diff options
author | Peter Rudenko <petro.rudenko@gmail.com> | 2015-02-16 00:07:23 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-02-16 00:07:23 -0800 |
commit | d51d6ba1547ae75ac76c9e6d8ea99e937eb7d09f (patch) | |
tree | 5c33800c77fad824ad451a988cf4f8ee706dbb43 /sbt | |
parent | c78a12c4cc4d4312c4ee1069d3b218882d32d678 (diff) | |
download | spark-d51d6ba1547ae75ac76c9e6d8ea99e937eb7d09f.tar.gz spark-d51d6ba1547ae75ac76c9e6d8ea99e937eb7d09f.tar.bz2 spark-d51d6ba1547ae75ac76c9e6d8ea99e937eb7d09f.zip |
[Ml] SPARK-5804 Explicitly manage cache in Crossvalidator k-fold loop
On a big dataset explicitly unpersist train and validation folds allows to load more data into memory in the next loop iteration. On my environment (single node 8Gb worker RAM, 2 GB dataset file, 3 folds for cross validation), saved more than 5 minutes.
Author: Peter Rudenko <petro.rudenko@gmail.com>
Closes #4595 from petro-rudenko/patch-2 and squashes the following commits:
66a7cfb [Peter Rudenko] Move validationDataset cache to declaration
c5f3265 [Peter Rudenko] [Ml] SPARK-5804 Explicitly manage cache in Crossvalidator k-fold loop
Diffstat (limited to 'sbt')
0 files changed, 0 insertions, 0 deletions