卡在 Jupyter Notebook 上的模型构建中

Question

我试图适应随机森林树模型，但我不断遇到错误，我的 CV 迭代器被告知为空，但事实并非如此。

下面是代码片段和错误

%%time
rf_val.fit(X_train, y_train)

Fitting 0 folds for each of 32 candidates, totalling 0 fits
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   0 out of   0 | elapsed:    0.0s finished
ValueError                                Traceback (most recent call last)
<timed eval> in <module>

/opt/conda/lib/python3.7/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
    708                 return results
    709 
--> 710             self._run_search(evaluate_candidates)
    711 
    712         # For multi-metric evaluation, store the best_index_, best_params_ and

/opt/conda/lib/python3.7/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
   1149     def _run_search(self, evaluate_candidates):
   1150         """Search all candidates in param_grid"""
-> 1151         evaluate_candidates(ParameterGrid(self.param_grid))
   1152 
   1153 

/opt/conda/lib/python3.7/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
    690 
    691                 if len(out) < 1:
--> 692                     raise ValueError('No fits were performed. '
    693                                      'Was the CV iterator empty? '
    694                                      'Were there no candidates?')

ValueError: No fits were performed. Was the CV iterator empty? Were there no candidates?

我试图调整并适应随机森林模型，并希望随着时间的推移完成它，但我遇到了这个错误，我无法理解它。

Answer 1

在原始sklearn代码中，在

fit

函数下：

def evaluate_candidates(candidate_params):
    candidate_params = list(candidate_params)
    n_candidates = len(candidate_params)

    if self.verbose > 0:
        print("Fitting {0} folds for each of {1} candidates,"
              " totalling {2} fits".format(
                  n_splits, n_candidates, n_candidates * n_splits))

    out = parallel(delayed(_fit_and_score)(clone(base_estimator),
                                           X, y,
                                           train=train, test=test,
                                           parameters=parameters,
                                           **fit_and_score_kwargs)
                   for parameters, (train, test)
                   in product(candidate_params,
                              cv.split(X, y, groups)))

    if len(out) < 1:
        raise ValueError('No fits were performed. '
                         'Was the CV iterator empty? '
                         'Were there no candidates?')

在您的错误消息中：

Fitting 0 folds for each of 32 candidates, totalling 0 fits

这意味着

n_split = 0

。

n_split

定义为：

 n_splits = cv.get_n_splits(X, y, groups)

在您的情况下，您的

group

设置为

None

，因此错误可能是由您的输入数据

X

和

y

引起的。