogin\\ReadMoreLoginController\" type=\"hidden\"\/><input name=\"_view\" value=\"ARU_ReadMoreLogin\\ReadMoreLoginView\" type=\"hidden\"\/><table class=\"wpf-table-placeholder\"><tbody class=\"wpf-table-placeholder\"><tr class=\"wpf-table-placeholder\"><td class=\"wpf-table-placeholder-input\" width=\"400px\"><table class=\"wpf-table-placeholder\"><tbody class=\"wpf-table-placeholder\"><tr class=\"wpf-table-placeholder\"><th class=\"wpf-table-placeholder-input\"><label class=\"wpf-label\">Username:<\/label><\/th><\/tr><tr class=\"wpf-table-placeholder\"><td class=\"wpf-table-placeholder-input\"><input class=\"regular-text text_input\" name=\"username\" value=\"\" type=\"text\"\/><\/td><\/tr><tr class=\"wpf-table-placeholder\"><th class=\"wpf-table-placeholder-input\"><label class=\"wpf-label\">Password:<\/label><\/th><\/tr><tr class=\"wpf-table-placeholder\"><td class=\"wpf-table-placeholder-input\"><input class=\"regular-text text_input\" name=\"password\" value=\"\" type=\"password\"\/><\/td><\/tr><\/tbody><\/table><p class=\"wpf-table-placeholder submit\"><button class=\"wp_plugin_framework_ajax_button\" type=\"button\" style=\"background-color:#4D90FE;;color:#ffffff;;border:1px solid #3079ed;\" name=\"_event\" value=\"ButtonLogin\">Log in<\/button><\/p><\/td><td class=\"wpf-table-placeholder-input\"><\/td><\/tr><\/tbody><\/table><\/form><div id=\"ButtonStartRegister\"><a href=\"https:\/\/egonlin.com\/wp-login.php?action=register\">Register<\/a><\/div><div id=\"Link1\"><a href=\"https:\/\/egonlin.com\/wp-login.php?action=lostpassword\">Forgotten username or password?<\/a><\/div><div id=\"StatusBarFooter\"><\/div><\/div><\/div><div id=aru_remaining_content><\/div>","protected":false},"excerpt":{"rendered":"<p>\u63a8\u8350\u7cfb\u7edf &emsp;&emsp;\u76ee\u524d\u63a8\u8350\u7cfb\u7edf\u88ab\u5e94\u7528\u4e8e\u5404\u4e2a\u9886\u57df\uff0c\u4f8b\u5982\u6dd8\u5b9d\u7684\u5546\u54c1\u63a8\u8350\u3001b\u7ad9\u7684\u89c6\u9891\u63a8\u8350\u3001\u7f51\u6613\u4e91\u97f3\u4e50 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":3393,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[276,303,306],"tags":[],"_links":{"self":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3395"}],"collection":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3395"}],"version-history":[{"count":0,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3395\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/media\/3393"}],"wp:attachment":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3395"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3395"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}