The Altair Community is migrating to a new platform to provide a better experience for you. The RapidMiner Community will merge with the Altair Community at the same time. In preparation for the migration, both communities are on read-only mode from July 15th - July 24th, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here.
Options

How can I calculate VIF multicorrelated in Rapidminer?

soheeparksoheepark Member Posts: 3 Newbie
edited June 2022 in Help
Hi, I have a question about VIF multicorrelated in rapidminer.

In Python, when I calculated VIF (multicorrelated), it was found that 'holiday - workingday', 'temp - atemp' and 'month - season'  were highly correlated.
So I was able to remove one of the two variables.

But, in Rapidminer, as a result of on of the variable with a high correlation using 'Correlation Matrix' and 'Remove Correlated Attributes' operators, only  'atemp' among 'temp - atemp' was removed.

I don't know much about data analysis yet, but I feel the need to calculate VIF.

I don't know which operator to use to calculate VIF, so I can't calculate it.
As for as I know, there is no operator in Rapidminer to help calculate VIF right away,
It would be nice to have someone to help me in detail on which operator to enter the formula.

Plus, please let me know if you can tell me how to check the visualization that tells me the correlation figures of the two independent variables, such as Python's heatmap in Rapidminer.

Please answer my Q.
Thank you for reading it.




Answers

  • Options
    ceaperezceaperez Member Posts: 541 Unicorn
    Hi @soheepark
    for heatmap visualization you have two options. 
    first, when you use the Correlation Matrix operator it provides you a heatmap visualization option:



    if you want to work with the resulting data you can use the Matrix to exampleset Operator and then create your own heatmap with the data:


    I hope this can help you.

    Regards

    Cesar
Sign In or Register to comment.