Commit graph

4405 commits

Author SHA1 Message Date
Zhenwen Dai
6119c33078 Support non-symmetric dL_dKmm for stationary kernel 2014-06-03 11:34:32 +01:00
Zhenwen Dai
2b5753e6f6 Merge branch 'devel' of github.com:SheffieldML/GPy into devel 2014-05-30 18:56:32 +01:00
Zhenwen Dai
6e30f3c6c3 [splitkern] support idx_p==0 2014-05-30 18:56:23 +01:00
James Hensman
8eaa0bbf8a basic vardtc working 2014-05-30 16:45:51 +01:00
Ricardo
6877b21fad Merge branch 'devel' of github.com:SheffieldML/GPy into devel 2014-05-30 16:23:51 +01:00
James Hensman
2a69312aa0 Merge branc( 'devel' of github.com:SheffieldML/GPy into devel 2014-05-30 09:22:47 +01:00
James Hensman
ed74a81732 editied whitespace 2014-05-30 09:22:43 +01:00
Zhenwen Dai
47ba2542c2 minor changes 2014-05-29 17:11:26 +01:00
Zhenwen Dai
4c538efb64 DiffGenomeKern bug fix 2014-05-29 17:10:14 +01:00
Neil Lawrence
dd6f7c1f4c Modified Spellman et al data load. 2014-05-29 16:57:01 +01:00
zhenwen
ea1326c8c8 [splitkern] some more changes 2014-05-29 14:54:11 +01:00
Ricardo
7dd6031a0b Merge branch 'devel' of github.com:SheffieldML/GPy into devel 2014-05-29 14:37:18 +01:00
Zhenwen Dai
5f08152651 [splitkern] some additional implmentation 2014-05-29 14:03:59 +01:00
Zhenwen Dai
c2568d2e9f [splitkern] bug fix 2014-05-29 13:21:14 +01:00
Zhenwen Dai
f9291fe7da [splitkern] buf fix 2014-05-29 11:21:19 +01:00
Zhenwen Dai
5d728f7715 Merge branch 'devel' of github.com:SheffieldML/GPy into devel 2014-05-29 10:30:11 +01:00
Zhenwen Dai
74b62ab3c3 merge the bug of fixing function 2014-05-29 10:29:18 +01:00
James Hensman
dadbc6c92d merging 2014-05-29 10:27:37 +01:00
Zhenwen Dai
988889247c developing split kernel 2014-05-29 10:27:36 +01:00
James Hensman
7a3d13894f reverting the fixing behaviour.
two reasons: 1) the new behaviour is confusing for new users. Either
something is fixed, or it's not. 2) the fixing didn't work! things that
should have been fixed were passed to the optimizer for optimization.

If we really want to save keystrokes, consider this:

m.foo.fix()
m.foo.unfix()
m.foo.constrain_positive()

is the same as

m.foo.fix()
m.foo.constrain_positive()

but the latter throws a warning.
2014-05-29 10:24:20 +01:00
Zhenwen Dai
627cf9c86c developing split kernel 2014-05-29 10:13:16 +01:00
James Hensman
ac2d28e2fd reverting the fixing behaviour.
two reasons: 1) the new behaviour is confusing for new users. Either
something is fixed, or it's not. 2) the fixing didn't work! things that
should have been fixed were passed to the optimizer for optimization.

If we really want to save keystrokes, consider this:

m.foo.fix()
m.foo.unfix()
m.foo.constrain_positive()

is the same as

m.foo.fix()
m.foo.constrain_positive()

but the latter throws a warning.
2014-05-29 09:55:49 +01:00
Neil Lawrence
0fde50f56d Changes to configuration file set up: now uses defaults.cfg, installation.cfg and searches locally for .gpy_user.cfg in the users home directory. 2014-05-28 10:25:02 +01:00
Neil Lawrence
9ea236112e Added CIFAR-10 data to data sets. 2014-05-27 16:27:27 +01:00
Neil Lawrence
e3b6d9c9c5 Merge branch 'devel' of https://github.com/SheffieldML/GPy into devel 2014-05-24 15:31:50 +01:00
Neil Lawrence
de75d7dac1 New data sets 2014-05-24 15:31:42 +01:00
teodecampos
f84f3f4308 Fixed an assertion, it was checking the dimensionality of the input data matrix, rather than that of the labels. 2014-05-23 17:18:38 +01:00
mzwiessele
0252fae298 [bgplvm] do test latents updated for devel branch 2014-05-23 13:26:41 +01:00
mzwiessele
3525e45b2f [copy] is now fully functional, only hierarchy observers will be copied and pickled 2014-05-23 11:11:21 +01:00
mzwiessele
96e1e13f7e [dim_reduce examples] updated robot_wireless 2014-05-22 15:32:59 +01:00
mzwiessele
d6bf3b0d79 [dim_reduce examples] updated swiss roll 2014-05-22 15:25:26 +01:00
mzwiessele
fa750d4ba4 [dim_reduce examples] updated plotting of brendan and bgplvm_oil 2014-05-22 15:08:36 +01:00
mzwiessele
6534e6606d [tests] added some unfix fix print and gradcheck tests, it basically just behaves as a user would do with a model 2014-05-22 12:56:02 +01:00
mzwiessele
c2e3bf5bce [caching] catching key error, when individuum is already gone 2014-05-22 12:55:18 +01:00
mzwiessele
9bf7e1baf6 [optimizer&fixing] optimizer has only one optimizer copy and fixing remembers old constraint 2014-05-22 12:44:50 +01:00
mzwiessele
5a2bc4863b [optimizer] one copy for the optimizer in optimizer_array, use this instead of _set|get_params_transformed 2014-05-22 11:39:04 +01:00
Max Zwiessele
43ee8ce614 [reverts] some reverts, as one param etc does not work 2014-05-21 16:49:47 +01:00
Zhenwen Dai
b945c20004 restructure rbf kernel 2014-05-21 16:42:35 +01:00
Max Zwiessele
6b2681d849 [caching] first things first 2014-05-21 16:40:57 +01:00
Max Zwiessele
24a34aee95 [model] exactly two parameter copy in memory 2014-05-21 16:33:44 +01:00
Max Zwiessele
dc628f558a [gp] output data is a copy now 2014-05-21 16:32:44 +01:00
Max Zwiessele
156ba00719 [bgplvm&mrd] missing data greatly improved, still not there yet 2014-05-21 16:32:06 +01:00
Zhenwen Dai
04ab93a961 BayersianGPLVM mpi support 2014-05-21 12:44:24 +01:00
Alan Saul
a0d6634387 Added a numpy version of univariate gaussian, untested
and is significantly slower but may be useful soon.
2014-05-21 11:30:52 +01:00
Zhenwen Dai
52c0be1848 merge devel branch in 2014-05-21 10:38:34 +01:00
Zhenwen Dai
a2203179f6 [psi2] implement RBF cpu 2014-05-21 10:34:51 +01:00
Max Zwiessele
b520eb212c [fixing] fixing now saves the old constraint 2014-05-20 16:39:52 +01:00
Max Zwiessele
c507cfe4ab [index operations] added lookup for properties for a given index as dict <properties, subindex> for given index 2014-05-20 16:06:56 +01:00
Max Zwiessele
ef256223d1 [mrd] more control for init, some missing data adjustements, init greatly improved 2014-05-20 14:49:20 +01:00
Max Zwiessele
995de897b3 [core updates] first try to switch updates off and on. Use m.updates = False to switch updates off, and vice-versa 2014-05-20 14:48:53 +01:00