我正在学习机器学习并在#mnist数据集上创建我的第一个模型。
有人可以在这里帮助我吗？我尝试了分层折叠，折叠和其他方法来解决此问题。
Pandas版本'0.25.1'，Python版本3.7，使用Anaconda发行版。
from sklearn.model_selection import train_test_split
train_set ,test_set = train_test_split(mnist,test_size = 0.2, random_state = 29)
from sklearn.linear_model import SGDClassifier
sgd_clf = SGDClassifier(random_state=29)
sgd_clf.fit(X_train,y_train_5)
X_train, y_train = train_set.drop('label',axis = 1), train_set[['label']]
X_test, y_test = test_set.drop('label',axis = 1),test_set[['label']]
y_train_5 = (y_train == 5) #True for all 5's and false otherwise
y_test_5 = (y_train == 5)
from sklearn.model_selection import cross_val_predict
print(X_train.shape)
print(y_train_5.shape)
cross_val_predict(sgd_clf, X_train, y_train_5, cv=3, method="decision_function")
代码块的最后一行给出了错误：
RuntimeWarning: Number of classes in training fold (2) does not match total number of classes (1). Results may not be appropriate for your use case. To fix this, use a cross-validation technique resulting in properly stratified folds
RuntimeWarning)
ValueError Traceback (most recent call last)
<ipython-input-39-da1ad024473a> in <module>
3 print(X_train.shape)
4 print(y_train_5.shape)
----> 5 cross_val_predict(sgd_clf, X_train, y_train_5, cv=3, method="decision_function")
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in cross_val_predict(estimator, X, y, groups, cv, n_jobs, verbose, fit_params, pre_dispatch, method)
787 prediction_blocks = parallel(delayed(_fit_and_predict)(
788 clone(estimator), X, y, train, test, verbose, fit_params, method)
--> 789 for train, test in cv.split(X, y, groups))
790
791 # Concatenate the predictions
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
919 # remaining jobs.
920 self._iterating = False
--> 921 if self.dispatch_one_batch(iterator):
922 self._iterating = self._original_iterator is not None
923
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
714 with self._lock:
715 job_idx = len(self._jobs)
--> 716 job = self._backend.apply_async(batch, callback=cb)
717 # A job can complete so quickly than its callback is
718 # called before we get here, causing self._jobs to
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
180 def apply_async(self, func, callback=None):
181 """Schedule a func to be run"""
--> 182 result = ImmediateResult(func)
183 if callback:
184 callback(result)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
547 # Don't delay the application, to avoid keeping the input
548 # arguments in memory
--> 549 self.results = batch()
550
551 def get(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_predict(estimator, X, y, train, test, verbose, fit_params, method)
887 n_classes = len(set(y)) if y.ndim == 1 else y.shape[1]
888 predictions = _enforce_prediction_order(
--> 889 estimator.classes_, predictions, n_classes, method)
890 return predictions, test
891
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _enforce_prediction_order(classes, predictions, n_classes, method)
933 'is not supported for decision_function '
934 'with imbalanced folds. {}'.format(
--> 935 len(classes), n_classes, recommendation))
936
937 float_min = np.finfo(predictions.dtype).min
ValueError: Only 2 class/es in training fold, but 1 in overall dataset. This is not supported for decision_function with imbalanced folds. To fix this, use a cross-validation technique resulting in properly stratified folds
我遇到了类似的问题，在进一步调查中发现了带有错误日志的警告消息-
DataConversionWarning：当期望一个1d数组时，传递了列向量y。请将y的形状更改为（n_samples，），例如使用ravel（）。
有两种解决方法：
使用警告消息中的提示，并将代码更改为：
cross_val_predict(sgd_clf, X_train, y_train_5.values.ravel(), cv=3,
method="decision_function")
同样，使用-A column-vector y was passed when a 1d array was expected.中的提示；我发布了错误，并执行了以下操作：
Number of classes in training fold (2) does not match total number of classes (1)y_train_5是一个DataFrame，（可能您正在通过Aurelien的出版物进行工作]]y_train_5的期望类型是一个数组类型的对象（意味着Shaoe是（n，）或one-dimensional），但是在您的情况下（n，1），DataFrame是二维的。Series对象作为列向量传递为-y_train_5.iloc [：，0]（我喜欢这个）
y_train_5。{COLUMN_NAME}（另一个变体）
> y_train_5.iloc[:,0].shape
(n,)
cross_val_predict(sgd_clf, X_train, y_train_5.iloc[:,0], cv=3,
method="decision_function")