IndexError: too many indices for array

[jiandanjinxin]

Dear Taccio Yamamoto,
The project is remarkable. I have the following questions to need your help.
My data is creditcard.csv from kaggle fraud-detection . The preprocessing is from https://github.com/yazanobeidi/fraud-detection/blob/master/project.ipynb

After I run the following code, the problem comes out.

for sampler in [None, rus, ros, sm]:
if not sampler:
pipeline = Pipeline([('lr', linear_model.LogisticRegression(n_jobs=-1))])
else:
pipeline = Pipeline([('sampler', sampler), ('lr', linear_model.LogisticRegression(n_jobs=-1))])

parameters = {'lr__C':[.0001, .001, .01, .1, .5, .75, 1, 2.5, 5, 10]}
gscv = model_selection.GridSearchCV(cv=3, error_score='raise', n_jobs=-1,
                             scoring=aucpr, 
                             verbose=True,
                             estimator=pipeline, 
                             param_grid=parameters)
gscv.fit(X_train, y_train)
print(gscv.best_estimator_)
print(gscv.best_score_)

---

Fitting 3 folds for each of 10 candidates, totalling 30 fits

IndexError Traceback (most recent call last)
in ()
10 parameters = {'lr_C':[.0001, .001, .01, .1, .5, .75, 1, 2.5, 5, 10]}
11 gscv = GridSearchCV(cv=3, error_score='raise', n_jobs=-1,scoring=aucpr, verbose=True,estimator=pipeline, param_grid=parameters)
---> 12 gscv.fit(XX_train, YY_train)
13 print(gscv.best_estimator_)
14 print(gscv.best_score_)

/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_search.pyc in fit(self, X, y, groups, **fit_params)
636 error_score=self.error_score)
637 for parameters, (train, test) in product(candidate_params,
--> 638 cv.split(X, y, groups)))
639
640 # if one choose to see train score, "out" will contain train score info

/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_split.pyc in split(self, X, y, groups)
330 n_samples))
331
--> 332 for train, test in super(_BaseKFold, self).split(X, y, groups):
333 yield train, test
334

/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_split.pyc in split(self, X, y, groups)
93 X, y, groups = indexable(X, y, groups)
94 indices = np.arange(_num_samples(X))
---> 95 for test_index in self._iter_test_masks(X, y, groups):
96 train_index = indices[np.logical_not(test_index)]
97 test_index = indices[test_index]

/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_split.pyc in _iter_test_masks(self, X, y, groups)
624
625 def _iter_test_masks(self, X, y=None, groups=None):
--> 626 test_folds = self._make_test_folds(X, y)
627 for i in range(self.n_splits):
628 yield test_folds == i

/usr/local/lib/python2.7/dist-packages/sklearn/model_selection/_split.pyc in make_test_folds(self, X, y)
611 for test_fold_indices, per_cls_splits in enumerate(zip(*per_cls_cvs)):
612 for cls, (, test_split) in zip(unique_y, per_cls_splits):
--> 613 cls_test_folds = test_folds[y == cls]
614 # the test split can be too big because we used
615 # KFold(...).split(X[:max(c, n_splits)]) when data is not 100%

IndexError: too many indices for array

I am looking forward to your reply. Thanks