ML之xgboost：利用xgboost算法(sklearn+3Split+调参曲线)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)

本文主要是介绍ML之xgboost：利用xgboost算法(sklearn+3Split+调参曲线)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)，对大家解决编程问题具有一定的参考价值，需要的程序猿们随着小编来一起学习吧！

ML之xgboost：利用xgboost算法(sklearn+3Split+调参曲线)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)

目录

输出结果

设计思路

核心代码

更多输出

输出结果

设计思路

核心代码

eval_set = [(X_train_part, y_train_part), (X_validate, y_validate)]    
bst.fit(X_train_part, y_train_part, eval_metric=["error", "logloss"], eval_set=eval_set, verbose=True)


preds = bst.predict(X_test)
predictions = [round(value) for value in preds]
test_accuracy = accuracy_score(y_test, predictions)
print("【max_depth=2,lr=0.1】Test Accuracy: %.2f%%" % (test_accuracy * 100.0))

results = bst.evals_result() 

更多输出

X_train： (6513, 126)
X_test： (1611, 126)
After split(33%)，X_train_part： (4363, 126)
After split(33%)，X_validate： (2150, 126)
[0]	validation_0-error:0.045611	validation_0-logloss:0.614637	validation_1-error:0.048372	validation_1-logloss:0.615401
[1]	validation_0-error:0.041256	validation_0-logloss:0.549907	validation_1-error:0.042326	validation_1-logloss:0.550696
[2]	validation_0-error:0.045611	validation_0-logloss:0.49543	validation_1-error:0.048372	validation_1-logloss:0.496777
[3]	validation_0-error:0.041256	validation_0-logloss:0.449089	validation_1-error:0.042326	validation_1-logloss:0.450412
[4]	validation_0-error:0.041256	validation_0-logloss:0.409231	validation_1-error:0.042326	validation_1-logloss:0.410717
[5]	validation_0-error:0.041256	validation_0-logloss:0.373748	validation_1-error:0.042326	validation_1-logloss:0.375653
[6]	validation_0-error:0.023378	validation_0-logloss:0.343051	validation_1-error:0.023256	validation_1-logloss:0.344738
[7]	validation_0-error:0.041256	validation_0-logloss:0.315369	validation_1-error:0.042326	validation_1-logloss:0.317409
[8]	validation_0-error:0.041256	validation_0-logloss:0.290912	validation_1-error:0.042326	validation_1-logloss:0.292587
[9]	validation_0-error:0.023378	validation_0-logloss:0.269356	validation_1-error:0.023256	validation_1-logloss:0.271103
[10]	validation_0-error:0.00573	validation_0-logloss:0.249593	validation_1-error:0.006512	validation_1-logloss:0.251354
[11]	validation_0-error:0.01719	validation_0-logloss:0.228658	validation_1-error:0.017674	validation_1-logloss:0.230144
[12]	validation_0-error:0.01719	validation_0-logloss:0.210442	validation_1-error:0.017674	validation_1-logloss:0.21167
[13]	validation_0-error:0.01719	validation_0-logloss:0.194562	validation_1-error:0.017674	validation_1-logloss:0.19555
[14]	validation_0-error:0.01719	validation_0-logloss:0.1807	validation_1-error:0.017674	validation_1-logloss:0.181463
[15]	validation_0-error:0.01719	validation_0-logloss:0.168585	validation_1-error:0.017674	validation_1-logloss:0.169138
[16]	validation_0-error:0.01719	validation_0-logloss:0.157988	validation_1-error:0.017674	validation_1-logloss:0.158345
[17]	validation_0-error:0.01719	validation_0-logloss:0.149407	validation_1-error:0.017674	validation_1-logloss:0.149731
[18]	validation_0-error:0.0259	validation_0-logloss:0.140835	validation_1-error:0.024651	validation_1-logloss:0.140979
