{"id":3159,"date":"2022-02-27T12:38:00","date_gmt":"2022-02-27T04:38:00","guid":{"rendered":"https:\/\/egonlin.com\/?p=3159"},"modified":"2022-02-27T12:38:00","modified_gmt":"2022-02-27T04:38:00","slug":"%e7%ac%ac%e4%b8%89%e7%af%87%ef%bc%9ascikit-learn%e5%ba%93%e4%b9%8b%e6%a2%af%e5%ba%a6%e6%8f%90%e5%8d%87%e6%a0%91","status":"publish","type":"post","link":"https:\/\/egonlin.com\/?p=3159","title":{"rendered":"\u7b2c\u4e09\u7bc7\uff1ascikit-learn\u5e93\u4e4b\u68af\u5ea6\u63d0\u5347\u6811"},"content":{"rendered":"

scikit-learn\u5e93\u4e4b\u68af\u5ea6\u63d0\u5347\u6811<\/h1>\n

  \u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u68af\u5ea6\u63d0\u5347\u6811\u7684\u4e24\u4e2a\u6a21\u578bGradientBoostingClassifier<\/code>\u548cGradientBoostingRegressor<\/code>\uff0c\u8fd9\u4e24\u4e2a\u6a21\u578b\u8c03\u53c2\u5305\u62ec\u4e24\u90e8\u5206\uff0c\u7b2c\u4e00\u90e8\u5206\u662fBagging\u6846\u67b6\uff0c\u7b2c\u4e8c\u90e8\u5206\u662fCART\u51b3\u7b56\u6811\u7684\u53c2\u6570\u3002\u672c\u6587\u4f1a\u8be6\u89e3\u4ecb\u7ecdGradientBoostingClassifier<\/code>\u6a21\u578b\uff0c\u7136\u540e\u4f1a\u5bf9\u6bd4\u7740\u8bb2\u89e3GradientBoostingRegressor<\/code>\u6a21\u578b\u3002<\/p>\n

  \u63a5\u4e0b\u6765\u5c06\u4f1a\u8ba8\u8bba\u4e0a\u8ff0\u4e24\u8005\u7684\u533a\u522b\uff0c\u7531\u4e8e\u662f\u4ece\u5b98\u65b9\u6587\u6863\u7ffb\u8bd1\u800c\u6765\uff0c\u7ffb\u8bd1\u4f1a\u7565\u6709\u504f\u9887\uff0c\u6709\u5174\u8da3\u7684\u4e5f\u53ef\u4ee5\u53bbscikit-learn\u5b98\u65b9\u6587\u6863\u67e5\u770bhttps:\/\/scikit-learn.org\/stable\/modules\/classes.html#module-sklearn.ensemble<\/p>\n

GradietBoostingClassifier<\/h1>\n

\u4f7f\u7528\u573a\u666f<\/h2>\n

  GradientBoostingClassifier<\/code>\u6a21\u578b\u4e3b\u8981\u7528\u4e8e\u89e3\u51b3\u5206\u7c7b\u95ee\u9898\u3002<\/p>\n

