{"id":49783,"date":"2025-07-30T19:46:51","date_gmt":"2025-07-30T11:46:51","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/49783.html"},"modified":"2025-07-30T19:46:51","modified_gmt":"2025-07-30T11:46:51","slug":"%e3%80%8a%e9%9b%b6%e5%9f%ba%e7%a1%80%e5%85%a5%e9%97%a8ai%ef%bc%9a%e4%bc%a0%e7%bb%9f%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e6%a0%b8%e5%bf%83%e7%ae%97%e6%b3%95%e8%a7%a3%e6%9e%90%ef%bc%88knn%e3%80%81","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/49783.html","title":{"rendered":"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b"},"content":{"rendered":"
\u4e00\u3001Scikit-Learn\u673a\u5668\u5b66\u4e60\u6982\u8ff0<\/h5>\n

Scikit-Learn（sklearn）\u662fPython\u6700\u5e38\u7528\u7684\u673a\u5668\u5b66\u4e60\u5e93，\u7279\u70b9\u5305\u62ec：<\/p>\n

  • \u7edf\u4e00API\u8bbe\u8ba1：\u6240\u6709\u7b97\u6cd5\u90fd\u9075\u5faafit()（\u8bad\u7ec3）\u3001predict()（\u9884\u6d4b）\u7684\u7edf\u4e00\u63a5\u53e3<\/li>\n
  • \u7b97\u6cd5\u8986\u76d6\u5168\u9762：\u5305\u542b\u5206\u7c7b\u3001\u56de\u5f52\u3001\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u4f20\u7edfML\u7b97\u6cd5<\/li>\n
  • \u6570\u636e\u5904\u7406\u5de5\u5177：\u63d0\u4f9b\u7279\u5f81\u5de5\u7a0b\u3001\u6570\u636e\u9884\u5904\u7406\u3001\u6a21\u578b\u8bc4\u4f30\u7b49\u5168\u5957\u5de5\u5177<\/li>\n
  • \u6587\u6863\u5b8c\u5584：\u6bcf\u4e2aAPI\u90fd\u6709\u8be6\u7ec6\u8bf4\u660e\u548c\u793a\u4f8b（\u901a\u8fc7?\u67e5\u770b）<\/li>\n

    \u6838\u5fc3\u8bbe\u8ba1\u601d\u60f3：\u5c06\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u6807\u51c6\u5316\u4e3a"\u6570\u636e\u8f93\u5165 \u2192 \u7279\u5f81\u5904\u7406 \u2192 \u6a21\u578b\u8bad\u7ec3 \u2192 \u9884\u6d4b\u8f93\u51fa"\u7684\u6d41\u6c34\u7ebf<\/p>\n

    \n
    \u4e8c\u3001KNN\u7b97\u6cd5（K\u6700\u8fd1\u90bb\u5206\u7c7b）<\/h5>\n

    1. \u6837\u672c\u8ddd\u79bb\u5224\u65ad
    \nKNN\u7684\u6838\u5fc3\u662f\u8ba1\u7b97\u6837\u672c\u95f4\u7684\u8ddd\u79bb，\u5e38\u7528\u65b9\u6cd5：<\/p>\n

      \n
    • \n

      \u6b27\u6c0f\u8ddd\u79bb（\u76f4\u7ebf\u8ddd\u79bb）：
      \n( d = \\\\sqrt{\\\\sum_{i=1}^{n}(x_i – y_i)^2} )
      \n\u4f8b\u5982：\u70b9A(1,2)\u548c\u70b9B(4,6)\u7684\u8ddd\u79bb = (\\\\sqrt{(1-4)^2 + (2-6)^2} = 5)<\/p>\n<\/li>\n

    • \n

      \u66fc\u54c8\u987f\u8ddd\u79bb（\u57ce\u5e02\u8857\u533a\u8ddd\u79bb）：
      \n( d = \\\\sum_{i=1}^{n}|x_i – y_i| )
      \n\u540c\u4e0a\u4f8b：|1-4| + |2-6| = 3 + 4 = 7<\/p>\n<\/li>\n<\/ul>\n

      2. \u7b97\u6cd5\u539f\u7406
      \n\u6838\u5fc3\u601d\u60f3：\u201c\u7269\u4ee5\u7c7b\u805a\u201d\u2014\u2014\u672a\u77e5\u6837\u672c\u7684\u7c7b\u522b\u7531\u5176k\u4e2a\u6700\u8fd1\u90bb\u5c45\u7684\u591a\u6570\u6295\u7968\u51b3\u5b9a
      \n\u5de5\u4f5c\u6d41\u7a0b：<\/p>\n

    • \u8ba1\u7b97\u672a\u77e5\u6837\u672c\u4e0e\u6240\u6709\u8bad\u7ec3\u6837\u672c\u7684\u8ddd\u79bb<\/li>\n
    • \u9009\u53d6\u8ddd\u79bb\u6700\u5c0f\u7684k\u4e2a\u6837\u672c<\/li>\n
    • \u7edf\u8ba1k\u4e2a\u6837\u672c\u4e2d\u5404\u7c7b\u522b\u7684\u6570\u91cf<\/li>\n
    • \u5c06\u672a\u77e5\u6837\u672c\u5f52\u4e3a\u6570\u91cf\u6700\u591a\u7684\u7c7b\u522b<\/li>\n

