From b19008320bdf7064e764db04c43ef003a3ce0ecd Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Thu, 31 Jul 2014 21:14:08 -0700
Subject: [PATCH] [SPARK-2777][MLLIB] change ALS factors storage level to
MEMORY_AND_DISK
Now the factors are persisted in memory only. If they get kicked off by later jobs, we might have to start the computation from very beginning. A better solution is changing the storage level to `MEMORY_AND_DISK`.
srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes #1700 from mengxr/als-level and squashes the following commits:
c103d76 [Xiangrui Meng] change ALS factors storage level to MEMORY_AND_DISK
---
.../scala/org/apache/spark/mllib/recommendation/ALS.scala | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
index d208cfb917..36d262fed4 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
@@ -290,8 +290,8 @@ class ALS private (
val usersOut = unblockFactors(users, userOutLinks)
val productsOut = unblockFactors(products, productOutLinks)
- usersOut.setName("usersOut").persist()
- productsOut.setName("productsOut").persist()
+ usersOut.setName("usersOut").persist(StorageLevel.MEMORY_AND_DISK)
+ productsOut.setName("productsOut").persist(StorageLevel.MEMORY_AND_DISK)
// Materialize usersOut and productsOut.
usersOut.count()
--
GitLab