skip to navigation
skip to content

gplib 0.2.4

Python library for Gaussian Process Regression.

Latest Version: 0.5.2


A python library for Gaussian Process Regression.

Setup GPlib

  • The following packages must be installed before installing GPlib
# for ptyhon3
apt-get install python3-tk
# or for python2
apt-get install python-tk
  • Create and activate virtualenv (for python2) or venv (for ptyhon3)
# for ptyhon3
python3 -m venv --system-site-packages .env
# or for python2
virtualenv --system-site-packages .env

source .env/bin/activate
  • Upgrade pip
# for ptyhon3
python3 -m pip install --upgrade pip
# or for python2
python -m pip install --upgrade pip
  • Install GPlib package
python -m pip install gplib

Use GPlib

  • Import GPlib to use it in your python script.
import gplib
  • Generate some data and test points.
import numpy as np
data = {
  'X': np.arange(3, 8, 1)[:, None],
  'Y': np.random.uniform(0, 2, 5)[:, None]
plot_points = np.arange(0, 10, 0.01)[:, None]
  • Initialize the GP module with the desired modules.
mean_function = gplib.mea.Constant(data)
covariance_function = gplib.cov.SquaredExponential(data, is_ard=False)
likelihood_function = gplib.lik.Gaussian(is_noisy=True)
inference_method = gplib.inf.ExactGaussian()

gp = gplib.GP(
  • Sample the prior and the posterior GPs.
prior_samples = gp.sample(plot_points, n_samples=10)
posterior_samples = gp.posterior.sample(plot_points, n_samples=10)
  • Finally plot the samples.
import matplotlib.pyplot as plt'ggplot')

  prior_samples, color='#43dce5'
  posterior_samples, color='#b19df0'
  (data['Y']).flatten().tolist(), color='#714ce5',
  linestyle='None', marker='o'
  • There are more examples in examples/ directory. Check them out!

Develop GPlib

  • Download the repository using git
git clone
cd gplib
git config 'MAIL'
git config 'NAME'
git config credential.helper 'cache --timeout=300'
git config push.default simple
File Type Py Version Uploaded on Size
gplib-0.2.4-py2.py3-none-any.whl (md5) Python Wheel py2.py3 2017-10-12 32KB
gplib-0.2.4.tar.gz (md5) Source 2017-10-12 24KB