\u53c2\u6570<\/h2>\n
    \n
  • loss\uff1a<\/strong>\u635f\u5931\u51fd\u6570\uff0cstr\u7c7b\u578b\u3002\u5206\u7c7b\u68af\u5ea6\u63d0\u5347\u6811\u9ed8\u8ba4\u4e3a’deviance’\u3002\n
      \n
    • \u5bf9\u4e8e\u5206\u7c7b\u63d0\u5347\u6811\uff0c\u53ef\u4ee5\u9009\u62e9’deviance’\u5bf9\u6570\u4f3c\u7136\u635f\u5931\u51fd\u6570\u548c’exponential’\u6307\u6570\u635f\u5931\u51fd\u6570\u3002\u4e00\u822c\u63a8\u8350\u4f7f\u7528\u9ed8\u8ba4\u7684’deviance’\uff0c\u5982\u679c\u4f7f\u7528’exponential’\u4e8c\u5206\u7c7b\u65f6\u7b49\u540c\u4e8eAdaBoost\u7b97\u6cd5\u3002\u9ed8\u8ba4\u4e3a’deviance’\u3002<\/li>\n
    • \u5bf9\u4e8e\u56de\u5f52\u63d0\u5347\u6811\u53ef\u4ee5\u9009\u62e9’ls’\u5747\u65b9\u8bef\u5dee\u3001’lad’\u7edd\u5bf9\u635f\u5931\u3001’lad’\u7edd\u5bf9\u635f\u5931\u3001’hub’Huber\u635f\u5931\u3001’quantile’\u5206\u4f4d\u6570\u635f\u5931\u3002\u6570\u636e\u566a\u58f0\u4e0d\u591a\uff0c\u4f7f\u7528\u9ed8\u8ba4\u7684’ls’\uff1b\u566a\u97f3\u8f83\u591a\uff0c\u4f7f\u7528’huber’\uff1b\u5bf9\u8bad\u7ec3\u96c6\u5206\u6bb5\u9884\u6d4b\uff0c\u4f7f\u7528’quantile’\u3002\u4f7f\u7528’huber’\u548c’quantile’\u7684\u65f6\u5019\u9700\u8981\u6307\u5b9a\u53c2\u6570alpha\u3002\u9ed8\u8ba4\u4e3a’ls’\u3002<\/li>\n<\/ul>\n<\/li>\n
    • learning_rate\uff1a<\/strong>\u6743\u91cd\u7f29\u51cf\u7cfb\u6570\uff0cfloat\u7c7b\u578b\u3002\u8fd9\u4e2a\u53c2\u6570\u662f\u6b63\u5219\u5316\u9879\u7684\u53c2\u6570$\\lambda$\u3002\u8f83\u5c0f\u7684$\\lambda$\u9700\u8981\u66f4\u591a\u7684\u8fed\u4ee3\u6b21\u6570\uff0c\u5373learning_rate\u548cn_estimators\u9700\u8981\u4e00\u8d77\u8c03\u53c2\u3002\u9ed8\u8ba4\u4e3a1\u3002<\/li>\n
    • n_estimators\uff1a<\/strong>\uff1a\u5f31\u5b66\u4e60\u5668\u4e2a\u6570\uff0cint\u7c7b\u578b\u3002\u5f31\u5b66\u4e60\u5668\u7684\u4e2a\u6570\uff0c\u4e5f\u53ef\u4ee5\u8bf4\u662f\u5f31\u5b66\u4e60\u7684\u6700\u5927\u8fed\u4ee3\u6b21\u6570\uff0c\u5982\u679cn_estimators\u8fc7\u5927\uff0c\u5bb9\u6613\u8fc7\u62df\u5408\uff1b\u5982\u679cn_estimators\u8fc7\u5c0f\uff0c\u5bb9\u6613\u6b20\u62df\u5408\u3002\u9ed8\u8ba4\u4e3a10\u3002<\/li>\n
    • subsample\uff1a<\/strong>\u5b50\u91c7\u6837\uff0cfloat\u7c7b\u578b\u3002subsample\u53d6\u503c\u8303\u56f4\u4e3a$(0,1]$\uff0c\u8fd9\u91cc\u7684\u5b50\u91c7\u6837\u662f\u4e0d\u653e\u56de\u62bd\u6837\uff0c\u5982\u679c\u53d6\u503c\u4e3a1\uff0c\u5219\u4f7f\u7528\u5168\u90e8\u6837\u672c\uff0c\u5982\u679c\u53d6\u503c\u5c0f\u4e8e\u53bb\uff0c\u53ea\u6709\u8bad\u7ec3\u4e00\u90e8\u5206\u6837\u672c\uff0c\u4f7f\u7528\u8be5\u53c2\u6570\u53ef\u4ee5\u51cf\u5c0f\u65b9\u5dee\uff0c\u9632\u6b62\u8fc7\u62df\u5408\uff0c\u4f46\u662f\u4f1a\u589e\u52a0\u6837\u672c\u62df\u5408\u7684\u504f\u5dee\uff0c\u4e00\u822c\u53d6\u503c\u5728$[0.5,0.8]$\u3002\u9ed8\u8ba4\u4e3a1.0\u3002<\/li>\n
