lsqfitgp

This is the documentation of the Python module lsqfitgp. It provides a simple but powerful interface to use Gaussian processes for inference. The code is open source, available on github under the GNU General Public License.

Gaussian processes are a statistical tool for fitting unknown functions. If you want to know more about Gaussian processes, the book Gaussian Processes for Machine Learning is a good reference available for free. However, understanding the technical details is not necessary to use the basic functionality of the module.

To start, read the Installation section, and then First example: a sine. To report bugs or request features, open an issue on github.

Contents

• Guide
  • 1. Installation
  • 2. First example: a sine
  • 3. More on kernels
  • 4. Taking derivatives
  • 5. Taking integrals
  • 6. A custom kernel: text classification
  • 7. Multidimensional input
  • 8. Partial derivatives
  • 9. Multidimensional output
  • 10. Splitting components
  • 11. Hyperparameters
  • 12. Hyperparameters in the input
  • 13. Nonlinear models
  • 14. Optimization
• Reference
  • Predefined kernels
  • Generic kernel classes
  • Kernel decorators
  • Kernel transformations
  • Derivative specification
  • Gaussian process class
  • Structured arrays
  • Fitting
  • Random sampling
  • Gaussian copulas
  • BART
  • Gvar extensions
• Example scripts
  • Short index
  • Index with figures
• Development
  • Setup
  • Changelog
  • Licensed sources

• Index

• Search Page

Manual for older versions

• Latest development version

• 0.20.2

• 0.20

• 0.19

• 0.18

• 0.17

• 0.16

• 0.15

• 0.14

• 0.13

• 0.12

• 0.11

• 0.10

• 0.9

• 0.8