From c24aeb6a310b49dba8db1f4642531780a2e27253 Mon Sep 17 00:00:00 2001 From: MechCoder Date: Thu, 30 Apr 2015 23:51:00 -0700 Subject: [SPARK-6257] [PYSPARK] [MLLIB] MLlib API missing items in Recommendation Adds rank, recommendUsers and RecommendProducts to MatrixFactorizationModel in PySpark. Author: MechCoder Closes #5807 from MechCoder/spark-6257 and squashes the following commits: 09629c6 [MechCoder] doc 953b326 [MechCoder] [SPARK-6257] MLlib API missing items in Recommendation --- python/pyspark/mllib/recommendation.py | 39 ++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'python/pyspark/mllib/recommendation.py') diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py index 4b7d17d64e..9c4647ddfd 100644 --- a/python/pyspark/mllib/recommendation.py +++ b/python/pyspark/mllib/recommendation.py @@ -65,6 +65,13 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader): >>> model.userFeatures().collect() [(1, array('d', [...])), (2, array('d', [...]))] + >>> model.recommendUsers(1, 2) + [Rating(user=2, product=1, rating=1.9...), Rating(user=1, product=1, rating=1.0...)] + >>> model.recommendProducts(1, 2) + [Rating(user=1, product=2, rating=1.9...), Rating(user=1, product=1, rating=1.0...)] + >>> model.rank + 4 + >>> first_user = model.userFeatures().take(1)[0] >>> latents = first_user[1] >>> len(latents) == 4 @@ -105,9 +112,15 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader): ... pass """ def predict(self, user, product): + """ + Predicts rating for the given user and product. + """ return self._java_model.predict(int(user), int(product)) def predictAll(self, user_product): + """ + Returns a list of predicted ratings for input user and product pairs. + """ assert isinstance(user_product, RDD), "user_product should be RDD of (user, product)" first = user_product.first() assert len(first) == 2, "user_product should be RDD of (user, product)" @@ -115,11 +128,37 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader): return self.call("predict", user_product) def userFeatures(self): + """ + Returns a paired RDD, where the first element is the user and the + second is an array of features corresponding to that user. + """ return self.call("getUserFeatures").mapValues(lambda v: array.array('d', v)) def productFeatures(self): + """ + Returns a paired RDD, where the first element is the product and the + second is an array of features corresponding to that product. + """ return self.call("getProductFeatures").mapValues(lambda v: array.array('d', v)) + def recommendUsers(self, product, num): + """ + Recommends the top "num" number of users for a given product and returns a list + of Rating objects sorted by the predicted rating in descending order. + """ + return list(self.call("recommendUsers", product, num)) + + def recommendProducts(self, user, num): + """ + Recommends the top "num" number of products for a given user and returns a list + of Rating objects sorted by the predicted rating in descending order. + """ + return list(self.call("recommendProducts", user, num)) + + @property + def rank(self): + return self.call("rank") + @classmethod def load(cls, sc, path): model = cls._load_java(sc, path) -- cgit v1.2.3