使用 scikit-optimize 调整管道中的自定义转换器

如何解决使用 scikit-optimize 调整管道中的自定义转换器

我正在实现一个自定义转换器以在我的管道中使用，它在初始化时使用一个参数 myClusters（它现在称为 K-Means Clustering，但只是一个测试类） :

class KMeansClustering:
    
    def __init__(self,myClusters = None):
        self.myClusters = myClusters
    
    def fit(self,X,y = None):
        return self
    
    def transform(self,y = None):
        
        return X.copy()

管道本身通过skicit-optimize进行调整：

from skopt import BayesSearchCV
from sklearn.pipeline import Pipeline
from sklearn import tree

opt = BayesSearchCV(
    Pipeline([
        ('KMeans',KMeansClustering()),('DecTree',tree.DecisionTreeClassifier(random_state = 0))
             ]),{'KMeans__myClusters' : myClusters,'DecTree__max_depth': list(range(1,41)),'DecTree__max_features': list(range(1,93)),'DecTree__min_samples_leaf': list(range(1,1001)),'DecTree__min_samples_split': list(range(1,},cv = 10,random_state=0,n_jobs = -1,refit = False
)

现在调用 opt.fit(X,y) 会出现以下错误：

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-26-c7a7ae6901e0> in <module>
----> 1 opt.fit(X,y)

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\searchcv.py in fit(self,y,groups,callback)
    690                 n_points_adjusted = min(n_iter,n_points)
    691 
--> 692                 optim_result = self._step(
    693                     X,search_space,optimizer,694                     groups=groups,n_points=n_points_adjusted

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\searchcv.py in _step(self,n_points)
    563 
    564         # get parameter values to evaluate
--> 565         params = optimizer.ask(n_points=n_points)
    566 
    567         # convert parameters to python native types

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\optimizer\optimizer.py in ask(self,n_points,strategy)
    393         X = []
    394         for i in range(n_points):
--> 395             x = opt.ask()
    396             X.append(x)
    397 

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\optimizer\optimizer.py in ask(self,strategy)
    365         """
    366         if n_points is None:
--> 367             return self._ask()
    368 
    369         supported_strategies = ["cl_min","cl_mean","cl_max"]

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\optimizer\optimizer.py in _ask(self)
    432             # our random state.
    433             if self._initial_samples is None:
--> 434                 return self.space.rvs(random_state=self.rng)[0]
    435             else:
    436                 # The samples are evaluated starting form initial_samples[0]

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\space.py in rvs(self,n_samples,random_state)
    892 
    893         for dim in self.dimensions:
--> 894             columns.append(dim.rvs(n_samples=n_samples,random_state=rng))
    895 
    896         # Transpose

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\space.py in rvs(self,random_state)
    690             return self.inverse_transform([(choices)])
    691         elif self.transform_ == "normalize":
--> 692             return self.inverse_transform(list(choices))
    693         else:
    694             return [self.categories[c] for c in choices]

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\space.py in inverse_transform(self,Xt)
    677         # The concatenation of all transformed dimensions makes Xt to be
    678         # of type float,hence the required cast back to int.
--> 679         inv_transform = super(Categorical,self).inverse_transform(Xt)
    680         if isinstance(inv_transform,list):
    681             inv_transform = np.array(inv_transform)

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\space.py in inverse_transform(self,Xt)
    166            original space.
    167         """
--> 168         return self.transformer.inverse_transform(Xt)
    169 
    170     def set_transformer(self):

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\transformers.py in inverse_transform(self,X)
    307     def inverse_transform(self,X):
    308         for transformer in self.transformers[::-1]:
--> 309             X = transformer.inverse_transform(X)
    310         return X

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\transformers.py in inverse_transform(self,Xt)
    214         else:
    215             Xt = np.asarray(Xt)
--> 216         return [
    217             self.inverse_mapping_[int(np.round(i))] for i in Xt
    218         ]

D:\Program Files (x86)\Anaconda\lib\site-packages\skopt\space\transformers.py in <listcomp>(.0)
    215             Xt = np.asarray(Xt)
    216         return [
--> 217             self.inverse_mapping_[int(np.round(i))] for i in Xt
    218         ]
    219 

KeyError: 15

我不确定如何处理这个问题，但是，如果变量 myClusters 从转换器中移除，并且在管道中，则不会抛出任何错误。