🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

Pivoting/grouping multiple attributes after time-series feature extraction

el_Raphael_Rapha Member Posts: 1 Newbie
Hello,
I extracted features of multiple time series batches (IDx) with multiple signal columns (signalx) using the extract aggregates block on these multiple signals.
I receive data in the form of:
ID1 - "signal1" - feat1 - feat2 - ...
ID1 - "signal2" - feat1 - feat2 - ...
ID2 - "signal1" - feat1 - feat2 - ...
ID2 - "signal2" - feat1 - feat2 - ...
...

How can I perform a pivoting/grouping-like operation (with multiple attributes) that gives me somthing like this:
ID1 - signal1_feat1 - signal1_feat2 - signal2_feat1 - signal2_feat2 - ...
ID2 - signal1_feat1 - signal1_feat2 - signal2_feat1 - signal2_feat2 - ...
...

Thanks for your help!

Best Answer

  • mschmitzmschmitz Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,159  RM Data Scientist
    Solution Accepted
    Hi,
    there is a setting in the operator called "add time series name". If you check it you get the format you ask for.

    Best,
    Martin
    - Head of Data Science Services at RapidMiner -
    Dortmund, Germany
    el_Rapha
Sign In or Register to comment.