    • criterion\uff1a<\/strong>\u7279\u5f81\u9009\u62e9\uff0cstr\u7c7b\u578b\u3002criterion=’gini’\u8868\u793a\u57fa\u5c3c\u6307\u6570\uff1bcriterion=’entropy’\u8868\u793a\u4fe1\u606f\u589e\u76ca\uff0c\u63a8\u8350\u4f7f\u7528’gini’\u3002\u9ed8\u8ba4\u4e3a’gini’\u3002<\/li>\n
    • splitter\uff1a<\/strong>\u7279\u5f81\u5212\u5206\u70b9\u9009\u62e9\uff0cstr\u7c7b\u578b\u3002\u9ed8\u8ba4\u4e3a’friedman_mse’\u3002<\/li>\n
    • min_samples_split\uff1a<\/strong>\u5185\u90e8\u8282\u70b9\u5212\u5206\u9700\u8981\u6700\u5c11\u6837\u672c\u6570\uff0cfloat\u7c7b\u578b\u3002\u9650\u5b9a\u5b50\u6811\u7ee7\u7eed\u5212\u5206\u7684\u6761\u4ef6\uff0c\u5982\u679c\u67d0\u8282\u70b9\u7684\u6837\u672c\u6570\u5c11\u4e8emin_samples_split\uff0c\u5219\u4f1a\u505c\u6b62\u7ee7\u7eed\u5212\u5206\u5b50\u6811\u3002\u5982\u679c\u6837\u672c\u6570\u91cf\u8fc7\u5927\uff0c\u5efa\u8bae\u589e\u5927\u8be5\u503c\uff0c\u5426\u5219\u5efa\u8bae\u4f7f\u7528\u9ed8\u8ba4\u503c\u3002\u9ed8\u8ba4\u4e3a2\u3002<\/li>\n
    • min_samples_leaf\uff1a<\/strong>\u53f6\u5b50\u8282\u70b9\u6700\u5c11\u6837\u672c\u6570float\u7c7b\u578b\u3002\u5982\u679c\u5728\u67d0\u6b21\u5212\u5206\u53f6\u5b50\u8282\u70b9\u6570\u76ee\u5c0f\u4e8e\u6837\u672c\u6570\uff0c\u5219\u4f1a\u548c\u5144\u5f1f\u8282\u70b9\u4e00\u8d77\u526a\u679d\u3002\u5982\u679c\u6837\u672c\u6570\u91cf\u8fc7\u5927\uff0c\u5efa\u8bae\u589e\u5927\u8be5\u503c\uff0c\u5426\u5219\u5efa\u8bae\u4f7f\u7528\u9ed8\u8ba4\u503c\u3002\u9ed8\u8ba4\u4e3a1\u3002<\/li>\n
    • min_weight_fraction_leaf\uff1a<\/strong>\u53f6\u5b50\u8282\u70b9\u6700\u5c0f\u7684\u6837\u672c\u6743\u91cd\u548c\uff0cfloat\u7c7b\u578b\u3002\u8be5\u53c2\u6570\u9650\u5236\u4e86\u53f6\u5b50\u8282\u70b9\u6240\u6709\u6837\u672c\u6743\u91cd\u548c\u7684\u6700\u5c0f\u503c\uff0c\u5982\u679c\u5c0f\u4e8e\u8be5\u503c\uff0c\u5219\u4f1a\u548c\u5144\u5f1f\u8282\u70b9\u4e00\u8d77\u526a\u679d\u3002\u5982\u679c\u6837\u672c\u6709\u89d2\u5ea6\u7684\u7f3a\u5931\u503c\uff0c\u6216\u8005\u6837\u672c\u7684\u5206\u5e03\u504f\u5dee\u8f83\u5927\uff0c\u5219\u53ef\u4ee5\u8003\u8651\u6743\u91cd\u95ee\u9898\u3002\u9ed8\u8ba4\u4e3a0\u3002<\/li>\n
    • max_depth\uff1a<\/strong>\u6700\u5927\u6df1\u5ea6\uff0cint\u7c7b\u578b\u3002\u9650\u5236\u51b3\u7b56\u6811\u7684\u6df1\u5ea6\u3002\u9ed8\u8ba4\u4e3a3\u3002<\/li>\n