      3. \u5173\u952e\u53c2\u6570\u4e0e\u7f3a\u70b9<\/p>\n

        \n
      • k\u503c\u9009\u62e9：\n
          \n
        • k\u592a\u5c0f \u2192 \u5bf9\u566a\u58f0\u654f\u611f（\u8fc7\u62df\u5408）<\/li>\n
        • k\u592a\u5927 \u2192 \u5ffd\u7565\u5c40\u90e8\u7279\u5f81（\u6b20\u62df\u5408）<\/li>\n<\/ul>\n<\/li>\n
        • \u7f3a\u70b9：\n
            \n
          • \u8ba1\u7b97\u6548\u7387\u4f4e（\u9ad8\u65f6\u95f4\u590d\u6742\u5ea6）：KNN\u9700\u8981\u8ba1\u7b97\u6d4b\u8bd5\u6837\u672c\u4e0e\u6240\u6709\u8bad\u7ec3\u6837\u672c\u7684\u8ddd\u79bb（\u5982\u6b27\u6c0f\u8ddd\u79bb），\u65f6\u95f4\u590d\u6742\u5ea6\u4e3a O(n)（n\u4e3a\u8bad\u7ec3\u6837\u672c\u6570）\u3002\u5f53\u6570\u636e\u91cf\u5f88\u5927\u65f6，\u9884\u6d4b\u901f\u5ea6\u6781\u6162\u3002<\/li>\n
          • \u5b58\u50a8\u7a7a\u95f4\u9700\u6c42\u5927：KNN\u662f\u201c\u60f0\u6027\u5b66\u4e60\u201d（Lazy Learning），\u8bad\u7ec3\u9636\u6bb5\u4ec5\u5b58\u50a8\u6570\u636e，\u4e0d\u751f\u6210\u663e\u5f0f\u6a21\u578b\u3002\u56e0\u6b64，\u9884\u6d4b\u65f6\u9700\u4fdd\u7559\u5168\u90e8\u8bad\u7ec3\u6570\u636e，\u7a7a\u95f4\u590d\u6742\u5ea6\u4e3a O(n)\u3002<\/li>\n
          • \u5bf9\u9ad8\u7ef4\u6570\u636e\u654f\u611f（\u7ef4\u5ea6\u707e\u96be）：\u5728\u9ad8\u7ef4\u7a7a\u95f4\u4e2d，\u6837\u672c\u95f4\u8ddd\u79bb\u5dee\u5f02\u53d8\u5c0f（\u6240\u6709\u70b9\u8d8b\u4e8e\u7b49\u8ddd），\u5bfc\u81f4KNN\u96be\u4ee5\u627e\u5230\u771f\u6b63\u76f8\u4f3c\u7684\u90bb\u5c45\u3002<\/li>\n
          • \u4e0d\u5e73\u8861\u6570\u636e\u7684\u5206\u7c7b\u504f\u5dee：\u82e5\u5404\u7c7b\u522b\u6837\u672c\u6570\u91cf\u5dee\u5f02\u5927，KNN\u53ef\u80fd\u504f\u5411\u591a\u6570\u7c7b，\u5ffd\u7565\u5c11\u6570\u7c7b\u3002\u3010\u89e3\u51b3\u65b9\u6cd5：\u52a0\u6743\u6295\u7968（\u6839\u636e\u8ddd\u79bb\u8d4b\u4e88\u4e0d\u540c\u6743\u91cd），\u91c7\u6837\u5e73\u8861\u6570\u636e（\u8fc7\u91c7\u6837\u5c11\u6570\u7c7b\u6216\u6b20\u91c7\u6837\u591a\u6570\u7c7b）\u3011<\/li>\n
          • \u53c2\u6570K\u7684\u9009\u62e9\u654f\u611f：K\u503c（\u90bb\u5c45\u6570\u91cf）\u5bf9\u7ed3\u679c\u5f71\u54cd\u663e\u8457：
            \nK\u8fc7\u5c0f：\u6a21\u578b\u5bf9\u566a\u58f0\u654f\u611f，\u5bb9\u6613\u8fc7\u62df\u5408（\u5982K=1\u65f6，\u9884\u6d4b\u4ec5\u4f9d\u8d56\u6700\u8fd1\u4e00\u4e2a\u6837\u672c）\u3002
            \nK\u8fc7\u5927：\u6a21\u578b\u53ef\u80fd\u5ffd\u7565\u5c40\u90e8\u7ed3\u6784，\u5bfc\u81f4\u6b20\u62df\u5408（\u5982K=\u8bad\u7ec3\u96c6\u5927\u5c0f\u65f6，\u9884\u6d4b\u7ed3\u679c\u6052\u4e3a\u591a\u6570\u7c7b）\u3002\u3010\u89e3\u51b3\u65b9\u6cd5：\u901a\u8fc7\u4ea4\u53c9\u9a8c\u8bc1\u9009\u62e9\u6700\u4f18K，\u4f46\u589e\u52a0\u8ba1\u7b97\u6210\u672c\u3011<\/li>\n
          • \u5bf9\u566a\u58f0\u548c\u5f02\u5e38\u503c\u654f\u611f：KNN\u7684\u9884\u6d4b\u57fa\u4e8e\u5c40\u90e8\u90bb\u5c45，\u82e5\u90bb\u5c45\u4e2d\u5305\u542b\u566a\u58f0\u6216\u5f02\u5e38\u503c，\u7ed3\u679c\u4f1a\u88ab\u5e72\u6270\u3002\u3010\u7f13\u89e3\u65b9\u6cd5：\u6570\u636e\u6e05\u6d17（\u53bb\u9664\u5f02\u5e38\u503c），\u4f7f\u7528\u52a0\u6743KNN（\u8ddd\u79bb\u8d8a\u8fd1\u7684\u90bb\u5c45\u6743\u91cd\u8d8a\u9ad8）\u3011<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n

