{"id":23135,"date":"2024-11-20T10:13:58","date_gmt":"2024-11-20T02:13:58","guid":{"rendered":"https:\/\/aif.amtbbs.org\/?p=23135"},"modified":"2024-11-20T10:13:59","modified_gmt":"2024-11-20T02:13:59","slug":"python-%e4%ba%ba%e5%b7%a5%e6%99%ba%e8%83%bd%e9%a1%b9%e7%9b%ae%e7%9a%84%e4%ba%94%e5%a4%a7%e5%ae%9e%e6%88%98%e6%8a%80%e5%b7%a7","status":"publish","type":"post","link":"https:\/\/aif.amtbbs.org\/index.php\/2024\/11\/20\/23135\/","title":{"rendered":"Python \u4eba\u5de5\u667a\u80fd\u9879\u76ee\u7684\u4e94\u5927\u5b9e\u6218\u6280\u5de7"},"content":{"rendered":"<div class=\"article-desc\">\u672c\u6587\u4ecb\u7ecd\u4e86 Python \u4eba\u5de5\u667a\u80fd\u9879\u76ee\u7684\u4e94\u5927\u5b9e\u6218\u6280\u5de7\uff0c\u5305\u62ec\u6570\u636e\u9884\u5904\u7406\u3001\u7279\u5f81\u5de5\u7a0b\u3001\u6a21\u578b\u9009\u62e9\u4e0e\u8bc4\u4f30\u3001\u96c6\u6210\u5b66\u4e60\u548c\u6a21\u578b\u89e3\u91ca\u4e0e\u53ef\u89c6\u5316\u3002<\/div>\n<div id=\"postspictures\" class=\"article-content\">\n<div id=\"container\" class=\"container am-engine\" data-v-1d7a5742=\"\" data-element=\"root\">\n<p>\u5728\u4eca\u5929\u7684\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u6211\u4eec\u5c06\u4e00\u8d77\u63a2\u7d22 Python \u4eba\u5de5\u667a\u80fd\u9879\u76ee\u7684\u4e94\u5927\u5b9e\u6218\u6280\u5de7\u3002\u65e0\u8bba\u4f60\u662f\u521a\u521a\u63a5\u89e6 AI \u7684\u65b0\u624b\uff0c\u8fd8\u662f\u6709\u4e00\u5b9a\u7ecf\u9a8c\u7684\u5f00\u53d1\u8005\uff0c\u76f8\u4fe1\u90fd\u80fd\u4ece\u4e2d\u627e\u5230\u5bf9\u81ea\u5df1\u6709\u5e2e\u52a9\u7684\u5185\u5bb9\u3002\u8ba9\u6211\u4eec\u4e00\u6b65\u6b65\u6765\uff0c\u4ece\u57fa\u7840\u5230\u8fdb\u9636\uff0c\u4e00\u8d77\u5b66\u4e60\u5982\u4f55\u66f4\u597d\u5730\u5229\u7528 Python \u8fdb\u884c\u4eba\u5de5\u667a\u80fd\u9879\u76ee\u5f00\u53d1\u3002<\/p>\n<p><img data-dominant-color=\"9d9493\" data-has-transparency=\"false\" style=\"--dominant-color: #9d9493;\" loading=\"lazy\" decoding=\"async\" class=\"not-transparent alignnone size-full wp-image-23137\" src=\"https:\/\/aiforumimage.oss-cn-shanghai.aliyuncs.com\/wp-content\/uploads\/2024\/11\/914de637-2991-42d7-9cd1-6c43776d0671-300x167-1.png\" width=\"300\" height=\"167\" alt=\"\" srcset=\"https:\/\/aiforumimage.oss-cn-shanghai.aliyuncs.com\/wp-content\/uploads\/2024\/11\/914de637-2991-42d7-9cd1-6c43776d0671-300x167-1.png 300w, https:\/\/aiforumimage.oss-cn-shanghai.aliyuncs.com\/wp-content\/uploads\/2024\/11\/914de637-2991-42d7-9cd1-6c43776d0671-300x167-1-150x84.png 150w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4>\u6280\u5de7\u4e00\uff1a\u6570\u636e\u9884\u5904\u7406\u7684\u91cd\u8981\u6027<\/h4>\n<p>\u7406\u8bba\u8bb2\u89e3\uff1a<\/p>\n<p>\u6570\u636e\u662f\u673a\u5668\u5b66\u4e60\u7684\u57fa\u7840\uff0c\u800c\u6570\u636e\u9884\u5904\u7406\u5219\u662f\u786e\u4fdd\u6a21\u578b\u6027\u80fd\u7684\u5173\u952e\u6b65\u9aa4\u3002\u5e38\u89c1\u7684\u6570\u636e\u9884\u5904\u7406\u6280\u672f\u5305\u62ec\u6570\u636e\u6e05\u6d17\u3001\u7f3a\u5931\u503c\u5904\u7406\u3001\u7279\u5f81\u7f29\u653e\u548c\u7f16\u7801\u7b49\u3002\u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u53ef\u4ee5\u63d0\u9ad8\u6a21\u578b\u7684\u51c6\u786e\u6027\u548c\u6cdb\u5316\u80fd\u529b\u3002<\/p>\n<p>\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_0\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\"><span class=\"token keyword\">import<\/span> pandas <span class=\"token keyword\">as<\/span> pd\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>preprocessing <span class=\"token keyword\">import<\/span> StandardScaler<span class=\"token punctuation\">,<\/span> OneHotEncoder\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>compose <span class=\"token keyword\">import<\/span> ColumnTransformer\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>pipeline <span class=\"token keyword\">import<\/span> Pipeline\r\n\r\n# \u8bfb\u53d6\u6570\u636e\r\ndata <span class=\"token operator\">=<\/span> pd<span class=\"token punctuation\">.<\/span><span class=\"token function\">read_csv<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">'data.csv'<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u67e5\u770b\u6570\u636e\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span><span class=\"token function\">head<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u6570\u636e\u6e05\u6d17\uff1a\u5220\u9664\u7f3a\u5931\u503c\r\ndata<span class=\"token punctuation\">.<\/span><span class=\"token function\">dropna<\/span><span class=\"token punctuation\">(<\/span>inplace<span class=\"token operator\">=<\/span>True<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7279\u5f81\u9009\u62e9\r\n<span class=\"token constant\">X<\/span> <span class=\"token operator\">=<\/span> data<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">'age'<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">'income'<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">'gender'<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span>\r\ny <span class=\"token operator\">=<\/span> data<span class=\"token punctuation\">[<\/span><span class=\"token string\">'target'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n# \u5b9a\u4e49\u6570\u503c\u578b\u548c\u7c7b\u522b\u578b\u7279\u5f81\r\nnumeric_features <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'age'<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">'income'<\/span><span class=\"token punctuation\">]<\/span>\r\ncategorical_features <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token string\">'gender'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n# \u521b\u5efa\u9884\u5904\u7406\u7ba1\u9053\r\npreprocessor <span class=\"token operator\">=<\/span> <span class=\"token function\">ColumnTransformer<\/span><span class=\"token punctuation\">(<\/span>\r\n    transformers<span