diff --git a/python-package/xgboost/compat.py b/python-package/xgboost/compat.py
index 14be8870c..10221cb72 100644
--- a/python-package/xgboost/compat.py
+++ b/python-package/xgboost/compat.py
@@ -46,12 +46,12 @@ except ImportError:
 try:
     from sklearn.base import BaseEstimator
     from sklearn.base import RegressorMixin, ClassifierMixin
-    from sklearn.preprocessing import LabelEncoder                # noqa
+    from sklearn.preprocessing import LabelEncoder
     try:
         from sklearn.model_selection import KFold, StratifiedKFold
     except ImportError:
         from sklearn.cross_validation import KFold, StratifiedKFold
-    
+
     SKLEARN_INSTALLED = True
 
     XGBModelBase = BaseEstimator
diff --git a/python-package/xgboost/training.py b/python-package/xgboost/training.py
index 5bf2b4f38..a1ad4c2b4 100644
--- a/python-package/xgboost/training.py
+++ b/python-package/xgboost/training.py
@@ -232,14 +232,12 @@ def mknfold(dall, nfold, param, seed, evals=(), fpreproc=None, stratified=False,
         randidx = np.random.permutation(dall.num_row())
         kstep = int(len(randidx) / nfold)
         idset = [randidx[(i * kstep): min(len(randidx), (i + 1) * kstep)] for i in range(nfold)]
-    elif folds is not None:
+    elif folds is not None and isinstance(folds, list):
         idset = [x[1] for x in folds]
         nfold = len(idset)
     else:
-        idset = [x[1] for x in XGBStratifiedKFold(dall.get_label(),
-                                                  n_folds=nfold,
-                                                  shuffle=True,
-                                                  random_state=seed)]
+        sfk = XGBStratifiedKFold(n_splits=nfold, shuffle=True, random_state=seed)
+        idset = [x[1] for x in sfk.split(X=dall.get_label(), y=dall.get_label())]
 
     ret = []
     for k in range(nfold):
diff --git a/tests/python/test_with_sklearn.py b/tests/python/test_with_sklearn.py
index d079d99fe..19de5abb9 100644
--- a/tests/python/test_with_sklearn.py
+++ b/tests/python/test_with_sklearn.py
@@ -251,7 +251,7 @@ def test_sklearn_plotting():
 def test_sklearn_nfolds_cv():
     tm._skip_if_no_sklearn()
     from sklearn.datasets import load_digits
-    from sklearn.cross_validation import StratifiedKFold
+    from sklearn.model_selection import StratifiedKFold
 
     digits = load_digits(3)
     X = digits['data']
@@ -269,10 +269,10 @@ def test_sklearn_nfolds_cv():
 
     seed = 2016
     nfolds = 5
-    skf = StratifiedKFold(y, n_folds=nfolds, shuffle=True, random_state=seed)
+    skf = StratifiedKFold(n_splits=nfolds, shuffle=True, random_state=seed)
 
     cv1 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, seed=seed)
-    cv2 = xgb.cv(params, dm, num_boost_round=10, folds=skf, seed=seed)
+    cv2 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, folds=skf, seed=seed)
     cv3 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, stratified=True, seed=seed)
     assert cv1.shape[0] == cv2.shape[0] and cv2.shape[0] == cv3.shape[0]
     assert cv2.iloc[-1, 0] == cv3.iloc[-1, 0]