Python 未来警告消息

Question

我在 Jupyter Notebook 中使用 Python 3.7。我正在根据 Jason Brownlee 的电子书 Machine Learning Mastery with Python 创建分类模型。代码基本上是从电子书中剪切并粘贴到 Jupyter Notebook 中的。当我拆分数据时，模型工作正常，但是当我使用 k 折交叉验证时，它会生成一个 Future 警告消息，我将剪切并粘贴下面的代码和消息。我输入了 error_score =np.nan 并没有解决问题，但我不知道应该在哪里输入代码。我会很感激任何建议，但请记住，我是新手。谢谢

#逻辑回归分类

        from pandas import read_csv
        from sklearn.model_selection import KFold
        from sklearn.model_selection import cross_val_score
        from sklearn.linear_model import LogisticRegression
        df = pd.read_csv('Diabetes_Classification.csv')
        array = df.values
        X = array[:,0:8]
        Y = array[:,8]
        kfold = KFold(n_splits=10, random_state=7)
        model = LogisticRegression(solver='liblinear')
        error_score = np.nan
        results = cross_val_score(model, X, Y, cv=kfold)
        print(results.mean())
        # Logistic Regression Classification
        from pandas import read_csv
        from sklearn.model_selection import KFold
        from sklearn.model_selection import cross_val_score
        from sklearn.linear_model import LogisticRegression
        df = pd.read_csv('Diabetes_Classification.csv')
        array = df.values
        X = array[:,0:8]
        Y = array[:,8]
        kfold = KFold(n_splits=10, random_state=7)
        model = LogisticRegression(solver='liblinear')
        error_score = np.nan
        results = cross_val_score(model, X, Y, cv=kfold)
        print(results.mean())

/Users/roberthoyt/opt/anaconda3/lib/python3.7/site- 
packages/sklearn/model_selection/_validation.py:530: FutureWarning: From version 0.22, errors during 
fit will result in a cross validation score of NaN by default. Use error_score='raise' if you want 
an exception raised or error_score=np.nan to adopt the behavior from version 0.22.
FutureWarning)

---

    ValueError                                Traceback (most recent call last)
     <ipython-input-105-010e5612fd63> in <module>
     11 model = LogisticRegression(solver='liblinear')
     12 error_score = np.nan
---> 13 results = cross_val_score(model, X, Y, cv=kfold)
     14 print(results.mean())



 ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in 
    cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, 
    error_score)
    389                                 fit_params=fit_params,
    390                                 pre_dispatch=pre_dispatch,
    --> 391                                 error_score=error_score)
    392     return cv_results['test_score']
    393 

    ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in 
    cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, 
    return_train_score, return_estimator, error_score)
    230             return_times=True, return_estimator=return_estimator,
    231             error_score=error_score)
    --> 232         for train, test in cv.split(X, y, groups))
    233 
    234     zipped_scores = list(zip(*scores))

    ~/opt/anaconda3/lib/python3.7/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 

    ~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in dispatch_one_batch(self, 
    iterator)
    757                 return False
    758             else:
    --> 759                 self._dispatch(tasks)
    760                 return True
    761 

    ~/opt/anaconda3/lib/python3.7/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

    ~/opt/anaconda3/lib/python3.7/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)

    ~/opt/anaconda3/lib/python3.7/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):

    ~/opt/anaconda3/lib/python3.7/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):

    ~/opt/anaconda3/lib/python3.7/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):

    ~/opt/anaconda3/lib/python3.7/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, return_estimator, 
    error_score)
    514             estimator.fit(X_train, **fit_params)
    515         else:
    --> 516             estimator.fit(X_train, y_train, **fit_params)
    517 
    518     except Exception as e:

    ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/linear_model/logistic.py in fit(self, X, y, 
    sample_weight)
   1531         X, y = check_X_y(X, y, accept_sparse='csr', dtype=_dtype, order="C",
   1532                          accept_large_sparse=solver != 'liblinear')
    -> 1533         check_classification_targets(y)
   1534         self.classes_ = np.unique(y)
   1535         n_samples, n_features = X.shape

    ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/multiclass.py in 
    check_classification_targets(y)
    167     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    168                       'multilabel-indicator', 'multilabel-sequences']:
    --> 169         raise ValueError("Unknown label type: %r" % y_type)
    170 
    171 

    ValueError: Unknown label type: 'continuous'

Answer 1

问题在于您的目标是连续的，并且您正在执行分类任务。确保您使用目标的列是分类的。您可能必须将其转换为整数。所有这些都在回溯中报告：

check_classification_targets(y)
    167     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    168                       'multilabel-indicator', 'multilabel-sequences']:
    --> 169         raise ValueError("Unknown label type: %r" % y_type)

您的目标不在接受的目标中。你的目标是连续的：

ValueError: Unknown label type: 'continuous'

使用df.dtypes 检查您的目标是否为整数，如果不是则将其更改为整数。

Y = array[:,8].astype(int)

这是假设您没有犯过对连续值进行分类任务的错误。您还可以检查所有值是否代表 0 和 1：

np.unique(array[:, 8])