{"id":162263,"date":"2024-11-04T13:34:24","date_gmt":"2024-11-04T05:34:24","guid":{"rendered":"https:\/\/server.hk\/cnblog\/162263\/"},"modified":"2024-11-04T13:34:25","modified_gmt":"2024-11-04T05:34:25","slug":"%e7%b0%a1%e4%be%bf%e6%9c%89%e6%95%88%e7%9a%84%e6%95%b8%e6%93%9a%e5%ba%ab%e5%8e%bb%e9%87%8d%e6%96%b9%e6%b3%95%ef%bc%8c%e8%bc%95%e9%ac%86%e8%a7%a3%e6%b1%ba%e9%87%8d%e8%a4%87%e6%95%b8%e6%93%9a%e5%95%8f","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/162263\/","title":{"rendered":"\u7c21\u4fbf\u6709\u6548\u7684\u6578\u64da\u5eab\u53bb\u91cd\u65b9\u6cd5\uff0c\u8f15\u9b06\u89e3\u6c7a\u91cd\u8907\u6578\u64da\u554f\u984c (\u6578\u64da\u5eab \u53bb\u9664\u91cd\u8907)"},"content":{"rendered":"<h1 id=\"%e7%b0%a1%e4%be%bf%e6%9c%89%e6%95%88%e7%9a%84%e6%95%b8%e6%93%9a%e5%ba%ab%e5%8e%bb%e9%87%8d%e6%96%b9%e6%b3%95%ef%bc%8c%e8%bc%95%e9%ac%86%e8%a7%a3%e6%b1%ba%e9%87%8d%e8%a4%87%e6%95%b8%e6%93%9a%e5%95%8f-XEuMghVgMu\">\u7c21\u4fbf\u6709\u6548\u7684\u6578\u64da\u5eab\u53bb\u91cd\u65b9\u6cd5\uff0c\u8f15\u9b06\u89e3\u6c7a\u91cd\u8907\u6578\u64da\u554f\u984c<\/h1>\n<p>\u5728\u7576\u4eca\u6578\u64da\u9a45\u52d5\u7684\u4e16\u754c\u4e2d\uff0c\u6578\u64da\u7684\u6e96\u78ba\u6027\u548c\u5b8c\u6574\u6027\u81f3\u95dc\u91cd\u8981\u3002\u91cd\u8907\u6578\u64da\u4e0d\u50c5\u6703\u6d6a\u8cbb\u5b58\u5132\u7a7a\u9593\uff0c\u9084\u53ef\u80fd\u5c0e\u81f4\u932f\u8aa4\u7684\u5206\u6790\u7d50\u679c\u548c\u6c7a\u7b56\u3002\u56e0\u6b64\uff0c\u6578\u64da\u5eab\u53bb\u91cd\u6210\u70ba\u4e86\u6578\u64da\u7ba1\u7406\u4e2d\u7684\u4e00\u500b\u91cd\u8981\u8ab2\u984c\u3002\u672c\u6587\u5c07\u63a2\u8a0e\u4e00\u4e9b\u7c21\u4fbf\u6709\u6548\u7684\u6578\u64da\u5eab\u53bb\u91cd\u65b9\u6cd5\uff0c\u5e6b\u52a9\u60a8\u8f15\u9b06\u89e3\u6c7a\u91cd\u8907\u6578\u64da\u554f\u984c\u3002<\/p>\n<h2 id=\"%e7%82%ba%e4%bb%80%e9%ba%bc%e9%9c%80%e8%a6%81%e5%8e%bb%e9%87%8d%ef%bc%9f-XEuMghVgMu\">\u70ba\u4ec0\u9ebc\u9700\u8981\u53bb\u91cd\uff1f<\/h2>\n<p>\u91cd\u8907\u6578\u64da\u7684\u5b58\u5728\u6703\u5c0d\u4f01\u696d\u7684\u904b\u71df\u9020\u6210\u591a\u65b9\u9762\u7684\u5f71\u97ff\uff0c\u5305\u62ec\uff1a<\/p>\n<ul>\n<li>\u6578\u64da\u5206\u6790\u4e0d\u6e96\u78ba\uff1a\u91cd\u8907\u6578\u64da\u6703\u5c0e\u81f4\u5206\u6790\u7d50\u679c\u5931\u771f\uff0c\u5f71\u97ff\u6c7a\u7b56\u7684\u6e96\u78ba\u6027\u3002<\/li>\n<li>\u5b58\u5132\u6210\u672c\u589e\u52a0\uff1a\u91cd\u8907\u6578\u64da\u4f54\u7528\u984d\u5916\u7684\u5b58\u5132\u7a7a\u9593\uff0c\u589e\u52a0\u4e86\u6578\u64da\u7ba1\u7406\u7684\u6210\u672c\u3002<\/li>\n<li>\u7528\u6236\u9ad4\u9a57\u4e0b\u964d\uff1a\u5728\u5ba2\u6236\u95dc\u4fc2\u7ba1\u7406\u4e2d\uff0c\u91cd\u8907\u7684\u5ba2\u6236\u8a18\u9304\u53ef\u80fd\u5c0e\u81f4\u5ba2\u6236\u670d\u52d9\u7684\u6df7\u4e82\u3002<\/li>\n<\/ul>\n<h2 