{"id":478223,"date":"2023-08-09T09:29:19","date_gmt":"2023-08-09T09:29:19","guid":{"rendered":""},"modified":"2023-09-05T11:16:19","modified_gmt":"2023-09-05T11:16:19","slug":"normalization-in-data-preprocessing","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/cn\/wiki\/normalization-in-data-preprocessing\/","title":{"rendered":"\u6570\u636e\u9884\u5904\u7406\u4e2d\u7684\u6807\u51c6\u5316"},"content":{"rendered":"<p>\u6570\u636e\u9884\u5904\u7406\u7684\u6807\u51c6\u5316\u662f\u51c6\u5907\u6570\u636e\u4ee5\u4f9b\u5404\u4e2a\u9886\u57df\uff08\u5305\u62ec\u673a\u5668\u5b66\u4e60\u3001\u6570\u636e\u6316\u6398\u548c\u7edf\u8ba1\u5206\u6790\uff09\u5206\u6790\u548c\u5efa\u6a21\u7684\u5173\u952e\u6b65\u9aa4\u3002\u5b83\u6d89\u53ca\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u6807\u51c6\u5316\u683c\u5f0f\uff0c\u4ee5\u6d88\u9664\u4e0d\u4e00\u81f4\u5e76\u786e\u4fdd\u4e0d\u540c\u7684\u7279\u5f81\u5177\u6709\u53ef\u6bd4\u8f83\u7684\u89c4\u6a21\u3002\u901a\u8fc7\u8fd9\u6837\u505a\uff0c\u5f52\u4e00\u5316\u53ef\u4ee5\u63d0\u9ad8\u4f9d\u8d56\u4e8e\u8f93\u5165\u53d8\u91cf\u5927\u5c0f\u7684\u7b97\u6cd5\u7684\u6548\u7387\u548c\u51c6\u786e\u6027\u3002<\/p>\n<h2>\u6570\u636e\u9884\u5904\u7406\u4e2d\u6807\u51c6\u5316\u7684\u8d77\u6e90\u548c\u9996\u6b21\u63d0\u53ca\u7684\u5386\u53f2<\/h2>\n<p>\u6570\u636e\u9884\u5904\u7406\u4e2d\u6807\u51c6\u5316\u7684\u6982\u5ff5\u53ef\u4ee5\u8ffd\u6eaf\u5230\u65e9\u671f\u7684\u7edf\u8ba1\u5b9e\u8df5\u3002\u7136\u800c\uff0c\u5b83\u4f5c\u4e3a\u4e00\u79cd\u57fa\u672c\u6570\u636e\u9884\u5904\u7406\u6280\u672f\u7684\u5f62\u5f0f\u5316\u548c\u8ba4\u53ef\u53ef\u4ee5\u8ffd\u6eaf\u5230 19 \u4e16\u7eaa\u672b\u548c 20 \u4e16\u7eaa\u521d\u5361\u5c14\u00b7\u76ae\u5c14\u900a (Karl Pearson) \u548c\u7f57\u7eb3\u5fb7\u00b7\u8d39\u820d\u5c14 (Ronald Fisher) \u7b49\u7edf\u8ba1\u5b66\u5bb6\u7684\u4f5c\u54c1\u3002\u76ae\u5c14\u900a\u5728\u4ed6\u7684\u76f8\u5173\u7cfb\u6570\u4e2d\u5f15\u5165\u4e86\u6807\u51c6\u5316\u7684\u6982\u5ff5\uff08\u5f52\u4e00\u5316\u7684\u4e00\u79cd\u5f62\u5f0f\uff09\uff0c\u5b83\u5141\u8bb8\u5bf9\u5177\u6709\u4e0d\u540c\u5355\u4f4d\u7684\u53d8\u91cf\u8fdb\u884c\u6bd4\u8f83\u3002<\/p>\n<p>\u5728\u673a\u5668\u5b66\u4e60\u9886\u57df\uff0c\u89c4\u8303\u5316\u7684\u6982\u5ff5\u968f\u7740 20 \u4e16\u7eaa 40 \u5e74\u4ee3\u4eba\u5de5\u795e\u7ecf\u7f51\u7edc\u7684\u5174\u8d77\u800c\u6d41\u884c\u3002\u7814\u7a76\u4eba\u5458\u53d1\u73b0\uff0c\u6807\u51c6\u5316\u8f93\u5165\u6570\u636e\u663e\u7740\u63d0\u9ad8\u4e86\u8fd9\u4e9b\u6a21\u578b\u7684\u6536\u655b\u6027\u548c\u6027\u80fd\u3002<\/p>\n<h2>\u6709\u5173\u6570\u636e\u9884\u5904\u7406\u4e2d\u6807\u51c6\u5316\u7684\u8be6\u7ec6\u4fe1\u606f<\/h2>\n<p>\u89c4\u8303\u5316\u65e8\u5728\u5c06\u6570\u636e\u96c6\u7684\u6240\u6709\u7279\u5f81\u5f52\u4e00\u5316\u5230\u4e00\u4e2a\u5171\u540c\u7684\u5c3a\u5ea6\u4e0a\uff0c\u901a\u5e38\u5728 0 \u5230 1 \u4e4b\u95f4\uff0c\u800c\u4e0d\u4f1a\u626d\u66f2\u6570\u636e\u7684\u5e95\u5c42\u5206\u5e03\u3002\u5728\u5904\u7406\u5177\u6709\u660e\u663e\u4e0d\u540c\u8303\u56f4\u6216\u5355\u4f4d\u7684\u7279\u5f81\u65f6\uff0c\u8fd9\u4e00\u70b9\u81f3\u5173\u91cd\u8981\uff0c\u56e0\u4e3a\u7b97\u6cd5\u53ef\u80fd\u4f1a\u8fc7\u5206\u91cd\u89c6\u5177\u6709\u8f83\u5927\u503c\u7684\u7279\u5f81\u3002<\/p>\n<p>\u89c4\u8303\u5316\u8fc7\u7a0b\u6d89\u53ca\u4ee5\u4e0b\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u8bc6\u522b\u7279\u5f81<\/strong>\uff1a\u6839\u636e\u7279\u5f81\u7684\u5c3a\u5ea6\u548c\u5206\u5e03\u786e\u5b9a\u54ea\u4e9b\u7279\u5f81\u9700\u8981\u6807\u51c6\u5316\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u7f29\u653e<\/strong>\uff1a\u72ec\u7acb\u5730\u5c06\u6bcf\u4e2a\u7279\u5f81\u53d8\u6362\u5230\u7279\u5b9a\u8303\u56f4\u5185\u3002\u5e38\u89c1\u7684\u7f29\u653e\u6280\u672f\u5305\u62ec\u6700\u5c0f-\u6700\u5927\u7f29\u653e\u548c Z \u5206\u6570\u6807\u51c6\u5316\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u5f52\u4e00\u5316\u516c\u5f0f<\/strong>\uff1a\u6700\u5e7f\u6cdb\u4f7f\u7528\u7684\u6700\u5c0f-\u6700\u5927\u7f29\u653e\u516c\u5f0f\u662f\uff1a<\/p>\n<pre><div class=\"bg-black rounded-md mb-4\"><div class=\"flex items-center relative text-gray-200 bg-gray-800 px-4 py-2 text-xs font-sans justify-between rounded-t-md\"><span>CSS<\/span><button class=\"flex ml-auto gap-2\"><svg stroke=\"currentColor\" fill=\"none\" stroke-width=\"2\" viewbox=\"0 0 24 24\" stroke-linecap=\"round\" stroke-linejoin=\"round\" class=\"h-4 w-4\" height=\"1em\" width=\"1em\" ><path d=\"M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2\"><\/path><rect x=\"8\" y=\"2\" width=\"8\" height=\"4\" rx=\"1\" ry=\"1\"><\/rect><\/svg>\u590d\u5236\u4ee3\u7801<\/button><\/div><div class=\"p-4 overflow-y-auto\"><code class=\"!whitespace-pre hljs language-scss\" data-no-translation=\"\">x_normalized = (x - min(x)) \/ (max(x) - <span class=\"hljs-built_in\">min<\/span>(x))\n<\/code><\/div><\/div><\/pre>\n<p>\u5728\u54ea\u91cc <code data-no-translation=\"\">x<\/code> \u662f\u539f\u59cb\u503c\uff0c\u5e76\u4e14 <code data-no-translation=\"\">x_normalized<\/code> \u662f\u6807\u51c6\u5316\u503c\u3002<\/p>\n<\/li>\n<li>\n<p><strong>Z \u5206\u6570\u6807\u51c6\u5316\u516c\u5f0f<\/strong>\uff1a\u5bf9\u4e8e Z \u5206\u6570\u6807\u51c6\u5316\uff0c\u516c\u5f0f\u4e3a\uff1a<\/p>\n<pre><div class=\"bg-black rounded-md mb-4\"><div class=\"flex items-center relative text-gray-200 bg-gray-800 px-4 py-2 text-xs font-sans justify-between rounded-t-md\"><span>\u751f\u6210\u6587\u4ef6<\/span><button class=\"flex ml-auto gap-2\"><svg stroke=\"currentColor\" fill=\"none\" stroke-width=\"2\" viewbox=\"0 0 24 24\" stroke-linecap=\"round\" stroke-linejoin=\"round\" class=\"h-4 w-4\" height=\"1em\" width=\"1em\" ><path d=\"M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2\"><\/path><rect x=\"8\" y=\"2\" width=\"8\" height=\"4\" rx=\"1\" ry=\"1\"><\/rect><\/svg>\u590d\u5236\u4ee3\u7801<\/button><\/div><div class=\"p-4 overflow-y-auto\"><code class=\"!whitespace-pre hljs language-makefile\" data-no-translation=\"\">z = (x - mean) \/ standard_deviation\n<\/code><\/div><\/div><\/pre>\n<p>\u5728\u54ea\u91cc <code