Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

V0.1.0rc #37

Merged
merged 17 commits into from
Oct 22, 2019
Merged

V0.1.0rc #37

merged 17 commits into from
Oct 22, 2019

Conversation

edaub
Copy link
Collaborator

@edaub edaub commented Oct 18, 2019

Suggested commit to use for v0.1.0. This and all future commits to master will be tagged and use Semantic Versioning (major = API changes, minor = new features backwards compatible with API, micro = bugfixes only with no new features). This commit has working codecov and documentation, so we can fix readthedocs to build master from this commit.

Changes include the version number in setup.py, and code to transmit this information to the documentation and package (mogp_emulator.__version__ should now correctly display the version number).

edaub and others added 17 commits April 23, 2019 15:31
* implemented all cases for init method of ExperimentalDesign

* implemented monte carlo experimental design

* implemented lhd class, and moved generic sampling method to the appropriate base class

* modified benchmarks to use experimental design implementations and deleted old lhd utility

* set up documentation file for experimental design classes

* wrote docstrings for experimental design class and init method

* added docstrings for additional methods in experimental design implementation

* finished docstrings for experimental design class

* added docstrings for monte carlo designs

* added docstrings for latin hypercube designs

* fixed issues with documentation showing up for base experimental design class

* modified README to show badge for travis and documentation

* added codecov hook to travis file

* added codecov hook to travis file
* added support for fixed and adaptive noise addition to emulator

* initial work on sequential design class

* implemented simple get methods and corresponding unit tests

* have most basic functionality of sequential design working with unit tests

* finished base implementation of sequential design class

* initial structure and tests for MICE implementation

* renamed jitter parameter to nugget to match with usage in MICE design implementation

* have all basic pieces of MICE design implemented

* changed mice implementation to use woodbury identity to speed up algorithm

* reemoved n_targets from the sequential design implementation and started writing docstrings

* finished writing MICE docstrings plus a few code corrections and unit test changes

* added a benchmark demonstrating use of the MICE algorithm
* added separate functions to calculated squared exponential kernel

* added matern 5/2 covariance function

* put kernel computations into a separate function and removed conjugate gradient based unit test that always gave problems

* moved kernel functions and tests to separate files

* added function to compute gradient of the squared exponential kernel

* changed GP class to use derivative function

* added derivatives for matern 5/2 kernel

* quick and dirty modification to GP in order to use kernel functions

* cleaned up distance calculation to use standardized euclidean distance

* modified fast GP in MICE code to use kernel interface

* made correction to meaning of nugget parameter for MICE candidate GP to be relative to current variance

* fixed minor issues in MICE design to allow for zero samples and ensuring that parameter values are correctly set

* updated MICE benchmark details

* cosmetic tweaks to MICE benchmark

* full hessian implementation in kernel functions

* refactored kernel functions into objects

* implemented Hessian computation into GP class

* Documented base kernel class

* Documented derived kernel classes

* added documentation pages for kernels

* corrected documentation to include newly implemented classes and fixed some old bugs

* renamed run_init_design to be consistent with other methods that use *_initial_design

* made minor change in MICEFastGP documentation

* added full docstring for GP hessian method

* Fixed bug in GP predictions where roundoff error gave negative variances

* added simple capabilities to save and load sequential designs

* implemented batch version of sequential design in base class and in MICE
…n GP (#26)

* updates to readme to cover installation in more detail and add mice benchmark

* fixed minor problem in example in GP docstring and removed cdist function
* modified docs pages and conf.py file to try to fix readthedocs build

* added yaml file for readthedocs

* modifications to conf.py file

* changed conf.py file for docs again

* modified readthedocs yaml file again to try and build package

* fixed readthedocs yaml file again

* more tweaks to readthedocs yaml

* more fixes to readthedocs yaml file

* modification to conf.py file for sphinx
Minor tweaks to ensure results get uploaded correctly.
@edaub edaub requested a review from ots22 October 18, 2019 16:21
Copy link
Member

@ots22 ots22 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good for v0.1, let's merge.

@edaub edaub merged commit e46437c into master Oct 22, 2019
@edaub edaub deleted the v0.1.0rc branch October 22, 2019 10:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants