Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/2378#discussion_r17686887
--- Diff: python/pyspark/mllib/recommendation.py ---
@@ -54,34 +64,51 @@ def __del__(self):
def predict(self, user, product):
return self._java_model.predict(user, product)
- def predictAll(self, usersProducts):
- usersProductsJRDD = _get_unmangled_rdd(usersProducts,
_serialize_tuple)
- return RDD(self._java_model.predict(usersProductsJRDD._jrdd),
- self._context, RatingDeserializer())
+ def predictAll(self, user_product):
+ assert isinstance(user_product, RDD), "user_product should be RDD
of (user, product)"
+ sc = self._context
+ tuplerdd =
sc._jvm.SerDe.asTupleRDD(user_product._to_java_object_rdd().rdd())
+ jresult = self._java_model.predict(tuplerdd).toJavaRDD()
+ return RDD(sc._jvm.PythonRDD.javaToPython(jresult), sc,
+ AutoBatchedSerializer(PickleSerializer()))
class ALS(object):
@classmethod
+ def _prepare(cls, ratings):
+ assert isinstance(ratings, RDD), "ratings should be RDD"
+ first = ratings.first()
+ if not isinstance(first, Rating):
+ if isinstance(first, (tuple, list)):
+ ratings = ratings.map(lambda x: Rating(*x))
+ else:
+ raise ValueError("rating should be RDD of Rating or
tuple/list")
+ # serialize them by AutoBatchedSerializer before cache to reduce
the
+ # objects overhead in JVM
+ cached =
ratings._reserialize(AutoBatchedSerializer(PickleSerializer())).cache()
--- End diff --
@mengxr Any comments about it?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
