Michael Hippke
Michael Hippke
Implemented in 1.3 (to be released) GP hspline rspline sliders
Hey Luke, thanks for bringing this up. It was indeed a feature request to change it to `stdev_cut` to make it user configurable. Would changing the loop to `for i...
A major difference between ground-based and space observations is cadence and gaps. So the best method can be very different. I assume your group has chosen polynomials because they work...
MARS: https://numbersandcode.com/non-greedy-mars-regression
That would be a useful feature. For splines or GPs, it would be easy to implement. For a slider, if the boxcar is shorter than the gap, it would be...
Boosted: https://github.com/chenyang45/BoostedHP
Thanks! Sounds like the same numba memory leak I encountered in the past. Can you check if it goes away with`method=medfilt`? Not that you should use the median, just to...
Thanks! I have narrowed down the problem to be a bug in numba, which is known and discussed [here](https://github.com/numba/numba/issues/4093). This will probably be fixed in the next numba release. In...
Mhm, I'm trying to make a simple example to show the leak, but I can't reproduce it. Can you try to run this code on your machine to check if...
Hi, thanks for this idea. I have personally iterated over all of the Kepler light curves and had no performance issues. Can you describe the use case in more detail?