class=\"token operator\">=<\/span><span class=\"token punctuation\">[<\/span>\r\n        <span class=\"token punctuation\">(<\/span><span class=\"token string\">'num'<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token function\">StandardScaler<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> numeric_features<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n        <span class=\"token punctuation\">(<\/span><span class=\"token string\">'cat'<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token function\">OneHotEncoder<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> categorical_features<span class=\"token punctuation\">)<\/span>\r\n    <span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u521b\u5efa\u5b8c\u6574\u7684\u673a\u5668\u5b66\u4e60\u7ba1\u9053\r\npipeline <span class=\"token operator\">=<\/span> <span class=\"token function\">Pipeline<\/span><span class=\"token punctuation\">(<\/span>steps<span class=\"token operator\">=<\/span><span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">'preprocessor'<\/span><span class=\"token punctuation\">,<\/span> preprocessor<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u5e94\u7528\u9884\u5904\u7406\r\nX_processed <span class=\"token operator\">=<\/span> pipeline<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit_transform<\/span><span class=\"token punctuation\">(<\/span><span class=\"token constant\">X<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8f93\u51fa\u5904\u7406\u540e\u7684\u6570\u636e\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span>X_processed<span class=\"token punctuation\">[<\/span><span class=\"token operator\">:<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_0\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<li>13.<\/li>\n<li>14.<\/li>\n<li>15.<\/li>\n<li>16.<\/li>\n<li>17.<\/li>\n<li>18.<\/li>\n<li>19.<\/li>\n<li>20.<\/li>\n<li>21.<\/li>\n<li>22.<\/li>\n<li>23.<\/li>\n<li>24.<\/li>\n<li>25.<\/li>\n<li>26.<\/li>\n<li>27.<\/li>\n<li>28.<\/li>\n<li>29.<\/li>\n<li>30.<\/li>\n<li>31.<\/li>\n<li>32.<\/li>\n<li>33.<\/li>\n<li>34.<\/li>\n<li>35.<\/li>\n<li>36.<\/li>\n<li>37.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>\u4ee3\u7801\u89e3\u91ca\uff1a<\/p>\n<ul data-id=\"u738a58b-eBZd1h45\">\n<li data-id=\"ld70c578-TQA6hJxe\">\u8bfb\u53d6\u6570\u636e\uff1a\u4f7f\u7528 pandas \u8bfb\u53d6 CSV \u6587\u4ef6\u3002<\/li>\n<li data-id=\"ld70c578-uDMCNmJB\">\u6570\u636e\u6e05\u6d17\uff1a\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c\u3002<\/li>\n<li data-id=\"ld70c578-AIGslOj8\">\u7279\u5f81\u9009\u62e9\uff1a\u9009\u62e9\u7528\u4e8e\u8bad\u7ec3\u7684\u7279\u5f81\u548c\u76ee\u6807\u53d8\u91cf\u3002<\/li>\n<li data-id=\"ld70c578-BripV07e\">\u5b9a\u4e49\u7279\u5f81\u7c7b\u578b\uff1a\u533a\u5206\u6570\u503c\u578b\u548c\u7c7b\u522b\u578b\u7279\u5f81\u3002<\/li>\n<li data-id=\"ld70c578-boYS66nS\">\u521b\u5efa\u9884\u5904\u7406\u7ba1\u9053\uff1a\u4f7f\u7528 ColumnTransformer \u548c Pipeline \u5c06\u4e0d\u540c\u7684\u9884\u5904\u7406\u6b65\u9aa4\u7ec4\u5408\u5728\u4e00\u8d77\u3002<\/li>\n<li data-id=\"ld70c578-aqvER16U\">\u5e94\u7528\u9884\u5904\u7406\uff1a\u5c06\u9884\u5904\u7406\u5e94\u7528\u4e8e\u6570\u636e\u5e76\u8f93\u51fa\u524d\u4e94\u884c\u5904\u7406\u540e\u7684\u6570\u636e\u3002<\/li>\n<\/ul>\n<h4>\u6280\u5de7\u4e8c\uff1a\u7279\u5f81\u5de5\u7a0b\u7684\u827a\u672f<\/h4>\n<p>\u7406\u8bba\u8bb2\u89e3\uff1a<\/p>\n<p>\u7279\u5f81\u5de5\u7a0b\u662f\u5c06\u539f\u59cb\u6570\u636e\u8f6c\u6362\u4e3a\u66f4\u6709\u52a9\u4e8e\u673a\u5668\u5b66\u4e60\u7b97\u6cd5\u7684\u5f62\u5f0f\u7684\u8fc7\u7a0b\u3002\u597d\u7684\u7279\u5f81\u53ef\u4ee5\u663e\u8457\u63d0\u5347\u6a21\u578b\u7684\u6027\u80fd\u3002\u5e38\u89c1\u7684\u7279\u5f81\u5de5\u7a0b\u65b9\u6cd5\u5305\u62ec\u7279\u5f81\u9009\u62e9\u3001\u7279\u5f81\u6784\u9020\u548c\u7279\u5f81\u8f6c\u6362\u7b49\u3002<\/p>\n<p>\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_1\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\"><span class=\"token keyword\">import<\/span> numpy <span class=\"token keyword\">as<\/span> np\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>feature_selection <span class=\"token keyword\">import<\/span> SelectKBest<span class=\"token punctuation\">,<\/span> f_classif\r\n\r\n# \u5047\u8bbe <span class=\"token constant\">X<\/span> \u662f\u5904\u7406\u540e\u7684\u7279\u5f81\u77e9\u9635\uff0cy \u662f\u76ee\u6807\u53d8\u91cf\r\n<span class=\"token constant\">X<\/span> <span class=\"token operator\">=<\/span> np<span class=\"token punctuation\">.<\/span>random<span class=\"token punctuation\">.<\/span><span class=\"token function\">rand<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">100<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">)<\/span>  # \u751f\u6210\u968f\u673a\u6570\u636e\r\ny <span class=\"token operator\">=<\/span> np<span class=\"token punctuation\">.<\/span>random<span class=\"token punctuation\">.<\/span><span class=\"token function\">randint<\/span><span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">100<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u4f7f\u7528 SelectKBest \u9009\u62e9\u6700\u91cd\u8981\u7684 <span class=\"token number\">5<\/span> \u4e2a\u7279\u5f81\r\nselector <span class=\"token operator\">=<\/span> <span class=\"token function\">SelectKBest<\/span><span class=\"token punctuation\">(<\/span>score_func<span class=\"token operator\">=<\/span>f_classif<span class=\"token punctuation\">,<\/span> k<span class=\"token operator\">=<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">)<\/span>\r\nX_new <span class=\"token operator\">=<\/span> selector<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit_transform<\/span><span class=\"token punctuation\">(<\/span><span class=\"token constant\">X<\/span><span class=\"token punctuation\">,<\/span> y<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8f93\u51fa\u9009\u62e9\u7684\u7279\u5f81\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Selected features:\"<\/span><span class=\"token punctuation\">,<\/span> selector<span class=\"token punctuation\">.