examples to group
Guru| days |
| 325 |
| 100 |
| 3250 |
| 1250 |
| 2200 |
| 4500 |
| 10 |
| 75 |
| 100 |
| 478 |
| 4250 |
| 3400 |
| 1000 |
I've an attribute similar to the above. I want to generate new attribute with new values ( as smll, medium, mediumbig, big )
after classify the examples of above attribute into 4 groups : days <100 -> small , <1550 - medium , < 3500 - mediumbig, >3500 - big. I tried to use "if then" description , but it doesnt give the results. can some one help?
thanks
thiru
0
Best Answers
-
MartinLiebig
Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,453 
RM Data Scientist
Hi,I think the operator you search for is Discretize by User Specification.Best,Martin- Sr. Director Data Solutions, Altair RapidMiner -
Dortmund, Germany5 -
kayman
Member Posts: 662 
Unicorn
the if then approach should work also, but ensure your logic states it needs to be smaller as figure a AND bigger as figure b.
If you just state smaller then and forget not bigger then you just overrule all your previous definitions
example
assume date is 50
date smaller than 100 ? TRUE
date smaller than 500 ? Also TRUE
Discretize does the same, and is far less error prone than a multi if then else function so better use that one indeed. Also here ensure you set a complete boundary rather than just a single one.5
