The Data Mining Forum                             open-source data mining software data mining conferences Data Science for Social and Behavioral Analytics DSSBA 2022 data science journal
IMPORTANT: This is the old Data Mining forum.
I keep it online so that you can read the old messages.

Please post your new messages in the new forum:
SPMF vs Weka implementation of FPGrowth
Date: November 12, 2012 07:49PM

Hi everyone,

I have performed some tests to compare my implementation of FPGrowth in SPMF with the WEKA implementation.

The results are on this page:

It shows that the SPMF implementation can be much more efficient, both in terms of execution time and memory usage. For example:



Edited 2 time(s). Last edit at 11/14/2012 04:26PM by webmasterphilfv.

Options: ReplyQuote
Re: SPMF vs Weka implementation of FPGrowth
Posted by: Dvijesh88
Date: December 06, 2012 07:03AM

Hello sir

thats great....

I never imagine this... weka vs SPMF?

but have question that in 2nd figure why slop using weka is up ans down? it should not be continuous?

Options: ReplyQuote
Re: SPMF vs Weka implementation of FPGrowth
Date: December 06, 2012 07:41AM

Hi Dvijesh,

Long time, that I did not discuss with you! Hope you are going well.

Yes. I made some tests by modifying Weka so that it can take the same files as input as SPMF. Then I have compared the modified Weka files with SPMF. I spend two evenings to do that to compare the performance. The goal was just to compare the performance to see how good or bad my implementation is. Actually, it seems that my implementations beat Weka, which is encouraging. But it could still be improved further.

In the second figure, the memory go up and down probably because Java is not reliable for memory measurement (because of the garbage collection). I think that this is the most likely explanation. But it could also be because of how they implemented it.



Options: ReplyQuote

This forum is powered by Phorum and provided by P. Fournier-Viger (© 2012).
Terms of use.