data-no-translation=\"\">mean<\/code> \u662f\u7279\u5f81\u503c\u7684\u5e73\u5747\u503c\uff0c <code data-no-translation=\"\">standard_deviation<\/code> \u662f\u6807\u51c6\u5dee\uff0c\u5e76\u4e14 <code data-no-translation=\"\">z<\/code> \u662f\u6807\u51c6\u5316\u503c\u3002<\/p>\n<\/li>\n<\/ol>\n<h2>\u6570\u636e\u9884\u5904\u7406\u4e2d\u5f52\u4e00\u5316\u7684\u5185\u90e8\u7ed3\u6784\u3002\u6570\u636e\u9884\u5904\u7406\u4e2d\u7684\u6807\u51c6\u5316\u5982\u4f55\u5de5\u4f5c<\/h2>\n<p>\u6807\u51c6\u5316\u5bf9\u6570\u636e\u96c6\u7684\u5404\u4e2a\u7279\u5f81\u8fdb\u884c\u64cd\u4f5c\uff0c\u4f7f\u5176\u6210\u4e3a\u7279\u5f81\u7ea7\u8f6c\u6362\u3002\u8be5\u8fc7\u7a0b\u6d89\u53ca\u8ba1\u7b97\u6bcf\u4e2a\u7279\u5f81\u7684\u7edf\u8ba1\u5c5e\u6027\uff0c\u4f8b\u5982\u6700\u5c0f\u503c\u3001\u6700\u5927\u503c\u3001\u5e73\u5747\u503c\u548c\u6807\u51c6\u5dee\uff0c\u7136\u540e\u5bf9\u8be5\u7279\u5f81\u5185\u7684\u6bcf\u4e2a\u6570\u636e\u70b9\u5e94\u7528\u9002\u5f53\u7684\u7f29\u653e\u516c\u5f0f\u3002<\/p>\n<p>\u6807\u51c6\u5316\u7684\u4e3b\u8981\u76ee\u6807\u662f\u9632\u6b62\u67d0\u4e9b\u7279\u5f81\u56e0\u5176\u8f83\u5927\u7684\u91cf\u7ea7\u800c\u4e3b\u5bfc\u5b66\u4e60\u8fc7\u7a0b\u3002\u901a\u8fc7\u5c06\u6240\u6709\u7279\u5f81\u7f29\u653e\u5230\u4e00\u4e2a\u5171\u540c\u8303\u56f4\uff0c\u6807\u51c6\u5316\u53ef\u786e\u4fdd\u6bcf\u4e2a\u7279\u5f81\u5bf9\u5b66\u4e60\u8fc7\u7a0b\u6309\u6bd4\u4f8b\u505a\u51fa\u8d21\u732e\uff0c\u5e76\u9632\u6b62\u4f18\u5316\u671f\u95f4\u7684\u6570\u503c\u4e0d\u7a33\u5b9a\u3002<\/p>\n<h2>\u6570\u636e\u9884\u5904\u7406\u4e2d\u89c4\u8303\u5316\u7684\u5173\u952e\u7279\u5f81\u5206\u6790<\/h2>\n<p>\u6807\u51c6\u5316\u5728\u6570\u636e\u9884\u5904\u7406\u65b9\u9762\u63d0\u4f9b\u4e86\u51e0\u4e2a\u5173\u952e\u4f18\u52bf\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u6539\u5584\u6536\u655b\u6027<\/strong>\uff1a\u5f52\u4e00\u5316\u6709\u52a9\u4e8e\u7b97\u6cd5\u5728\u8bad\u7ec3\u671f\u95f4\u66f4\u5feb\u5730\u6536\u655b\uff0c\u5c24\u5176\u662f\u5728\u68af\u5ea6\u4e0b\u964d\u7b49\u57fa\u4e8e\u4f18\u5316\u7684\u7b97\u6cd5\u4e2d\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u589e\u5f3a\u6a21\u578b\u6027\u80fd<\/strong>\uff1a\u6807\u51c6\u5316\u6570\u636e\u53ef\u4ee5\u5e26\u6765\u66f4\u597d\u7684\u6a21\u578b\u6027\u80fd\u548c\u6cdb\u5316\u80fd\u529b\uff0c\u56e0\u4e3a\u5b83\u53ef\u4ee5\u964d\u4f4e\u8fc7\u5ea6\u62df\u5408\u7684\u98ce\u9669\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u7279\u5f81\u7684\u53ef\u6bd4\u6027<\/strong>\uff1a\u5b83\u5141\u8bb8\u76f4\u63a5\u6bd4\u8f83\u4e0d\u540c\u5355\u4f4d\u548c\u8303\u56f4\u7684\u7279\u5f81\uff0c\u4fc3\u8fdb\u5206\u6790\u8fc7\u7a0b\u4e2d\u7684\u516c\u5e73\u52a0\u6743\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u5bf9\u5f02\u5e38\u503c\u7684\u7a33\u5065\u6027<\/strong>\uff1a\u4e00\u4e9b\u6807\u51c6\u5316\u6280\u672f\uff0c\u4f8b\u5982 Z \u5206\u6570\u6807\u51c6\u5316\uff0c\u5bf9\u5f02\u5e38\u503c\u66f4\u5177\u9c81\u68d2\u6027\uff0c\u56e0\u4e3a\u5b83\u4eec\u5bf9\u6781\u7aef\u503c\u4e0d\u592a\u654f\u611f\u3002<\/p>\n<\/li>\n<\/ol>\n<h2>\u6570\u636e\u9884\u5904\u7406\u4e2d\u7684\u6807\u51c6\u5316\u7c7b\u578b<\/h2>\n<p>\u5b58\u5728\u591a\u79cd\u7c7b\u578b\u7684\u6807\u51c6\u5316\u6280\u672f\uff0c\u6bcf\u79cd\u6280\u672f\u90fd\u6709\u5176\u7279\u5b9a\u7684\u7528\u4f8b\u548c\u7279\u5f81\u3002\u4ee5\u4e0b\u662f\u6700\u5e38\u89c1\u7684\u6807\u51c6\u5316\u7c7b\u578b\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u6700\u5c0f-\u6700\u5927\u7f29\u653e\uff08\u6807\u51c6\u5316\uff09<\/strong>:<\/p>\n<ul>\n<li>\u5c06\u6570\u636e\u7f29\u653e\u5230\u7279\u5b9a\u8303\u56f4\uff0c\u901a\u5e38\u5728 0 \u5230 1 \u4e4b\u95f4\u3002<\/li>\n<li>\u4fdd\u7559\u6570\u636e\u70b9\u4e4b\u95f4\u7684\u76f8\u5bf9\u5173\u7cfb\u3002<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><strong>Z \u5206\u6570\u6807\u51c6\u5316<\/strong>:<\/p>\n<ul>\n<li>\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u5747\u503c\u4e3a\u96f6\u4e14\u5355\u4f4d\u65b9\u5dee\u4e3a\u96f6\u7684\u6570\u636e\u3002<\/li>\n<li>\u5f53\u6570\u636e\u670d\u4ece\u9ad8\u65af\u5206\u5e03\u65f6\u5f88\u6709\u7528\u3002<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><strong>\u5341\u8fdb\u5236\u7f29\u653e<\/strong>:<\/p>\n<ul>\n<li>\u79fb\u52a8\u6570\u636e\u7684\u5c0f\u6570\u70b9\uff0c\u4f7f\u5176\u843d\u5728\u7279\u5b9a\u8303\u56f4\u5185\u3002<\/li>\n<li>\u4fdd\u7559\u6709\u6548\u4f4d\u6570\u3002<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><strong>\u6700\u5927\u7f29\u653e\u6bd4\u4f8b<\/strong>:<\/p>\n<ul>\n<li>\u5c06\u6570\u636e\u9664\u4ee5\u6700\u5927\u503c\uff0c\u8bbe\u7f6e\u8303\u56f4\u4ecb\u4e8e 0 \u548c 1 \u4e4b\u95f4\u3002<\/li>\n<li>\u5f53\u6700\u5c0f\u503c\u4e3a\u96f6\u65f6\u9002\u7528\u3002<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><strong>\u5411\u91cf\u8303\u6570<\/strong>:<\/p>\n<ul>\n<li>\u5c06\u6bcf\u4e2a\u6570\u636e\u70b9\u6807\u51c6\u5316\u4e3a\u5177\u6709\u5355\u4f4d\u8303\u6570\uff08\u957f\u5ea6\uff09\u3002<\/li>\n<li>\u5e38\u7528\u4e8e\u6587\u672c\u5206\u7c7b\u548c\u805a\u7c7b\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h2>\u6570\u636e\u9884\u5904\u7406\u4e2d\u5f52\u4e00\u5316\u7684\u4f7f\u7528\u65b9\u6cd5\u3001\u4f7f\u7528\u4e2d\u51fa\u73b0\u7684\u95ee\u9898\u53ca\u89e3\u51b3\u65b9\u6848<\/h2>\n<p>\u6807\u51c6\u5316\u662f\u4e00\u79cd\u7528\u4e8e\u5404\u79cd\u6570\u636e\u9884\u5904\u7406\u573a\u666f\u7684\u901a\u7528\u6280\u672f\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u673a\u5668\u5b66\u4e60<\/strong>\uff1a\u5728\u8bad\u7ec3\u673a\u5668\u5b66\u4e60\u6a21\u578b\u4e4b\u524d\uff0c\u89c4\u8303\u5316\u7279\u5f81\u5bf9\u4e8e\u9632\u6b62\u67d0\u4e9b\u5c5e\u6027\u4e3b\u5bfc\u5b66\u4e60\u8fc7\u7a0b\u81f3\u5173\u91cd\u8981\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u805a\u7c7b<\/strong>\uff1a\u5f52\u4e00\u5316\u53ef\u786e\u4fdd\u5177\u6709\u4e0d\u540c\u5355\u4f4d\u6216\u5c3a\u5ea6\u7684\u7279\u5f81\u4e0d\u4f1a\u8fc7\u5ea6\u5f71\u54cd\u805a\u7c7b\u8fc7\u7a0b\uff0c\u4ece\u800c\u83b7\u5f97\u66f4\u51c6\u786e\u7684\u7ed3\u679c\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u56fe\u50cf\u5904\u7406<\/