apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-06-02 14:45:15 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[spgp minibatch] added new routine for psi NxMxM, much faster, little bigger mem footbprint

Browse source
This commit is contained in:
Max Zwiessele 2015-09-04 10:33:32 +01:00
parent b73932c350
commit cb024f0bf8
5 changed files with 101 additions and 146 deletions
Download patch file Download diff file Expand all files Collapse all files

37
GPy/inference/optimization/stochastics.py
View file

@ -43,7 +43,7 @@ class SparseGPMissing(StochasticStorage):
np.set_printoptions(threshold='nan')
for d in range(self.Y.shape[1]):
inan = np.isnan(self.Y)[:, d]
arr_str = np.array2string(~inan, np.inf, 0, True, '', formatter={'bool':lambda x: '1' if x else '0'})
arr_str = np.array2string(inan, np.inf, 0, True, '', formatter={'bool':lambda x: '1' if x else '0'})
try:
bdict[arr_str][0].append(d)
except:
@ -56,35 +56,36 @@ class SparseGPStochastics(StochasticStorage):
For the sparse gp we need to store the dimension we are in,
and the indices corresponding to those
"""
def __init__(self, model, batchsize=1):
def __init__(self, model, batchsize=1, missing_data=True):
self.batchsize = batchsize
self.output_dim = model.Y.shape[1]
self.Y = model.Y_normalized
self.missing_data = missing_data
self.reset()
self.do_stochastics()
def do_stochastics(self):
import numpy as np
if self.batchsize == 1:
self.current_dim = (self.current_dim+1)%self.output_dim
self.d = [[[self.current_dim], np.isnan(self.Y[:, self.d])]]
self.d = [[[self.current_dim], np.isnan(self.Y[:, self.current_dim]) if self.missing_data else None]]
else:
import numpy as np
self.d = np.random.choice(self.output_dim, size=self.batchsize, replace=False)
bdict = {}
opt = np.get_printoptions()
np.set_printoptions(threshold='nan')
for d in self.d:
inan = np.isnan(self.Y[:, d])
arr_str = int(np.array2string(inan,
np.inf, 0,
True, '',
formatter={'bool':lambda x: '1' if x else '0'}), 2)
try:
bdict[arr_str][0].append(d)
except:
bdict[arr_str] = [[d], ~inan]
np.set_printoptions(**opt)
self.d = bdict.values()
if self.missing_data:
opt = np.get_printoptions()
np.set_printoptions(threshold='nan')
for d in self.d:
inan = np.isnan(self.Y[:, d])
arr_str = np.array2string(inan,np.inf, 0,True, '',formatter={'bool':lambda x: '1' if x else '0'})
try:
bdict[arr_str][0].append(d)
except:
bdict[arr_str] = [[d], ~inan]
np.set_printoptions(**opt)
self.d = bdict.values()
else:
self.d = [[self.d, None]]
def reset(self):
self.current_dim = -1