Import Excel

3erthe3er

Hi there, 

I want to start a cluster analysis and put some random animals into different clusters. I startet of by finding some general similarities between a set of animals. Now that I come though the running process, the k-means Cluster is not showing the names of the animals, just some numerical value. I guess the cause of this problem is the first column in my RM Table. That one I didn't put in the original Excel. How can I get rid of the first column?? 

Thank you for ur help! 

ClaudioKeck

Hi, 

The first column shown as "Row No." is always there as this is the Row ID for vizualisation purposes and has no impact in your analysis. Therefore you can't remove it.

The Operator to remove columns is called " Select Attributes"

If you click on a Operator you can open under help as well example processes/turorials. This might help you to set up the clustering.

3erthe3er

Hi, thank you for your quick respond. Just wondering right now if there is a better way to find the different animals in the clusters? My respond looks like that: But I would like to have that the Output is not the line of the column, but instead the Name of the animal.   

ClaudioKeck

Overall typically close to any type of data transformation is possible. You just need some simple data manipulation steps. 

One option could be to add a label column. you could try to add the "Animal column" as label to the clustering, therefore use the "set role" operator
then it would similar to this: 


Or you could create sth like this: 

first column: Cluster

second column: Animals in Cluster

third column:  count

similar to the output of the tutorial process. 


don't get confused by the Row No. it has nothing to do with the results