strong>\uff1a\u5728\u8ba1\u7b97\u673a\u89c6\u89c9\u4efb\u52a1\u4e2d\uff0c\u50cf\u7d20\u5f3a\u5ea6\u7684\u6807\u51c6\u5316\u6709\u52a9\u4e8e\u6807\u51c6\u5316\u56fe\u50cf\u6570\u636e\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u65f6\u95f4\u5e8f\u5217\u5206\u6790<\/strong>\uff1a\u53ef\u4ee5\u5bf9\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u8fdb\u884c\u5f52\u4e00\u5316\uff0c\u4f7f\u4e0d\u540c\u7684\u5e8f\u5217\u5177\u6709\u53ef\u6bd4\u6027\u3002<\/p>\n<\/li>\n<\/ol>\n<p>\u7136\u800c\uff0c\u4f7f\u7528\u6807\u51c6\u5316\u65f6\u5b58\u5728\u6f5c\u5728\u7684\u6311\u6218\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u5bf9\u5f02\u5e38\u503c\u654f\u611f<\/strong>\uff1a\u6700\u5c0f-\u6700\u5927\u7f29\u653e\u5bf9\u5f02\u5e38\u503c\u53ef\u80fd\u5f88\u654f\u611f\uff0c\u56e0\u4e3a\u5b83\u6839\u636e\u6700\u5c0f\u503c\u548c\u6700\u5927\u503c\u4e4b\u95f4\u7684\u8303\u56f4\u7f29\u653e\u6570\u636e\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u6570\u636e\u6cc4\u9732<\/strong>\uff1a\u5e94\u5bf9\u8bad\u7ec3\u6570\u636e\u8fdb\u884c\u5f52\u4e00\u5316\uff0c\u5e76\u4e00\u81f4\u5730\u5e94\u7528\u4e8e\u6d4b\u8bd5\u6570\u636e\uff0c\u4ee5\u907f\u514d\u6570\u636e\u6cc4\u6f0f\u548c\u6709\u504f\u5dee\u7684\u7ed3\u679c\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u8de8\u6570\u636e\u96c6\u6807\u51c6\u5316<\/strong>\uff1a\u5982\u679c\u65b0\u6570\u636e\u7684\u7edf\u8ba1\u7279\u6027\u4e0e\u8bad\u7ec3\u6570\u636e\u6709\u663e\u8457\u5dee\u5f02\uff0c\u5219\u6807\u51c6\u5316\u53ef\u80fd\u65e0\u6cd5\u6709\u6548\u53d1\u6325\u4f5c\u7528\u3002<\/p>\n<\/li>\n<\/ol>\n<p>\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e9b\u95ee\u9898\uff0c\u6570\u636e\u5206\u6790\u5e08\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u5f3a\u5927\u7684\u6807\u51c6\u5316\u65b9\u6cd5\u6216\u63a2\u7d22\u7279\u5f81\u5de5\u7a0b\u6216\u6570\u636e\u8f6c\u6362\u7b49\u66ff\u4ee3\u65b9\u6cd5\u3002<\/p>\n<h2>\u4e3b\u8981\u7279\u5f81\u4ee5\u53ca\u4e0e\u7c7b\u4f3c\u672f\u8bed\u7684\u5176\u4ed6\u6bd4\u8f83\u4ee5\u8868\u683c\u548c\u5217\u8868\u7684\u5f62\u5f0f<\/h2>\n<p>\u4e0b\u9762\u662f\u5f52\u4e00\u5316\u548c\u5176\u4ed6\u76f8\u5173\u6570\u636e\u9884\u5904\u7406\u6280\u672f\u7684\u5bf9\u6bd4\u8868\uff1a<\/p>\n<table>\n<thead>\n<tr>\n<th>\u6280\u672f<\/th>\n<th>\u76ee\u7684<\/th>\n<th>\u7279\u6027<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>\u6b63\u5e38\u5316<\/strong><\/td>\n<td>\u5c06\u7279\u5f81\u7f29\u653e\u5230\u516c\u5171\u8303\u56f4<\/td>\n<td>\u4fdd\u7559\u76f8\u5bf9\u5173\u7cfb<\/td>\n<\/tr>\n<tr>\n<td><strong>\u6807\u51c6\u5316<\/strong><\/td>\n<td>\u5c06\u6570\u636e\u8f6c\u6362\u4e3a\u96f6\u5747\u503c\u548c\u5355\u4f4d\u65b9\u5dee<\/td>\n<td>\u5047\u8bbe\u9ad8\u65af\u5206\u5e03<\/td>\n<\/tr>\n<tr>\n<td><strong>\u7279\u5f81\u7f29\u653e<\/strong><\/td>\n<td>\u6ca1\u6709\u7279\u5b9a\u8303\u56f4\u7684\u5c3a\u5ea6\u7279\u5f81<\/td>\n<td>\u4fdd\u7559\u7279\u5f81\u6bd4\u4f8b<\/td>\n<\/tr>\n<tr>\n<td><strong>\u6570\u636e\u8f6c\u6362<\/strong><\/td>\n<td>\u66f4\u6539\u6570\u636e\u5206\u5e03\u4ee5\u8fdb\u884c\u5206\u6790<\/td>\n<td>\u53ef\u4ee5\u662f\u975e\u7ebf\u6027\u7684<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u4e0e\u6570\u636e\u9884\u5904\u7406\u6807\u51c6\u5316\u76f8\u5173\u7684\u672a\u6765\u524d\u666f\u548c\u6280\u672f<\/h2>\n<p>\u6570\u636e\u9884\u5904\u7406\u7684\u6807\u51c6\u5316\u5c06\u7ee7\u7eed\u5728\u6570\u636e\u5206\u6790\u548c\u673a\u5668\u5b66\u4e60\u4e2d\u53d1\u6325\u81f3\u5173\u91cd\u8981\u7684\u4f5c\u7528\u3002\u968f\u7740\u4eba\u5de5\u667a\u80fd\u548c\u6570\u636e\u79d1\u5b66\u9886\u57df\u7684\u8fdb\u6b65\uff0c\u53ef\u80fd\u4f1a\u51fa\u73b0\u9488\u5bf9\u7279\u5b9a\u6570\u636e\u7c7b\u578b\u548c\u7b97\u6cd5\u7684\u65b0\u6807\u51c6\u5316\u6280\u672f\u3002\u672a\u6765\u7684\u53d1\u5c55\u53ef\u80fd\u4f1a\u96c6\u4e2d\u5728\u81ea\u9002\u5e94\u6807\u51c6\u5316\u65b9\u6cd5\u4e0a\uff0c\u8be5\u65b9\u6cd5\u53ef\u4ee5\u81ea\u52a8\u8c03\u6574\u4ee5\u9002\u5e94\u4e0d\u540c\u7684\u6570\u636e\u5206\u5e03\uff0c\u4ece\u800c\u63d0\u9ad8\u9884\u5904\u7406\u7ba1\u9053\u7684\u6548\u7387\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u6df1\u5ea6\u5b66\u4e60\u548c\u795e\u7ecf\u7f51\u7edc\u67b6\u6784\u7684\u8fdb\u6b65\u53ef\u80fd\u4f1a\u5c06\u5f52\u4e00\u5316\u5c42\u4f5c\u4e3a\u6a21\u578b\u7684\u7ec4\u6210\u90e8\u5206\uff0c\u4ece\u800c\u51cf\u5c11\u5bf9\u663e\u5f0f\u9884\u5904\u7406\u6b65\u9aa4\u7684\u9700\u6c42\u3002\u8fd9\u79cd\u96c6\u6210\u53ef\u4ee5\u8fdb\u4e00\u6b65\u7b80\u5316\u8bad\u7ec3\u8fc7\u7a0b\u5e76\u63d0\u9ad8\u6a21\u578b\u6027\u80fd\u3002<\/p>\n<h2>\u5982\u4f55\u5728\u6570\u636e\u9884\u5904\u7406\u4e2d\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\u6216\u5c06\u4ee3\u7406\u670d\u52a1\u5668\u4e0e\u89c4\u8303\u5316\u76f8\u5173\u8054<\/h2>\n<p>OneProxy \u7b49\u63d0\u4f9b\u5546\u63d0\u4f9b\u7684\u4ee3\u7406\u670d\u52a1\u5668\u5145\u5f53\u5ba2\u6237\u7aef\u4e0e\u5176\u4ed6\u670d\u52a1\u5668\u4e4b\u95f4\u7684\u4e2d\u4ecb\uff0c\u53ef\u589e\u5f3a\u5b89\u5168\u6027\u3001\u9690\u79c1\u6027\u548c\u6027\u80fd\u3002\u867d\u7136\u4ee3\u7406\u670d\u52a1\u5668\u672c\u8eab\u4e0e\u89c4\u8303\u5316\u7b49\u6570\u636e\u9884\u5904\u7406\u6280\u672f\u6ca1\u6709\u76f4\u63a5\u5173\u8054\uff0c\u4f46\u5b83\u4eec\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u65b9\u5f0f\u95f4\u63a5\u5f71\u54cd\u6570\u636e\u9884\u5904\u7406\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u6570\u636e\u91c7\u96c6<\/strong>\uff1a\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u7528\u4e8e\u4ece\u5404\u79cd\u6765\u6e90\u6536\u96c6\u6570\u636e\uff0c\u786e\u4fdd\u533f\u540d\u5e76\u9632\u6b62\u76f4\u63a5\u8bbf\u95ee\u539f\u59cb\u6570\u636e\u6e90\u3002\u8fd9\u5728\u5904\u7406\u654f\u611f\u6216\u5730\u7406\u53d7\u9650\u6570\u636e\u65f6\u7279\u522b\u6709\u7528\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u6d41\u91cf\u5206\u6790<\/strong>\uff1a\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u4ee5\u534f\u52a9\u5206\u6790\u7f51\u7edc\u6d41\u91cf\uff0c\u8fd9\u53ef\u4ee5\u4f5c\u4e3a\u6570\u636e\u9884\u5904\u7406\u7684\u4e00\u90e8\u5206\uff0c\u4ee5\u8bc6\u522b\u6a21\u5f0f\u3001\u5f02\u5e38\u548c\u6f5c\u5728\u7684\u89c4\u8303\u5316\u8981\u6c42\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u6570\u636e\u6293\u53d6<\/strong>\uff1a\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u7528\u4e8e\u9ad8\u6548\u3001\u5408\u4e4e\u9053\u5fb7\u5730\u4ece\u7f51\u7ad9\u6293\u53d6\u6570\u636e\uff0c\u9632\u6b62 