select attributes based on occurrence

ticemba

Hi,

I'm running the text mining process.
I load 3 documents (file1, file2 and file3) and then I use the operator "Tokenize".
In output I want only the tokens(attributes) that have occurrence>0 in file3 (in file1 and file2 tokens can have also occurrence=0).
What operator can I use to do it?

thank you

ticemba

Viktor_Meyer

Hallo ticemba,

i think you have to pre filter "file 3" with an example filter...
-->attribute valuefilter
an then load it in together !

i hope it helped.

Viktor