python - Sklearn.model_selection GridsearchCV ValueError : C <= 0

Question

我正在尝试使用 sklearn.model_selection 中的 GridSearhCV 进行参数调整

我不知何故不断收到 ValueError: C <= 0。我认为这与网格搜索的 fit 方法有关。如果有人可以提供帮助，我会很高兴。

尝试在sklearn中对SVR模型进行网格搜索

这是我的代码:

print(x_train.shape,y_train.shape, x_train.dtype,y_train.dtype)
#output: (3023, 1) (3023, 14) float64 float64

#svr model:

from sklearn.svm import SVR
reg = SVR(kernel = 'linear')
reg.fit(x_train,y_train)

#output: SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, 
gamma='auto', kernel='linear', max_iter=-1, shrinking=True, tol=0.001, 
verbose=False)


#GridSearch

from sklearn.model_selection import GridSearchCV
parameters = [{'C': [0,1,5], 'kernel':['linear']},
             {'C': [0,1,5], 'kernel':['rbf'], 'gamma':[0.01, 0.05]}]

gs = GridSearchCV(estimator = reg, param_grid = parameters, scoring = 
'accuracy',cv =10)
gs = gs.fit(x_train, y_train)


Error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-120-cf037d4a6af8> in <module>()
      1 gs = GridSearchCV(estimator = reg, param_grid = parameters, scoring = 'accuracy',cv =10)
----> 2 gs = gs.fit(x_train, y_train)

C:\Program Files\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
    637                                   error_score=self.error_score)
    638           for parameters, (train, test) in product(candidate_params,
--> 639                                                    cv.split(X, y, groups)))
    640 
    641         # if one choose to see train score, "out" will contain train score info

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
    777             # was dispatched. In particular this covers the edge
    778             # case of Parallel used with an exhausted iterator.
--> 779             while self.dispatch_one_batch(iterator):
    780                 self._iterating = True
    781             else:

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
    623                 return False
    624             else:
--> 625                 self._dispatch(tasks)
    626                 return True
    627 

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
    586         dispatch_timestamp = time.time()
    587         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588         job = self._backend.apply_async(batch, callback=cb)
    589         self._jobs.append(job)
    590 

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
    109     def apply_async(self, func, callback=None):
    110         """Schedule a func to be run"""
--> 111         result = ImmediateResult(func)
    112         if callback:
    113             callback(result)

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
    330         # Don't delay the application, to avoid keeping the input
    331         # arguments in memory
--> 332         self.results = batch()
    333 
    334     def get(self):

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

C:\Program Files\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

C:\Program Files\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
    456             estimator.fit(X_train, **fit_params)
    457         else:
--> 458             estimator.fit(X_train, y_train, **fit_params)
    459 
    460     except Exception as e:

C:\Program Files\Anaconda3\lib\site-packages\sklearn\svm\base.py in fit(self, X, y, sample_weight)
    185 
    186         seed = rnd.randint(np.iinfo('i').max)
--> 187         fit(X, y, sample_weight, solver_type, kernel, random_seed=seed)
    188         # see comment on the other call to np.iinfo in this file
    189 

C:\Program Files\Anaconda3\lib\site-packages\sklearn\svm\base.py in _dense_fit(self, X, y, sample_weight, solver_type, kernel, random_seed)
    252                 cache_size=self.cache_size, coef0=self.coef0,
    253                 gamma=self._gamma, epsilon=self.epsilon,
--> 254                 max_iter=self.max_iter, random_seed=random_seed)
    255 
    256         self._warn_from_fit_status()

sklearn\svm\libsvm.pyx in sklearn.svm.libsvm.fit()

ValueError: C <= 0

Answer 1

将参数网格中的 C 值更改为始终 > 0。当前参数网格为

parameters = [{'C': [0,1,5], 'kernel':['linear']},
             {'C': [0,1,5], 'kernel':['rbf'], 'gamma':[0.01, 0.05]}]

其中一种可能性是 C=0。因此，当网格搜索去拟合 C=0 的 SVR 模型时，SVR 会提示 C 不能 <=0(小于或等于 0)。

因此将其更改为:

parameters = [{'C': [0.001, 0.1 ,1,5], 'kernel':['linear']},
             {'C': [0.001, 0.1, 1,5], 'kernel':['rbf'], 'gamma':[0.01, 0.05]}]

您可以查看这些示例来检查 C 的搜索是如何完成的:

• http://scikit-learn.org/stable/auto_examples/svm/plot_rbf_parameters.html#sphx-glr-auto-examples-svm-plot-rbf-parameters-py
• http://scikit-learn.org/stable/auto_examples/exercises/plot_cv_digits.html#sphx-glr-auto-examples-exercises-plot-cv-digits-py

评论更新:

您正在使用scoring='accuracy'。准确率主要是针对分类任务定义的。对于回归模型，准确性不是一个有效的指标。请检查此页面的有效指标:-

• http://scikit-learn.org/stable/modules/model_evaluation.html#common-cases-predefined-values

您可以从网格搜索中删除评分参数，如下所示:

gs = GridSearchCV(estimator = reg, param_grid = parameters,cv =10)

在这种情况下，将使用估计器的默认评分方法(本例中为 SVR)，即 R 平方分数(最常用于回归)

或者您可以将评分设置为我上面链接的页面上的任何有效回归指标。像这样:

gs = GridSearchCV(estimator = reg, param_grid = parameters,
                  scoring='neg_mean_squared_error', cv =10)