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.
How to DFT
tennenrishin
Member Posts: 177 Contributor II
I want to DFT a series, discard frequencies above a certain threshold, and then DFT it back again. In other words, I want to pass a (recurrent) series through an optimal low-pass filter.
I am stuck at the first step. I cannot get the full DFT of a series as an exampleset. In the following process, the first and second outputs are equivalent (as expected) but the third output has reset the phase of the sinusoid, presumably because the Series to Data operator outputs only the magnitude and discards phase of each element. How can I get hold of the phase information? (Or alternatively, the real/imaginary component.)
Or alternatively, how can I accomplish my original goal?
I am stuck at the first step. I cannot get the full DFT of a series as an exampleset. In the following process, the first and second outputs are equivalent (as expected) but the third output has reset the phase of the sinusoid, presumably because the Series to Data operator outputs only the magnitude and discards phase of each element. How can I get hold of the phase information? (Or alternatively, the real/imaginary component.)
Or alternatively, how can I accomplish my original goal?
0
Answers
However, there is the Fourier Transformation operator that works directly on an example set. Did you try that one?
Best regards,
Marius
"This operator uses the label as a function of each attribute..."
If I just want the Discrete Fourier Transform of some sequence of numbers, how would I use the operator to obtain it?
I've tried this: but this seems incorrect, as a 100-point function would have a 100-point DFT (rather than a 32-point DFT).