{"id":165925,"date":"2024-11-05T13:59:19","date_gmt":"2024-11-05T05:59:19","guid":{"rendered":"https:\/\/server.hk\/cnblog\/165925\/"},"modified":"2024-11-05T13:59:20","modified_gmt":"2024-11-05T05:59:20","slug":"%e5%bf%ab%e9%80%9f%e5%ae%9a%e4%bd%8d%e9%87%8d%e8%a4%87%e6%95%b8%e6%93%9a%e7%9a%84%e6%96%b9%e6%b3%95%e5%a4%a7%e5%85%a8%e3%80%82-%e6%9f%a5%e6%89%be%e6%95%b8%e6%93%9a%e5%ba%ab%e9%87%8d%e8%a4%87%e6%95%b8","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/165925\/","title":{"rendered":"\u5feb\u901f\u5b9a\u4f4d\u91cd\u8907\u6578\u64da\u7684\u65b9\u6cd5\u5927\u5168\u3002 (\u67e5\u627e\u6578\u64da\u5eab\u91cd\u8907\u6578\u64da)"},"content":{"rendered":"<h1 id=\"%e5%bf%ab%e9%80%9f%e5%ae%9a%e4%bd%8d%e9%87%8d%e8%a4%87%e6%95%b8%e6%93%9a%e7%9a%84%e6%96%b9%e6%b3%95%e5%a4%a7%e5%85%a8-%e6%9f%a5%e6%89%be%e6%95%b8%e6%93%9a%e5%ba%ab%e9%87%8d%e8%a4%87%e6%95%b8%e6%93%9a-oRYeCeMDHy\">\u5feb\u901f\u5b9a\u4f4d\u91cd\u8907\u6578\u64da\u7684\u65b9\u6cd5\u5927\u5168 (\u67e5\u627e\u6578\u64da\u5eab\u91cd\u8907\u6578\u64da)<\/h1>\n<p>\u5728\u6578\u64da\u7ba1\u7406\u4e2d\uff0c\u91cd\u8907\u6578\u64da\u662f\u4e00\u500b\u5e38\u898b\u7684\u554f\u984c\uff0c\u5c24\u5176\u662f\u5728\u5927\u578b\u6578\u64da\u5eab\u4e2d\u3002\u91cd\u8907\u6578\u64da\u4e0d\u50c5\u6703\u4f54\u7528\u5b58\u5132\u7a7a\u9593\uff0c\u9084\u53ef\u80fd\u5c0e\u81f4\u6578\u64da\u5206\u6790\u7684\u932f\u8aa4\u548c\u696d\u52d9\u6c7a\u7b56\u7684\u5931\u8aa4\u3002\u56e0\u6b64\uff0c\u5feb\u901f\u5b9a\u4f4d\u548c\u8655\u7406\u91cd\u8907\u6578\u64da\u662f\u6578\u64da\u7ba1\u7406\u7684\u91cd\u8981\u4efb\u52d9\u4e4b\u4e00\u3002\u672c\u6587\u5c07\u4ecb\u7d39\u5e7e\u7a2e\u6709\u6548\u7684\u65b9\u6cd5\u4f86\u67e5\u627e\u6578\u64da\u5eab\u4e2d\u7684\u91cd\u8907\u6578\u64da\u3002<\/p>\n<h2 id=\"1-%e4%bd%bf%e7%94%a8sql%e6%9f%a5%e8%a9%a2-oRYeCeMDHy\">1. \u4f7f\u7528SQL\u67e5\u8a62<\/h2>\n<p>SQL\uff08\u7d50\u69cb\u5316\u67e5\u8a62\u8a9e\u8a00\uff09\u662f\u67e5\u627e\u91cd\u8907\u6578\u64da\u7684\u6700\u5e38\u7528\u5de5\u5177\u4e4b\u4e00\u3002\u901a\u904e\u4f7f\u7528GROUP BY\u548cHAVING\u5b50\u53e5\uff0c\u53ef\u4ee5\u8f15\u9b06\u8b58\u5225\u91cd\u8907\u7684\u8a18\u9304\u3002\u4ee5\u4e0b\u662f\u4e00\u500b\u793a\u4f8b\u67e5\u8a62\uff1a<\/p>\n<pre><code>SELECT column_name, COUNT(*)\nFROM table_name\nGROUP BY column_name\nHAVING COUNT(*) &gt; 1;<\/code><\/pre>\n<p>\u5728\u9019\u500b\u67e5\u8a62\u4e2d\uff0c\u5c07<code>column_name<\/code>\u66ff\u63db\u70ba\u9700\u8981\u6aa2\u67e5\u91cd\u8907\u7684\u5217\u540d\uff0c<code>table_name<\/code>\u66ff\u63db\u70ba\u76f8\u61c9\u7684\u8868\u540d\u3002\u9019\u6a23\u53ef\u4ee5\u5217\u51fa\u6240\u6709\u91cd\u8907\u7684\u503c\u53ca\u5176\u51fa\u73fe\u7684\u6b21\u6578\u3002<\/p>\n<h2 