<\/span><span class=\"token function\">get_support<\/span><span class=\"token punctuation\">(<\/span>indices<span class=\"token operator\">=<\/span>True<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_1\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<li>13.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>\u4ee3\u7801\u89e3\u91ca\uff1a<\/p>\n<ul data-id=\"u738a58b-ZAXqxJs9\">\n<li data-id=\"ld70c578-EOVlDIXl\">\u751f\u6210\u968f\u673a\u6570\u636e\uff1a\u521b\u5efa\u4e00\u4e2a 100 \u884c 10 \u5217\u7684\u968f\u673a\u7279\u5f81\u77e9\u9635\u548c\u4e00\u4e2a 100 \u884c\u7684\u76ee\u6807\u53d8\u91cf\u3002<\/li>\n<li data-id=\"ld70c578-JrOsGKQP\">\u9009\u62e9\u7279\u5f81\uff1a\u4f7f\u7528 SelectKBest \u9009\u62e9\u6700\u91cd\u8981\u7684 5 \u4e2a\u7279\u5f81\u3002<\/li>\n<li data-id=\"ld70c578-P3lv8NVE\">\u8f93\u51fa\u9009\u62e9\u7684\u7279\u5f81\uff1a\u6253\u5370\u51fa\u88ab\u9009\u4e2d\u7684\u7279\u5f81\u7d22\u5f15\u3002<\/li>\n<\/ul>\n<h4>\u6280\u5de7\u4e09\uff1a\u6a21\u578b\u9009\u62e9\u4e0e\u8bc4\u4f30<\/h4>\n<p>\u7406\u8bba\u8bb2\u89e3\uff1a<\/p>\n<p>\u9009\u62e9\u5408\u9002\u7684\u6a21\u578b\u5e76\u8fdb\u884c\u6709\u6548\u7684\u8bc4\u4f30\u662f\u673a\u5668\u5b66\u4e60\u9879\u76ee\u7684\u91cd\u8981\u73af\u8282\u3002\u5e38\u7528\u7684\u6a21\u578b\u9009\u62e9\u65b9\u6cd5\u5305\u62ec\u4ea4\u53c9\u9a8c\u8bc1\u3001\u7f51\u683c\u641c\u7d22\u7b49\u3002\u8bc4\u4f30\u6307\u6807\u5219\u5305\u62ec\u51c6\u786e\u7387\u3001\u7cbe\u786e\u7387\u3001\u53ec\u56de\u7387\u548c F1 \u5206\u6570\u7b49\u3002<\/p>\n<p>\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_2\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\">from sklearn<span class=\"token punctuation\">.<\/span>model_selection <span class=\"token keyword\">import<\/span> train_test_split<span class=\"token punctuation\">,<\/span> GridSearchCV\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>ensemble <span class=\"token keyword\">import<\/span> RandomForestClassifier\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>metrics <span class=\"token keyword\">import<\/span> accuracy_score<span class=\"token punctuation\">,<\/span> classification_report\r\n\r\n# \u5212\u5206\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\r\nX_train<span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">,<\/span> y_train<span class=\"token punctuation\">,<\/span> y_test <span class=\"token operator\">=<\/span> <span class=\"token function\">train_test_split<\/span><span class=\"token punctuation\">(<\/span>X_new<span class=\"token punctuation\">,<\/span> y<span class=\"token punctuation\">,<\/span> test_size<span class=\"token operator\">=<\/span><span class=\"token number\">0.2<\/span><span class=\"token punctuation\">,<\/span> random_state<span class=\"token operator\">=<\/span><span class=\"token number\">42<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u521d\u59cb\u5316\u6a21\u578b\r\nmodel <span class=\"token operator\">=<\/span> <span class=\"token function\">RandomForestClassifier<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u5b9a\u4e49\u53c2\u6570\u7f51\u683c\r\nparam_grid <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">{<\/span>\r\n    \r\n<span class=\"token string-property property\">'n_estimators'<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">50<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">100<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>\r\n    \r\n<span class=\"token string-property property\">'max_depth'<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span>None<span class=\"token punctuation\">,<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">20<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">30<\/span><span class=\"token punctuation\">]<\/span>\r\n<span class=\"token punctuation\">}<\/span>\r\n\r\n# \u4f7f\u7528\u7f51\u683c\u641c\u7d22\u8fdb\u884c\u8d85\u53c2\u6570\u8c03\u4f18\r\ngrid_search <span class=\"token operator\">=<\/span> <span class=\"token function\">GridSearchCV<\/span><span class=\"token punctuation\">(<\/span>model<span class=\"token punctuation\">,<\/span> param_grid<span class=\"token punctuation\">,<\/span> cv<span class=\"token operator\">=<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> scoring<span class=\"token operator\">=<\/span><span class=\"token string\">'accuracy'<\/span><span class=\"token punctuation\">)<\/span>\r\ngrid_search<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit<\/span><span class=\"token punctuation\">(<\/span>X_train<span class=\"token punctuation\">,<\/span> y_train<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8f93\u51fa\u6700\u4f73\u53c2\u6570\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Best parameters:\"<\/span><span class=\"token punctuation\">,<\/span> grid_search<span class=\"token punctuation\">.<\/span>best_params_<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u9884\u6d4b\u6d4b\u8bd5\u96c6\r\ny_pred <span class=\"token operator\">=<\/span> grid_search<span class=\"token punctuation\">.