pyGPGO - GitLite

KO | EN

gitlite — search

#python #golang #machine-learning #deep-learning #docker #macos #java #windows #awesome #vue #awesome-list #pytorch #ios #open-source

pyGPGO

(★ 245)

Bayesian optimization for Python

File Explorer

Download Latest Version (.zip)

- - api.rst
  - comparison.rst
  - conf.py
  - features.rst
  - index.rst
  - modules.rst
  - pyGPGO.acquisition.rst
  - pyGPGO.covfunc.rst
  - pyGPGO.GPGO.rst
  - pyGPGO.logger.rst
  - pyGPGO.rst
  - pyGPGO.surrogates.BoostedTrees.rst
  - pyGPGO.surrogates.GaussianProcess.rst
  - pyGPGO.surrogates.GaussianProcessMCMC.rst
  - pyGPGO.surrogates.RandomForest.rst
  - pyGPGO.surrogates.rst
  - pyGPGO.surrogates.tStudentProcess.rst
  - pyGPGO.surrogates.tStudentProcessMCMC.rst
  - pyGPGO.version.rst
- Makefile
- acqzoo.py
- bayoptwork.py
- covzoo.py
- drawGP.py
- example1d.py
- example2d.py
- exampleGBM.py
- exampleint.py
- exampleRF.py
- franke.py
- gif_gen.py
- hyperopt.py
- hyperpost.py
- integratedacq.py
- minimalexample.py
- sineGP.py
- sklearnexample.py
- - __init__.cpython-36.pyc
  - acquisition.cpython-36.pyc
  - covfunc.cpython-36.pyc
  - GPGO.cpython-36.pyc
  - logger.cpython-36.pyc
  - version.cpython-36.pyc
- - __init__.py
  - BoostedTrees.py
  - GaussianProcess.py
  - GaussianProcessMCMC.py
  - RandomForest.py
  - tStudentProcess.py
  - tStudentProcessMCMC.py
- __init__.py
- acquisition.py
- covfunc.py
- GPGO.py
- logger.py
- version.py
- test_acquisition.py
- test_covfunc.py
- test_GPGO.py
- test_surrogates.py
- test_surrogates_mcmc.py
- test_surrogates_sk.py
- hyperparam.ipynb
- mlopt.ipynb
.coverage
.gitattributes
.travis.yml
CONTRIBUTING.md
franke.gif
LICENSE
MANIFEST.in
paper.bib
paper.md
README.md
requirements_rtd.txt
setup.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# pyGPGO: Bayesian Optimization for Python
[![Build Status](https://travis-ci.org/hawk31/pyGPGO.svg?branch=master)](https://travis-ci.org/hawk31/pyGPGO)
[![codecov](https://codecov.io/gh/hawk31/pyGPGO/branch/master/graph/badge.svg)](https://codecov.io/gh/hawk31/pyGPGO)
[![Documentation Status](https://readthedocs.org/projects/pygpgo/badge/?version=latest)](http://pygpgo.readthedocs.io/en/latest/?badge=latest)
[![DOI](https://zenodo.org/badge/74589922.svg)](https://zenodo.org/badge/latestdoi/74589922)
[![status](http://joss.theoj.org/papers/7d60820fabf7fa81501e3d638cac522d/status.svg)](http://joss.theoj.org/papers/7d60820fabf7fa81501e3d638cac522d)

![sine](http://i.giphy.com/l3q2s3MQ4bPb5RogU.gif)

pyGPGO is a simple and modular Python (>3.5) package for bayesian optimization.

Bayesian optimization is a framework that can be used in situations where:

* Your objective function may not have a closed form. (e.g. the result of a simulation)
* No gradient information is available.
* Function evaluations may be noisy.
* Evaluations are expensive (time/cost-wise)

### Installation

Retrieve the latest stable release from pyPI:

```bash
pip install pyGPGO
```

Or if you're feeling adventurous, retrieve it from this repo,

```bash
pip install git+https://github.com/hawk31/pyGPGO
```

Check our documentation in http://pygpgo.readthedocs.io/.

### Features

* Different surrogate models: Gaussian Processes, Student-t Processes, Random Forests, Gradient Boosting Machines.
* Type II Maximum-Likelihood of covariance function hyperparameters. 
* MCMC sampling for full-Bayesian inference of hyperparameters (via `pyMC3`).
* Integrated acquisition functions

### A small example!

The user only has to define a function to maximize and a dictionary specifying input space.

```python
import numpy as np
from pyGPGO.covfunc import matern32
from pyGPGO.acquisition import Acquisition
from pyGPGO.surrogates.GaussianProcess import GaussianProcess
from pyGPGO.GPGO import GPGO

def f(x, y):
    # Franke's function (https://www.mathworks.com/help/curvefit/franke.html)
    one = 0.75 * np.exp(-(9 * x - 2) ** 2 / 4 - (9 * y - 2) ** 2 / 4)
    two = 0.75 * np.exp(-(9 * x + 1) ** 2/ 49 - (9 * y + 1) / 10)
    three = 0.5 * np.exp(-(9 * x - 7) ** 2 / 4 - (9 * y -3) ** 2 / 4)
    four = 0.25 * np.exp(-(9 * x - 4) ** 2 - (9 * y - 7) ** 2)
    return one + two + three - four

cov = matern32()
gp = GaussianProcess(cov)
acq = Acquisition(mode='ExpectedImprovement')
param = {'x': ('cont', [0, 1]),
         'y': ('cont', [0, 1])}

np.random.seed(1337)
gpgo = GPGO(gp, acq, f, param)
gpgo.run(max_iter=10)

```

Check the `tutorials` and `examples` folders for more ideas on how to use the software.

### Citation

If you use pyGPGO in academic work please cite:

Jiménez, J., & Ginebra, J. (2017). pyGPGO: Bayesian Optimization for Python. The Journal of Open Source Software, 2, 431.