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-oRYeCeMDHy\">2. \u4f7f\u7528\u6578\u64da\u6e05\u7406\u5de5\u5177<\/h2>\n<p>\u5e02\u5834\u4e0a\u6709\u8a31\u591a\u6578\u64da\u6e05\u7406\u5de5\u5177\u53ef\u4ee5\u5e6b\u52a9\u7528\u6236\u81ea\u52d5\u6aa2\u6e2c\u548c\u522a\u9664\u91cd\u8907\u6578\u64da\u3002\u4f8b\u5982\uff0c\u5de5\u5177\u5982OpenRefine\u548cData Ladder\u63d0\u4f9b\u4e86\u5f37\u5927\u7684\u529f\u80fd\u4f86\u6e05\u7406\u548c\u6a19\u6e96\u5316\u6578\u64da\u3002\u9019\u4e9b\u5de5\u5177\u901a\u5e38\u5177\u6709\u7528\u6236\u53cb\u597d\u7684\u754c\u9762\uff0c\u4e26\u652f\u6301\u591a\u7a2e\u6578\u64da\u683c\u5f0f\u3002<\/p>\n<h2 id=\"3-%e5%88%a9%e7%94%a8%e7%b7%a8%e7%a8%8b%e8%aa%9e%e8%a8%80-oRYeCeMDHy\">3. \u5229\u7528\u7de8\u7a0b\u8a9e\u8a00<\/h2>\n<p>\u9664\u4e86SQL\uff0c\u9084\u53ef\u4ee5\u4f7f\u7528\u7de8\u7a0b\u8a9e\u8a00\uff08\u5982Python\u6216R\uff09\u4f86\u67e5\u627e\u91cd\u8907\u6578\u64da\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528Python\u7684Pandas\u5eab\u4f86\u67e5\u627e\u91cd\u8907\u6578\u64da\u7684\u793a\u4f8b\uff1a<\/p>\n<pre><code>import pandas as pd\n\n# \u8b80\u53d6\u6578\u64da\ndata = pd.read_csv('data.csv')\n\n# \u67e5\u627e\u91cd\u8907\u6578\u64da\nduplicates = data[data.duplicated()]\n\n# \u986f\u793a\u91cd\u8907\u6578\u64da\nprint(duplicates)<\/code><\/pre>\n<p>\u9019\u6bb5\u4ee3\u78bc\u5c07\u8b80\u53d6\u4e00\u500bCSV\u6587\u4ef6\uff0c\u7136\u5f8c\u4f7f\u7528<code>duplicated()<\/code>\u65b9\u6cd5\u4f86\u67e5\u627e\u91cd\u8907\u7684\u884c\u3002<\/p>\n<h2 id=\"4-%e6%95%b8%e6%93%9a%e5%ba%ab%e7%b4%a2%e5%bc%95-oRYeCeMDHy\">4. \u6578\u64da\u5eab\u7d22\u5f15<\/h2>\n<p>\u5728\u6578\u64da\u5eab\u4e2d\uff0c\u5275\u5efa\u7d22\u5f15\u53ef\u4ee5\u63d0\u9ad8\u67e5\u627e\u91cd\u8907\u6578\u64da\u7684\u6548\u7387\u3002\u901a\u904e\u5728\u9700\u8981\u6aa2\u67e5\u91cd\u8907\u7684\u5217\u4e0a\u5275\u5efa\u7d22\u5f15\uff0c\u53ef\u4ee5\u52a0\u5feb\u67e5\u8a62\u901f\u5ea6\u3002\u4ee5\u4e0b\u662f\u5275\u5efa\u7d22\u5f15\u7684SQL\u8a9e\u53e5\u793a\u4f8b\uff1a<\/p>\n<pre><code>CREATE INDEX idx_column_name\nON table_name (column_name);<\/code><\/pre>\n<p>\u9019\u6a23\u53ef\u4ee5\u5728\u67e5\u8a62\u91cd\u8907\u6578\u64da\u6642\u63d0\u9ad8\u6027\u80fd\uff0c\u7279\u5225\u662f\u5728\u8655\u7406\u5927\u578b\u6578\u64da\u96c6\u6642\u3002<\/p>\n<h2 