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.

time series dataset labeling around positive instance

wesselwessel Member Posts: 537 Maven
edited June 2019 in Help
Hello,

I have an animal dataset which contains a time series.
At some point in time an animal is flagged ill.
But an animal is also ill before and after this time point.

What filter can I use to add a positive label to instances before and after time points flagged ill?

Regards,

Wessel
Tagged:

Answers

  • TobiasMalbrechtTobiasMalbrecht Moderator, Employee, Member Posts: 295 RM Product Management
    Hello Wessel,

    well, this one is not trival though. Is the flag indicating illness a nominal attribute?

    A first (potentially working ;-)) solution to that problem might be to define the illness incident as a peak of a time series (e.g. by marking that point as 1 in contrast to a series of zeros) and to extract the index of that peak using the series extension. You could then define this index as a macro and use this one to set the illness flag using the [tt]Set Data[/tt] operator around that index.

    A second solution should be to write a script to extract the same index and to set illness flag of the examples around that index.

    Hope that gives you a hint,
    Tobias
Sign In or Register to comment.