Python 如何用多输出分类器实现网格搜索cv?
我正在处理一个数据集,必须做出两个预测,即2列y,每列也是多类的。 因此,我将XGBoost与多输出分类器一起使用,为了对其进行调优,我想使用Grid Search CVPython 如何用多输出分类器实现网格搜索cv?,python,machine-learning,scikit-learn,xgboost,gridsearchcv,Python,Machine Learning,Scikit Learn,Xgboost,Gridsearchcv,我正在处理一个数据集,必须做出两个预测,即2列y,每列也是多类的。 因此,我将XGBoost与多输出分类器一起使用,为了对其进行调优,我想使用Grid Search CV xgb_clf = xgb.XGBClassifier(learning_rate=0.1, n_estimators=3000, max_depth=3, min_child_weight=1, s
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_
但是当我这样做的时候,我得到了一个错误
_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", line 253, in <listcomp>
for func, args, 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, X_test, 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, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
----> 7 gsearch1.fit(X_train_split,y_train_split)
8 gsearch1.grid_scores_, gsearch1.best_params_, 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, y, 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
\u远程回溯回溯(最近一次呼叫最后一次)
_远程回溯:
"""
回溯(最近一次呼叫最后一次):
文件“/usr/local/lib/python3.6/dist packages/joblib/externals/loky/process\u executor.py”,第431行,in\u process\u worker
r=调用_项()
文件“/usr/local/lib/python3.6/dist packages/joblib/externals/loky/process_executor.py”,第285行,在调用中__
返回self.fn(*self.args,**self.kwargs)
文件“/usr/local/lib/python3.6/dist packages/joblib/_parallel_backends.py”,第595行,在调用中__
返回self.func(*args,**kwargs)
文件“/usr/local/lib/python3.6/dist-packages/joblib/parallel.py”,第253行,在调用中__
对于self.items中的func、args、kwargs]
文件“/usr/local/lib/python3.6/dist-packages/joblb/parallel.py”,第253行,在
对于self.items中的func、args、kwargs]
文件“/usr/local/lib/python3.6/dist-packages/sklearn/model\u-selection/\u-validation.py”,第544行,在“fit”和“score”中
测试分数=_分数(估计员、X_测试、y_测试、计分员)
文件“/usr/local/lib/python3.6/dist-packages/sklearn/model\u-selection/\u-validation.py”,第591行,in\u-score
分数=记分员(估计员、X_检验、y_检验)
文件“/usr/local/lib/python3.6/dist packages/sklearn/metrics/_scorer.py”,第87行,在调用中__
*args,**kwargs)
文件“/usr/local/lib/python3.6/dist packages/sklearn/metrics/_scorer.py”,第300行,in_score
raise VALUERROR(“{0}格式不受支持”。格式(y_类型))
ValueError:不支持多类多输出格式
"""
上述异常是以下异常的直接原因:
ValueError回溯(最近一次调用上次)
在()
5 gsearch1=GridSearchCV(估计器=模型,
6参数网格=参数测试1,评分='roc_auc',n_作业=4,iid=假,cv=5)
---->7 G搜索1.安装(X\U列\U拆分,y\U列\U拆分)
8 gsearch1.grid_分数,gsearch1.best_参数,gsearch1.best_分数_
7帧
/usr/local/lib/python3.6/dist-packages/sklearn/model\u selection//u search.py in fit(self、X、y、groups、**fit\u参数)
708返回结果
709
-->710自我评估运行搜索(评估候选人)
711
712#对于多指标评估,存储最佳指数、最佳参数和
/usr/local/lib/python3.6/dist-packages/sklearn/model\u selection//u search.py in\u run\u search(自我评估候选人)
1149定义-运行-搜索(自我评估-候选人):
1150“搜索参数网格中的所有候选项”
->1151评估候选参数(参数网格(self.param网格))
1152
1153
/usr/local/lib/python3.6/dist-packages/sklearn/model\u selection//u search.py用于评估候选对象(候选参数)
687参数(列车、试验)
688英寸产品(候选参数,
-->689等速分割(X、y、组)
690
691如果len(out)<1:
/usr/local/lib/python3.6/dist-packages/joblb/parallel.py in_u_调用(self,iterable)
1040
1041带有self.\u backend.retrieval\u context():
->1042 self.retrieve()
1043#确保我们收到最后一条消息,告诉我们我们完成了
1044已用时间=time.time()-self.\u开始时间
/检索中的usr/local/lib/python3.6/dist-packages/joblb/parallel.py(self)
919试试:
920如果getattr(self.\u后端“支持\u超时”,则为False):
-->921 self.\u output.extend(job.get(timeout=self.timeout))
922其他:
923 self.\u output.extend(job.get())
/usr/local/lib/python3.6/dist-packages/joblib//\u parallel\u backends.py in wrap\u future\u结果(future,超时)
540 AsyncResults.get from multiprocessing。”“”
541尝试:
-->542返回future.result(超时=超时)
543除CFTIMEOUTER错误为e外:
544从e提升超时错误
/usr/lib/python3.6/concurrent/futures//\u base.py输入结果(self,超时)
430升高取消错误()
431 elif self.\u state==完成:
-->432返回self.\u获取\u结果()
433其他:
434 raise TimeoutError()
/usr/lib/python3.6/concurrent/futures//u base.py in\u\u get\u result(self)
382定义获取结果(自身):
383如果自身存在例外情况:
-->384升起自我。\u异常
385其他:
386返回自我。\u结果
ValueError:不支持多类多输出格式
我认为错误发生在我使用roc_auc作为评分方法时,但我不知道如何修复它。我应该使用其他评分方法吗?是的,你认为正确。问题在于roc auc评分对二元分类有效。相反,你可以使用所有类别的roc auc评分平均值
# 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()])
使用此函数,您可以获得每个类相对于所有其他类的ROC AUC分数。然后您可以取该值的平均值并将其用作计分器。您可能需要使用
make_scorer
函数()将您的函数转换为计分器对象.请编辑并为您的问题添加更多上下文:您使用的是哪种技术、平台和运行时环境,您正在解决的问题是什么。此外,请指定您试图实现的目标。我的问题不是多类。我的问题是我有多个输出,即我的模型预测了y的两列。因此,我需要评估te them.yep,因此提供的函数执行您想要的操作,它接收2个数组并计算ROC AUC,并计算所有ROC AUC的平均值/