[19]	validation_0-error:0.022003	validation_0-logloss:0.133937	validation_1-error:0.020465	validation_1-logloss:0.13405
[20]	validation_0-error:0.022003	validation_0-logloss:0.126967	validation_1-error:0.020465	validation_1-logloss:0.126914
[21]	validation_0-error:0.022003	validation_0-logloss:0.121386	validation_1-error:0.020465	validation_1-logloss:0.121303
[22]	validation_0-error:0.022003	validation_0-logloss:0.115692	validation_1-error:0.020465	validation_1-logloss:0.115456
[23]	validation_0-error:0.022003	validation_0-logloss:0.111147	validation_1-error:0.020465	validation_1-logloss:0.110881
[24]	validation_0-error:0.022003	validation_0-logloss:0.106477	validation_1-error:0.020465	validation_1-logloss:0.10607
[25]	validation_0-error:0.022003	validation_0-logloss:0.102434	validation_1-error:0.020465	validation_1-logloss:0.102319
[26]	validation_0-error:0.022003	validation_0-logloss:0.098434	validation_1-error:0.020465	validation_1-logloss:0.09819
[27]	validation_0-error:0.022003	validation_0-logloss:0.094875	validation_1-error:0.020465	validation_1-logloss:0.094824
[28]	validation_0-error:0.022003	validation_0-logloss:0.091579	validation_1-error:0.020465	validation_1-logloss:0.091784
[29]	validation_0-error:0.013294	validation_0-logloss:0.086202	validation_1-error:0.013488	validation_1-logloss:0.086807
[30]	validation_0-error:0.022003	validation_0-logloss:0.083247	validation_1-error:0.020465	validation_1-logloss:0.083741
[31]	validation_0-error:0.022003	validation_0-logloss:0.080496	validation_1-error:0.020465	validation_1-logloss:0.080924
[32]	validation_0-error:0.022003	validation_0-logloss:0.077298	validation_1-error:0.020465	validation_1-logloss:0.077394
[33]	validation_0-error:0.015815	validation_0-logloss:0.074507	validation_1-error:0.016279	validation_1-logloss:0.074765
[34]	validation_0-error:0.022003	validation_0-logloss:0.071848	validation_1-error:0.020465	validation_1-logloss:0.071811
[35]	validation_0-error:0.010543	validation_0-logloss:0.069488	validation_1-error:0.009302	validation_1-logloss:0.069385
[36]	validation_0-error:0.001834	validation_0-logloss:0.067147	validation_1-error:0.002326	validation_1-logloss:0.067341
[37]	validation_0-error:0.001834	validation_0-logloss:0.06504	validation_1-error:0.002326	validation_1-logloss:0.065406
[38]	validation_0-error:0.001834	validation_0-logloss:0.062898	validation_1-error:0.002326	validation_1-logloss:0.063381
[39]	validation_0-error:0.001834	validation_0-logloss:0.060837	validation_1-error:0.002326	validation_1-logloss:0.061088
[40]	validation_0-error:0.001834	validation_0-logloss:0.058894	validation_1-error:0.002326	validation_1-logloss:0.059039
[41]	validation_0-error:0.001834	validation_0-logloss:0.057112	validation_1-error:0.002326	validation_1-logloss:0.057326
[42]	validation_0-error:0.001834	validation_0-logloss:0.055391	validation_1-error:0.002326	validation_1-logloss:0.05543
[43]	validation_0-error:0.001834	validation_0-logloss:0.053745	validation_1-error:0.002326	validation_1-logloss:0.053871
[44]	validation_0-error:0.001834	validation_0-logloss:0.052198	validation_1-error:0.002326	validation_1-logloss:0.052235
[45]	validation_0-error:0.001834	validation_0-logloss:0.050776	validation_1-error:0.002326	validation_1-logloss:0.051033
