https://github.com/wildtreetech/bayesian-optimisation
Finding the best parameters for any algorithm
https://github.com/wildtreetech/bayesian-optimisation
bayesian-optimization ipynb notebook regression
Last synced: 4 months ago
JSON representation
Finding the best parameters for any algorithm
- Host: GitHub
- URL: https://github.com/wildtreetech/bayesian-optimisation
- Owner: wildtreetech
- Created: 2017-07-17T13:13:56.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-11-01T09:07:07.000Z (over 8 years ago)
- Last Synced: 2025-02-01T10:41:35.484Z (about 1 year ago)
- Topics: bayesian-optimization, ipynb, notebook, regression
- Language: Jupyter Notebook
- Size: 4.16 MB
- Stars: 41
- Watchers: 5
- Forks: 10
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Bayesian optimisation
=====================
How to find the best parameters of any algorithm.
Notebooks
=========
Follow along with these notebooks:
1. [`scipy.optimize` for the win](01-scipy-optimize.ipynb)
1. [Bayesian optimisation](02-bayesian-optimisation.ipynb)
1. [Acquisition functions](03-acquisition-functions.ipynb)
1. [Regression with errorbars](04-regression-with-errorbars.ipynb)
1. [Bayesian beer](05-bayesian-beer.ipynb)
Setup
=====
You will need the following python libraries: `scikit-learn`, `jupyter`,
`matplotlib`, `scikit-optimize`* and their dependencies.
To install `scikit-optimize` use:
```
$ pip install https://github.com/scikit-optimize/scikit-optimize/archive/1677188ee6de3365f7925de780dd2f31e5e34ee4.zip
```
This will install a particular snapshot of the library that is known to work. You can
probably use `pip install scikit-learn` as well.