IP \u5c01\u9501\u5e76\u786e\u4fdd\u516c\u5e73\u7684\u6570\u636e\u6536\u96c6\u3002<\/p>\n<\/li>\n<\/ol>\n<p>\u867d\u7136\u4ee3\u7406\u670d\u52a1\u5668\u4e0d\u76f4\u63a5\u6267\u884c\u89c4\u8303\u5316\uff0c\u4f46\u5b83\u4eec\u53ef\u4ee5\u4fc3\u8fdb\u6570\u636e\u6536\u96c6\u548c\u9884\u5904\u7406\u9636\u6bb5\uff0c\u4f7f\u5176\u6210\u4e3a\u6574\u4e2a\u6570\u636e\u5904\u7406\u7ba1\u9053\u4e2d\u7684\u5b9d\u8d35\u5de5\u5177\u3002<\/p>\n<h2>\u76f8\u5173\u94fe\u63a5<\/h2>\n<p>\u6709\u5173\u6570\u636e\u9884\u5904\u7406\u4e2d\u89c4\u8303\u5316\u7684\u66f4\u591a\u4fe1\u606f\uff0c\u60a8\u53ef\u4ee5\u6d4f\u89c8\u4ee5\u4e0b\u8d44\u6e90\uff1a<\/p>\n<ul>\n<li><a href=\"https:\/\/en.wikipedia.org\/wiki\/Normalization_(statistics)\" target=\"_new\" rel=\"noopener nofollow\">\u6807\u51c6\u5316\uff08\u7edf\u8ba1\uff09\u2014\u2014\u7ef4\u57fa\u767e\u79d1<\/a><\/li>\n<li><a href=\"https:\/\/towardsdatascience.com\/feature-scaling-why-it-matters-and-how-to-do-it-fc9b8601aa0d\" target=\"_new\" rel=\"noopener nofollow\">\u529f\u80fd\u6269\u5c55\uff1a\u4e3a\u4ec0\u4e48\u91cd\u8981\u4ee5\u53ca\u5982\u4f55\u6b63\u786e\u6267\u884c<\/a><\/li>\n<li><a href=\"https:\/\/machinelearningmastery.com\/normalize-standardize-machine-learning-data-weka\/\" target=\"_new\" rel=\"noopener nofollow\">\u89c4\u8303\u5316\u7684\u7b80\u5355\u4ecb\u7ecd<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/cn\/blog\/proxy-servers-and-their-benefits\/\" target=\"_new\" rel=\"noopener\">\u4ee3\u7406\u670d\u52a1\u5668\u53ca\u5176\u4f18\u70b9<\/a><\/li>\n<\/ul>\n<p>\u8bf7\u8bb0\u4f4f\uff0c\u7406\u89e3\u548c\u5b9e\u65bd\u9002\u5f53\u7684\u6807\u51c6\u5316\u6280\u672f\u5bf9\u4e8e\u6570\u636e\u9884\u5904\u7406\u81f3\u5173\u91cd\u8981\uff0c\u800c\u6570\u636e\u9884\u5904\u7406\u53c8\u4e3a\u6210\u529f\u7684\u6570\u636e\u5206\u6790\u548c\u5efa\u6a21\u5960\u5b9a\u4e86\u57fa\u7840\u3002<\/p>","protected":false},"featured_media":469025,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-478223","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Normalization in Data Preprocessing<\/mark>","faq_items":[{"question":"What is normalization in data preprocessing?","answer":"<p>Normalization in data preprocessing is a vital step that transforms data into a standardized format to ensure all features are on a comparable scale. It eliminates inconsistencies and enhances the efficiency and accuracy of algorithms used in machine learning, data mining, and statistical analysis.<\/p>"},{"question":"How did normalization in data preprocessing originate?","answer":"<p>The concept of normalization dates back to early statistical practices. Its formalization can be traced to statisticians like Karl Pearson and Ronald Fisher in the late 19th and early 20th centuries. It gained popularity with the rise of artificial neural networks in the 1940s.