Details
-
Improvement
-
Status: Closed
-
Minor
-
Resolution: Fixed
-
0.6
-
None
-
None
Description
The transaction sorting job could have been made map-only, and another mapreduce job follows, so it made sense to combine them. It would have been possible to use a ChainMapper approach, but it seemed simpler to fold the functionality into the following mapper (ParallelFPGrowthMapper). The attached patch does just that.
Attachments
Attachments
Issue Links
- is related to
-
MAHOUT-890 Performance issue in FPGrowth
- Closed
- relates to
-
MAHOUT-921 FPG uses a lot of boxed primitives - this patch eliminates a bunch of List<Integer>
- Closed
-
MAHOUT-927 FPG saves a mapping from from feature to mining group, when this can be calculated on the fly
- Closed