[AstroPy] reconstruct signal from periodogram

[Paola Galdi]

Hello,
I've been working with the LombScargle class from astropy.stats and I have
a question about using the periodogram to reconstruct the signal at given
time points.

My problem is that I have a time series where some of the time points are
censored, and I'd like to reconstruct the signal in the missing points by
using the frequency content of uncensored data.

So far I've been able to obtain the best fit sinusoid (as in
http://docs.astropy.org/en/stable/stats/lombscargle.html) but what I'd like
to do is to reconstruct the signal using all frequencies.

I tried to sum up all the sinusoidal models for each frequency (weighted by
powers) but the result was a quite flat line around the mean of the signal.

Do you have any suggestions on how I could achieve signal reconstruction?

Thank you,
Paola
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/astropy/attachments/20170706/df722e79/attachment.html>