id=\"5-%e6%95%b8%e6%93%9a%e5%ba%ab%e7%ae%a1%e7%90%86%e7%b3%bb%e7%b5%b1%e7%9a%84%e5%85%a7%e5%bb%ba%e5%8a%9f%e8%83%bd-oRYeCeMDHy\">5. \u6578\u64da\u5eab\u7ba1\u7406\u7cfb\u7d71\u7684\u5167\u5efa\u529f\u80fd<\/h2>\n<p>\u8a31\u591a\u6578\u64da\u5eab\u7ba1\u7406\u7cfb\u7d71\uff08\u5982MySQL\u3001PostgreSQL\u548cOracle\uff09\u90fd\u63d0\u4f9b\u4e86\u5167\u5efa\u7684\u529f\u80fd\u4f86\u67e5\u627e\u548c\u8655\u7406\u91cd\u8907\u6578\u64da\u3002\u4f8b\u5982\uff0cMySQL\u7684<code>UNIQUE<\/code>\u7d04\u675f\u53ef\u4ee5\u9632\u6b62\u63d2\u5165\u91cd\u8907\u7684\u6578\u64da\uff0c\u800cPostgreSQL\u5247\u63d0\u4f9b\u4e86<code>DISTINCT<\/code>\u95dc\u9375\u5b57\u4f86\u67e5\u8a62\u552f\u4e00\u503c\u3002<\/p>\n<h2 id=\"%e7%b8%bd%e7%b5%90-oRYeCeMDHy\">\u7e3d\u7d50<\/h2>\n<p>\u91cd\u8907\u6578\u64da\u7684\u7ba1\u7406\u5c0d\u65bc\u4fdd\u6301\u6578\u64da\u5eab\u7684\u6574\u6f54\u548c\u6e96\u78ba\u81f3\u95dc\u91cd\u8981\u3002\u901a\u904e\u4f7f\u7528SQL\u67e5\u8a62\u3001\u6578\u64da\u6e05\u7406\u5de5\u5177\u3001\u7de8\u7a0b\u8a9e\u8a00\u3001\u6578\u64da\u5eab\u7d22\u5f15\u4ee5\u53ca\u6578\u64da\u5eab\u7ba1\u7406\u7cfb\u7d71\u7684\u5167\u5efa\u529f\u80fd\uff0c\u60a8\u53ef\u4ee5\u6709\u6548\u5730\u67e5\u627e\u548c\u8655\u7406\u91cd\u8907\u6578\u64da\u3002\u9019\u4e0d\u50c5\u80fd\u63d0\u9ad8\u6578\u64da\u7684\u8cea\u91cf\uff0c\u9084\u80fd\u589e\u5f37\u696d\u52d9\u6c7a\u7b56\u7684\u6e96\u78ba\u6027\u3002<\/p>\n<p>\u5982\u679c\u60a8\u6b63\u5728\u5c0b\u627e\u9ad8\u6548\u7684\u6578\u64da\u7ba1\u7406\u89e3\u6c7a\u65b9\u6848\uff0c\u8003\u616e\u4f7f\u7528<a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a>\u4f86\u652f\u6301\u60a8\u7684\u6578\u64da\u5eab\u64cd\u4f5c\u3002\u7121\u8ad6\u662f\u6578\u64da\u5b58\u5132\u9084\u662f\u6578\u64da\u8655\u7406\uff0c\u9078\u64c7\u5408\u9069\u7684<a href=\"https:\/\/server.hk\">\u4f3a\u670d\u5668<\/a>\u90fd\u80fd\u70ba\u60a8\u7684\u696d\u52d9\u63d0\u4f9b\u7a69\u5b9a\u7684\u652f\u6301\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22\u5feb\u901f\u5b9a\u4f4d\u6578\u64da\u5eab\u4e2d\u91cd\u8907\u6578\u64da\u7684\u6709\u6548\u65b9\u6cd5\uff0c\u63d0\u5347\u6578\u64da\u7ba1\u7406\u6548\u7387\uff0c\u78ba\u4fdd\u6578\u64da\u6e96\u78ba\u6027\u8207\u4e00\u81f4\u6027\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-165925","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/165925","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=165925"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/165925\/revisions"}],"predecessor-version":[{"id":165926,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/165925\/revisions\/165926"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=165925"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=165925"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=165925"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}