python - 值错误 : Unknown label type: 'continuous

Question

我正在尝试执行网格搜索以优化我的参数我的代码是:

from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC



parameters = [{'kernel':['rbf'], 'gamma' :[1e-2, 1e-3, 1e-4 ,1e-5], 
          'C': [1, 10, 100, 1000]},
          {'kernel': ['poly'], 'C': [1, 10, 100, 1000], 'degree':[1,2,3,4]}]  

clf = GridSearchCV (SVC(C=1), parameters, cv=5, scoring='f1_macro')
clf.fit(X_train, y_train)

我的 X_train, y_train 是 float ，它们是:

x_train = [[3.30049159],[2.25226244],[1.44078451] ...,[5.63927925],[5.431458],[4.35674369]]

y_train = [[0.2681013],[0.03454225],[0.02062136]...,[0.21827915],[0.28768273,[0.27969417]]

我认为错误可能是我使用的是 float ，如果是这种情况，可能只能将整数传递到分类器中，如何解决？我的完整回溯错误消息是:

ValueError                                Traceback (most recent call last)
<ipython-input-51-fb016a0a90cc> in <module>()
     11 
     12 clf = GridSearchCV (SVC(C=1), parameters, cv=5, scoring='f1_macro')
---> 13 clf.fit(X_train, y_train)

~/anaconda3_501/lib/python3.6/site-packages/sklearn/grid_search.py in fit(self, X, y)
    836 
    837         """
--> 838         return self._fit(X, y, ParameterGrid(self.param_grid))
    839 
    840 

~/anaconda3_501/lib/python3.6/site-packages/sklearn/grid_search.py in _fit(self, X, y, parameter_iterable)
    572                                     self.fit_params, return_parameters=True,
    573                                     error_score=self.error_score)
--> 574                 for parameters in parameter_iterable
    575                 for train, test in cv)
    576 

~/anaconda3_501/lib/python3.6/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:

~/anaconda3_501/lib/python3.6/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 

~/anaconda3_501/lib/python3.6/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 


        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)

    ~/anaconda3_501/lib/python3.6/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):

    ~/anaconda3_501/lib/python3.6/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):

~/anaconda3_501/lib/python3.6/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):

~/anaconda3_501/lib/python3.6/site-packages/sklearn/cross_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, error_score)
   1673             estimator.fit(X_train, **fit_params)
   1674         else:
-> 1675             estimator.fit(X_train, y_train, **fit_params)
   1676 
   1677     except Exception as e:

~/anaconda3_501/lib/python3.6/site-packages/sklearn/svm/base.py in fit(self, X, y, sample_weight)
    148 
    149         X, y = check_X_y(X, y, dtype=np.float64, order='C', accept_sparse='csr')
--> 150         y = self._validate_targets(y)
    151 
    152         sample_weight = np.asarray([]

~/anaconda3_501/lib/python3.6/site-packages/sklearn/svm/base.py in _validate_targets(self, y)
    498     def _validate_targets(self, y):
    499         y_ = column_or_1d(y, warn=True)
--> 500         check_classification_targets(y)
    501         cls, y = np.unique(y_, return_inverse=True)
    502         self.class_weight_ = compute_class_weight(self.class_weight, cls, y_)

~/anaconda3_501/lib/python3.6/site-packages/sklearn/utils/multiclass.py in check_classification_targets(y)
    170     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    171                       'multilabel-indicator', 'multilabel-sequences']:
--> 172         raise ValueError("Unknown label type: %r" % y_type)
    173 
    174 

ValueError: Unknown label type: 'continuous'

我们将不胜感激。

Answer 1

您正在使用分类器。您只能对二元或分类变量进行分类。如果你想使用支持向量但预测数值，你应该使用支持向量回归。否则，您将不得不将您的 y 值分组。