id=\"%e5%b8%b8%e8%a6%8b%e7%9a%84%e6%95%b8%e6%93%9a%e5%ba%ab%e5%8e%bb%e9%87%8d%e6%96%b9%e6%b3%95-XEuMghVgMu\">\u5e38\u898b\u7684\u6578\u64da\u5eab\u53bb\u91cd\u65b9\u6cd5<\/h2>\n<h3 id=\"1-%e4%bd%bf%e7%94%a8sql%e6%9f%a5%e8%a9%a2%e5%8e%bb%e9%87%8d-XEuMghVgMu\">1. \u4f7f\u7528SQL\u67e5\u8a62\u53bb\u91cd<\/h3>\n<p>\u5728\u95dc\u4fc2\u578b\u6578\u64da\u5eab\u4e2d\uff0c\u4f7f\u7528SQL\u67e5\u8a62\u662f\u6700\u5e38\u898b\u7684\u53bb\u91cd\u65b9\u6cd5\u3002\u53ef\u4ee5\u4f7f\u7528 <code>SELECT DISTINCT<\/code> \u8a9e\u53e5\u4f86\u9078\u64c7\u552f\u4e00\u7684\u8a18\u9304\u3002\u4f8b\u5982\uff1a<\/p>\n<pre><code>SELECT DISTINCT column_name FROM table_name;<\/code><\/pre>\n<p>\u9019\u6a23\u53ef\u4ee5\u7372\u53d6\u6307\u5b9a\u5217\u4e2d\u6240\u6709\u552f\u4e00\u7684\u503c\u3002\u82e5\u8981\u522a\u9664\u91cd\u8907\u7684\u884c\uff0c\u53ef\u4ee5\u4f7f\u7528 <code>ROW_NUMBER()<\/code> \u51fd\u6578\u4f86\u6a19\u8a18\u91cd\u8907\u884c\uff0c\u7136\u5f8c\u522a\u9664\u6a19\u8a18\u7684\u884c\uff1a<\/p>\n<pre><code>WITH CTE AS (\n    SELECT *,\n           ROW_NUMBER() OVER (PARTITION BY column_name ORDER BY (SELECT NULL)) AS rn\n    FROM table_name\n)\nDELETE FROM CTE WHERE rn &gt; 1;<\/code><\/pre>\n<h3 id=\"2-%e4%bd%bf%e7%94%a8%e6%95%b8%e6%93%9a%e6%b8%85%e7%90%86%e5%b7%a5%e5%85%b7-XEuMghVgMu\">2. \u4f7f\u7528\u6578\u64da\u6e05\u7406\u5de5\u5177<\/h3>\n<p>\u5e02\u5834\u4e0a\u6709\u8a31\u591a\u6578\u64da\u6e05\u7406\u5de5\u5177\u53ef\u4ee5\u5e6b\u52a9\u81ea\u52d5\u5316\u53bb\u91cd\u904e\u7a0b\u3002\u9019\u4e9b\u5de5\u5177\u901a\u5e38\u63d0\u4f9b\u7528\u6236\u53cb\u597d\u7684\u754c\u9762\uff0c\u5141\u8a31\u7528\u6236\u8f15\u9b06\u4e0a\u50b3\u6578\u64da\u4e26\u9078\u64c7\u53bb\u91cd\u9078\u9805\u3002\u4f8b\u5982\uff0c\u5de5\u5177\u5982 OpenRefine \u548c Talend \u90fd\u662f\u6d41\u884c\u7684\u9078\u64c7\u3002\u9019\u4e9b\u5de5\u5177\u80fd\u5920\u8b58\u5225\u548c\u5408\u4f75\u91cd\u8907\u7684\u8a18\u9304\uff0c\u4e26\u63d0\u4f9b\u6578\u64da\u8cea\u91cf\u5831\u544a\u3002<\/p>\n<h3 id=\"3-%e7%b7%a8%e5%af%ab%e8%87%aa%e5%ae%9a%e7%be%a9%e8%85%b3%e6%9c%ac-XEuMghVgMu\">3. \u7de8\u5beb\u81ea\u5b9a\u7fa9\u8173\u672c<\/h3>\n<p>\u5c0d\u65bc\u7279\u5b9a\u9700\u6c42\uff0c\u7de8\u5beb\u81ea\u5b9a\u7fa9\u8173\u672c\u662f\u4e00\u7a2e\u9748\u6d3b\u7684\u89e3\u6c7a\u65b9\u6848\u3002\u4f7f\u7528 Python \u548c Pandas \u5eab\uff0c\u53ef\u4ee5\u8f15\u9b06\u5730\u8b80\u53d6\u6578\u64da\u4e26\u53bb\u9664\u91cd\u8907\u9805\uff1a<\/p>\n<pre><code>import pandas as pd\n\n# \u8b80\u53d6\u6578\u64da\ndata = pd.read_csv('data.csv')\n\n# \u53bb\u9664\u91cd\u8907\u884c\ndata_cleaned = data.drop_duplicates()\n\n# \u4fdd\u5b58\u6e05\u7406\u5f8c\u7684\u6578\u64da\ndata_cleaned.to_csv('data_cleaned.csv', index=False)<\/code><\/pre>\n<h3 