<\/span><span class=\"token function\">predict<\/span><span class=\"token punctuation\">(<\/span>X_test<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8ba1\u7b97\u51c6\u786e\u7387\r\naccuracy <span class=\"token operator\">=<\/span> <span class=\"token function\">accuracy_score<\/span><span class=\"token punctuation\">(<\/span>y_test<span class=\"token punctuation\">,<\/span> y_pred<span class=\"token punctuation\">)<\/span>\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Accuracy:\"<\/span><span class=\"token punctuation\">,<\/span> accuracy<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u6253\u5370\u5206\u7c7b\u62a5\u544a\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token function\">classification_report<\/span><span class=\"token punctuation\">(<\/span>y_test<span class=\"token punctuation\">,<\/span> y_pred<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_2\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<li>13.<\/li>\n<li>14.<\/li>\n<li>15.<\/li>\n<li>16.<\/li>\n<li>17.<\/li>\n<li>18.<\/li>\n<li>19.<\/li>\n<li>20.<\/li>\n<li>21.<\/li>\n<li>22.<\/li>\n<li>23.<\/li>\n<li>24.<\/li>\n<li>25.<\/li>\n<li>26.<\/li>\n<li>27.<\/li>\n<li>28.<\/li>\n<li>29.<\/li>\n<li>30.<\/li>\n<li>31.<\/li>\n<li>32.<\/li>\n<li>33.<\/li>\n<li>34.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>\u4ee3\u7801\u89e3\u91ca\uff1a<\/p>\n<ul data-id=\"u738a58b-0gIRiEO2\">\n<li data-id=\"ld70c578-BD3umo7B\">\u5212\u5206\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\uff1a\u4f7f\u7528 train_test_split \u5c06\u6570\u636e\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\u3002<\/li>\n<li data-id=\"ld70c578-tq6ODOvp\">\u521d\u59cb\u5316\u6a21\u578b\uff1a\u9009\u62e9 RandomForestClassifier \u4f5c\u4e3a\u6a21\u578b\u3002<\/li>\n<li data-id=\"ld70c578-HFLFWIQb\">\u5b9a\u4e49\u53c2\u6570\u7f51\u683c\uff1a\u8bbe\u7f6e\u8981\u641c\u7d22\u7684\u8d85\u53c2\u6570\u8303\u56f4\u3002<\/li>\n<li data-id=\"ld70c578-gxZ4baBU\">\u7f51\u683c\u641c\u7d22\uff1a\u4f7f\u7528 GridSearchCV \u8fdb\u884c\u8d85\u53c2\u6570\u8c03\u4f18\u3002<\/li>\n<li data-id=\"ld70c578-tTMAHwk0\">\u8f93\u51fa\u6700\u4f73\u53c2\u6570\uff1a\u6253\u5370\u51fa\u6700\u4f73\u8d85\u53c2\u6570\u7ec4\u5408\u3002<\/li>\n<li data-id=\"ld70c578-erboSmYy\">\u9884\u6d4b\u6d4b\u8bd5\u96c6\uff1a\u4f7f\u7528\u6700\u4f73\u6a21\u578b\u9884\u6d4b\u6d4b\u8bd5\u96c6\u3002<\/li>\n<li data-id=\"ld70c578-RNSsncxV\">\u8ba1\u7b97\u51c6\u786e\u7387\uff1a\u8ba1\u7b97\u6a21\u578b\u5728\u6d4b\u8bd5\u96c6\u4e0a\u7684\u51c6\u786e\u7387\u3002<\/li>\n<li data-id=\"ld70c578-wyubtBhY\">\u6253\u5370\u5206\u7c7b\u62a5\u544a\uff1a\u8f93\u51fa\u8be6\u7ec6\u7684\u5206\u7c7b\u62a5\u544a\uff0c\u5305\u62ec\u7cbe\u786e\u7387\u3001\u53ec\u56de\u7387\u548c F1 \u5206\u6570\u3002<\/li>\n<\/ul>\n<h4>\u6280\u5de7\u56db\uff1a\u96c6\u6210\u5b66\u4e60\u7684\u529b\u91cf<\/h4>\n<p>\u7406\u8bba\u8bb2\u89e3\uff1a<\/p>\n<p>\u96c6\u6210\u5b66\u4e60\u901a\u8fc7\u7ed3\u5408\u591a\u4e2a\u6a21\u578b\u7684\u9884\u6d4b\u7ed3\u679c\u6765\u63d0\u9ad8\u6a21\u578b\u7684\u6027\u80fd\u3002\u5e38\u89c1\u7684\u96c6\u6210\u5b66\u4e60\u65b9\u6cd5\u5305\u62ec bagging\u3001boosting \u548c stacking \u7b49\u3002\u96c6\u6210\u5b66\u4e60\u53ef\u4ee5\u6709\u6548\u51cf\u5c11\u8fc7\u62df\u5408\uff0c\u63d0\u9ad8\u6a21\u578b\u7684\u9c81\u68d2\u6027\u3002<\/p>\n<p>\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_3\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\">from sklearn<span class=\"token punctuation\">.<\/span>ensemble <span class=\"token keyword\">import<\/span> VotingClassifier\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>linear_model <span class=\"token keyword\">import<\/span> LogisticRegression\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>svm <span class=\"token keyword\">import<\/span> <span class=\"token constant\">SVC<\/span>\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>neighbors <span class=\"token keyword\">import<\/span> KNeighborsClassifier\r\n\r\n# \u521d\u59cb\u5316\u4e0d\u540c\u7684\u57fa\u6a21\u578b\r\nmodel1 <span class=\"token operator\">=<\/span> <span class=\"token function\">LogisticRegression<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\nmodel2 <span class=\"token operator\">=<\/span> <span class=\"token constant\">SVC<\/span><span class=\"token punctuation\">(<\/span>probability<span class=\"token operator\">=<\/span>True<span class=\"token punctuation\">)<\/span>\r\nmodel3 <span class=\"token operator\">=<\/span> <span class=\"token function\">KNeighborsClassifier<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u521b\u5efa\u6295\u7968\u5206\u7c7b\u5668\r\nvoting_clf <span class=\"token operator\">=<\/span> <span class=\"token function\">VotingClassifier<\/span><span class=\"token punctuation\">(<\/span>estimators<span class=\"token operator\">=<\/span><span class=\"token punctuation\">[<\/span>\r\n    <span class=\"token punctuation\">(<\/span><span class=\"token string\">'lr'<\/span><span class=\"token punctuation\">,<\/span> model1<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n    <span class=\"token punctuation\">(<\/span><span class=\"token string\">'svc'<\/span><span class=\"token punctuation\">,<\/span> model2<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span>\r\n    <span class=\"token punctuation\">(<\/span><span class=\"token string\">'knn'<\/span><span class=\"token punctuation\">,<\/span> model3<span class=\"token punctuation\">)<\/span>\r\n<span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> voting<span class=\"token operator\">=<\/span><span class=\"token string\">'soft'<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8bad\u7ec3\u6295\u7968\u5206\u7c7b\u5668\r\nvoting_clf<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit<\/span><span class=\"token punctuation\">(<\/span>X_train<span class=\"token punctuation\">,<\/span> y_train<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u9884\u6d4b\u6d4b\u8bd5\u96c6\r\ny_pred <span class=\"token operator\">=<\/span> voting_clf<span class=\"token punctuation\">.