Bivaraite with testing #41
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ical combinations of step functions
…ully this would increase the speed
…at the initialization of jetscape methods and then using it throughout. Seems to work. 3 times speed up
…ing of weights if two models have same parameters it will only infer the common set of parameters instead of treating them as entirely different ones
…and v42, They happen for very small values. I enforce taking the abs value hence of the varaince before taking the sqrt to find sd
…set of model paramters instead of two times that
…sum. We might be able to modify this to include error correlations
…ad of sum) and same parameter option
…scape get update from laptop push to the repo
…full error covariance matrix into account
…ng the diagonal fron np.diagonal() does not work as expected for 1,n,n arrays). And then updating the models to include a log_likelihood function ontop of log_likelihood_elementwise for the newest mixing method that takes into account cross correlations
…anOSU/Taweret into jetscape_cross_correlation_mix updates from the local computer. Now linear mixing with the full error matrix works
…to utile. We can copy the source code and put it in util later on
…riate rather than in the model -- some argument name changes
…the initialization of the bivaraite mixing method
…so it can be put to general use without sims package dependence
… the data is unavialable
…s given by the model when it is evaluvated at input parameters with no experimental data
…n be merged. No need to keeep as two seperate mixing methods
…ences. Taking into accoun Nan is done by numpy
… under bivariate linear mixing
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Updated bivariatelinear mixing method with three possible ways to mix modes. BMMC, BMMcor and BMMmean. All the mixing methods have the ability to calibrate model parameters while mixing. Pytests for the three mixing methods are also included. To get an idea about how mixing methods are used in practice please take a look at coleman_models_BMM_comparative_study notebook. There I apply all three different mixing methods to the same Coleman toy models to mix + calibrate models at the same time.