diff --git a/python/pyspark/mllib/classification.py b/python/pyspark/mllib/classification.py
index 71ab46b61d7fa..7f4a4737c7837 100644
--- a/python/pyspark/mllib/classification.py
+++ b/python/pyspark/mllib/classification.py
@@ -242,7 +242,7 @@ def train(cls, data, lambda_=1.0):
         @param lambda_: The smoothing parameter
         """
         sc = data.context
-        dataBytes = _get_unmangled_labeled_point_rdd(data)
+        dataBytes = _get_unmangled_labeled_point_rdd(data, cache=False)
         ans = sc._jvm.PythonMLLibAPI().trainNaiveBayes(dataBytes._jrdd, lambda_)
         return NaiveBayesModel(
             _deserialize_double_vector(ans[0]),
diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py
index f3e952a1d842a..46b41b9199ce1 100644
--- a/python/pyspark/mllib/clustering.py
+++ b/python/pyspark/mllib/clustering.py
@@ -22,7 +22,7 @@
     _get_unmangled_rdd, _get_unmangled_double_vector_rdd, _squared_distance, \
     _serialize_double_matrix, _deserialize_double_matrix, \
     _serialize_double_vector, _deserialize_double_vector, \
-    _get_initial_weights, _serialize_rating, _regression_train_wrapper
+    _get_initial_weights, _serialize_rating
 from pyspark.mllib.linalg import SparseVector
 
 __all__ = ['KMeansModel', 'KMeans']
diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py
index 2df23394da6f8..6c07adc98a949 100644
--- a/python/pyspark/mllib/recommendation.py
+++ b/python/pyspark/mllib/recommendation.py
@@ -20,8 +20,8 @@
     _get_unmangled_rdd, _get_unmangled_double_vector_rdd, \
     _serialize_double_matrix, _deserialize_double_matrix, \
     _serialize_double_vector, _deserialize_double_vector, \
-    _get_initial_weights, _serialize_rating, _regression_train_wrapper, \
-    _serialize_tuple, RatingDeserializer
+    _get_initial_weights, _serialize_rating, _serialize_tuple, \
+    RatingDeserializer
 from pyspark.rdd import RDD
 
 __all__ = ['MatrixFactorizationModel', 'ALS']
@@ -65,7 +65,7 @@ class ALS(object):
     @classmethod
     def train(cls, ratings, rank, iterations=5, lambda_=0.01, blocks=-1):
         sc = ratings.context
-        ratingBytes = _get_unmangled_rdd(ratings, _serialize_rating)
+        ratingBytes = _get_unmangled_rdd(ratings, _serialize_rating, cache=False)
         mod = sc._jvm.PythonMLLibAPI().trainALSModel(
             ratingBytes._jrdd, rank, iterations, lambda_, blocks)
         return MatrixFactorizationModel(sc, mod)
@@ -73,7 +73,7 @@ def train(cls, ratings, rank, iterations=5, lambda_=0.01, blocks=-1):
     @classmethod
     def trainImplicit(cls, ratings, rank, iterations=5, lambda_=0.01, blocks=-1, alpha=0.01):
         sc = ratings.context
-        ratingBytes = _get_unmangled_rdd(ratings, _serialize_rating)
+        ratingBytes = _get_unmangled_rdd(ratings, _serialize_rating, cache=False)
         mod = sc._jvm.PythonMLLibAPI().trainImplicitALSModel(
             ratingBytes._jrdd, rank, iterations, lambda_, blocks, alpha)
         return MatrixFactorizationModel(sc, mod)
diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py
index 5b13ab682bbfc..7f5d0b14c281a 100644
--- a/python/pyspark/mllib/tree.py
+++ b/python/pyspark/mllib/tree.py
@@ -161,7 +161,7 @@ def trainClassifier(data, numClasses, categoricalFeaturesInfo,
         :return: DecisionTreeModel
         """
         sc = data.context
-        dataBytes = _get_unmangled_labeled_point_rdd(data)
+        dataBytes = _get_unmangled_labeled_point_rdd(data, cache=False)
         categoricalFeaturesInfoJMap = \
             MapConverter().convert(categoricalFeaturesInfo,
                                    sc._gateway._gateway_client)
@@ -169,7 +169,6 @@ def trainClassifier(data, numClasses, categoricalFeaturesInfo,
             dataBytes._jrdd, "classification",
             numClasses, categoricalFeaturesInfoJMap,
             impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain)
-        dataBytes.unpersist()
         return DecisionTreeModel(sc, model)
 
     @staticmethod
@@ -196,7 +195,7 @@ def trainRegressor(data, categoricalFeaturesInfo,
         :return: DecisionTreeModel
         """
         sc = data.context
-        dataBytes = _get_unmangled_labeled_point_rdd(data)
+        dataBytes = _get_unmangled_labeled_point_rdd(data, cache=False)
         categoricalFeaturesInfoJMap = \
             MapConverter().convert(categoricalFeaturesInfo,
                                    sc._gateway._gateway_client)
@@ -204,7 +203,6 @@ def trainRegressor(data, categoricalFeaturesInfo,
             dataBytes._jrdd, "regression",
             0, categoricalFeaturesInfoJMap,
             impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain)
-        dataBytes.unpersist()
         return DecisionTreeModel(sc, model)