<\/span><span class=\"token function\">predict<\/span><span class=\"token punctuation\">(<\/span>X_test<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8ba1\u7b97\u51c6\u786e\u7387\r\naccuracy <span class=\"token operator\">=<\/span> <span class=\"token function\">accuracy_score<\/span><span class=\"token punctuation\">(<\/span>y_test<span class=\"token punctuation\">,<\/span> y_pred<span class=\"token punctuation\">)<\/span>\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Voting Classifier Accuracy:\"<\/span><span class=\"token punctuation\">,<\/span> accuracy<span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_3\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<li>13.<\/li>\n<li>14.<\/li>\n<li>15.<\/li>\n<li>16.<\/li>\n<li>17.<\/li>\n<li>18.<\/li>\n<li>19.<\/li>\n<li>20.<\/li>\n<li>21.<\/li>\n<li>22.<\/li>\n<li>23.<\/li>\n<li>24.<\/li>\n<li>25.<\/li>\n<li>26.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>\u4ee3\u7801\u89e3\u91ca\uff1a<\/p>\n<ul data-id=\"u738a58b-b3jdpkfq\">\n<li data-id=\"ld70c578-V2at6nQR\">\u521d\u59cb\u5316\u57fa\u6a21\u578b\uff1a\u9009\u62e9 LogisticRegression\u3001SVC \u548c KNeighborsClassifier \u4f5c\u4e3a\u57fa\u6a21\u578b\u3002<\/li>\n<li data-id=\"ld70c578-jASP1SbE\">\u521b\u5efa\u6295\u7968\u5206\u7c7b\u5668\uff1a\u4f7f\u7528 VotingClassifier \u5c06\u57fa\u6a21\u578b\u7ec4\u5408\u5728\u4e00\u8d77\uff0c\u91c7\u7528\u8f6f\u6295\u7968(\u5373\u6982\u7387\u52a0\u6743)\u3002<\/li>\n<li data-id=\"ld70c578-O49za3gu\">\u8bad\u7ec3\u6295\u7968\u5206\u7c7b\u5668\uff1a\u4f7f\u7528\u8bad\u7ec3\u96c6\u6570\u636e\u8bad\u7ec3\u6295\u7968\u5206\u7c7b\u5668\u3002<\/li>\n<li data-id=\"ld70c578-2Acnayii\">\u9884\u6d4b\u6d4b\u8bd5\u96c6\uff1a\u4f7f\u7528\u6295\u7968\u5206\u7c7b\u5668\u9884\u6d4b\u6d4b\u8bd5\u96c6\u3002<\/li>\n<li data-id=\"ld70c578-8DwZMUwB\">\u8ba1\u7b97\u51c6\u786e\u7387\uff1a\u8ba1\u7b97\u6295\u7968\u5206\u7c7b\u5668\u5728\u6d4b\u8bd5\u96c6\u4e0a\u7684\u51c6\u786e\u7387\u3002<\/li>\n<\/ul>\n<h4>\u6280\u5de7\u4e94\uff1a\u6a21\u578b\u89e3\u91ca\u4e0e\u53ef\u89c6\u5316<\/h4>\n<p>\u7406\u8bba\u8bb2\u89e3\uff1a<\/p>\n<p>\u6a21\u578b\u89e3\u91ca\u548c\u53ef\u89c6\u5316\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u66f4\u597d\u5730\u7406\u89e3\u6a21\u578b\u7684\u5de5\u4f5c\u539f\u7406\u548c\u51b3\u7b56\u8fc7\u7a0b\u3002\u5e38\u7528\u7684\u5de5\u5177\u5305\u62ec SHAP\u3001LIME \u548c\u9ec4\u65ed\u56fe\u7b49\u3002\u901a\u8fc7\u8fd9\u4e9b\u5de5\u5177\uff0c\u6211\u4eec\u53ef\u4ee5\u8bc6\u522b\u51fa\u54ea\u4e9b\u7279\u5f81\u5bf9\u6a21\u578b\u7684\u9884\u6d4b\u7ed3\u679c\u5f71\u54cd\u6700\u5927\u3002<\/p>\n<p>\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_4\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\"><span class=\"token keyword\">import<\/span> shap\r\n<span class=\"token keyword\">import<\/span> matplotlib<span class=\"token punctuation\">.<\/span>pyplot <span class=\"token keyword\">as<\/span> plt\r\n\r\n# \u8bad\u7ec3 <span class=\"token constant\">SHAP<\/span> \u89e3\u91ca\u5668\r\nexplainer <span class=\"token operator\">=<\/span> shap<span class=\"token punctuation\">.<\/span><span class=\"token function\">TreeExplainer<\/span><span class=\"token punctuation\">(<\/span>voting_clf<span class=\"token punctuation\">.<\/span>named_estimators_<span class=\"token punctuation\">[<\/span><span class=\"token string\">'lr'<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span>\r\nshap_values <span class=\"token operator\">=<\/span> explainer<span class=\"token punctuation\">.<\/span><span class=\"token function\">shap_values<\/span><span class=\"token punctuation\">(<\/span>X_test<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7ed8\u5236 <span class=\"token constant\">SHAP<\/span> \u6c47\u603b\u56fe\r\nshap<span class=\"token punctuation\">.<\/span><span class=\"token function\">summary_plot<\/span><span class=\"token punctuation\">(<\/span>shap_values<span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">,<\/span> plot_type<span class=\"token operator\">=<\/span><span class=\"token string\">\"bar\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7ed8\u5236 <span class=\"token constant\">SHAP<\/span> \u8702\u7fa4\u56fe\r\nshap<span class=\"token punctuation\">.<\/span><span class=\"token function\">summary_plot<\/span><span class=\"token punctuation\">(<\/span>shap_values<span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_4\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>\u4ee3\u7801\u89e3\u91ca\uff1a<\/p>\n<ul data-id=\"u738a58b-m1cMviGs\">\n<li data-id=\"ld70c578-l93BxG7S\">\u8bad\u7ec3 SHAP \u89e3\u91ca\u5668\uff1a\u4f7f\u7528 shap.TreeExplainer \u5bf9 LogisticRegression \u6a21\u578b\u8fdb\u884c\u89e3\u91ca\u3002<\/li>\n<li data-id=\"ld70c578-mjh5Nn1a\">\u8ba1\u7b97 SHAP \u503c\uff1a\u8ba1\u7b97\u6d4b\u8bd5\u96c6\u4e0a\u6bcf\u4e2a\u6837\u672c\u7684 SHAP \u503c\u3002<\/li>\n<li data-id=\"ld70c578-QNg3QmA1\">\u7ed8\u5236 SHAP \u6c47\u603b\u56fe\uff1a\u4f7f\u7528 shap.summary_plot \u7ed8\u5236 SHAP \u503c\u7684\u6c47\u603b\u56fe\uff0c\u663e\u793a\u6bcf\u4e2a\u7279\u5f81\u5bf9\u6a21\u578b\u9884\u6d4b\u7684\u5f71\u54cd\u3002<\/li>\n<li data-id=\"ld70c578-EbSvCZuy\">\u7ed8\u5236 SHAP \u8702\u7fa4\u56fe\uff1a\u4f7f\u7528 shap.summary_plot \u7ed8\u5236 SHAP \u8702\u7fa4\u56fe\uff0c\u663e\u793a\u6bcf\u4e2a\u6837\u672c\u7684 SHAP \u503c\u5206\u5e03\u3002<\/li>\n<\/ul>\n<h4>\u5b9e\u6218\u6848\u4f8b\uff1a\u4fe1\u7528\u5361\u6b3a\u8bc8\u68c0\u6d4b<\/h4>\n<p>(1) \u6848\u4f8b\u80cc\u666f<\/p>\n<p>\u4fe1\u7528\u5361\u6b3a\u8bc8\u68c0\u6d4b\u662f\u4e00\u4e2a\u5178\u578b\u7684\u4e8c\u5206\u7c7b\u95ee\u9898\u3002\u6211\u4eec\u7684\u76ee\u6807\u662f\u901a\u8fc7\u5386\u53f2\u4ea4\u6613\u6570\u636e\uff0c\u6784\u5efa\u4e00\u4e2a\u6a21\u578b\u6765\u9884\u6d4b\u672a\u6765\u7684\u4ea4\u6613\u662f\u5426\u4e3a\u6b3a\u8bc8\u4ea4\u6613\u3002<\/p>\n<p>(2) \u6570\u636e\u51c6\u5907<\/p>\n<p>\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u5305\u542b\u4ee5\u4e0b\u7279\u5f81\u7684\u6570\u636e\u96c6\uff1a<\/p>\n<ul