id=\"4-%e6%95%b8%e6%93%9a%e5%ba%ab%e7%b4%84%e6%9d%9f-XEuMghVgMu\">4. \u6578\u64da\u5eab\u7d04\u675f<\/h3>\n<p>\u5728\u6578\u64da\u5eab\u8a2d\u8a08\u968e\u6bb5\uff0c\u53ef\u4ee5\u901a\u904e\u8a2d\u7f6e\u552f\u4e00\u7d04\u675f\u4f86\u9632\u6b62\u91cd\u8907\u6578\u64da\u7684\u63d2\u5165\u3002\u4f8b\u5982\uff0c\u5728 MySQL \u4e2d\uff0c\u53ef\u4ee5\u5728\u5275\u5efa\u8868\u6642\u4f7f\u7528 <code>UNIQUE<\/code> \u7d04\u675f\uff1a<\/p>\n<pre><code>CREATE TABLE table_name (\n    id INT PRIMARY KEY,\n    column_name VARCHAR(255) UNIQUE\n);<\/code><\/pre>\n<p>\u9019\u6a23\u53ef\u4ee5\u78ba\u4fdd\u5728\u63d2\u5165\u65b0\u6578\u64da\u6642\uff0c\u8a72\u5217\u4e0d\u6703\u6709\u91cd\u8907\u7684\u503c\u3002<\/p>\n<h2 id=\"%e7%b5%90%e8%ab%96-XEuMghVgMu\">\u7d50\u8ad6<\/h2>\n<p>\u91cd\u8907\u6578\u64da\u554f\u984c\u5728\u6578\u64da\u7ba1\u7406\u4e2d\u662f\u4e0d\u53ef\u5ffd\u8996\u7684\uff0c\u63a1\u7528\u5408\u9069\u7684\u53bb\u91cd\u65b9\u6cd5\u53ef\u4ee5\u6709\u6548\u63d0\u9ad8\u6578\u64da\u8cea\u91cf\u3002\u7121\u8ad6\u662f\u4f7f\u7528 SQL \u67e5\u8a62\u3001\u6578\u64da\u6e05\u7406\u5de5\u5177\u3001\u7de8\u5beb\u81ea\u5b9a\u7fa9\u8173\u672c\uff0c\u9084\u662f\u8a2d\u7f6e\u6578\u64da\u5eab\u7d04\u675f\uff0c\u9078\u64c7\u6700\u9069\u5408\u60a8\u9700\u6c42\u7684\u65b9\u6cd5\u81f3\u95dc\u91cd\u8981\u3002\u901a\u904e\u9019\u4e9b\u65b9\u6cd5\uff0c\u60a8\u53ef\u4ee5\u8f15\u9b06\u89e3\u6c7a\u91cd\u8907\u6578\u64da\u554f\u984c\uff0c\u63d0\u5347\u696d\u52d9\u904b\u71df\u7684\u6548\u7387\u3002<\/p>\n<p>\u5982\u9700\u4e86\u89e3\u66f4\u591a\u95dc\u65bc\u6578\u64da\u7ba1\u7406\u548c\u96f2\u8a08\u7b97\u7684\u89e3\u6c7a\u65b9\u6848\uff0c\u8acb\u8a2a\u554f\u6211\u5011\u7684\u7db2\u7ad9 <a href=\"https:\/\/server.hk\">Server.HK<\/a>\uff0c\u63a2\u7d22\u6211\u5011\u7684 <a href=\"https:\/\/server.hk\">VPS<\/a> \u548c <a href=\"https:\/\/server.hk\">\u9999\u6e2f\u4f3a\u670d\u5668<\/a> \u670d\u52d9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7c21\u4fbf\u6709\u6548\u7684\u6578\u64da\u5eab\u53bb\u91cd\u65b9\u6cd5\uff0c\u8f15\u9b06\u89e3\u6c7a\u91cd\u8907\u6578\u64da\u554f\u984c\uff0c\u63d0\u5347\u6578\u64da\u8cea\u91cf\u8207\u7ba1\u7406\u6548\u7387\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-162263","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/162263","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=162263"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/162263\/revisions"}],"predecessor-version":[{"id":162264,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/162263\/revisions\/162264"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=162263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=162263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=162263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}