Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.
Cross Distance Operator
abdul_wahab
Member Posts: 2 Contributor I
Hi,
I have a training File with 14 instances (All attributes are nominal )from which I sample one instance and use the cross distance Operator;
Correct me if I am wrong , that the Distance function is only applied on regular attribute and not on special attributes e.g label , id
Second Question:
After this If I choose Nominal Measure and Nominal Distance , for the same Instance it gives me 0 which I absolutely Understand
but When I choose Measure type as Nominal Measures and nominal Measure as Simple Matching SImilarity , I get -1 , why is it so ?
and Please suggest the best way of Visualization of Distance Measuring.
Waiting for reply
I have a training File with 14 instances (All attributes are nominal )from which I sample one instance and use the cross distance Operator;
Correct me if I am wrong , that the Distance function is only applied on regular attribute and not on special attributes e.g label , id
Second Question:
After this If I choose Nominal Measure and Nominal Distance , for the same Instance it gives me 0 which I absolutely Understand
but When I choose Measure type as Nominal Measures and nominal Measure as Simple Matching SImilarity , I get -1 , why is it so ?
and Please suggest the best way of Visualization of Distance Measuring.
Waiting for reply
0
Answers
yes your assumption is correct.
Well if you want to convert a similarity into a distance you have two choices: Either use the formular: distance = 1 / similarity which will deform your scale or accept that you have negative distances and use distance = (-1) * similarity. Which will fulfill the order and no not affect the scale.
The best way for visualizing depends on your task. And I guess that this now starts to become more consulting that free support.
Greetings,
Sebastian