data-id=\"u738a58b-mHlwnGVp\">\n<li data-id=\"ld70c578-e7d1DkbR\">time\uff1a\u4ea4\u6613\u65f6\u95f4<\/li>\n<li data-id=\"ld70c578-btVQsvtk\">amount\uff1a\u4ea4\u6613\u91d1\u989d<\/li>\n<li data-id=\"ld70c578-oI2FIdNW\">v1 \u81f3 v28\uff1a\u7ecf\u8fc7 PCA \u5904\u7406\u7684\u533f\u540d\u7279\u5f81<\/li>\n<li data-id=\"ld70c578-gZy9W6Gi\">class\uff1a\u76ee\u6807\u53d8\u91cf\uff0c0 \u8868\u793a\u6b63\u5e38\u4ea4\u6613\uff0c1 \u8868\u793a\u6b3a\u8bc8\u4ea4\u6613<\/li>\n<\/ul>\n<p>(3) \u4ee3\u7801\u5b9e\u73b0<\/p>\n<div>\n<div class=\"hljs-cto\">\n<div class=\"hljs-cto\"><button class=\"copy_btn disable\" data-clipboard-target=\"#code_id_5\">\u590d\u5236<\/button><\/p>\n<div class=\"code-toolbar\">\n<pre class=\"has-pre-numbering language-javascript\" tabindex=\"0\"><code class=\"language-javascript\"><span class=\"token keyword\">import<\/span> pandas <span class=\"token keyword\">as<\/span> pd\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>model_selection <span class=\"token keyword\">import<\/span> train_test_split\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>preprocessing <span class=\"token keyword\">import<\/span> StandardScaler\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>ensemble <span class=\"token keyword\">import<\/span> RandomForestClassifier\r\nfrom sklearn<span class=\"token punctuation\">.<\/span>metrics <span class=\"token keyword\">import<\/span> confusion_matrix<span class=\"token punctuation\">,<\/span> classification_report\r\n<span class=\"token keyword\">import<\/span> shap\r\n\r\n# \u8bfb\u53d6\u6570\u636e\r\ndata <span class=\"token operator\">=<\/span> pd<span class=\"token punctuation\">.<\/span><span class=\"token function\">read_csv<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">'creditcard.csv'<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u67e5\u770b\u6570\u636e\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span><span class=\"token function\">head<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u6570\u636e\u9884\u5904\u7406\r\nscaler <span class=\"token operator\">=<\/span> <span class=\"token function\">StandardScaler<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\ndata<span class=\"token punctuation\">[<\/span><span class=\"token string\">'amount'<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token operator\">=<\/span> scaler<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit_transform<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">[<\/span><span class=\"token string\">'amount'<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span>values<span class=\"token punctuation\">.<\/span><span class=\"token function\">reshape<\/span><span class=\"token punctuation\">(<\/span><span class=\"token operator\">-<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7279\u5f81\u9009\u62e9\r\n<span class=\"token constant\">X<\/span> <span class=\"token operator\">=<\/span> data<span class=\"token punctuation\">.<\/span><span class=\"token function\">drop<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> axis<span class=\"token operator\">=<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span>\r\ny <span class=\"token operator\">=<\/span> data<span class=\"token punctuation\">[<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n# \u5212\u5206\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\r\nX_train<span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">,<\/span> y_train<span class=\"token punctuation\">,<\/span> y_test <span class=\"token operator\">=<\/span> <span class=\"token function\">train_test_split<\/span><span class=\"token punctuation\">(<\/span><span class=\"token constant\">X<\/span><span class=\"token punctuation\">,<\/span> y<span class=\"token punctuation\">,<\/span> test_size<span class=\"token operator\">=<\/span><span class=\"token number\">0.2<\/span><span class=\"token punctuation\">,<\/span> random_state<span class=\"token operator\">=<\/span><span class=\"token number\">42<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u521d\u59cb\u5316\u6a21\u578b\r\nmodel <span class=\"token operator\">=<\/span> <span class=\"token function\">RandomForestClassifier<\/span><span class=\"token punctuation\">(<\/span>n_estimators<span class=\"token operator\">=<\/span><span class=\"token number\">100<\/span><span class=\"token punctuation\">,<\/span> random_state<span class=\"token operator\">=<\/span><span class=\"token number\">42<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8bad\u7ec3\u6a21\u578b\r\nmodel<span class=\"token punctuation\">.<\/span><span class=\"token function\">fit<\/span><span class=\"token punctuation\">(<\/span>X_train<span class=\"token punctuation\">,<\/span> y_train<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u9884\u6d4b\u6d4b\u8bd5\u96c6\r\ny_pred <span class=\"token operator\">=<\/span> model<span class=\"token punctuation\">.<\/span><span class=\"token function\">predict<\/span><span class=\"token punctuation\">(<\/span>X_test<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u8ba1\u7b97\u6df7\u6dc6\u77e9\u9635\r\nconf_matrix <span class=\"token operator\">=<\/span> <span class=\"token function\">confusion_matrix<\/span><span class=\"token punctuation\">(<\/span>y_test<span class=\"token punctuation\">,<\/span> y_pred<span class=\"token punctuation\">)<\/span>\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Confusion Matrix:\\n\"<\/span><span class=\"token punctuation\">,<\/span> conf_matrix<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u6253\u5370\u5206\u7c7b\u62a5\u544a\r\n<span class=\"token function\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Classification Report:\\n\"<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token function\">classification_report<\/span><span class=\"token punctuation\">(<\/span>y_test<span class=\"token punctuation\">,<\/span> y_pred<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u6a21\u578b\u89e3\u91ca\r\nexplainer <span class=\"token operator\">=<\/span> shap<span class=\"token punctuation\">.