            4. sklearn API<\/p>\n

            from<\/span> sklearn.<\/span>neighbors import<\/span> KNeighborsClassifier
            \nmodel =<\/span> KNeighborsClassifier(<\/span>n_neighbors=<\/span>5<\/span>,<\/span> metric=<\/span>'euclidean'<\/span>)<\/span> # metric\u53ef\u9009'manhattan'<\/span><\/p>\n

            5. \u5b9e\u6218\u793a\u4f8b：\u9e22\u5c3e\u82b1\u5206\u7c7b<\/p>\n

            from<\/span> sklearn.<\/span>datasets import<\/span> load_iris
            \nfrom<\/span> sklearn.<\/span>model_selection import<\/span> train_test_split<\/p>\n

            # \u52a0\u8f7d\u6570\u636e<\/span>
            \niris =<\/span> load_iris(<\/span>)<\/span>
            \nX,<\/span> y =<\/span> iris.<\/span>data,<\/span> iris.<\/span>target<\/p>\n

            # \u5212\u5206\u6570\u636e\u96c6<\/span>
            \nX_train,<\/span> X_test,<\/span> y_train,<\/span> y_test =<\/span> train_test_split(<\/span>X,<\/span> y,<\/span> test_size=<\/span>0.2<\/span>)<\/span><\/p>\n

            # \u8bad\u7ec3\u6a21\u578b<\/span>
            \nmodel =<\/span> KNeighborsClassifier(<\/span>n_neighbors=<\/span>3<\/span>)<\/span>
            \nmodel.<\/span>fit(<\/span>X_train,<\/span> y_train)<\/span><\/p>\n

            # \u8bc4\u4f30\u51c6\u786e\u7387<\/span>
            \naccuracy =<\/span> model.<\/span>score(<\/span>X_test,<\/span> y_test)<\/span> # \u8f93\u51fa\u59820.95<\/span><\/p>\n

            6. \u6a21\u578b\u4fdd\u5b58\u4e0e\u52a0\u8f7d<\/p>\n

            import<\/span> joblib<\/p>\n

            # \u4fdd\u5b58\u6a21\u578b<\/span>
            \njoblib.<\/span>dump(<\/span>model,<\/span> 'knn_model.pkl'<\/span>)<\/span> <\/p>\n

            # \u52a0\u8f7d\u6a21\u578b<\/span>
            \nloaded_model =<\/span> joblib.<\/span>load(<\/span>'knn_model.pkl'<\/span>)<\/span><\/p>\n

            \n
            \u4e09\u3001\u6a21\u578b\u9009\u62e9\u4e0e\u8c03\u4f18<\/h5>\n

            1. \u4e3a\u4ec0\u4e48\u9700\u8981\u8c03\u4f18？<\/p>\n

              \n
            • \u95ee\u9898：\u4f20\u7edf\u8bad\u7ec3\/\u6d4b\u8bd5\u96c6\u5212\u5206\u53ef\u80fd\u5bfc\u81f4\u6570\u636e\u5229\u7528\u4e0d\u5145\u5206\u6216\u8bc4\u4f30\u504f\u5dee（\u5982\u968f\u673a\u5212\u5206\u65f6\u6d4b\u8bd5\u96c6\u6070\u597d\u5305\u542b\u7b80\u5355\u6837\u672c）\u3002<\/li>\n
            • \u76ee\u6807：\u901a\u8fc7\u591a\u6b21\u5212\u5206\u6570\u636e，\u66f4\u53ef\u9760\u5730\u4f30\u8ba1\u6a21\u578b\u5728\u672a\u89c1\u6570\u636e\u4e0a\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/li>\n<\/ul>\n

              2. \u4ea4\u53c9\u9a8c\u8bc1（Cross-Validation）
              \n\u89e3\u51b3\u7684\u95ee\u9898：\u5355\u6b21\u6570\u636e\u5212\u5206\u53ef\u80fd\u5f15\u5165\u968f\u673a\u504f\u5dee
              \n（1）K\u6298\u4ea4\u53c9\u9a8c\u8bc1\u6d41\u7a0b（K-Fold CV）<\/p>\n

              （\u4ee55\u6298\u4e3a\u4f8b）：<\/p>\n

            • \u5c06\u8bad\u7ec3\u96c6\u5747\u5206\u4e3a5\u4efd<\/li>\n
            • \u8f6e\u6d41\u7528\u5176\u4e2d4\u4efd\u8bad\u7ec3，1\u4efd\u9a8c\u8bc1<\/li>\n
            • \u91cd\u590d5\u6b21，\u53d6\u5e73\u5747\u51c6\u786e\u7387
              \n\"\"<\/li>\n

              \u4f18\u70b9：<\/p>\n

                \n
              • \u6570\u636e\u5229\u7528\u7387\u9ad8（\u6bcf\u4e2a\u6837\u672c\u5747\u53c2\u4e0e\u9a8c\u8bc1）\u3002<\/li>\n
              • \u51cf\u5c11\u56e0\u5355\u6b21\u5212\u5206\u5bfc\u81f4\u7684\u8bc4\u4f30\u6ce2\u52a8\u3002<\/li>\n<\/ul>\n

                \u7f3a\u70b9：\u8ba1\u7b97\u6210\u672c\u968fK\u589e\u52a0\u800c\u4e0a\u5347（K\u901a\u5e38\u53d65\u621610）\u3002<\/p>\n

                （2）\u7559\u4e00\u6cd5\u4ea4\u53c9\u9a8c\u8bc1（LOOCV）<\/p>\n

                  \n
                • \u6b65\u9aa4：K\u6298CV\u7684\u7279\u4f8b，K=\u6837\u672c\u6570，\u6bcf\u6b21\u4ec5\u75591\u4e2a\u6837\u672c\u9a8c\u8bc1\u3002<\/li>\n
                • \u4f18\u70b9：\u504f\u5dee\u6781\u4f4e（\u51e0\u4e4e\u7528\u5168\u90e8\u6570\u636e\u8bad\u7ec3）\u3002<\/li>\n
                • \u7f3a\u70b9：\u8ba1\u7b97\u91cf\u6781\u5927（\u5c24\u5176\u5927\u6570\u636e\u96c6）\u3002<\/li>\n<\/ul>\n