    • max_leaf_nodes\uff1a<\/strong>\u6700\u5927\u53f6\u5b50\u8282\u70b9\u6570\uff0cint\u7c7b\u578b\u3002\u9650\u5236\u6700\u5927\u53f6\u5b50\u8282\u70b9\u6570\uff0c\u53ef\u4ee5\u9632\u6b62\u6811\u8fc7\u6df1\uff0c\u56e0\u6b64\u53ef\u4ee5\u9632\u6b62\u8fc7\u62df\u5408\u3002\u9ed8\u8ba4\u4e3aNone\u3002<\/li>\n
    • min_impurity_decrease\uff1a<\/strong>\u8282\u70b9\u51cf\u5c0f\u4e0d\u7eaf\u5ea6\uff0cfloat\u7c7b\u578b\u3002\u5982\u679c\u67d0\u8282\u70b9\u5212\u5206\u4f1a\u5bfc\u81f4\u4e0d\u7eaf\u5ea6\u7684\u51cf\u5c11\u5927\u4e8emin_impurity_decrease\uff0c\u5219\u505c\u6b62\u8be5\u8282\u70b9\u5212\u5206\u3002\u9ed8\u8ba4\u4e3a0\u3002<\/li>\n
    • min_impurity_split\uff1a<\/strong>\u8282\u70b9\u5212\u5206\u6700\u5c0f\u4e0d\u7eaf\u5ea6\uff0cfloat\u7c7b\u578b\u3002\u5982\u679c\u67d0\u8282\u70b9\u7684\u4e0d\u7eaf\u5ea6\u5c0f\u4e8emin_impurity_split\uff0c\u5219\u505c\u6b62\u8be5\u8282\u70b9\u5212\u5206\uff0c\u5373\u4e0d\u751f\u6210\u53f6\u5b50\u8282\u70b9\u3002\u9ed8\u8ba4\u4e3a1e-7(0.0000001)\u3002<\/li>\n
    • class_weight\uff1a<\/strong>\u7c7b\u522b\u6743\u91cd\uff0cdict\u7c7b\u578b\u6216str\u7c7b\u578b\u3002\u5bf9\u4e8e\u4e8c\u5143\u5206\u7c7b\u95ee\u9898\u53ef\u4ee5\u4f7f\u7528class_weight={0:0.9,1:0.1}\uff0c\u8868\u793a0\u7c7b\u522b\u6743\u91cd\u4e3a0.9\uff0c1\u7c7b\u522b\u6743\u91cd\u4e3a0.1\uff0cstr\u7c7b\u578b\u5373\u4e3a’balanced’\uff0c\u6a21\u578b\u5c06\u6839\u636e\u8bad\u7ec3\u96c6\u81ea\u52a8\u4fee\u6539\u4e0d\u540c\u7c7b\u522b\u7684\u6743\u91cd\u3002\u9ed8\u8ba4\u4e3aNone\u3002<\/li>\n
    • init\uff1a<\/strong>\u521d\u59cb\u5f31\u5b66\u4e60\u5668\uff0c\u5f31\u5b66\u4e60\u5668\u7c7b\u578b\u3002\u5bf9\u5e94\u524d\u5411\u5206\u6b65\u7b97\u6cd5\u4e2d\u7684$f_0(x)$\uff0c\u9664\u975e\u5bf9\u6570\u636e\u6709\u5148\u9a8c\u77e5\u8bc6\uff0c\u5426\u5219\u4e0d\u7528\u7ba1\u8fd9\u4e2a\u53c2\u6570\u3002\u53ef\u9009\u53c2\u6570\u3002<\/li>\n
    • random_state\uff1a<\/strong>\u968f\u673a\u6570\u79cd\u5b50\uff0cint\u7c7b\u578b\u3002random_state=None\uff0c\u4e0d\u540c\u65f6\u523b\u4ea7\u751f\u7684\u968f\u673a\u6570\u636e\u662f\u4e0d\u540c\u7684\uff1brandom_state=int\u7c7b\u578b\uff0c\u76f8\u540c\u968f\u673a\u6570\u79cd\u5b50\u4e0d\u540c\u65f6\u523b\u4ea7\u751f\u7684\u968f\u673a\u6570\u662f\u76f8\u540c\u7684\u3002\u9ed8\u8ba4\u4e3aNone\u3002<\/li>\n
    • max_features\uff1a<\/strong>\u5212\u5206\u7684\u6700\u5927\u7279\u5f81\u6570\uff0cstr\u3001int\u3001float\u7c7b\u578b\u3002max_depth=’log2’\u8868\u793a\u6700\u591a\u8003\u8651$log_2n$\u4e2a\u7279\u5f81\uff1bmax_depth={‘sqrt’,’auto’}\u8868\u793a\u6700\u591a\u8003\u8651$\\sqrt{n}$\u4e2a\u7279\u5f81\uff1bmax_depth=int\u7c7b\u578b\uff0c\u8003\u8651$|int\u7c7b\u578b|$\u4e2a\u7279\u5f81\uff1bmax_depth=float\u7c7b\u578b\uff0c\u59820.3\uff0c\u5219\u8003\u8651$0.3n$\u4e2a\u7279\u5f81\uff0c\u5176\u4e2d$n$\u4e3a\u6837\u672c\u603b\u7279\u5f81\u6570\u3002\u9ed8\u8ba4\u4e3aNone\uff0c\u6837\u672c\u7279\u5f81\u6570\u4e0d\u5927\u4e8e50\u63a8\u8350\u4f7f\u7528\u9ed8\u8ba4\u503c\u3002<\/li>\n
