Releases: jgomezdans/gp_emulator
Added inverse emulators
Sometimes, plain old regression is required. So I added inverse emulators (in goes reflectance, out comes parameters).
Python 3 and documentation
This release deals with Python 3 and starts documentation. Can also install from pip, or conda.
Consistent predict keyword options.
This bump to version 1.5.5 brings the possibility to only limit the prediction to only calculate the mean, with the variance and emulated gradient being now optional. Note that the return is now always a 3-element tuple, with some of those elements set to None
if they're not being calculated.
This version also gives you the chance to specialise the training set. While that could already be done by changing the PDF of the parameters for the LHS scheme, you can now add reinforced sampling of same areas of interest.
Finally, the dependency on h5py has now been take out (I think!). At some point, we'll have a sensible way to save and retrieve emulators and metadata, but so far hdf5 is causing more headaches than problems it is solving!
Removed h5py dependency
Nothing new here, I just got rid of HDF5, as it's not ready to be used to load/save emulators, and the library has some really dodgy properties depending on how you compile it.
Release of Remote Sensing paper code
This code has been used in the Remote Sensing paper that cites this release (a recursive software release we're dealing with here... No less and no more...). The paper reference is
Gomez-Dans, J L, Lewis, P E, Disney M, "Efficient Emulation of Radiative Transfer Codes Using Gaussian Processes and Application to Land Surface Parameter Inferences", Remote Sensing, 2016
Now with emulator validation and testing utilities
Main update here has been the inclusion of a function that allows one to easily create an emulator from a simulator Python function. The function tests the emulator with an independent run of the simulator, and will also test the partial derivatives using finite differences.
Solves a fairly simple bug
Solves a regression in the code base.
Now with HDF5 storage format, version 1.0
This new version has changed the internal save format, using an HDF5 format. Note that for the time being, the old format is ignored, although in a new update, we'll bring it back so that whenever old .npz
files are used, they will be saved on to the new HDF5 storage. Hopefully by 1.5.1 we'll have this ready.