r2

2024-07-01 08:50| 来源: 网络整理| 查看: 265

r2_score与accuracy_score都是sklearn.metrics中的计算准确率的函数，r2_score适用于回归问题，accuracy_score适用于分类问题，r2_score的输入可以是浮点数，而accuracy_score必须是整形。以下是我用回归模型得到的一个结果与label：

y_test>> >>array([37.6, 27.9, 22.6, 13.8, 35.2, 10.4, 23.9, 29. , 22.8, 23.2, 33.2, 19. , 20.3, 36.1, 24.4, 17.2, 17.9, 19.6, 19.7, 15. , 8.1, 23. , 44.8, 23.1, 32.2, 10.8, 23.1, 21.2, 22.2, 24.1, 17.3, 7. , 12.7, 17.8, 26.4, 19.6, 25.1, 8.3, 48.8, 34.9, 13.8, 14.4, 30.1, 12.7, 27.1, 24.8, 7. , 20.5, 21.5, 14. , 20.4, 22.2, 21.4, 13.5, 19.4, 24.7, 43.8, 14.1, 28.6, 19.7, 16.8, 23.2, 16.2, 41.3, 22.7, 8.3, 18.4, 24.7, 21.7, 20.6, 16.7, 22.1, 19.4, 27.5, 27.9, 30.1, 17.4, 15.4, 31. , 14.2, 19.6, 50. , 21.7, 11.7, 19.4, 13. , 17.5, 9.7, 20.3, 18.6, 50. , 19.6, 21.4, 18.4, 22.6, 25. , 15.6, 26.6, 22.4, 13.1, 23. , 24.5, 13.1, 50. , 8.8, 20.6, 12.1, 50. , 24.1, 16.1, 23.9, 24.3, 13.1, 30.3, 15.2, 13.8, 26.4, 16.6, 18.9, 17.6, 18.7, 33.4, 20.7, 17.1, 23.4, 26.5, 21.4, 21.5, 19.2, 50. , 50. , 23. , 10.5, 17.8, 10.9, 21. , 13.8, 10.5, 22.2, 30.5, 19.4, 15.6, 20.2, 19.3, 34.6, 50. , 24. , 18.7, 19.8, 22.5, 13.3, 50. , 11.8, 11. , 23.7, 35.4, 15.2, 24.4, 33.4, 31.6, 13.4, 34.9, 14.4, 35.4, 25.3, 18.3, 16.6]) y_pred>> >>array([42.8935 , 29.481709 , 22.72152 , 11.088902 , 36.746834 , 7.662948 , 25.651855 , 26.15493 , 22.378397 , 20.48603 , 31.907364 , 21.468454 , 19.578026 , 33.49744 , 24.67272 , 19.555578 , 11.753345 , 19.214586 , 18.709223 , 31.103544 , 15.263955 , 18.056026 , 46.764435 , 20.962772 , 28.798655 , 12.729027 , 24.205221 , 19.359875 , 23.571661 , 23.366013 , 14.890141 , 14.506024 , 12.925098 , 18.63654 , 23.8615 , 18.018988 , 24.455381 , 9.127385 , 44.779827 , 30.45871 , 14.542292 , 12.877257 , 24.352776 , 19.731707 , 24.305807 , 29.125399 , 6.7823567, 18.452114 , 19.873116 , 15.277843 , 20.32614 , 20.995363 , 23.444897 , 13.011057 , 15.695927 , 22.84157 , 40.82488 , 16.551765 , 28.262928 , 22.071127 , 20.19384 , 23.047424 , 15.8135805, 33.986725 , 20.49732 , 9.303558 , 17.742878 , 23.760605 , 22.339514 , 20.652113 , 17.204014 , 23.734058 , 19.895483 , 16.18355 , 27.209406 , 30.087381 , 23.134361 , 16.869543 , 27.65251 , 15.05091 , 20.549377 , 48.79272 , 19.200642 , 14.059941 , 19.002571 , 15.965145 , 19.86551 , 12.318311 , 18.471226 , 18.855583 , 45.140923 , 17.670074 , 19.20084 , 15.104687 , 21.808868 , 28.353735 , 15.893917 , 27.171299 , 23.067072 , 16.823427 , 20.375757 , 23.710732 , 14.467891 , 45.121735 , 6.5880733, 15.1293745, 11.600112 , 35.43435 , 20.81486 , 20.350136 , 26.358343 , 22.667938 , 12.507106 , 31.27376 , 17.66091 , 14.144321 , 27.607632 , 20.588734 , 19.055277 , 19.021236 , 21.626543 , 32.219128 , 23.16837 , 20.517244 , 22.340687 , 25.62456 , 18.89042 , 21.882483 , 19.37657 , 45.726486 , 45.302307 , 22.80424 , 10.673209 , 15.832766 , 11.838937 , 21.147217 , 15.90029 , 7.2176995, 22.684954 , 32.22356 , 18.45632 , 16.48581 , 18.660404 , 19.969202 , 31.537455 , 46.797897 , 27.281012 , 17.965696 , 20.106264 , 25.843502 , 13.627041 , 36.923767 , 11.221506 , 11.055304 , 23.62714 , 33.77936 , 15.634852 , 23.593822 , 31.300879 , 31.799702 , 13.880334 , 29.288174 , 18.79593 , 34.537792 , 24.082203 , 19.168953 , 17.133886 ], dtype=float32) print( r2_score(y_test, y_pred))>> >>0.8818477865859173