                  （3）\u5206\u5c42K\u6298\u4ea4\u53c9\u9a8c\u8bc1（Stratified K-Fold）<\/p>\n

                    \n
                  • \u9002\u7528\u573a\u666f：\u5206\u7c7b\u4efb\u52a1\u4e2d\u7c7b\u522b\u4e0d\u5e73\u8861\u65f6\u3002<\/li>\n
                  • \u6539\u8fdb：\u786e\u4fdd\u6bcf\u6298\u4e2d\u5404\u7c7b\u522b\u6bd4\u4f8b\u4e0e\u539f\u59cb\u6570\u636e\u96c6\u4e00\u81f4，\u907f\u514d\u56e0\u5212\u5206\u5bfc\u81f4\u9a8c\u8bc1\u96c6\u7c7b\u522b\u5206\u5e03\u5931\u771f\u3002<\/li>\n<\/ul>\n

                    3. \u8d85\u53c2\u6570\u641c\u7d22<\/p>\n

                      \n
                    • \u7f51\u683c\u641c\u7d22（Grid Search）：\u904d\u5386\u6240\u6709\u53ef\u80fd\u7684\u53c2\u6570\u7ec4\u5408<\/li>\n
                    • \u968f\u673a\u641c\u7d22（Random Search）：\u968f\u673a\u62bd\u6837\u53c2\u6570\u7ec4\u5408（\u6548\u7387\u66f4\u9ad8）<\/li>\n<\/ul>\n

                      4. sklearn API<\/p>\n

                      class<\/span> sklearn<\/span>.<\/span>model_selection.<\/span>GridSearchCV(<\/span>estimator,<\/span> param_grid)<\/span><\/p>\n

                      \u8bf4\u660e：
                      \n\u540c\u65f6\u8fdb\u884c\u4ea4\u53c9\u9a8c\u8bc1(<\/span>CV)<\/span>\u3001\u548c\u7f51\u683c\u641c\u7d22(<\/span>GridSearch)<\/span>，GridSearchCV\u5b9e\u9645\u4e0a\u4e5f\u662f\u4e00\u4e2a\u4f30\u8ba1\u5668(<\/span>estimator)<\/span>，\u540c\u65f6\u5b83\u6709\u51e0\u4e2a\u91cd\u8981\u5c5e\u6027：
                      \n best_params_ \u6700\u4f73\u53c2\u6570
                      \n best_score_ \u5728\u8bad\u7ec3\u96c6\u4e2d\u7684\u51c6\u786e\u7387
                      \n best_estimator_ \u6700\u4f73\u4f30\u8ba1\u5668
                      \n cv_results_ \u4ea4\u53c9\u9a8c\u8bc1\u8fc7\u7a0b\u63cf\u8ff0
                      \n best_index_\u6700\u4f73k\u5728\u5217\u8868\u4e2d\u7684\u4e0b\u6807
                      \n\u53c2\u6570：
                      \nestimator： scikit–<\/span>learn\u4f30\u8ba1\u5668\u5b9e\u4f8b
                      \nparam_grid:<\/span>\u4ee5\u53c2\u6570\u540d\u79f0（str<\/span>）\u4f5c\u4e3a\u952e，\u5c06\u53c2\u6570\u8bbe\u7f6e\u5217\u8868\u5c1d\u8bd5\u4f5c\u4e3a\u503c\u7684\u5b57\u5178
                      \n\u793a\u4f8b： {<\/span>"n_neighbors"<\/span>:<\/span> [<\/span>1<\/span>,<\/span> 3<\/span>,<\/span> 5<\/span>,<\/span> 7<\/span>,<\/span> 9<\/span>,<\/span> 11<\/span>]<\/span>}<\/span>
                      \n cv:<\/span> \u786e\u5b9a\u4ea4\u53c9\u9a8c\u8bc1\u5207\u5206\u7b56\u7565,<\/span>\u503c\u4e3a:<\/span>
                      \n (<\/span>1<\/span>)<\/span>None<\/span> \u9ed8\u8ba45<\/span>\u6298
                      \n (<\/span>2<\/span>)<\/span>integer \u8bbe\u7f6e\u591a\u5c11\u6298
                      \n \u5982\u679c\u4f30\u8ba1\u5668\u662f\u5206\u7c7b\u5668，\u4f7f\u7528"\u5206\u5c42k-\u6298\u4ea4\u53c9\u9a8c\u8bc1(StratifiedKFold)"<\/span>\u3002\u5728\u6240\u6709\u5176\u4ed6\u60c5\u51b5\u4e0b，\u4f7f\u7528KFold\u3002<\/p>\n

                      5. \u793a\u4f8b：\u9e22\u5c3e\u82b1\u5206\u7c7b\u8c03\u4f18<\/p>\n

                      # \u7528KNN\u7b97\u6cd5\u5bf9\u9e22\u5c3e\u82b1\u8fdb\u884c\u5206\u7c7b，\u6dfb\u52a0\u7f51\u683c\u641c\u7d22\u548c\u4ea4\u53c9\u9a8c\u8bc1<\/span>
                      \nfrom<\/span> sklearn.<\/span>datasets import<\/span> load_iris
                      \nfrom<\/span> sklearn.<\/span>model_selection import<\/span> train_test_split
                      \nfrom<\/span> sklearn.<\/span>preprocessing import<\/span> StandardScaler
                      \nfrom<\/span> sklearn.<\/span>neighbors import<\/span> KNeighborsClassifier
                      \nfrom<\/span> sklearn.<\/span>model_selection import<\/span> GridSearchCV<\/p>\n

                      def<\/span> knn_iris_gscv<\/span>(<\/span>)<\/span>:<\/span>
                      \n # 1）\u83b7\u53d6\u6570\u636e<\/span>
                      \n iris =<\/span> load_iris(<\/span>)<\/span><\/p>\n