<\/span><span class=\"token function\">TreeExplainer<\/span><span class=\"token punctuation\">(<\/span>model<span class=\"token punctuation\">)<\/span>\r\nshap_values <span class=\"token operator\">=<\/span> explainer<span class=\"token punctuation\">.<\/span><span class=\"token function\">shap_values<\/span><span class=\"token punctuation\">(<\/span>X_test<span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7ed8\u5236 <span class=\"token constant\">SHAP<\/span> \u6c47\u603b\u56fe\r\nshap<span class=\"token punctuation\">.<\/span><span class=\"token function\">summary_plot<\/span><span class=\"token punctuation\">(<\/span>shap_values<span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">,<\/span> plot_type<span class=\"token operator\">=<\/span><span class=\"token string\">\"bar\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n# \u7ed8\u5236 <span class=\"token constant\">SHAP<\/span> \u8702\u7fa4\u56fe\r\nshap<span class=\"token punctuation\">.<\/span><span class=\"token function\">summary_plot<\/span><span class=\"token punctuation\">(<\/span>shap_values<span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> X_test<span class=\"token punctuation\">)<\/span><\/code><\/pre>\n<ul id=\"code_id_5\" class=\"pre-numbering\">\n<li>1.<\/li>\n<li>2.<\/li>\n<li>3.<\/li>\n<li>4.<\/li>\n<li>5.<\/li>\n<li>6.<\/li>\n<li>7.<\/li>\n<li>8.<\/li>\n<li>9.<\/li>\n<li>10.<\/li>\n<li>11.<\/li>\n<li>12.<\/li>\n<li>13.<\/li>\n<li>14.<\/li>\n<li>15.<\/li>\n<li>16.<\/li>\n<li>17.<\/li>\n<li>18.<\/li>\n<li>19.<\/li>\n<li>20.<\/li>\n<li>21.<\/li>\n<li>22.<\/li>\n<li>23.<\/li>\n<li>24.<\/li>\n<li>25.<\/li>\n<li>26.<\/li>\n<li>27.<\/li>\n<li>28.<\/li>\n<li>29.<\/li>\n<li>30.<\/li>\n<li>31.<\/li>\n<li>32.<\/li>\n<li>33.<\/li>\n<li>34.<\/li>\n<li>35.<\/li>\n<li>36.<\/li>\n<li>37.<\/li>\n<li>38.<\/li>\n<li>39.<\/li>\n<li>40.<\/li>\n<li>41.<\/li>\n<li>42.<\/li>\n<li>43.<\/li>\n<li>44.<\/li>\n<li>45.<\/li>\n<li>46.<\/li>\n<li>47.<\/li>\n<li>48.<\/li>\n<li>49.<\/li>\n<\/ul>\n<div class=\"toolbar\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<p>(4) \u6848\u4f8b\u5206\u6790<\/p>\n<ul data-id=\"u738a58b-Ap6FkD3n\">\n<li data-id=\"ld70c578-Uo7Nlgz0\">\u6570\u636e\u9884\u5904\u7406\uff1a\u5bf9\u4ea4\u6613\u91d1\u989d\u8fdb\u884c\u6807\u51c6\u5316\u5904\u7406\uff0c\u4f7f\u5176\u7b26\u5408\u6a21\u578b\u8f93\u5165\u7684\u8981\u6c42\u3002<\/li>\n<li data-id=\"ld70c578-paTtTN0t\">\u7279\u5f81\u9009\u62e9\uff1a\u9009\u62e9\u6240\u6709\u7279\u5f81\u8fdb\u884c\u8bad\u7ec3\uff0c\u76ee\u6807\u53d8\u91cf\u4e3a class\u3002<\/li>\n<li data-id=\"ld70c578-xJD3cE3s\">\u6a21\u578b\u8bad\u7ec3\uff1a\u4f7f\u7528 RandomForestClassifier \u8fdb\u884c\u8bad\u7ec3\u3002<\/li>\n<li data-id=\"ld70c578-KglBa2WM\">\u6a21\u578b\u8bc4\u4f30\uff1a\u901a\u8fc7\u6df7\u6dc6\u77e9\u9635\u548c\u5206\u7c7b\u62a5\u544a\u8bc4\u4f30\u6a21\u578b\u6027\u80fd\u3002<\/li>\n<li data-id=\"ld70c578-D8lH2ykr\">\u6a21\u578b\u89e3\u91ca\uff1a\u4f7f\u7528 SHAP \u503c\u5bf9\u6a21\u578b\u8fdb\u884c\u89e3\u91ca\uff0c\u8bc6\u522b\u51fa\u5bf9\u6b3a\u8bc8\u68c0\u6d4b\u5f71\u54cd\u6700\u5927\u7684\u7279\u5f81\u3002<\/li>\n<\/ul>\n<h4>\u603b\u7ed3<\/h4>\n<p>\u672c\u6587\u4ecb\u7ecd\u4e86 Python \u4eba\u5de5\u667a\u80fd\u9879\u76ee\u7684\u4e94\u5927\u5b9e\u6218\u6280\u5de7\uff0c\u5305\u62ec\u6570\u636e\u9884\u5904\u7406\u3001\u7279\u5f81\u5de5\u7a0b\u3001\u6a21\u578b\u9009\u62e9\u4e0e\u8bc4\u4f30\u3001\u96c6\u6210\u5b66\u4e60\u548c\u6a21\u578b\u89e3\u91ca\u4e0e\u53ef\u89c6\u5316\u3002<\/p>\n<p>\u6587\u7ae0\u6765\u81ea\uff1a51CTO<\/p>\n<\/div>\n<\/div>\n<div class=\"pvc_clear\"><\/div>\n<p id=\"pvc_stats_23135\" class=\"pvc_stats total_only  \" data-element-id=\"23135\" style=\"\"><i class=\"pvc-stats-icon medium\" aria-hidden=\"true\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" version=\"1.0\" viewBox=\"0 0 502 315\" preserveAspectRatio=\"xMidYMid meet\"><g transform=\"translate(0,332) scale(0.1,-0.1)\" fill=\"\" stroke=\"none\"><path d=\"M2394 3279 l-29 -30 -3 -207 c-2 -182 0 -211 15 -242 39 -76 157 -76 196 0 15 31 17 60 15 243 l-3 209 -33 29 c-26 23 -41 29 -80 29 -41 0 -53 -5 -78 -31z\"\/><path d=\"M3085 3251 c-45 -19 -58 -50 -96 -229 -47 -217 -49 -260 -13 -295 52 -53 146 -42 177 20 16 31 87 366 87 410 0 70 -86 122 -155 94z\"\/><path d=\"M1751 3234 c-13 -9 -29 -31 -37 -50 -12 -29 -10 -49 21 -204 19 -94 39 -189 45 -210 14 -50 54 -80 110 -80 34 0 48 6 76 34 21 21 34 44 34 59 0 14 -18 113 -40 219 -37 178 -43 195 -70 221 -36 32 -101 37 -139 11z\"\/><path d=\"M1163 3073 c-36 -7 -73 -59 -73 -102 0 -56 133 -378 171 -413 34 -32 83 -37 129 -13 70 36 67 87 -16 290 -86 209 -89 214 -129 231 -35 14 -42 15 -82 7z\"\/><path d=\"M3689 3066 c-15 -9 -33 -30 -42 -48 -48 -103 -147 -355 -147 -375 0 -98 131 -148 192 -74 13 15 57 108 97 206 80 196 84 226 37 273 -30 30 -99 39 -137 18z\"\/><path d=\"M583 2784 c-38 -19 -67 -74 -58 -113 9 -42 211 -354 242 -373 16 -10 45 -18 66 -18 51 0 107 52 107 100 0 39 -1 41 -124 234 -80 126 -108 162 -133 173 -41 17 -61 16 -100 -3z\"\/><path d=\"M4250 2784 c-14 -9 -74 -91 -133 -183 -95 -150 -107 -173 -107 -213 0 -55 33 -94 87 -104 67 -13 90 8 211 198 130 202 137 225 78 284 -27 27 -42 34 -72 34 -22 0 -50 -8 -64 -16z\"\/><path d=\"M2275 2693 c-553 -48 -1095 -270 -1585 -649 -135 -104 -459 -423 -483 -476 -23 -49 -22 -139 2 -186 73 -142 361 -457 571 -626 285 -228 642 -407 990 -497 242 -63 336 -73 660 -74 310 0 370 5 595 52 535 111 1045 392 1455 803 122 121 250 273 275 326 19 41 19 137 0 174 -41 79 -309 363 -465 492 -447 370 -946 591 -1479 653 -113 14 -422 18 -536 8z m395 -428 c171 -34 330 -124 456 -258 112 -119 167 -219 211 -378 27 -96 24 -300 -5 -401 -72 -255 -236 -447 -474 -557 -132 -62 -201 -76 -368 -76 -167 0 -236 14 -368 76 -213 98 -373 271 -451 485 -162 444 86 934 547 1084 153 49 292 57 452 25z m909 -232 c222 -123 408 -262 593 -441 76 -74 138 -139 138 -144 0 -16 -233 -242 -330 -319 -155 -123 -309 -223 -461 -299 l-81 -41 32 46 c18 26 49 83 70 128 143 306 141 649 -6 957 -25 52 -61 116 -79 142 l-34 47 45 -20 c26 -10 76 -36 113 -56z m-2057 25 c-40 -58 -105 -190 -130 -263 -110 -324 -59 -707 132 -981 25 -35 42 -64 37 -64 -19 0 -241 119 -326 174 -188 122 -406 314 -532 468 l-58 71 108 103 c185 178 428 349 672 473 66 33 121 60 123 61 2 0 -10 -19 -26 -42z\"\/><path d=\"M2375 1950 c-198 -44 -350 -190 -395 -379 -18 -76 -8 -221 19 -290 114 -284 457 -406 731 -260 98 52 188 154 231 260 27 69 37 214 19 290 -38 163 -166 304 -326 360 -67 23 -215 33 -279 19z\"\/><\/g><\/svg><\/i> <img loading=\"lazy\" decoding=\"async\" width=\"16\" height=\"16\" alt=\"Loading\" src=\"https:\/\/aif.amtbbs.org\/wp-content\/plugins\/page-views-count\/ajax-loader-2x.gif\" border=0 \/><\/p>\n<div class=\"pvc_clear\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u672c\u6587\u4ecb\u7ecd\u4e86 Python \u4eba\u5de5\u667a\u80fd\u9879\u76ee\u7684\u4e94\u5927\u5b9e\u6218\u6280\u5de7\uff0c\u5305\u62ec\u6570\u636e\u9884\u5904\u7406\u3001\u7279\u5f81\u5de5\u7a0b\u3001\u6a21\u578b\u9009\u62e9\u4e0e\u8bc4\u4f30\u3001\u96c6\u6210\u5b66\u4e60\u548c\u6a21\u578b [&hellip;]<\/p>\n<div class=\"pvc_clear\"><\/div>\n<p id=\"pvc_stats_23135\" class=\"pvc_stats total_only  \" data-element-id=\"23135\" style=\"\"><i class=\"pvc-stats-icon medium\" aria-hidden=\"true\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" version=\"1.0\" viewBox=\"0 0 502 315\" preserveAspectRatio=\"xMidYMid meet\"><g transform=\"translate(0,332) scale(0.1,-0.1)\" fill=\"\" stroke=\"none\"><path d=\"M2394 3279 l-29 -30 -3 -207 c-2 -182 0 -211 15 -242 39 -76 157 -76 196 0 15 31 17 60 15 243 l-3 209 -33 29 c-26 23 -41 29 -80 29 -41 0 -53 -5 -78 -31z\"\/><path d=\"M3085 3251 c-45 -19 -58 -50 -96 -229 -47 -217 -49 -260 -13 -295 52 -53 146 -42 177 20 16 31 87 366 87 410 0 70 -86 122 -155 94z\"\/><path d=\"M1751 3234 c-13 -9 -29 -31 -37 -50 -12 -29 -10 -49 21 -204 19 -94 39 -189 45 -210 14 -50 54 -80 110 -80 34 0 48 6 76 34 21 21 34 44 34 59 0 14 -18 113 -40 219 -37 178 -43 195 -70 221 -36 32 -101 37 -139 11z\"\/><path d=\"M1163 3073 c-36 -7 -73 -59 -73 -102 0 -56 133 -378 171 -413 34 -32 83 -37 129 -13 70 36 67 87 -16 290 -86 209 -89 214 -129 231 -35 14 -42 15 -82 7z\"\/><path d=\"M3689 3066 c-15 -9 -33 -30 -42 -48 -48 -103 -147 -355 -147 -375 0 -98 131 -148 192 -74 13 15 57 108 97 206 80 196 84 226 37 273 -30 30 -99 39 -137 18z\"\/><path d=\"M583 2784 c-38 -19 -67 -74 -58 -113 9 -42 211 -354 242 -373 16 -10 45 -18 66 -18 51 0 107 52 107 100 0 39 -1 41 -124 234 -80 126 -108 162 -133 173 -41 17 -61 16 -100 -3z\"\/><path d=\"M4250 2784 c-14 -9 -74 -91 -133 -183 -95 -150 -107 -173 -107 -213 0 -55 33 -94 87 -104 67 -13 90 8 211 198 130 202 137 225 78 284 -27 27 -42 34 -72 34 -22 0 -50 -8 -64 -16z\"\/><path d=\"M2275 2693 c-553 -48 -1095 -270 -1585 -649 -135 -104 -459 -423 -483 -476 -23 -49 -22 -139 2 -186 73 -142 361 -457 571 -626 285 -228 642 -407 990 -497 242 -63 336 -73 660 -74 310 0 370 5 595 52 535 111 1045 392 1455 803 122 121 250 273 275 326 19 41 19 137 0 174 -41 79 -309 363 -465 492 -447 370 -946 591 -1479 653 -113 14 -422 18 -536 8z m395 -428 c171 -34 330 -124 456 -258 112 -119 167 -219 211 -378 27 -96 24 -300 -5 -401 -72 -255 -236 -447 -474 -557 -132 -62 -201 -76 -368 -76 -167 0 -236 14 -368 76 -213 98 -373 271 -451 485 -162 444 86 934 547 1084 153 49 292 57 452 25z m909 -232 c222 -123 408 -262 593 -441 76 -74 138 -139 138 -144 0 -16 -233 -242 -330 -319 -155 -123 -309 -223 -461 -299 l-81 -41 32 46 c18 26 49 83 70 128 143 306 141 649 -6 957 -25 52 -61 116 -79 142 l-34 47 45 -20 c26 -10 76 -36 113 -56z m-2057 25 c-40 -58 -105 -190 -130 -263 -110 -324 -59 -707 132 -981 25 -35 42 -64 37 -64 -19 0 -241 119 -326 174 -188 122 -406 314 -532 468 l-58 71 108 103 c185 178 428 349 672 473 66 33 121 60 123 61 2 0 -10 -19 -26 -42z\"\/><path d=\"M2375 1950 c-198 -44 -350 -190 -395 -379 -18 -76 -8 -221 19 -290 114 -284 457 -406 731 -260 98 52 188 154 231 260 27 69 37 214 19 290 -38 163 -166 304 -326 360 -67 23 -215 33 -279 19z\"\/><\/g><\/svg><\/i> <img loading=\"lazy\" decoding=\"async\" width=\"16\" height=\"16\" alt=\"Loading\" src=\"https:\/\/aif.amtbbs.org\/wp-content\/plugins\/page-views-count\/ajax-loader-2x.gif\" border=0 \/><\/p>\n<div class=\"pvc_clear\"><\/div>\n","protected":false},"author":56,"featured_media":23137,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23,20,80],"tags":[896,113],"class_list":["post-23135","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-23","category-20","category-80","tag-python","tag-113"],"_links":{"self":[{"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/posts\/23135","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/users\/56"}],"replies":[{"embeddable":true,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/comments?post=23135"}],"version-history":[{"count":1,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/posts\/23135\/revisions"}],"predecessor-version":[{"id":23138,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/posts\/23135\/revisions\/23138"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/media\/23137"}],"wp:attachment":[{"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/media?parent=23135"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/categories?post=23135"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aif.amtbbs.org\/index.php\/wp-json\/wp\/v2\/tags?post=23135"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}