python - 如何在 iris 数据集上使用逻辑回归修复值错误

Question

我正在尝试使用逻辑回归对 iris 数据集进行分类，但在拟合模型时遇到值错误。

我正在使用 iris 数据集。我不明白为什么它会返回 value_error。感谢您的帮助。

iris = datasets.load_iris()
X, y = iris.data, iris.target
x_train, x_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state= 81,
                                                           test_size=0.3)
logreg = LogisticRegression()
params_grid = {"C":[0.001, 0.01, 0.1, 1, 10, 100]}
gridcv = GridSearchCV(logreg, params_grid, cv=10, scoring='roc_auc')
gridcv.fit(x_train, y_train)

然后我在 fitting 时得到 value_error

ValueError                                Traceback (most recent call last)
<ipython-input-108-f4ab6e5f5a79> in <module>()
----> 1 gridcv.fit(x_train, y_train)

C:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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:\ProgramData\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)
    486         fit_time = time.time() - start_time
    487         # _score will return dict if is_multimetric is True
--> 488         test_scores = _score(estimator, X_test, y_test, scorer, is_multimetric)
    489         score_time = time.time() - start_time - fit_time
    490         if return_train_score:

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _score(estimator, X_test, y_test, scorer, is_multimetric)
    521     """
    522     if is_multimetric:
--> 523         return _multimetric_score(estimator, X_test, y_test, scorer)
    524     else:
    525         if y_test is None:

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _multimetric_score(estimator, X_test, y_test, scorers)
    551             score = scorer(estimator, X_test)
    552         else:
--> 553             score = scorer(estimator, X_test, y_test)
    554 
    555         if hasattr(score, 'item'):

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\metrics\scorer.py in __call__(self, clf, X, y, sample_weight)
    179         y_type = type_of_target(y)
    180         if y_type not in ("binary", "multilabel-indicator"):
--> 181             raise ValueError("{0} format is not supported".format(y_type))
    182 
    183         if is_regressor(clf):

ValueError: multiclass format is not supported

Answer 1

如果是多类，您将需要使用 支持的评分。一个例子是“recall_micro”

iris = datasets.load_iris()
X, y = iris.data, iris.target
x_train, x_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state= 81,
                                                           test_size=0.3)
logreg = LogisticRegression()
params_grid = {"C":[0.001, 0.01, 0.1, 1, 10, 100]}
gridcv = GridSearchCV(logreg, params_grid, cv=10, scoring='recall_micro')
gridcv.fit(x_train, y_train)