问题描述
我正在研究应在sklearn中的gridsearchcv函数中传递的自定义估算器。我现在创建了估算器，但是遇到内存错误。在下面的代码中，您将看到一些常量，例如'KxRange [0]'或数组，例如keep_rate。它们只是预先定义的，其中包含一些随机值。 这是我的代码：
# 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,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,y):
# calculate the MSE
return np.dot(y - self.predict(X),y - self.predict(X))/len(X)
以下类似于“主要”功能
# initiliaze estimator
t = MyEstimator()
# parameter grid
# tau
param_grid = {'tau': [100,200],\
# K
'K1': [K1Range[0],K1Range[1]],'K2' : [K2Range[0],K2Range[1]],'K3': [K3Range[0],K3Range[1]],'K4' : [K4Range[0],K4Range[1]],'K5' : [K5Range[0],K5Range[1]],'K6' : [K6Range[0],K6Range[1]],'K7' : [K7Range[0],K7Range[1]],'K8': [K8Range[0],K8Range[1]],'K9': [K9Range[0],K9Range[1]],\
# S
'S1': [1,100],'S2': [1,'S3': [1,'S4': [1,'S5': [1,'S6': [1,'S7': [1,'S8': [1,'S9': [1,\
# alpha
'alpha1': [0.1,0.5],'alpha2': [0.1,'alpha3': [0.1,'alpha4': [0.1,'alpha5': [0.1,'alpha6': [0.1,'alpha7': [0.1,'alpha8': [0.1,'alpha9': [0.1,\
# beta
'beta1': [100,'beta2': [100,'beta3': [100,'beta4': [100,'beta5': [100,'beta6': [100,'beta7': [100,'beta8': [100,'beta9': [100,200]}
#
clf = GridSearchCV(t,param_grid)
clf.fit(X_media,actual_sales)
#clf.predict(X_media)
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,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:
谁能告诉我如何解决此错误？还是我的代码有问题？谢谢！
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）