                      # 2）\u5212\u5206\u6570\u636e\u96c6<\/span>
                      \n x_train,<\/span> x_test,<\/span> y_train,<\/span> y_test =<\/span> train_test_split(<\/span>iris.<\/span>data,<\/span> iris.<\/span>target,<\/span> random_state=<\/span>22<\/span>)<\/span><\/p>\n

                      # 3）\u7279\u5f81\u5de5\u7a0b：\u6807\u51c6\u5316<\/span>
                      \n transfer =<\/span> StandardScaler(<\/span>)<\/span>
                      \n x_train =<\/span> transfer.<\/span>fit_transform(<\/span>x_train)<\/span>
                      \n x_test =<\/span> transfer.<\/span>transform(<\/span>x_test)<\/span><\/p>\n

                      # 4）KNN\u7b97\u6cd5\u9884\u4f30\u5668, \u8fd9\u91cc\u5c31\u4e0d\u4f20\u53c2\u6570n_neighbors\u4e86，\u4ea4\u7ed9GridSearchCV\u6765\u4f20\u9012<\/span>
                      \n estimator =<\/span> KNeighborsClassifier(<\/span>)<\/span>
                      \n # \u52a0\u5165\u7f51\u683c\u641c\u7d22\u4e0e\u4ea4\u53c9\u9a8c\u8bc1, GridSearchCV\u4f1a\u8ba9k\u5206\u522b\u7b49\u4e8e1,2,5,7,9,11\u8fdb\u884c\u7f51\u683c\u641c\u7d22\u507f\u8bd5\u3002cv=10\u8868\u793a\u8fdb\u884c10\u6b21\u4ea4\u53c9\u9a8c\u8bc1<\/span>
                      \n estimator =<\/span> GridSearchCV(<\/span>estimator,<\/span> param_grid=<\/span>{<\/span>"n_neighbors"<\/span>:<\/span> [<\/span>1<\/span>,<\/span> 3<\/span>,<\/span> 5<\/span>,<\/span> 7<\/span>,<\/span> 9<\/span>,<\/span> 11<\/span>]<\/span>}<\/span>,<\/span> cv=<\/span>10<\/span>)<\/span>
                      \n estimator.<\/span>fit(<\/span>x_train,<\/span> y_train)<\/span><\/p>\n

                      # 5）\u6a21\u578b\u8bc4\u4f30<\/span>
                      \n # \u65b9\u6cd51：\u76f4\u63a5\u6bd4\u5bf9\u771f\u5b9e\u503c\u548c\u9884\u6d4b\u503c<\/span>
                      \n y_predict =<\/span> estimator.<\/span>predict(<\/span>x_test)<\/span>
                      \n print<\/span>(<\/span>"y_predict:\\\\n"<\/span>,<\/span> y_predict)<\/span>
                      \n print<\/span>(<\/span>"\u76f4\u63a5\u6bd4\u5bf9\u771f\u5b9e\u503c\u548c\u9884\u6d4b\u503c:\\\\n"<\/span>,<\/span> y_test ==<\/span> y_predict)<\/span><\/p>\n

                      # \u65b9\u6cd52：\u8ba1\u7b97\u51c6\u786e\u7387<\/span>
                      \n score =<\/span> estimator.<\/span>score(<\/span>x_test,<\/span> y_test)<\/span>
                      \n print<\/span>(<\/span>"\u5728\u6d4b\u8bd5\u96c6\u4e2d\u7684\u51c6\u786e\u7387\u4e3a：\\\\n"<\/span>,<\/span> score)<\/span> #0.9736842105263158<\/span><\/p>\n

                      # \u6700\u4f73\u53c2\u6570：best_params_<\/span>
                      \n print<\/span>(<\/span>"\u6700\u4f73\u53c2\u6570：\\\\n"<\/span>,<\/span> estimator.<\/span>best_params_)<\/span> #{'n_neighbors': 3}， \u8bf4\u660ek=3\u65f6\u6700\u597d<\/span>
                      \n # \u6700\u4f73\u7ed3\u679c：best_score_<\/span>
                      \n print<\/span>(<\/span>"\u5728\u8bad\u7ec3\u96c6\u4e2d\u7684\u51c6\u786e\u7387：\\\\n"<\/span>,<\/span> estimator.<\/span>best_score_)<\/span> #0.9553030303030303<\/span>
                      \n # \u6700\u4f73\u4f30\u8ba1\u5668：best_estimator_<\/span>
                      \n print<\/span>(<\/span>"\u6700\u4f73\u4f30\u8ba1\u5668:\\\\n"<\/span>,<\/span> estimator.<\/span>best_estimator_)<\/span> # KNeighborsClassifier(n_neighbors=3)<\/span>
                      \n # \u4ea4\u53c9\u9a8c\u8bc1\u7ed3\u679c：cv_results_<\/span>
                      \n print<\/span>(<\/span>"\u4ea4\u53c9\u9a8c\u8bc1\u8fc7\u7a0b\u63cf\u8ff0:\\\\n"<\/span>,<\/span> estimator.<\/span>cv_results_)<\/span>
                      \n #\u6700\u4f73\u53c2\u6570\u7ec4\u5408\u7684\u7d22\u5f15:\u6700\u4f73k\u5728\u5217\u8868\u4e2d\u7684\u4e0b\u6807<\/span>
                      \n print<\/span>(<\/span>"\u6700\u4f73\u53c2\u6570\u7ec4\u5408\u7684\u7d22\u5f15:\\\\n"<\/span>,<\/span>estimator.<\/span>best_index_)<\/span><\/p>\n

