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: https://forum2.philippe-fournier-viger.com/index.php
 
rules count of TopSeqRules algorithm is not K, why?
Posted by: xiaowei
Date: April 07, 2020 05:52AM

Hi, everyone

my sequence database is input into the TopSeqRules algorithm using the graphical interface, the parameter K= 50, minconf=0.6. But the sequential rules count is 4898, not 50, why? I am confused.


Kind regards,
Xiaowei

Options: ReplyQuote
Re: rules count of TopSeqRules algorithm is not K, why?
Date: April 08, 2020 05:11PM

Hi Xiaowei,

Sorry to answer late. The last two days have been very busy, and I did not check the forum.

The number of rules can be more than k because sometimes many rules have exactly the same support.

For example, if you set k=50, but there are 1000 rules that have exactly the same support, the algorithm should give you all these rules because they are equal in terms of support.

It is also possible that the algorithm return less than k rules if the database does not contain k rules. For example, if you set k = 1000 but there does not exist 1000 rules in the database, then the algorithm cannot return 1000.

Those are special cases. But it may happen.

Best regards,

Philippe

Options: ReplyQuote
Re: rules count of TopSeqRules algorithm is not K, why?
Posted by: xiaowei
Date: April 08, 2020 06:57PM

Thanks a lot, Professor Philippe. I got it.

Kind regards,
Xiaowei

Options: ReplyQuote


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