PDA

View Full Version : New to weka, can this be done?



rsmaniak
09-17-2008, 07:13 AM
hello,

im just starting with data mining and i was wondering if i can use weka for my needs.

i have the following data:

ProjectId Contributors Subjects
1 {"joe","Karen"} {"Datamining","BI","html"}
2 {""} {"modern literature"}
3 {"michael","roger","jen"} {"medicine"}
4 {"ken","karen"} {"web design", "html", "flash", "css"}
5 {"steve", "andrew",ken} {"BI"}


I want to calculate or predict the probability of each project given the following user selections:

Contributors:
joe
ken
andrew
michael
jen

Subjects
html
BI
modern literature


Can i do this with weka? i've been trying out the examples but i cant really see how i can do this, how can i specify multiple nominal values for subjects and contributors? if anyone can provide any info
i will be greatly appreciated.

thanks.

Mark
09-17-2008, 06:01 PM
You could try coding contributers and subjects as multiple binary (indicator) features. E.g.

contributer=joe, contributer=Karen, contributer=michael, ..., subject=Datamining, subject=BI, subject=html, ...

Cheers,
Mark.