Python Xgboost未使用校准分类器运行
我正在尝试使用校准的分类器运行XGboost,下面是我遇到错误的代码片段:Python Xgboost未使用校准分类器运行,python,machine-learning,xgboost,Python,Machine Learning,Xgboost,我正在尝试使用校准的分类器运行XGboost,下面是我遇到错误的代码片段: from sklearn.calibration import CalibratedClassifierCV from xgboost import XGBClassifier import numpy as np x_train =np.array([1,2,2,3,4,5,6,3,4,10,]).reshape(-1,1) y_train = np.array([1,1,1,1,1,3,3,3,3,3]) x_c
from sklearn.calibration import CalibratedClassifierCV
from xgboost import XGBClassifier
import numpy as np
x_train =np.array([1,2,2,3,4,5,6,3,4,10,]).reshape(-1,1)
y_train = np.array([1,1,1,1,1,3,3,3,3,3])
x_cfl=XGBClassifier(n_estimators=1)
x_cfl.fit(x_train,y_train)
sig_clf = CalibratedClassifierCV(x_cfl, method="sigmoid")
sig_clf.fit(x_train, y_train)
错误:
TypeError: predict_proba() got an unexpected keyword argument 'X'"
完整跟踪:
TypeError Traceback (most recent call last)
<ipython-input-48-08dd0b4ae8aa> in <module>
----> 1 sig_clf.fit(x_train, y_train)
~/anaconda3/lib/python3.8/site-packages/sklearn/calibration.py in fit(self, X, y, sample_weight)
309 parallel = Parallel(n_jobs=self.n_jobs)
310
--> 311 self.calibrated_classifiers_ = parallel(
312 delayed(_fit_classifier_calibrator_pair)(
313 clone(base_estimator), X, y, train=train, test=test,
~/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
1039 # remaining jobs.
1040 self._iterating = False
-> 1041 if self.dispatch_one_batch(iterator):
1042 self._iterating = self._original_iterator is not None
1043
~/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
857 return False
858 else:
--> 859 self._dispatch(tasks)
860 return True
861
~/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in _dispatch(self, batch)
775 with self._lock:
776 job_idx = len(self._jobs)
--> 777 job = self._backend.apply_async(batch, callback=cb)
778 # A job can complete so quickly than its callback is
779 # called before we get here, causing self._jobs to
~/anaconda3/lib/python3.8/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
206 def apply_async(self, func, callback=None):
207 """Schedule a func to be run"""
--> 208 result = ImmediateResult(func)
209 if callback:
210 callback(result)
~/anaconda3/lib/python3.8/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
570 # Don't delay the application, to avoid keeping the input
571 # arguments in memory
--> 572 self.results = batch()
573
574 def get(self):
~/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in <listcomp>(.0)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/anaconda3/lib/python3.8/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
220 def __call__(self, *args, **kwargs):
221 with config_context(**self.config):
--> 222 return self.function(*args, **kwargs)
~/anaconda3/lib/python3.8/site-packages/sklearn/calibration.py in _fit_classifier_calibrator_pair(estimator, X, y, train, test, supports_sw, method, classes, sample_weight)
443 n_classes = len(classes)
444 pred_method = _get_prediction_method(estimator)
--> 445 predictions = _compute_predictions(pred_method, X[test], n_classes)
446
447 sw = None if sample_weight is None else sample_weight[test]
~/anaconda3/lib/python3.8/site-packages/sklearn/calibration.py in _compute_predictions(pred_method, X, n_classes)
499 (X.shape[0], 1).
500 """
--> 501 predictions = pred_method(X=X)
502 if hasattr(pred_method, '__name__'):
503 method_name = pred_method.__name__
TypeError: predict_proba() got an unexpected keyword argument 'X'
输出:
CalibratedClassifierCV(base_estimator=LGBMClassifier(n_estimators=1))
我的Xgboost安装有问题吗??我使用conda进行安装,我记得我昨天卸载了xgboost并再次安装了它
我的xgboost版本:
1.3.0
现在已经修复了,好像scikit learn=0.24中有一个bug
我降级到0.22.2.post1,它被修复了 我认为问题来自XGBoost。 这里解释如下: XGBoost已定义:
预测概率(自我、数据等)
而不是:
预测概率(self,X,…
由于sklearn 0.24调用了clf.predict_proba(X=X)
,因此引发了一个异常
下面是一个在不更改包版本的情况下解决问题的方法:创建一个继承
XGBoostClassifier
的类,用正确的参数名覆盖predict\u proba
,并调用super()
请接受您自己的答案,以便它在将来对其他人有明显的帮助。如果您已经识别了这个bug,那么scikit learn的github是否存在问题?是的,在PR线程之后出现了一个bug,很好,看起来xgboost版本>=1.3.2(sklearn any版本)的修复程序。我在catboost(0.24.4)中得到了完全相同的错误:TypeError:predict_proba()得到一个意外的关键字参数“X”。你知道如何修复它吗?@6761646f6e你有从XGBoostClassifier继承的新类的模板吗?您好,我从XGBoostClassifier继承的新类包含:def predict_proba(self,X,…):return super(CustomXGBClassifier,self)。predict_proba(X,…)
。我还注意到kwargs
属性存在问题,如果需要sklearn.base.clone
模型,则需要覆盖get_params
。
CalibratedClassifierCV(base_estimator=LGBMClassifier(n_estimators=1))