edc4a651c6
ADD Mixins for normalized and stationary kernels
2015-10-19 18:07:14 +02:00
c3a41a310f
FIX String comparison via equality and not identity in Hyperparameter.__init__
2015-10-19 18:07:14 +02:00
e2a340a4ee
REF More meaningful names for hyperparameters of GP kernels
2015-10-19 18:07:14 +02:00
2dd1f285b9
PEP8 Making pep8 and pyflakes happy
2015-10-19 18:07:14 +02:00
f76e64c9c7
FIX Fix failing tests (doctest, order of hyperparameters, pairwise_kernels)
2015-10-19 18:07:14 +02:00
1813322d0a
DOC Documenting GP kernel API
2015-10-19 18:07:14 +02:00
c85177ef51
DEL Removing bounds.setter in kernels.py
2015-10-19 18:07:14 +02:00
eb54b496d2
REF Removing theta_vars attribute from kernels and using Hyperparameter instances instead
2015-10-19 18:07:14 +02:00
4c40f64753
FIX theta_vars correctly supported in KernelOperators
2015-10-19 18:07:14 +02:00
d344fa6588
ENH Full support of (deep) get_params() and set_params() in GP kernels
2015-10-19 18:07:14 +02:00
d0eb99be76
ENH More efficient computation of K_gradient for anisotropic Matern kernel
2015-10-19 18:07:13 +02:00
c6db24e56f
REF Several small changes based on @eickenberg's suggestions
2015-10-19 18:07:13 +02:00
9b86186ceb
COS Removing keyword magic from PairwiseKernel
2015-10-19 18:07:13 +02:00
adc7451201
PEP8 Fixing PEP8 issues in gaussian_process package
2015-10-19 18:07:13 +02:00
c8f23f401b
FIX Using six.string_types instead of basestring (python3 compatibility)
2015-10-19 18:07:12 +02:00
bf0e290a38
ADD CompoundKernel for multi-class GP classification
2015-10-19 18:07:12 +02:00
37a6348e30
FIX RBF and Matern kernel handle 1d length 1 length-scales correctly
2015-10-19 18:07:12 +02:00
9443f948c6
FIX Checking for correct dimensionality of anisotropic kernels
2015-10-19 18:07:12 +02:00
daa90c22d3
ENH Adding Matern kernel for Gaussian Processes
2015-10-19 18:07:12 +02:00
8af909b96e
FIX Correcly composing theta vector in GP kernels
2015-10-19 18:07:12 +02:00
4db5142bb8
REFACTOR GP kernel hyperparameters theta and their bounds are log-tranformed
...
This representation of the search space is more amenable for
hyperparameter search, as hyperparameters like
length-scales naturally live on a log-scale.
2015-10-19 18:07:11 +02:00
698ecf5a01
DOC Backported documentation to kernels module
2015-10-19 18:07:11 +02:00
d0a5ff89f2
FIX GP kernels check for type equality before checking attribute equality
2015-10-19 18:07:11 +02:00
c961392424
REFACTOR Changed order of l and alpha in RationalQuadratic kernel
2015-10-19 18:07:10 +02:00
ebf3f05994
REFACTOR Removed literal form of specifying bounds for ConstantKernel
2015-10-19 18:07:10 +02:00
caa4196c3a
DOC Revised docstrings of kernels.py
2015-10-19 18:07:10 +02:00
31ef64571e
FIX Dealing with anisotropic length-scales correctly
2015-10-19 18:07:10 +02:00
e3413b70f7
FIX Kernel property theta can deal with anisotropic RBF kernel
2015-10-19 18:07:10 +02:00
79d2194331
REFACTOR Kernel hyperparamters are now set via their name
...
The property theta, its gradient and bounds are used solely for optimization but not during kernel specification.
2015-10-19 18:07:10 +02:00
1c70e52dd6
ENH Adding diag(X) method to GP kernels.
...
Using this method rather than np.diag(kernel(X)) or np.apply_along_axis
reduces memory-consumption and speeds up computation considerably
2015-10-19 18:04:56 +02:00
0a23d9e604
REFACTOR Compute standard deviation of predictive distribution at n points in O(n)
2015-10-19 18:04:56 +02:00
e3423b989a
FIX Minor bugfixes and downward-compatibility/python3 issue
2015-10-19 18:04:56 +02:00
91b5739a43
FIX Using numpy-downward compatible ones_lile() instead of full_like()
2015-10-19 18:04:56 +02:00
a3abc09456
ENH Added Exponentiation kernel (DotProduct no longer has internal degree)
2015-10-19 18:04:56 +02:00
2feb6e02cf
REFACTOR Replacing all calls to deepcopy() by clone()
2015-10-19 18:04:55 +02:00
8699a4c03f
ENH Kernel implements equality check and get_params() method
2015-10-19 18:04:55 +02:00
403b5f1412
REFACTOR REnamed kernel property params to theta
2015-10-19 18:04:55 +02:00
9f6e48f6cc
REFACTOR GP kernels use separate specification of bounds and params (no joint param_space)
2015-10-19 18:04:55 +02:00
c259905021
ENH Adding method is_stationary to GP kernels
2015-10-19 18:04:55 +02:00
cb7c4243e8
MISC Reorganizing kernel module
2015-10-19 18:04:55 +02:00
a13f76508f
DOC Extended documentation of GP kernels module
2015-10-19 18:04:55 +02:00
209b202fba
ENH Analytic gradients for ExpSine2, RationalQuadratic, DotProduct kernels
2015-10-19 18:04:55 +02:00
d8405c2403
REFACTOR Hyperparameter optimization in GPs enabled explicitly by optimizer parameter
2015-10-19 18:04:55 +02:00
eb44a42b17
ENH Adding DotProduct kernel and fixing ExpSine2 kernel
2015-10-19 18:04:55 +02:00
6b3df1b164
ENH Adding RationalQuadratic and ExpSineSquared kernels
2015-10-19 18:04:55 +02:00
4dcd70678f
ENH More efficient approximation of gradient in PairwiseKernel
2015-10-19 18:04:55 +02:00
5eaa8cf594
ENH Adding PairwiseKernel for GPs (wraps kernels from metrics.pairwise)
2015-10-19 18:04:54 +02:00
03e35758f8
REFACTOR Merging kernel methods auto() and cross() in __call__()
2015-10-19 18:04:54 +02:00
a5dc3491ad
MISC Revised gaussian_process package based on @eickenberg's suggestions
2015-10-19 18:04:54 +02:00
7b4d93535b
DOC Revised GP examples (added doc etc.)
2015-10-19 18:04:54 +02:00
Jan Hendrik Metzen