Scikit-Optimize, or skopt, is a simple and efficient library for sequential model-based optimization, accessible to everybody and reusable in various contexts.

The library is built on top of NumPy, SciPy and Scikit-Learn.

We do not do gradient-based optimization. For gradient-based optimization you should be looking at scipy.optimize

Approximated objective function after 50 iterations of gp_minimize. Plot made using skopt.plots.plot_objective.

• Static documentation - Static documentation
• Example notebooks - can be found under the examples/ directory.
• Issue tracker - https://github.com/scikit-optimize/scikit-optimize/issues
• Releases - https://pypi.python.org/pypi/scikit-optimize

pip install scikit-optimize

Find the minimum of the noisy function f(x) over the range -2 < x < 2 with skopt:

import numpy as np
from skopt import gp_minimize

def f(x):
    return (np.sin(5 * x[0]) * (1 - np.tanh(x[0] ** 2)) *
            np.random.randn() * 0.1)

res = gp_minimize(f, [(-2.0, 2.0)])

For more read our introduction to bayesian optimization and the other examples.

The library is still experimental and under heavy development. Checkout the ROADMAP for the next release or look at some easy issues to get started contributing.

The development version can be installed through:

git clone https://github.com/scikit-optimize/scikit-optimize.git
cd scikit-optimize
pip install -r requirements.txt
python setup.py develop

Run the tests by executing nosetests in the top level directory.

Contributors are welcome!