    • verbose\uff1a<\/strong>\u65e5\u5fd7\u5197\u957f\u5ea6\uff0cint\u7c7b\u578b\u3002verbose=0\uff0c\u4e0d\u8f93\u51fa\u8bad\u7ec3\u8fc7\u7a0b\uff1bverbose=1\uff0c\u8f93\u51fa\u90e8\u5206\u8bad\u7ec3\u8fc7\u7a0b\uff1bverbose>1\uff0c\u8f93\u51fa\u6240\u6709\u7684\u8bad\u7ec3\u8fc7\u7a0b\u3002\u9ed8\u8ba4\u4e3a0\u3002<\/li>\n
    • max_leaf_nodes\uff1a<\/strong>\u6700\u5927\u53f6\u5b50\u8282\u70b9\u6570\uff0cint\u7c7b\u578b\u3002\u9650\u5236\u6700\u5927\u53f6\u5b50\u8282\u70b9\u6570\uff0c\u53ef\u4ee5\u9632\u6b62\u6811\u8fc7\u6df1\uff0c\u56e0\u6b64\u53ef\u4ee5\u9632\u6b62\u8fc7\u62df\u5408\u3002\u9ed8\u8ba4\u4e3aNone\u3002<\/li>\n
    • warm_start\uff1a<\/strong>\u70ed\u542f\u52a8\uff0cbool\u7c7b\u578b\u3002\u5982\u679c\u4e3aTrue\uff0c\u5219\u57fa\u4e8e\u4e0a\u4e00\u4e2a\u968f\u673a\u68ee\u6797\u6dfb\u52a0\u51b3\u7b56\u6811\uff1b\u5982\u679c\u4e3aFalse\uff0c\u5219\u91cd\u65b0\u751f\u6210\u4e00\u4e2a\u968f\u673a\u68ee\u6797\u3002\u9ed8\u8ba4\u4e3aFalse\u3002<\/li>\n
    • presort\uff1a<\/strong>\u6570\u636e\u662f\u5426\u6392\u5e8f\uff0cbool\u7c7b\u578b\u3002\u6837\u672c\u91cf\u8f83\u5c0f\uff0cpresort=True\uff0c\u5373\u8ba9\u6837\u672c\u6570\u636e\u6392\u5e8f\uff0c\u8282\u70b9\u5212\u5206\u901f\u5ea6\u66f4\u5feb\uff1b\u6837\u672c\u91cf\u8f83\u5927\uff0cpresort=True\uff0c\u8ba9\u6837\u672c\u6392\u5e8f\u53cd\u800c\u4f1a\u589e\u52a0\u8bad\u7ec3\u6a21\u578b\u7684\u65f6\u95f4\u3002\u901a\u5e38\u4f7f\u7528\u9ed8\u8ba4\u503c\u3002\u9ed8\u8ba4\u503c\u4e3aFalse\u3002<\/li>\n
    • validation_fraction\uff1a<\/strong>\u9884\u7559\u6570\u636e\uff0cfloat\u7c7b\u578b\u3002\u53d6\u503c\u8303\u56f4\u4e3a$[0,1]$\uff0c\u9884\u7559\u591a\u5c11\u6bd4\u4f8b\u7684\u6570\u636e\u505a\u9a8c\u8bc1\u3002\u9ed8\u8ba4\u4e3a0.1\u3002<\/li>\n
    • n_iter_no_change\uff1a<\/strong>\u505c\u6b62\u8bad\u7ec3\uff0cint\u7c7b\u578b\u3002\u53ef\u4ee5\u5728\u8bbe\u7f6e\u4e00\u4e2a\u53c2\u6570\u63a7\u5236\u7b97\u6cd5\uff0c\u5728\u9a8c\u8bc1\u5206\u6570\u6ca1\u6709\u63d0\u9ad8\u7684\u65f6\u5019\u63d0\u65e9\u7ed3\u675f\u3002\u9ed8\u8ba4\u4e3aNone\u3002<\/li>\n
    • tol\uff1a<\/strong>\u635f\u5931\u505c\u6b62\u8bad\u7ec3\uff0cfloat\u7c7b\u578b\u3002\u8bbe\u7f6e\u4e00\u4e2a\u503c\u5728\u635f\u5931\u5728\u67d0\u4e2a\u533a\u95f4\u5185\u6ca1\u6709\u6539\u5584\u65f6\u505c\u6b62\u7b97\u6cd5\u3002\u9ed8\u8ba4\u4e3a1e-4\u3002<\/li>\n<\/ul>\n

