[
https://issues.apache.org/jira/browse/MAHOUT-157?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12751990#action_12751990
]
Robin Anil commented on MAHOUT-157:
-----------------------------------
What I am merging are not integers its a pair of a list of integers(the pattern
found) and an integer(the support of the pattern). My Comparison operator is
first based on support(higher to lower), then sizes of the pattern(longer to
shorter), then the lexicographic ordering if the patterns are of same size and
support.
I have been reading up a couple of optmisations to fpgrowth
* Compressing the FPTree data structure representation for faster growth
recursion (http://ftp1.de.freebsd.org/Publications/CEUR-WS/Vol-90/liu.pdf
http://www.computing.edu.au/~sucahyoy/article/hpdm04.pdf )
* Detecting Frequent Closed item-sets.(if a pattern (a1 a2 .... an) is there
with some support. Instead of outputting 2^n sets in the power-set of that set,
output just the pattern provided the item-set is closed(definition here
http://ftp1.de.freebsd.org/Publications/CEUR-WS/Vol-90/liu.pdf )
> Frequent Pattern Mining using Parallel FP-Growth
> ------------------------------------------------
>
> Key: MAHOUT-157
> URL: https://issues.apache.org/jira/browse/MAHOUT-157
> Project: Mahout
> Issue Type: New Feature
> Affects Versions: 0.2
> Reporter: Robin Anil
> Fix For: 0.2
>
> Attachments: MAHOUT-157-August-17.patch, MAHOUT-157-August-24.patch,
> MAHOUT-157-August-31.patch, MAHOUT-157-August-6.patch,
> MAHOUT-157-Combinations-BSD-License.patch,
> MAHOUT-157-Combinations-BSD-License.patch,
> MAHOUT-157-inProgress-August-5.patch, MAHOUT-157-September-5.patch
>
>
> Implement: http://infolab.stanford.edu/~echang/recsys08-69.pdf
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
