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.

Euclidean Distance Normalization

limegreenman900limegreenman900 Member Posts: 26 Contributor II
edited November 2018 in Help

Hi everyone,

 

I am working at the moment with the process attached.
I have two questions in this regard:

1. When I am using "Term Frequency" as word vector, are my distance results already normalized or not? If not using the normalize operator I always get negative values which, to my understanding, cannot be as distance needs to be positive and euclidean distance is computed on a square root function? Either way I used the "normalize" operator afterwards, however I get results that are between -5,xxx and +0,4xxx. That doesn't seem to be normalized? I thought I would receive something between 0 and 1 (0=less distance=very similar; 1=great distance=dissimilar). When I use cosine similarity I get perfect results between 0 and 1 (which is consistent with the cosine function).

 

2. If I am using this exact process on RM7 (at the moment I am using RM5), I don't get the same results. I only get 0 or 1 values as output?! Is a process on RM5 not compatible with RM7?

 

Any help appreciated!

Sign In or Register to comment.