regression - Rescale data to be sinuosoidal -


i have time series data i'm looking @ in python know should follow sine2 function, various reasons doesn't quite fit it. i'm taking fft of , has broad frequency spread, when should narrow single frequency. however, errors causing quite consistent--if take data again matches closely previous data set , gives similar fft.

so i've been trying come way can rescale time axis of data @ single frequency, , apply same rescaling future data collect. i've tried various filtering techniques smooth data or cut frequencies fft without luck. i've tried fitting frequency varying sine2 data, haven't been able fit (if able to, use frequency vs time function rescale time axis of original data has constant frequency , apply same rescaling new data collect).

here's small sample of data i'm looking at (the full data goes few hundred cycles). , resulting fft of full data

any suggestions appreciated. thanks!


Comments

Popular posts from this blog

javascript - Clear button on addentry page doesn't work -

c# - Selenium Authentication Popup preventing driver close or quit -

tensorflow when input_data MNIST_data , zlib.error: Error -3 while decompressing: invalid block type -