Coverage for geometric_kernels/__init__.py: 100%

1""" 

2The library root. The kernel classes are contained within the 

3:py:mod:`kernels <geometric_kernels.kernels>` package. They need to be paired 

4with one of the space classes from the 

5:py:mod:`spaces <geometric_kernels.spaces>` package. 

6 

7The :py:mod:`frontends <geometric_kernels.frontends>` package contains kernel 

8wrapper classes compatible with Gaussian process libraries like 

9`GPFlow <https://www.gpflow.org/>`_, `GPyTorch <https://gpytorch.ai/>`_, 

10and `GPJax <https://jaxgaussianprocesses.com/>`_. 

11 

12The :py:mod:`feature_maps <geometric_kernels.feature_maps>` package provides 

13(approximate) finite-dimensional feature maps for various geometric kernels. 

14 

15The :py:mod:`sampling <geometric_kernels.sampling>` package contains routines 

16that allow efficient (approximate) sampling of functions from geometric Gaussian 

17process priors. 

18 

19The :py:mod:`utils <geometric_kernels.utils>` package provides (relatively) 

20general purpose utility code used throughout the library. This is an internal 

21part of the library. 

22 

23The :py:mod:`resources <geometric_kernels.resources>` package contains static 

24resources, such as results of symbolic algebra computations. This is an 

25internal part of the library. 

26 

27The :py:mod:`lab_extras <geometric_kernels.lab_extras>` package contains our 

28custom additions to `LAB <https://github.com/wesselb/lab>`_, the framework that 

29allows our library to be backend-independent. This is an internal part of the 

30library. 

31 

32""" 

33 

34import logging 

35 

36import geometric_kernels._logging # noqa: F401 

37 

38logging.getLogger(__name__).info( 

39 "Numpy backend is enabled. To enable other backends, don't forget to `import geometric_kernels.*backend name*`." 

40) 

41logging.getLogger(__name__).info( 

42 "We may be suppressing some logging of external libraries. To override the logging policy, call `logging.basicConfig`." 

43)