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-based moving average

turicumturicum Member Posts: 15 Contributor II
edited November 2018 in Help
Hi!

given a set of time-stamped data (e.g., double-precision values), what's the best way to compute time-based moving averages? For example, instead of computing the average over a window of width N, where N is the number of items in the input data array. I'd like to compute it on the items having time-stamp between times t_n and t_n+1, I suppose that filling the gaps in the data array (to get evenly-time-stamped data) would be one way of doing it: Is there any other solution that does not involve modifying the input data?

Thanks!
Alex

Answers

  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    Hi Alex,
    I must admit, that the ValueSeries Processing plugin still lacks this functionality. We are normally confronted with equidistant time series and I guess for learning, you will need them equidistant anyway. Filling these gaps with the moving average could be a good solution. Currently you would have to use the Fill Data Gaps operator and then build a process for filling in the missing values.

    But you might post this time moving average / fill data gaps as a feature request on our bug tracker. It seems to be a good idea to me.

    Greetings,
      Sebastian
Sign In or Register to comment.