<\/p>"},{"question":"How does normalization work?","answer":"<p>Normalization operates on individual features of the dataset, transforming each feature independently to a common scale. It involves calculating statistical properties like minimum, maximum, mean, and standard deviation and then applying the appropriate scaling formula to each data point within that feature.<\/p>"},{"question":"What are the key benefits of normalization?","answer":"<p>Normalization offers several benefits, including improved convergence in algorithms, enhanced model performance, comparability of features with different units, and robustness to outliers.<\/p>"},{"question":"What are the different types of normalization?","answer":"<p>There are various normalization techniques, including Min-Max Scaling, Z-score Standardization, Decimal Scaling, Max Scaling, and Vector Norms, each with its specific use cases and characteristics.<\/p>"},{"question":"How is normalization used in data preprocessing?","answer":"<p>Normalization is used in machine learning, clustering, image processing, time series analysis, and other data-related tasks. It ensures fair weighting of features, prevents data leakage, and makes different data sets comparable.<\/p>"},{"question":"What challenges can arise when using normalization?","answer":"<p>Normalization can be sensitive to outliers, may cause data leakage if not applied consistently, and may not work effectively if new data has significantly different statistical properties from the training data.<\/p>"},{"question":"How does normalization compare to other data preprocessing techniques?","answer":"<p>Normalization scales data to a common range, while standardization transforms data to have zero mean and unit variance. Feature scaling preserves proportions, and data transformation changes data distribution for analysis.<\/p>"},{"question":"What are the future perspectives of normalization in data preprocessing?","answer":"<p>Future developments may focus on adaptive normalization methods that automatically adjust to different data distributions. Integration of normalization layers in deep learning models could streamline training and enhance performance.<\/p>"},{"question":"How are proxy servers associated with normalization in data preprocessing?","answer":"<p>Proxy servers from providers like OneProxy can facilitate data collection and preprocessing stages, ensuring anonymity, preventing IP blocking, and aiding in efficient data scraping, indirectly impacting the overall data processing pipeline.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/478223","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/478223\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media\/469025"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media?parent=478223"}],"curies":[{"name":"\u53ef\u6e7f\u6027\u7c89\u5242","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}