当直接把r2_score直接替换成accuracy_score时，会报错

ValueError Traceback (most recent call last) in 8 y_pred = model.predict(X_test) 9 ---> 10 print( accuracy_score(y_test, y_pred)) D:\Program Files\ANACONDA\lib\site-packages\sklearn\metrics\classification.py in accuracy_score(y_true, y_pred, normalize, sample_weight) 174 175 # Compute accuracy for each possible representation --> 176 y_type, y_true, y_pred = _check_targets(y_true, y_pred) 177 check_consistent_length(y_true, y_pred, sample_weight) 178 if y_type.startswith('multilabel'): D:\Program Files\ANACONDA\lib\site-packages\sklearn\metrics\classification.py in _check_targets(y_true, y_pred) 86 # No metrics support "multiclass-multioutput" format 87 if (y_type not in ["binary", "multiclass", "multilabel-indicator"]): ---> 88 raise ValueError("{0} is not supported".format(y_type)) 89 90 if y_type in ["binary", "multiclass"]: ValueError: continuous is not supported

这是由于accuracy_score只适用于分类问题，而分类的结果都是用int型表示。加入下列代码：

y_tests=[round(value) for value in y_test] predictions=[round(value) for value in y_pred] print( accuracy_score(y_tests, predictions))

结果：

>>0.20359281437125748

为啥结果相差如此之大呢？这是因为y_tests与predictions都四舍五入变成整形了

y_tests>> >>[38.0, 28.0, 23.0, 14.0, 35.0, 10.0, 24.0, 29.0, 23.0, 23.0, 33.0, 19.0, 20.0, 36.0, 24.0, 17.0, 18.0, 20.0, 20.0, 15.0, 8.0, 23.0, 45.0, 23.0, 32.0, 11.0, 23.0, 21.0, 22.0, 24.0, 17.0, 7.0, 13.0, 18.0, 26.0, 20.0, 25.0, 8.0, 49.0, 35.0, 14.0, 14.0, 30.0, 13.0, 27.0, 25.0, 7.0, 20.0, 22.0, 14.0, 20.0, 22.0, 21.0, 14.0, 19.0, 25.0, 44.0, 14.0, 29.0, 20.0, 17.0, 23.0, 16.0, 41.0, 23.0, 8.0, 18.0, 25.0, 22.0, 21.0, 17.0, 22.0, 19.0, 28.0, 28.0, 30.0, 17.0, 15.0, 31.0, 14.0, 20.0, 50.0, 22.0, 12.0, 19.0, 13.0, 18.0, 10.0, 20.0, 19.0, 50.0, 20.0, 21.0, 18.0, 23.0, 25.0, 16.0, 27.0, 22.0, 13.0, 23.0, 