      \"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\"<\/div><\/p>\n

      \u5c5e\u6027<\/h2>\n
        \n
      • estimators_\uff1a<\/strong>list\u7c7b\u578b\u3002\u6240\u6709\u51b3\u7b56\u6811\u96c6\u5408\u3002<\/li>\n
      • featureimportances<\/em>\uff1a<\/strong>array\u7c7b\u578b\u3002\u7279\u5f81\u91cd\u8981\u5ea6\u3002<\/li>\n
      • oobimprovement<\/em>\uff1a<\/strong>array\u7c7b\u578b\u3002\u888b\u5916\u6837\u672c\u5bf9\u524d\u4e00\u6b21\u8fed\u4ee3\u635f\u5931\u7684\u6539\u5584\u7a0b\u5ea6\u3002<\/li>\n
      • trainscore<\/em>\uff1a<\/strong>array\u7c7b\u578b\u3002\u888b\u5185\u6837\u672c\u8bad\u7ec3\u6570\u636e\u7684\u504f\u5dee\u3002<\/li>\n
      • loss_\uff1a<\/strong>\u8fd4\u56de\u635f\u5931\u51fd\u6570\u3002<\/li>\n
      • init_\uff1a<\/strong>\u8fd4\u56de\u521d\u59cb\u5f31\u5b66\u4e60\u5668\u3002<\/li>\n
      • estimators_\uff1a<\/strong>ndarray\u7c7b\u578b\u3002\u5f31\u5b66\u4e60\u5668\u96c6\u3002<\/li>\n<\/ul>\n