[46]	validation_0-error:0.001834	validation_0-logloss:0.049351	validation_1-error:0.002326	validation_1-logloss:0.04973
[47]	validation_0-error:0.001834	validation_0-logloss:0.047848	validation_1-error:0.002326	validation_1-logloss:0.048287
[48]	validation_0-error:0.001834	validation_0-logloss:0.046406	validation_1-error:0.002326	validation_1-logloss:0.046702
[49]	validation_0-error:0.001834	validation_0-logloss:0.045141	validation_1-error:0.002326	validation_1-logloss:0.045492
[50]	validation_0-error:0.001834	validation_0-logloss:0.043917	validation_1-error:0.002326	validation_1-logloss:0.044133
[51]	validation_0-error:0.001834	validation_0-logloss:0.042729	validation_1-error:0.002326	validation_1-logloss:0.042999
[52]	validation_0-error:0.001834	validation_0-logloss:0.041608	validation_1-error:0.002326	validation_1-logloss:0.041807
[53]	validation_0-error:0.001834	validation_0-logloss:0.040493	validation_1-error:0.002326	validation_1-logloss:0.040855
[54]	validation_0-error:0.001834	validation_0-logloss:0.039457	validation_1-error:0.002326	validation_1-logloss:0.039871
[55]	validation_0-error:0.001834	validation_0-logloss:0.038452	validation_1-error:0.002326	validation_1-logloss:0.038755
[56]	validation_0-error:0.001834	validation_0-logloss:0.037478	validation_1-error:0.002326	validation_1-logloss:0.037717
[57]	validation_0-error:0.001834	validation_0-logloss:0.036439	validation_1-error:0.002326	validation_1-logloss:0.036777
[58]	validation_0-error:0.001834	validation_0-logloss:0.035552	validation_1-error:0.002326	validation_1-logloss:0.035936
[59]	validation_0-error:0.001834	validation_0-logloss:0.034694	validation_1-error:0.002326	validation_1-logloss:0.034984
[60]	validation_0-error:0.001834	validation_0-logloss:0.033826	validation_1-error:0.002326	validation_1-logloss:0.034132
[61]	validation_0-error:0.001834	validation_0-logloss:0.032959	validation_1-error:0.002326	validation_1-logloss:0.033348
[62]	validation_0-error:0.001834	validation_0-logloss:0.032192	validation_1-error:0.002326	validation_1-logloss:0.032526
[63]	validation_0-error:0.001834	validation_0-logloss:0.031476	validation_1-error:0.002326	validation_1-logloss:0.031754
[64]	validation_0-error:0.001834	validation_0-logloss:0.030756	validation_1-error:0.002326	validation_1-logloss:0.031081
[65]	validation_0-error:0.001834	validation_0-logloss:0.030038	validation_1-error:0.002326	validation_1-logloss:0.030377
[66]	validation_0-error:0.001834	validation_0-logloss:0.029332	validation_1-error:0.002326	validation_1-logloss:0.029594
[67]	validation_0-error:0.001834	validation_0-logloss:0.028703	validation_1-error:0.002326	validation_1-logloss:0.029079
[68]	validation_0-error:0.001834	validation_0-logloss:0.028064	validation_1-error:0.002326	validation_1-logloss:0.028391
[69]	validation_0-error:0.001834	validation_0-logloss:0.027404	validation_1-error:0.002326	validation_1-logloss:0.027725
[70]	validation_0-error:0.001834	validation_0-logloss:0.026824	validation_1-error:0.002326	validation_1-logloss:0.027187
[71]	validation_0-error:0.001834	validation_0-logloss:0.026268	validation_1-error:0.002326	validation_1-logloss:0.026565
[72]	validation_0-error:0.001834	validation_0-logloss:0.025679	validation_1-error:0.002326	validation_1-logloss:0.025982