24.0, 13.0, 50.0, 9.0, 21.0, 12.0, 50.0, 24.0, 16.0, 24.0, 24.0, 13.0, 30.0, 15.0, 14.0, 26.0, 17.0, 19.0, 18.0, 19.0, 33.0, 21.0, 17.0, 23.0, 26.0, 21.0, 22.0, 19.0, 50.0, 50.0, 23.0, 10.0, 18.0, 11.0, 21.0, 14.0, 10.0, 22.0, 30.0, 19.0, 16.0, 20.0, 19.0, 35.0, 50.0, 24.0, 19.0, 20.0, 22.0, 13.0, 50.0, 12.0, 11.0, 24.0, 35.0, 15.0, 24.0, 33.0, 32.0, 13.0, 35.0, 14.0, 35.0, 25.0, 18.0, 17.0] predictions>> >>[43.0, 29.0, 23.0, 11.0, 37.0, 8.0, 26.0, 26.0, 22.0, 20.0, 32.0, 21.0, 20.0, 33.0, 25.0, 20.0, 12.0, 19.0, 19.0, 31.0, 15.0, 18.0, 47.0, 21.0, 29.0, 13.0, 24.0, 19.0, 24.0, 23.0, 15.0, 15.0, 13.0, 19.0, 24.0, 18.0, 24.0, 9.0, 45.0, 30.0, 15.0, 13.0, 24.0, 20.0, 24.0, 29.0, 7.0, 18.0, 20.0, 15.0, 20.0, 21.0, 23.0, 13.0, 16.0, 23.0, 41.0, 17.0, 28.0, 22.0, 20.0, 23.0, 16.0, 34.0, 20.0, 9.0, 18.0, 24.0, 22.0, 21.0, 17.0, 24.0, 20.0, 16.0, 27.0, 30.0, 23.0, 17.0, 28.0, 15.0, 21.0, 49.0, 19.0, 14.0, 19.0, 16.0, 20.0, 12.0, 18.0, 19.0, 45.0, 18.0, 19.0, 15.0, 22.0, 28.0, 16.0, 27.0, 23.0, 17.0, 20.0, 24.0, 14.0, 45.0, 7.0, 15.0, 12.0, 35.0, 21.0, 20.0, 26.0, 23.0, 13.0, 31.0, 18.0, 14.0, 28.0, 21.0, 19.0, 19.0, 22.0, 32.0, 23.0, 21.0, 22.0, 26.0, 19.0, 22.0, 19.0, 46.0, 45.0, 23.0, 11.0, 16.0, 12.0, 21.0, 16.0, 7.0, 23.0, 32.0, 18.0, 16.0, 19.0, 20.0, 32.0, 47.0, 27.0, 18.0, 20.0, 26.0, 14.0, 37.0, 11.0, 11.0, 24.0, 34.0, 16.0, 24.0, 31.0, 32.0, 14.0, 29.0, 19.0, 35.0, 24.0, 19.0, 17.0]

在处理分类问题上，把预测结果处理成整数型是很常见的，且分类的结果也只有正确和错误，accuracy_score就是分类准确率分数是指所有分类正确的百分比，而回归任务需要计算的则是你的结果与正确结果之间的差距，这就是r2_score函数的目的。 r2_score也能·作为分类问题的计算准确率，此时的效果与accuracy_score一样，使用方法是加一个关键字 average=‘micro’,当我使用另外一个分类模型的结果（为了防止篇幅过大，这里就不给出了）进行计算时：

print( f1_score(y_test, y_pred, average='micro') ) print(accuracy_score(y_test, y_pred)) >>0.9473684210526315 0.9473684210526315

【本文地址】

公司简介

联系我们