问题描述
我正在处理数据集,必须做出两个预测,即y的2列,每列也是多类的。 因此,我将XGBoost与MultiOutput Classfier结合使用,并对其进行调整,以使用Grid Search CV。
xgb_clf = xgb.XGBClassifier(learning_rate=0.1,n_estimators=3000,max_depth=3,min_child_weight=1,subsample=0.8,colsample_bytree=0.8,objective='multi:softmax',nthread=4,num_class=9,seed=27
)
model = MultiOutputClassifier(estimator=xgb_clf)
param_test1 = { 'estimator__max_depth':[3],'estimator__min_child_weight':[4]}
gsearch1 = GridSearchCV(estimator =model,param_grid = param_test1,scoring='roc_auc',n_jobs=4,iid=False,cv=5)
gsearch1.fit(X_train_split,y_train_split)
gsearch1.grid_scores_,gsearch1.best_params_,gsearch1.best_score_
但是当我这样做时,我会得到一个错误
_RemoteTraceback Traceback (most recent call last)
_RemoteTraceback:
"""
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/joblib/externals/loky/process_executor.py",line 431,in _process_worker
r = call_item()
File "/usr/local/lib/python3.6/dist-packages/joblib/externals/loky/process_executor.py",line 285,in __call__
return self.fn(*self.args,**self.kwargs)
File "/usr/local/lib/python3.6/dist-packages/joblib/_parallel_backends.py",line 595,in __call__
return self.func(*args,**kwargs)
File "/usr/local/lib/python3.6/dist-packages/joblib/parallel.py",line 253,in __call__
for func,args,kwargs in self.items]
File "/usr/local/lib/python3.6/dist-packages/joblib/parallel.py",in <listcomp>
for func,kwargs in self.items]
File "/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py",line 544,in _fit_and_score
test_scores = _score(estimator,X_test,y_test,scorer)
File "/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_validation.py",line 591,in _score
scores = scorer(estimator,y_test)
File "/usr/local/lib/python3.6/dist-packages/sklearn/metrics/_scorer.py",line 87,in __call__
*args,**kwargs)
File "/usr/local/lib/python3.6/dist-packages/sklearn/metrics/_scorer.py",line 300,in _score
raise ValueError("{0} format is not supported".format(y_type))
ValueError: multiclass-multioutput format is not supported
"""
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-42-e53fdaaedf6b> in <module>()
5 gsearch1 = GridSearchCV(estimator =model,6 param_grid = param_test1,cv=5)
----> 7 gsearch1.fit(X_train_split,y_train_split)
8 gsearch1.grid_scores_,gsearch1.best_score_
7 frames
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_search.py in fit(self,X,y,groups,**fit_params)
708 return results
709
--> 710 self._run_search(evaluate_candidates)
711
712 # For multi-metric evaluation,store the best_index_,best_params_ and
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_search.py in _run_search(self,evaluate_candidates)
1149 def _run_search(self,evaluate_candidates):
1150 """Search all candidates in param_grid"""
-> 1151 evaluate_candidates(ParameterGrid(self.param_grid))
1152
1153
/usr/local/lib/python3.6/dist-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
687 for parameters,(train,test)
688 in product(candidate_params,--> 689 cv.split(X,groups)))
690
691 if len(out) < 1:
/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in __call__(self,iterable)
1040
1041 with self._backend.retrieval_context():
-> 1042 self.retrieve()
1043 # Make sure that we get a last message telling us we are done
1044 elapsed_time = time.time() - self._start_time
/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in retrieve(self)
919 try:
920 if getattr(self._backend,'supports_timeout',False):
--> 921 self._output.extend(job.get(timeout=self.timeout))
922 else:
923 self._output.extend(job.get())
/usr/local/lib/python3.6/dist-packages/joblib/_parallel_backends.py in wrap_future_result(future,timeout)
540 AsyncResults.get from multiprocessing."""
541 try:
--> 542 return future.result(timeout=timeout)
543 except CfTimeoutError as e:
544 raise TimeoutError from e
/usr/lib/python3.6/concurrent/futures/_base.py in result(self,timeout)
430 raise CancelledError()
431 elif self._state == FINISHED:
--> 432 return self.__get_result()
433 else:
434 raise TimeoutError()
/usr/lib/python3.6/concurrent/futures/_base.py in __get_result(self)
382 def __get_result(self):
383 if self._exception:
--> 384 raise self._exception
385 else:
386 return self._result
ValueError: multiclass-multioutput format is not supported
我认为该错误是由于我使用roc_auc作为计分方法而发生的,但我不知道如何解决。我应该使用其他计分方法吗?
解决方法
是的,您认为正确。问题来自ROC AUC分数对二进制分类情况有效。相反,您可以使用所有课程的ROC AUC分数的平均值。
# from https://stackoverflow.com/questions/39685740/calculate-sklearn-roc-auc-score-for-multi-class
from sklearn.metrics import roc_auc_score
import numpy as np
def roc_auc_score_multiclass(actual_class,pred_class,average = "macro"):
#creating a set of all the unique classes using the actual class list
unique_class = set(actual_class)
roc_auc_dict = {}
for per_class in unique_class:
#creating a list of all the classes except the current class
other_class = [x for x in unique_class if x != per_class]
#marking the current class as 1 and all other classes as 0
new_actual_class = [0 if x in other_class else 1 for x in actual_class]
new_pred_class = [0 if x in other_class else 1 for x in pred_class]
#using the sklearn metrics method to calculate the roc_auc_score
roc_auc = roc_auc_score(new_actual_class,new_pred_class,average = average)
roc_auc_dict[per_class] = roc_auc
return np.mean([x for x in roc_auc_dict.values()])
使用此功能,您可以获得每个班级与其他班级的ROC AUC得分。然后,您可以取这些值的平均值并将其用作计分器。您可能需要使用make_scorer
函数(https://scikit-learn.org/stable/modules/generated/sklearn.metrics.make_scorer.html)将函数转换为得分手对象。