        \u65b9\u6cd5<\/h2>\n
          \n
        • apply(X[, check_input])\uff1a<\/strong>\u8fd4\u56de\u6bcf\u4e2a\u6837\u672c\u9884\u6d4b\u7684\u53f6\u5b50\u8282\u70b9\u7d22\u5f15\u3002<\/li>\n
        • decision_function(X)\uff1a<\/strong>\u51b3\u7b56\u51fd\u6570\u5173\u4e8e\u6837\u672cX\u7684\u503c\u3002<\/li>\n
        • fit(X,y)\uff1a<\/strong>\u628a\u6570\u636e\u653e\u5165\u6a21\u578b\u4e2d\u8bad\u7ec3\u6a21\u578b\u3002<\/li>\n
        • get_params([deep])\uff1a<\/strong>\u8fd4\u56de\u6a21\u578b\u7684\u53c2\u6570\uff0c\u53ef\u4ee5\u7528\u4e8ePipeline\u4e2d\u3002<\/li>\n
        • predict(X)\uff1a<\/strong>\u9884\u6d4b\u6837\u672cX\u7684\u5206\u7c7b\u7c7b\u522b\u3002<\/li>\n
        • predict_log_proba(X)\uff1a<\/strong>\u8fd4\u56de\u6837\u672cX\u5728\u5404\u4e2a\u7c7b\u522b\u4e0a\u5bf9\u5e94\u7684\u5bf9\u6570\u6982\u7387\u3002<\/li>\n
        • predict_proba(X)\uff1a<\/strong>\u8fd4\u56de\u6837\u672cX\u5728\u5404\u4e2a\u7c7b\u522b\u4e0a\u5bf9\u5e94\u7684\u6982\u7387\u3002<\/li>\n
        • score(X,y)\uff1a<\/strong>\u57fa\u4e8e\u62a5\u544a\u51b3\u5b9a\u7cfb\u6570$R^2$\u8bc4\u4f30\u6a21\u578b\u3002<\/li>\n
        • set_prams(**params)\uff1a<\/strong>\u521b\u5efa\u6a21\u578b\u53c2\u6570\u3002<\/li>\n
        • staged_decision_function(X)\uff1a<\/strong>\u8fd4\u56de\u6bcf\u4e2a\u9636\u6bb5\u6837\u672cX\u7684\u51b3\u7b56\u51fd\u6570\u503c\u3002<\/li>\n
        • staged_predict(X)\uff1a<\/strong>\u8fd4\u56de\u6bcf\u4e2a\u9636\u6bb5\u6837\u672cX\u7684\u9884\u6d4b\u503c\u3002<\/li>\n
        • staged_predict_proba(X)\uff1a<\/strong>\u8fd4\u56de\u6bcf\u4e2a\u9636\u6bb5\u6837\u672cX\u5728\u5404\u4e2a\u7c7b\u522b\u4e0a\u5bf9\u5e94\u7684\u6982\u7387\u3002<\/li>\n<\/ul>\n

          GradietBoostingClassifier<\/h1>\n

            GradientBoostingClassifier<\/code>\u8f83\u4e8eGradientBoostingClassifier<\/code>\u6a21\u578b\u4e3b\u8981\u7528\u4e8e\u89e3\u51b3\u56de\u5f52\u95ee\u9898\uff0c\u4e0d\u540c\u4e4b\u5904\u5728\u4e8e\u5904\u7406\u9884\u6d4b\u503c\u7684\u65b9\u6cd5\u4e0d\u540c\u548c\u4f7f\u7528\u7684\u635f\u5931\u51fd\u6570\u7684\u4e0d\u540c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"

          scikit-learn\u5e93\u4e4b\u68af\u5ea6\u63d0\u5347\u6811   \u672c\u6587\u4e3b\u8981\u4ecb\u7ecd\u68af\u5ea6\u63d0\u5347\u6811\u7684\u4e24\u4e2a\u6a21\u578bGradien […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[276,296,293],"tags":[],"_links":{"self":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3159"}],"collection":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3159"}],"version-history":[{"count":0,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3159\/revisions"}],"wp:attachment":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3159"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3159"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3159"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}