[73]	validation_0-error:0.001834	validation_0-logloss:0.025153	validation_1-error:0.002326	validation_1-logloss:0.025413
[74]	validation_0-error:0.001834	validation_0-logloss:0.02461	validation_1-error:0.002326	validation_1-logloss:0.024927
[75]	validation_0-error:0.001834	validation_0-logloss:0.0241	validation_1-error:0.002326	validation_1-logloss:0.02446
[76]	validation_0-error:0.001834	validation_0-logloss:0.023615	validation_1-error:0.002326	validation_1-logloss:0.023921
[77]	validation_0-error:0.001834	validation_0-logloss:0.023118	validation_1-error:0.002326	validation_1-logloss:0.023423
[78]	validation_0-error:0.001834	validation_0-logloss:0.022671	validation_1-error:0.002326	validation_1-logloss:0.023015
[79]	validation_0-error:0.001834	validation_0-logloss:0.022244	validation_1-error:0.002326	validation_1-logloss:0.022538
[80]	validation_0-error:0.001834	validation_0-logloss:0.021793	validation_1-error:0.002326	validation_1-logloss:0.022087
[81]	validation_0-error:0.001834	validation_0-logloss:0.021396	validation_1-error:0.002326	validation_1-logloss:0.021654
[82]	validation_0-error:0.001834	validation_0-logloss:0.020948	validation_1-error:0.002326	validation_1-logloss:0.021198
[83]	validation_0-error:0.001834	validation_0-logloss:0.020559	validation_1-error:0.002326	validation_1-logloss:0.020806
[84]	validation_0-error:0.001834	validation_0-logloss:0.020144	validation_1-error:0.002326	validation_1-logloss:0.020388
[85]	validation_0-error:0.001834	validation_0-logloss:0.019775	validation_1-error:0.002326	validation_1-logloss:0.020057
[86]	validation_0-error:0.001834	validation_0-logloss:0.019029	validation_1-error:0.002326	validation_1-logloss:0.019235
[87]	validation_0-error:0.001834	validation_0-logloss:0.018672	validation_1-error:0.002326	validation_1-logloss:0.018823
[88]	validation_0-error:0.001834	validation_0-logloss:0.018313	validation_1-error:0.002326	validation_1-logloss:0.018507
[89]	validation_0-error:0.001834	validation_0-logloss:0.017989	validation_1-error:0.002326	validation_1-logloss:0.01815
[90]	validation_0-error:0.001834	validation_0-logloss:0.017376	validation_1-error:0.002326	validation_1-logloss:0.01748
[91]	validation_0-error:0.001834	validation_0-logloss:0.017087	validation_1-error:0.002326	validation_1-logloss:0.017189
[92]	validation_0-error:0.001834	validation_0-logloss:0.016778	validation_1-error:0.002326	validation_1-logloss:0.016877
[93]	validation_0-error:0.001834	validation_0-logloss:0.016458	validation_1-error:0.002326	validation_1-logloss:0.016527
[94]	validation_0-error:0.001834	validation_0-logloss:0.015932	validation_1-error:0.002326	validation_1-logloss:0.015956
[95]	validation_0-error:0.001834	validation_0-logloss:0.015645	validation_1-error:0.002326	validation_1-logloss:0.015665
[96]	validation_0-error:0.001834	validation_0-logloss:0.015379	validation_1-error:0.002326	validation_1-logloss:0.015397
[97]	validation_0-error:0.001834	validation_0-logloss:0.015116	validation_1-error:0.002326	validation_1-logloss:0.01513
[98]	validation_0-error:0.001834	validation_0-logloss:0.014883	validation_1-error:0.002326	validation_1-logloss:0.014893
[99]	validation_0-error:0.001834	validation_0-logloss:0.01464	validation_1-error:0.002326	validation_1-logloss:0.014624


