diff options
Diffstat (limited to 'python/pyspark/mllib/recommendation.py')
-rw-r--r-- | python/pyspark/mllib/recommendation.py | 12 |
1 files changed, 11 insertions, 1 deletions
diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py index 14d06cba21..0eeb5bb66b 100644 --- a/python/pyspark/mllib/recommendation.py +++ b/python/pyspark/mllib/recommendation.py @@ -20,7 +20,9 @@ from pyspark.mllib._common import \ _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 + _get_initial_weights, _serialize_rating, _regression_train_wrapper, \ + _serialize_tuple, RatingDeserializer +from pyspark.rdd import RDD class MatrixFactorizationModel(object): """A matrix factorisation model trained by regularized alternating @@ -33,6 +35,9 @@ class MatrixFactorizationModel(object): >>> model = ALS.trainImplicit(sc, ratings, 1) >>> model.predict(2,2) is not None True + >>> testset = sc.parallelize([(1, 2), (1, 1)]) + >>> model.predictAll(testset).count == 2 + True """ def __init__(self, sc, java_model): @@ -45,6 +50,11 @@ class MatrixFactorizationModel(object): 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()) + class ALS(object): @classmethod def train(cls, sc, ratings, rank, iterations=5, lambda_=0.01, blocks=-1): |