                      #\u901a\u5e38\u60c5\u51b5\u4e0b，\u76f4\u63a5\u4f7f\u7528best_params_\u66f4\u4e3a\u65b9\u4fbf<\/span>
                      \n return<\/span> None<\/span><\/p>\n

                      knn_iris_gscv(<\/span>)<\/span><\/p>\n

                      \n
                      \u56db\u3001\u6734\u7d20\u8d1d\u53f6\u65af\u5206\u7c7b<\/h5>\n

                      1. \u7b97\u6cd5\u57fa\u7840<\/p>\n

                        \n
                      • \u6761\u4ef6\u6982\u7387：\u4e8b\u4ef6A\u5728\u4e8b\u4ef6B\u5df2\u53d1\u751f\u65f6\u7684\u6982\u7387 ( P(A|B) = \\\\frac{P(A \\\\cap B)}{P(B)} )<\/li>\n
                      • \u5168\u6982\u7387\u516c\u5f0f：\u82e5\u4e8b\u4ef6B\u7531\u4e92\u65a5\u4e8b\u4ef6( A_1,\u2026,A_n )\u5f15\u53d1，\u5219
                        \n( P(B) = \\\\sum_{i=1}^{n} P(B|A_i)P(A_i) )<\/li>\n<\/ul>\n

                        2. \u8d1d\u53f6\u65af\u5b9a\u7406
                        \n( P(A|B) = \\\\frac{P(B|A)P(A)}{P(B)} )
                        \n\u5176\u4e2d：<\/p>\n

                          \n
                        • ( P(A|B) )：\u540e\u9a8c\u6982\u7387（\u6211\u4eec\u8981\u6c42\u89e3\u7684）<\/li>\n
                        • ( P(B|A) )：\u4f3c\u7136\u6982\u7387<\/li>\n
                        • ( P(A) )：\u5148\u9a8c\u6982\u7387<\/li>\n<\/ul>\n

                          3. \u6734\u7d20\u8d1d\u53f6\u65af\u539f\u7406
                          \n"\u6734\u7d20"\u5047\u8bbe：\u7279\u5f81\u4e4b\u95f4\u76f8\u4e92\u72ec\u7acb（\u7b80\u5316\u8ba1\u7b97）
                          \n\u5206\u7c7b\u51b3\u7b56：\u8ba1\u7b97\u6837\u672c\u5c5e\u4e8e\u5404\u7c7b\u522b\u7684\u6982\u7387，\u53d6\u6700\u5927\u503c
                          \n( P(y_k|x) = \\\\frac{P(x|y_k)P(y_k)}{P(x)} \\\\propto P(y_k) \\\\prod_{i} P(x_i|y_k) )<\/p>\n

                          4. \u62c9\u666e\u62c9\u65af\u5e73\u6ed1
                          \n\u95ee\u9898：\u5f53\u67d0\u4e2a\u7279\u5f81\u503c\u672a\u51fa\u73b0\u65f6，( P(x_i|y_k)=0 )\u5bfc\u81f4\u6574\u4f53\u6982\u7387\u4e3a0
                          \n\u89e3\u51b3\u65b9\u6848：\u6dfb\u52a0\u5e73\u6ed1\u7cfb\u6570\u03b1 （\u5982\u03b1 = 1）
                          \n( P(x_i|y_k) = \\\\frac{N_{y_k,x_i} + \\\\alpha}{N_{y_k} + \\\\alpha n} )
                          \n\u5176\u4e2d：<\/p>\n

                            \n
                          • ( N_{y_k,x_i} )：\u7c7b\u522b( y_k )\u4e2d\u7279\u5f81( x_i )\u51fa\u73b0\u7684\u6b21\u6570<\/li>\n
                          • ( N_{y_k} )：\u7c7b\u522b( y_k )\u7684\u603b\u6837\u672c\u6570<\/li>\n
                          • ( n )：\u7279\u5f81\u7684\u53ef\u80fd\u53d6\u503c\u6570<\/li>\n<\/ul>\n

                            5. sklearn API<\/p>\n

                            from<\/span> sklearn.<\/span>naive_bayes import<\/span> MultinomialNB # \u9002\u7528\u4e8e\u79bb\u6563\u7279\u5f81<\/span>
                            \nmodel =<\/span> MultinomialNB(<\/span>alpha=<\/span>1.0<\/span>)<\/span> # alpha\u5373\u5e73\u6ed1\u7cfb\u6570<\/span><\/p>\n

                            6. \u793a\u4f8b：\u65b0\u95fb\u5206\u7c7b<\/p>\n

                            from<\/span> sklearn.<\/span>datasets import<\/span> fetch_20newsgroups
                            \nfrom<\/span> sklearn.<\/span>feature_extraction.<\/span>text import<\/span> CountVectorizer<\/p>\n

                            # \u52a0\u8f7d\u6570\u636e<\/span>
                            \nnewsgroups =<\/span> fetch_20newsgroups(<\/span>subset=<\/span>'train'<\/span>)<\/span>
                            \nX,<\/span> y =<\/span> newsgroups.<\/span>data,<\/span> newsgroups.<\/span>target<\/p>\n