【max_depth=2,lr=0.1】Test Accuracy: 99.81%
{'validation_0': {'error': [0.045611, 0.041256, 0.045611, 0.041256, 0.041256, 0.041256, 0.023378, 0.041256, 0.041256, 0.023378, 0.00573, 0.01719, 0.01719, 0.01719, 0.01719, 0.01719, 0.01719, 0.01719, 0.0259, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.022003, 0.013294, 0.022003, 0.022003, 0.022003, 0.015815, 0.022003, 0.010543, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834, 0.001834], 'logloss': [0.614637, 0.549907, 0.49543, 0.449089, 0.409231, 0.373748, 0.343051, 0.315369, 0.290912, 0.269356, 0.249593, 0.228658, 0.210442, 0.194562, 0.1807, 0.168585, 0.157988, 0.149407, 0.140835, 0.133937, 0.126967, 0.121386, 0.115692, 0.111147, 0.106477, 0.102434, 0.098434, 0.094875, 0.091579, 0.086202, 0.083247, 0.080496, 0.077298, 0.074507, 0.071848, 0.069488, 0.067147, 0.06504, 0.062898, 0.060837, 0.058894, 0.057112, 0.055391, 0.053745, 0.052198, 0.050776, 0.049351, 0.047848, 0.046406, 0.045141, 0.043917, 0.042729, 0.041608, 0.040493, 0.039457, 0.038452, 0.037478, 0.036439, 0.035552, 0.034694, 0.033826, 0.032959, 0.032192, 0.031476, 0.030756, 0.030038, 0.029332, 0.028703, 0.028064, 0.027404, 0.026824, 0.026268, 0.025679, 0.025153, 0.02461, 0.0241, 0.023615, 0.023118, 0.022671, 0.022244, 0.021793, 0.021396, 0.020948, 0.020559, 0.020144, 0.019775, 0.019029, 0.018672, 0.018313, 0.017989, 0.017376, 0.017087, 0.016778, 0.016458, 0.015932, 0.015645, 0.015379, 0.015116, 0.014883, 0.01464]}, 'validation_1': {'error': [0.048372, 0.042326, 0.048372, 0.042326, 0.042326, 0.042326, 0.023256, 0.042326, 0.042326, 0.023256, 0.006512, 0.017674, 0.017674, 0.017674, 0.017674, 0.017674, 0.017674, 0.017674, 0.024651, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.020465, 0.013488, 0.020465, 0.020465, 0.020465, 0.016279, 0.020465, 0.009302, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326, 0.002326], 'logloss': [0.615401, 0.550696, 0.496777, 0.450412, 0.410717, 0.375653, 0.344738, 0.317409, 0.292587, 0.271103, 0.251354, 0.230144, 0.21167, 0.19555, 0.181463, 0.169138, 0.158345, 0.149731, 0.140979, 0.13405, 0.126914, 0.121303, 0.115456, 0.110881, 0.10607, 0.102319, 0.09819, 0.094824, 0.091784, 0.086807, 0.083741, 0.080924, 0.077394, 0.074765, 0.071811, 0.069385, 0.067341, 0.065406, 0.063381, 0.061088, 0.059039, 0.057326, 0.05543, 0.053871, 0.052235, 0.051033, 0.04973, 0.048287, 0.046702, 0.045492, 0.044133, 0.042999, 0.041807, 0.040855, 0.039871, 0.038755, 0.037717, 0.036777, 0.035936, 0.034984, 0.034132, 0.033348, 0.032526, 0.031754, 0.031081, 0.030377, 0.029594, 0.029079, 0.028391, 0.027725, 0.027187, 0.026565, 0.025982, 0.025413, 0.024927, 0.02446, 0.023921, 0.023423, 0.023015, 0.022538, 0.022087, 0.021654, 0.021198, 0.020806, 0.020388, 0.020057, 0.019235, 0.018823, 0.018507, 0.01815, 0.01748, 0.017189, 0.016877, 0.016527, 0.015956, 0.015665, 0.015397, 0.01513, 0.014893, 0.014624]}}

这篇关于ML之xgboost：利用xgboost算法(sklearn+3Split+调参曲线)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)的文章就介绍到这儿，希望我们推荐的文章对大家有所帮助，也希望大家多多支持为之网！