diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2015-04-22 17:22:26 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-04-22 17:22:26 -0700 |
commit | f4f39981f4f5e88c30eec7d0b107e2c3cdc268c9 (patch) | |
tree | d26235eae02cab27c9cdd537d53d41b4978fecfd /external | |
parent | baf865ddc2cff9b99d6aeab9861e030da511257f (diff) | |
download | spark-f4f39981f4f5e88c30eec7d0b107e2c3cdc268c9.tar.gz spark-f4f39981f4f5e88c30eec7d0b107e2c3cdc268c9.tar.bz2 spark-f4f39981f4f5e88c30eec7d0b107e2c3cdc268c9.zip |
[SPARK-6827] [MLLIB] Wrap FPGrowthModel.freqItemsets and make it consistent with Java API
Make PySpark ```FPGrowthModel.freqItemsets``` consistent with Java/Scala API like ```MatrixFactorizationModel.userFeatures```
It return a RDD with each tuple is composed of an array and a long value.
I think it's difficult to implement namedtuples to wrap the output because items of freqItemsets can be any type with arbitrary length which is tedious to impelement corresponding SerDe function.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #5614 from yanboliang/spark-6827 and squashes the following commits:
da8c404 [Yanbo Liang] use namedtuple
5532e78 [Yanbo Liang] Wrap FPGrowthModel.freqItemsets and make it consistent with Java API
Diffstat (limited to 'external')
0 files changed, 0 insertions, 0 deletions