Select distinct items from datatable using primay key

august5august5 Member Posts: 1 Contributor I
Hi all,
    I am using rapidminer 5.3 to perform cluster analysis.  I am using real data from industry. There are 16 attributes in the raw data. I have cleaned the data and selected two attributes out of 16, for cluster analysis. The results of the cluster analysis show 5 distinct groups of data. While reviewing the results in rapidminer, I see the row number or id(primary key) and the two attributes. We are not able to associate the remaining 14 attributes to the items in clusters. I have done some research to find an operator in rapidminer that could be used to select records based on primary key. I am not able to find any. Can anyone help me or direct me. Thanks in advance.



  • Options
    MariusHelfMariusHelf RapidMiner Certified Expert, Member Posts: 1,869 Unicorn
    Before selecting the 2 attributes use Generate Id to create a unique id for each record.

    After the clustering you can use the Join operator to associate the other attributes back to the clustered data using the id column. Does that help?

    Best regards,
Sign In or Register to comment.