Altair RISE

Hi Thomas
Thanks for replay
Yes, I checked it many times
The operator will filter out the document from the words in text file
I want the filter to filter the document from all words exepet the words inside the text file
the opposite what I need ..

Thomas_Ott

Would Filter by Content help? It has an inverse condition. What about Filter by POS tags? That also has an inverse condition.

Fatmah

I try Filter by content but it is insufficient for my situation because the text file have tens of words
Filter by content will be good for very small number of expression
In Filter by POS tag ? I can't determine the words I want !

Thank you again for your help and yes plz if you have any suggestion tell me or if you know how I can reach the code ?

hmhsing

I changed the dictionary txt file into Excel and then use Filter Tokens Using ExampleSet (need check invert filter), it works. See the attached file.

inverse of filter stopword (dictionary).rmp

kayman

In theory you could use the process documents from data operator and use your reversed stoplist (or whitelist) as a wordlist, this would allow only the words in your list as acceptable. There is no real out of the box operator to create your own wordlist but this one goes more in detail :

https://community.rapidminer.com/discussion/51131/creating-a-comparing-white-list-of-words-to-a-wordlist-from-a-data-mined-webpage