                            # \u6587\u672c\u7279\u5f81\u63d0\u53d6<\/span>
                            \nvectorizer =<\/span> CountVectorizer(<\/span>)<\/span>
                            \nX_vec =<\/span> vectorizer.<\/span>fit_transform(<\/span>X)<\/span><\/p>\n

                            # \u8bad\u7ec3\u6734\u7d20\u8d1d\u53f6\u65af<\/span>
                            \nmodel =<\/span> MultinomialNB(<\/span>alpha=<\/span>0.01<\/span>)<\/span>
                            \nmodel.<\/span>fit(<\/span>X_vec,<\/span> y)<\/span><\/p>\n

                            # \u9884\u6d4b\u65b0\u6587\u672c<\/span>
                            \nnew_text =<\/span> [<\/span>"GPU performance comparison"<\/span>]<\/span>
                            \nnew_vec =<\/span> vectorizer.<\/span>transform(<\/span>new_text)<\/span>
                            \npred =<\/span> model.<\/span>predict(<\/span>new_vec)<\/span> # \u8f93\u51fa\u7c7b\u522b\u7f16\u53f7<\/span><\/p>\n

                            \n

                            \u5173\u952e\u77e5\u8bc6\u70b9\u603b\u7ed3<\/h4>\n\n\u7b97\u6cd5\u9002\u7528\u573a\u666f\u4f18\u52bf\u6ce8\u610f\u4e8b\u9879<\/tr>\n\n\n\n\n
                            KNN<\/td>\n\u5c0f\u6570\u636e\u96c6，\u4f4e\u7ef4\u5ea6<\/td>\n\u76f4\u89c2\u6613\u7406\u89e3<\/td>\n\u8ba1\u7b97\u6548\u7387\u4f4e，\u9700\u7279\u5f81\u7f29\u653e<\/td>\n<\/tr>\n
                            \u6734\u7d20\u8d1d\u53f6\u65af<\/td>\n\u6587\u672c\u5206\u7c7b，\u9ad8\u7ef4\u5ea6<\/td>\n\u8ba1\u7b97\u9ad8\u6548，\u6297\u566a\u58f0<\/td>\n\u7279\u5f81\u72ec\u7acb\u6027\u5047\u8bbe\u53ef\u80fd\u4e0d\u6210\u7acb<\/td>\n<\/tr>\n
                            \u6a21\u578b\u8c03\u4f18<\/td>\n\u6240\u6709\u7b97\u6cd5<\/td>\n\u663e\u8457\u63d0\u5347\u6a21\u578b\u6027\u80fd<\/td>\n\u8ba1\u7b97\u6210\u672c\u9ad8<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"

