Python 尝试使用Gridsearchcv时出现内存错误

我正在开发一个定制的估计器，它应该在sklearn的gridsearchcv函数中传递。我现在已经创建了估计器，但是遇到了内存错误。在下面的代码中，您将看到一些常量，如“KxRange[0]”或数组，如retain_rate。它们只是用一些随机值预先定义的。 这是我的密码：

# sklearn grid search
from sklearn.model_selection import GridSearchCV
# import the base estimator
from sklearn.base import BaseEstimator, RegressorMixin
# define my own estimator
class MyEstimator(BaseEstimator,RegressorMixin):
    # define constructor
    #  possible tau: int/float
    #  other parameters: array of int/floats, length 9
    def __init__(self, tau=0, \
                       K1=K1Range[0], K2=K2Range[0], K3=K3Range[0], K4=K4Range[0], K5=K5Range[0], K6=K6Range[0], K7=K7Range[0], K8=K8Range[0], K9=K9Range[0], \
                       S1=0, S2=0, S3=0, S4=0, S5=0, S6=0, S7=0, S8=0, S9=0, \
                       alpha1=1, alpha2=1, alpha3=1, alpha4=1, alpha5=1, alpha6=1, alpha7=1, alpha8=1, alpha9=1, \
                       beta1=1, beta2=1, beta3=1, beta4=1, beta5=1, beta6=1, beta7=1, beta8=1, beta9=1):
        # initialize parameters
        self.tau = tau
        self.K1 = K1
        self.K2 = K2
        self.K3 = K3
        self.K4 = K4
        self.K5 = K5
        self.K6 = K6
        self.K7 = K7
        self.K8 = K8
        self.K9 = K9
        self.S1 = S1
        self.S2 = S2
        self.S3 = S3
        self.S4 = S4
        self.S5 = S5
        self.S6 = S6
        self.S7 = S7
        self.S8 = S8
        self.S9 = S9
        self.alpha1 = alpha1
        self.alpha2 = alpha2
        self.alpha3 = alpha3
        self.alpha4 = alpha4
        self.alpha5 = alpha5
        self.alpha6 = alpha6
        self.alpha7 = alpha7
        self.alpha8 = alpha8
        self.alpha9 = alpha9
        self.beta1 = beta1
        self.beta2 = beta2
        self.beta3 = beta3
        self.beta4 = beta4
        self.beta5 = beta5
        self.beta6 = beta6
        self.beta7 = beta7
        self.beta8 = beta8
        self.beta9 = beta9
    # to fit the model
    def fit(self, X,y=None):
        # define the mu vector
        self.mu_ = np.ones((N))
        # define lag weights
        lag_weights = np.ones((max_lag))
        # define retain_rate
        retain_rate = np.array([alpha1, alpha2, alpha3, alpha4, alpha5, alpha6, alpha7, alpha8, alpha9])
        # define cum_effect, set to a random value
        cum_effect = 1
        # define cum_effects_hill
        cum_effects_hill = np.ones((N, num_media))
        # parameter transformation
        for nn in range(N):
            for m in range(num_media):
                for l in range(max_lag): 
                    lag_weights[l] = retain_rate[m]**l
                cum_effect = Adstock(X[nn][m], lag_weights)
            cum_effects_hill[nn][m] = Hill(cum_effect, ec[m], slope[m])
            self.mu_[nn] = tau + np.dot(cum_effects_hill[nn], beta_medias)
        return self
    # the predict function
    def predict(self, X, y=None):
        # try to get the mu_ argument. If it does not exist, we throw an error
        try:
            getattr(self, "mu_")
        except AttributeError:
            raise RuntimeError("You must train classifer before predicting data!")
        return self.mu_
    # the score function
    def score(self, X, y):
        # calculate the MSE
        return np.dot(y - self.predict(X), y - self.predict(X))/len(X)   

以下类似于“main”函数

这是错误消息：

MemoryError                               Traceback (most recent call last)
<ipython-input-22-de0388db8453> in <module>
     14 #
     15 clf = GridSearchCV(t, param_grid)
---> 16 clf.fit(X_media, actual_sales)
     17 #clf.predict(X_media)

~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
    734                 return results
    735 
--> 736             self._run_search(evaluate_candidates)
    737 
    738         # For multi-metric evaluation, store the best_index_, best_params_ and

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
   1186     def _run_search(self, evaluate_candidates):
   1187         """Search all candidates in param_grid"""
-> 1188         evaluate_candidates(ParameterGrid(self.param_grid))
   1189 
   1190 

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
    698 
    699             def evaluate_candidates(candidate_params):
--> 700                 candidate_params = list(candidate_params)
    701                 n_candidates = len(candidate_params)
    702 

MemoryError: 

MemoryError回溯（最近一次调用）
在里面
14 #
15 clf=网格搜索CV（t，参数网格）
--->16 clf.fit（X_媒体，实际销售额）
17#clf.预测（X#U媒体）
内部文件中的~\Anaconda3\lib\site packages\sklearn\utils\validation.py（*args，**kwargs）
71未来警告）
72 kwargs.update（{k:arg代表k，arg在zip中（sig.parameters，args）}）
--->73返回f（**kwargs）
74返回内部\u f
75
~\Anaconda3\lib\site packages\sklearn\model\u selection\\u search.py in fit（self、X、y、groups、**fit\u参数）
734返回结果
735
-->736自我评估-运行搜索（评估候选人）
737
738#对于多指标评估，存储最佳指数、最佳参数和
~\Anaconda3\lib\site packages\sklearn\model\u selection\u search.py in\u run\u search（self，evaluate\u候选者）
1186定义-运行-搜索（自我评估-候选人）：
1187“搜索参数网格中的所有候选项”
->1188评估候选参数（参数网格（self.param网格））
1189
1190
~\Anaconda3\lib\site packages\sklearn\model\u selection\\u search.py in evaluate\u候选者（候选者参数）
698
699 def评估候选人（候选人参数）：
-->700候选参数=列表（候选参数）
701 n_候选者=len（候选者参数）
702
记忆错误：

---

有人能告诉我如何修复这个错误吗？或者我的代码有问题吗？谢谢

回溯显示网格搜索在尝试生成候选列表（即网格）时已耗尽内存。显然，您有37个参数，每个参数都有两个可能的值，因此候选参数的数量是

2^（37）

，超过1370亿。无论如何，你可能真的不想尝试那么多候选人，所以也许

随机搜索CV

更合适？

谢谢你，本。我现在正在尝试做

RandomizedSearchCV

MemoryError                               Traceback (most recent call last)
<ipython-input-22-de0388db8453> in <module>
     14 #
     15 clf = GridSearchCV(t, param_grid)
---> 16 clf.fit(X_media, actual_sales)
     17 #clf.predict(X_media)

~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
    734                 return results
    735 
--> 736             self._run_search(evaluate_candidates)
    737 
    738         # For multi-metric evaluation, store the best_index_, best_params_ and

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
   1186     def _run_search(self, evaluate_candidates):
   1187         """Search all candidates in param_grid"""
-> 1188         evaluate_candidates(ParameterGrid(self.param_grid))
   1189 
   1190 

~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
    698 
    699             def evaluate_candidates(candidate_params):
--> 700                 candidate_params = list(candidate_params)
    701                 n_candidates = len(candidate_params)
    702 

MemoryError: