Metadata-Version: 2.1
Name: bullseye_method
Version: 1.0.2
Summary: Implemented tensorflow version of the Bullseye method for prior approximation.
Home-page: https://github.com/Whenti/bullseye
Author: Quentin Leveque
Author-email: qleveque@hotmail.com
License: UNKNOWN
Description: # Bullseye!
        
        "Bullseye!" is a new algorithm for computing the Gaussian Variational Approximation of a target distribution. Its strong point lies in the fact that it can easily be parallelized and distributed.
        
        ## Getting Started
        
        These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
        
        ### Installing
        
        Bullseye! is now available as a [PyPI package](https://pypi.python.org/pypi/bullseye_method/):
        
        ```
        pip install bullseye_method
        ```
        
        or clone the repository :
        
        ```
        git clone https://github.com/Whenti/bullseye
        ```
        
        or [download and extract the zip](https://github.com/Whenti/bullseye/archive/master.zip) into your project folder.
        
        ## Running the tests
        
        To see if everything is working properly, you can already run the algorithm on a multilogit model with artificially generated data.
        
        ```py
        from Bullseye.Tests import simple_test
        simple_test()
        ```
        
        ## Example
        
        ```py
        import Bullseye
        from Bullseye import generate_multilogit
        
        theta_0, x_array, y_array = generate_multilogit(d = 10, n = 10**3, k = 5)
        
        bull = Bullseye.Graph()
        bull.feed_with(x_array,y_array)
        bull.set_predefined_model("multilogit")
        bull.set_predefined_prior("normal_iid")
        bull.init_with(mu_0 = 0, cov_0 = 1)
        bull.set_options(local_std_trick = True, s=5)
        bull.build()
        
        bull.run()
        ```
        
        ## Authors
        
        * **Quentin Lévêque** [Whenti](https://github.com/Whenti)
        
        See also the list of [contributors](https://github.com/Whenti/bullseye/contributors) who participated in this project. Hopefully, there will be more.
        
        ## License
        
        This project licensed under the GPL3 License - see the [LICENSE.txt](LICENSE.txt) file for details.
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