                            \u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb193\u6b21\uff0c\u70b9\u8d5e2\u6b21\uff0c\u6536\u85cf4\u6b21\u3002\u7edf\u4e00API\u8bbe\u8ba1\uff1a\u6240\u6709\u7b97\u6cd5\u90fd\u9075\u5faafit()\uff08\u8bad\u7ec3\uff09\u3001predict()\uff08\u9884\u6d4b\uff09\u7684\u7edf\u4e00\u63a5\u53e3\u7b97\u6cd5\u8986\u76d6\u5168\u9762\uff1a\u5305\u542b\u5206\u7c7b\u3001\u56de\u5f52\u3001\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u4f20\u7edfML\u7b97\u6cd5\u6570\u636e\u5904\u7406\u5de5\u5177\uff1a\u63d0\u4f9b\u7279\u5f81\u5de5\u7a0b\u3001\u6570\u636e\u9884\u5904\u7406\u3001\u6a21\u578b\u8bc4\u4f30\u7b49\u5168\u5957\u5de5\u5177\u6587\u6863\u5b8c\u5584\uff1a\u6bcf\u4e2aAPI\u90fd\u6709\u8be6\u7ec6\u8bf4\u660e\u548c\u793a\u4f8b\uff08\u901a\u8fc7?\u67e5\u770b\uff09\u6838\u5fc3\u8bbe\u8ba1\u601d\u60f3\uff1a\u5c06\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u6807\u51c6\u5316\u4e3a"\u6570\u636e\u8f93\u5165 \u2192 \u7279\u5f81\u5904\u7406 \u2192 \u6a21\u578b\u8bad\u7ec3 \u2192 \u9884\u6d4b\u8f93\u51fa"\u7684\u6d41\u6c34\u7ebf\u7b97\u6cd5\u9002\u7528\u573a\u666f\u4f18\u52bf\u6ce8\u610f\u4e8b\u9879KNN\u5c0f\u6570\u636e\u96c6\uff0c\u4f4e\u7ef4\u5ea6\u76f4\u89c2\u6613\u7406\u89e3\u8ba1\u7b97\u6548\u7387\u4f4e\uff0c\u9700\u7279\u5f81\u7f29\u653e\u6734\u7d20\u8d1d\u53f6\u65af\u6587\u672c\u5206\u7c7b\uff0c\u9ad8\u7ef4\u5ea6\u8ba1\u7b97\u9ad8\u6548\uff0c\u6297\u566a\u58f0\u3002<\/p>\n","protected":false},"author":2,"featured_media":49782,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[50,207,427],"topic":[],"class_list":["post-49783","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-50","tag-207","tag-427"],"yoast_head":"\n\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/49783.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb193\u6b21\uff0c\u70b9\u8d5e2\u6b21\uff0c\u6536\u85cf4\u6b21\u3002\u7edf\u4e00API\u8bbe\u8ba1\uff1a\u6240\u6709\u7b97\u6cd5\u90fd\u9075\u5faafit()\uff08\u8bad\u7ec3\uff09\u3001predict()\uff08\u9884\u6d4b\uff09\u7684\u7edf\u4e00\u63a5\u53e3\u7b97\u6cd5\u8986\u76d6\u5168\u9762\uff1a\u5305\u542b\u5206\u7c7b\u3001\u56de\u5f52\u3001\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u4f20\u7edfML\u7b97\u6cd5\u6570\u636e\u5904\u7406\u5de5\u5177\uff1a\u63d0\u4f9b\u7279\u5f81\u5de5\u7a0b\u3001\u6570\u636e\u9884\u5904\u7406\u3001\u6a21\u578b\u8bc4\u4f30\u7b49\u5168\u5957\u5de5\u5177\u6587\u6863\u5b8c\u5584\uff1a\u6bcf\u4e2aAPI\u90fd\u6709\u8be6\u7ec6\u8bf4\u660e\u548c\u793a\u4f8b\uff08\u901a\u8fc7?\u67e5\u770b\uff09\u6838\u5fc3\u8bbe\u8ba1\u601d\u60f3\uff1a\u5c06\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u6807\u51c6\u5316\u4e3a"\u6570\u636e\u8f93\u5165 \u2192 \u7279\u5f81\u5904\u7406 \u2192 \u6a21\u578b\u8bad\u7ec3 \u2192 \u9884\u6d4b\u8f93\u51fa"\u7684\u6d41\u6c34\u7ebf\u7b97\u6cd5\u9002\u7528\u573a\u666f\u4f18\u52bf\u6ce8\u610f\u4e8b\u9879KNN\u5c0f\u6570\u636e\u96c6\uff0c\u4f4e\u7ef4\u5ea6\u76f4\u89c2\u6613\u7406\u89e3\u8ba1\u7b97\u6548\u7387\u4f4e\uff0c\u9700\u7279\u5f81\u7f29\u653e\u6734\u7d20\u8d1d\u53f6\u65af\u6587\u672c\u5206\u7c7b\uff0c\u9ad8\u7ef4\u5ea6\u8ba1\u7b97\u9ad8\u6548\uff0c\u6297\u566a\u58f0\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/49783.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2025-07-30T11:46:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/07\/20250730114649-688a062981802.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/49783.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/49783.html\",\"name\":\"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2025-07-30T11:46:51+00:00\",\"dateModified\":\"2025-07-30T11:46:51+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/49783.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/49783.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/49783.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/49783.html","og_locale":"zh_CN","og_type":"article","og_title":"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb193\u6b21\uff0c\u70b9\u8d5e2\u6b21\uff0c\u6536\u85cf4\u6b21\u3002\u7edf\u4e00API\u8bbe\u8ba1\uff1a\u6240\u6709\u7b97\u6cd5\u90fd\u9075\u5faafit()\uff08\u8bad\u7ec3\uff09\u3001predict()\uff08\u9884\u6d4b\uff09\u7684\u7edf\u4e00\u63a5\u53e3\u7b97\u6cd5\u8986\u76d6\u5168\u9762\uff1a\u5305\u542b\u5206\u7c7b\u3001\u56de\u5f52\u3001\u805a\u7c7b\u3001\u964d\u7ef4\u7b49\u4f20\u7edfML\u7b97\u6cd5\u6570\u636e\u5904\u7406\u5de5\u5177\uff1a\u63d0\u4f9b\u7279\u5f81\u5de5\u7a0b\u3001\u6570\u636e\u9884\u5904\u7406\u3001\u6a21\u578b\u8bc4\u4f30\u7b49\u5168\u5957\u5de5\u5177\u6587\u6863\u5b8c\u5584\uff1a\u6bcf\u4e2aAPI\u90fd\u6709\u8be6\u7ec6\u8bf4\u660e\u548c\u793a\u4f8b\uff08\u901a\u8fc7?\u67e5\u770b\uff09\u6838\u5fc3\u8bbe\u8ba1\u601d\u60f3\uff1a\u5c06\u673a\u5668\u5b66\u4e60\u6d41\u7a0b\u6807\u51c6\u5316\u4e3a"\u6570\u636e\u8f93\u5165 \u2192 \u7279\u5f81\u5904\u7406 \u2192 \u6a21\u578b\u8bad\u7ec3 \u2192 \u9884\u6d4b\u8f93\u51fa"\u7684\u6d41\u6c34\u7ebf\u7b97\u6cd5\u9002\u7528\u573a\u666f\u4f18\u52bf\u6ce8\u610f\u4e8b\u9879KNN\u5c0f\u6570\u636e\u96c6\uff0c\u4f4e\u7ef4\u5ea6\u76f4\u89c2\u6613\u7406\u89e3\u8ba1\u7b97\u6548\u7387\u4f4e\uff0c\u9700\u7279\u5f81\u7f29\u653e\u6734\u7d20\u8d1d\u53f6\u65af\u6587\u672c\u5206\u7c7b\uff0c\u9ad8\u7ef4\u5ea6\u8ba1\u7b97\u9ad8\u6548\uff0c\u6297\u566a\u58f0\u3002","og_url":"https:\/\/www.wsisp.com\/helps\/49783.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2025-07-30T11:46:51+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/07\/20250730114649-688a062981802.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/49783.html","url":"https:\/\/www.wsisp.com\/helps\/49783.html","name":"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2025-07-30T11:46:51+00:00","dateModified":"2025-07-30T11:46:51+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/49783.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/49783.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/49783.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u300a\u96f6\u57fa\u7840\u5165\u95e8AI\uff1a\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u6838\u5fc3\u7b97\u6cd5\u89e3\u6790\uff08KNN\u3001\u6a21\u578b\u8c03\u4f18\u4e0e\u6734\u7d20\u8d1d\u53f6\u65af\uff09\u300b"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/49783","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=49783"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/49783\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/49782"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=49783"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=49783"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=49783"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=49783"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}