Francesco Andreuzzi
Francesco Andreuzzi
Could you please show the content of `dmd_opts`? If you take too many DMD modes you may be including divergent dynamics in your reconstruction.
There are some tools to select an acceptable number of singular values automatically. You can set the parameter `svd_rank` of the constructor `DMD(...)` to: - 0 for an optimal rank;...
See also `__doc__` attribute (https://www.sphinx-doc.org/en/master/usage/extensions/autodoc.html).
Also the tutorial needs to be integrated properly (missing entry in the table in `tutorials/README.md`, missing `.py` version).
I made some tests and I think there is actually no way to reach the desired behavior of `is_total_slice` since the modification proposed by @d-v-b relies on the relative position...
@d-v-b Thank you very much for the hints!
Just a question to check whether I understood the key idea of `zarr`. If we consider the example provided by @d-v-b, I would expect the result of `is_total_slice(slice(1,10,1), a._chunks)` to...
Hi @alirezakarimi82, I propose pairing `HankelDMD` with `ParametricDMD`: ```python from pydmd import ParametricDMD, HankelDMD from ezyrb import POD, RBF pdmd = ParametricDMD(dmds, POD(svd_rank=-1), RBF()) # params x space x time...
> By the way, as a side note, for each time series I have two parameters, so my params array has a shape of (10, 2), for example. I just...
Hi @alirezakarimi82, I'm happy that my solution did the work. > [...] But when I try to use this combination within `ParametricDMD`, I get an error [...] You're using a...