224 commits

Author	SHA1	Message	Date
bobturneruk	3375458dbb	change rst syntax	2020-06-18 14:41:05 +01:00
Zhenwen Dai	1f9ac259ca	Merge pull request #783 from MashaNaslidnyk/num-data-fix ... Update self.num_data in GP when X is updated	2020-03-13 10:08:05 +00:00
Antoine Blanchard	7550b1e5ef	fix normalizer	2020-01-14 15:32:25 -05:00
Masha Naslidnyk 🦉	7871af8dec	self.num_data and self.input_dim are set dynamically in class GP() after the shape of X. In MRD, the user-specific values are passed around until X is defined.	2020-01-10 12:42:03 +00:00
Masha Naslidnyk 🦉	1e06c6ce2f	Update self.num_data in GP when X is updated	2019-09-05 14:39:13 +01:00
mzwiessele	8446da628b	fix: samples tests and plotting, multioutput	2018-09-02 19:07:23 +01:00
Neil Lawrence	e623078954	Merge branch 'devel' into devel	2018-09-01 04:38:02 -07:00
robromijnders	4b998da73a	fix typo in docstring for GP.opimize()	2018-08-29 18:30:42 +02:00
Keerthana Elango	eca5806518	Return deserialized models with actual type instead of base type	2018-07-24 10:46:33 +01:00
Moreno	11aa6ea27b	Serialization: Add docstrings	2018-06-07 09:52:13 +01:00
Diego Torrejon	69eb888ad1	Maintains consistency with numpy arrays	2018-03-22 16:32:05 -04:00
Diego Torrejon	90c2912ace	Fixes the dimensions of the samples output	2018-03-21 18:00:13 -04:00
Max Zwiessele	56696ced27	Merge pull request #597 from marpulli/devel ... Allow calculation of full predictive covariance matrices with multipl…	2018-02-12 16:32:12 +01:00
Mark Pullin	aa116517cf	Make predictive_gradients more efficient	2018-02-06 20:51:59 +00:00
Mark Pullin	ccfcfa1a85	Allow calculation of full predictive covariance matrices with multiple outputs and normalization	2018-02-05 11:21:02 +00:00
Andrei Paleyes	ae3ea375f8	Moved posterior_covariance to Posterior class	2018-01-08 15:07:57 +00:00
Andrei Paleyes	0e2ec01839	Implemented utility function to compute covariance between points in GP Model	2018-01-05 11:40:59 +00:00
Neil Lawrence	0d26609b15	Rewrite poster_samples_f to return NxDxsize	2018-01-01 01:18:08 +01:00
Neil Lawrence	ff4f861fcb	Testing for dims should be checking whether 2nd dim is greater than 1	2017-12-31 23:22:23 +01:00
Neil Lawrence	cb1ab89d8a	Update gp.py ... Sample return seemed to have been based on number of training data, not number of posterior samples requested.	2017-12-31 22:54:43 +01:00
Mark Pullin	456b7cd83b	Small correction to doc	2017-11-27 10:58:21 +00:00
Moreno	e572bfb746	Basic framework for serializing GPy models	2017-09-11 12:18:01 +01:00
Alex Feldstein	221f7f792f	fix for parallel optimization	2017-03-17 19:32:47 -04:00
mzwiessele	6fc0cc630c	fix: predictive_gradients for new posterior class	2017-01-10 14:38:09 +00:00
mzwiessele	d343ec8b41	[warped stuff] plotting and normalizer in warped gps	2016-08-17 14:51:29 +01:00
Max Zwiessele	b1fd7c9aaf	[grads x]	2016-06-08 14:28:25 +01:00
Max Zwiessele	787168a394	[dxxdiag] some steps towards the diagonal gradients in xx	2016-06-08 10:22:36 +01:00
Max Zwiessele	a3f458926b	[gradsxx] putting tests in, not complete yet!	2016-06-07 09:24:38 +01:00
Max Zwiessele	4e833a4f3a	Merge branch 'devel' into gradientsxx	2016-06-06 10:50:34 +01:00
mzwiessele	375f3e0d6c	[setxy] was bugged	2016-05-11 15:02:44 +01:00
mzwiessele	17bfccb457	[gradxx] not working with X,X...	2016-05-06 16:02:53 +01:00
Max Zwiessele	da30663228	Merge branch 'gradientsxx' of github.com:SheffieldML/GPy into gradientsxx	2016-05-04 12:26:19 +01:00
Max Zwiessele	5d19039d90	[gradients xx] getting there	2016-05-04 09:11:04 +01:00
alessandratosi	bf56a2d85e	fixed covariance computation in predict_jacobian	2016-05-03 15:16:01 +01:00
mzwiessele	af286ba528	[slicing] fixed slicing for second order derivatives	2016-04-22 15:46:30 +01:00
Max Zwiessele	61286a10ee	[optimize] optional parameters taken over to GPy	2016-04-08 07:37:51 +01:00
Max Zwiessele	1753b89334	[magnification] prediction now accepts dimensions	2016-04-04 10:24:44 +01:00
Max Zwiessele	bb9626dd8b	Revert "Revert "[predict] added noiseless convenience function to gp, bc of whining about it..."" ... This reverts commit 7c95076b9f.	2016-04-01 15:48:21 +01:00
Max Zwiessele	7c95076b9f	Revert "[predict] added noiseless convenience function to gp, bc of whining about it..." ... This reverts commit 2001cd6dfd.	2016-04-01 15:47:03 +01:00
Max Zwiessele	2001cd6dfd	[predict] added noiseless convenience function to gp, bc of whining about it...	2016-04-01 15:27:03 +01:00
Zhenwen Dai	67ba9b60c6	move _raw_predict into posterior object	2016-03-17 11:29:33 +00:00
Zhenwen Dai	ba74e29aee	merge with upstream	2016-03-10 18:17:35 +00:00
Max Zwiessele	b4a32a8cb1	[deprecated] deprecated spelling mistake in wishart embedding	2016-03-04 11:34:41 +00:00
Zhenwen Dai	00e4ac152a	merge GPy upstream	2016-02-23 13:52:45 +00:00
Max Zwiessele	98daaba57e	[plotting] xlim setting	2016-02-19 14:55:36 +00:00
Max Zwiessele	7b5422b694	[plotting&kern] bugfixes in plotting and kernel size	2016-01-22 11:26:29 +00:00
Zhenwen Dai	8b279175c5	fix the issue of negative prediction variance of normal GP	2016-01-21 11:22:57 +00:00
mzwiessele	568a38dfba	[dir] structure preserved	2015-10-15 15:13:16 +01:00
mzwiessele	dce82847a7	[paramz] fully integrated all tests running	2015-10-15 14:59:57 +01:00
mzwiessele	e49c75ce2e	[paramz] started to pull paramz out	2015-10-14 10:28:23 +01:00