fp-tree and fp-growth in plain english

The normal use case is to discover interesting relations between variables in large databases, e.g:

i(t)
1 ABDE
2 BCE
3 ABDE
4 ABCE
5 ABCDE
6 BCD

the above are some transactions, let’s A, B, C … are some products people bought.

we want to find which set are frequent set .e.g: BC  is normally associated together. which means people buy B will likely buy C as well.

 

One good way is something  FP-tree /FP-growth. first construct FP-tree like this:

 

the use this FP-tree to do the mining using FP-growth method.

I have not find a good video to demo this.

Please  see details at:

https://en.wikibooks.org/wiki/Data_Mining_Algorithms_In_R/Frequent_Pattern_Mining/The_FP-Growth_Algorithm

http://wimleers.com/sites/wimleers.com/files/FP-Growth%20presentation%20handouts%20%E2%80%94%C2%A0Florian%20Verhein.pdf

Please rate this


Leave a Reply

Your email address will not be published. Required fields are marked *


*

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>