apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-18 13:55:14 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Import fix for Py3

Browse source
This commit is contained in:
Mike Croucher 2015-02-27 17:35:26 +00:00
parent 6554c32d23
commit 786feded41
2 changed files with 45 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

16
GPy/inference/latent_function_inference/__init__.py
View file

@ -61,15 +61,15 @@ class InferenceMethodList(LatentFunctionInference, list):
for inf in state: for inf in state:
self.append(inf) self.append(inf)
from exact_gaussian_inference import ExactGaussianInference from .exact_gaussian_inference import ExactGaussianInference
from laplace import Laplace from .laplace import Laplace
from GPy.inference.latent_function_inference.var_dtc import VarDTC from GPy.inference.latent_function_inference.var_dtc import VarDTC
from expectation_propagation import EP from .expectation_propagation import EP
from expectation_propagation_dtc import EPDTC from .expectation_propagation_dtc import EPDTC
from dtc import DTC from .dtc import DTC
from fitc import FITC from .fitc import FITC
from var_dtc_parallel import VarDTC_minibatch from .var_dtc_parallel import VarDTC_minibatch
from svgp import SVGP from .svgp import SVGP
# class FullLatentFunctionData(object): # class FullLatentFunctionData(object):
# #

73
GPy/util/univariate_Gaussian.py
View file

@ -2,7 +2,7 @@
# Licensed under the BSD 3-clause license (see LICENSE.txt) # Licensed under the BSD 3-clause license (see LICENSE.txt)
import numpy as np import numpy as np
from scipy import weave #from scipy import weave
def std_norm_pdf(x): def std_norm_pdf(x):
"""Standard Gaussian density function""" """Standard Gaussian density function"""
@ -37,41 +37,42 @@ def std_norm_cdf(x):
cdf_x = cdf_x.reshape(x_shape) cdf_x = cdf_x.reshape(x_shape)
return cdf_x return cdf_x
def std_norm_cdf_weave(x): #Commented out since this isn't used...and since it breaks Py3 compatibility
""" #def std_norm_cdf_weave(x):
Cumulative standard Gaussian distribution # """
Based on Abramowitz, M. and Stegun, I. (1970) # Cumulative standard Gaussian distribution
# Based on Abramowitz, M. and Stegun, I. (1970)
A weave implementation of std_norm_cdf, which is faster. this is unused, #
because of the difficulties of a weave dependency. (see github issue #94) # A weave implementation of std_norm_cdf, which is faster. this is unused,
# because of the difficulties of a weave dependency. (see github issue #94)
""" #
#Generalize for many x # """
x = np.asarray(x).copy() # #Generalize for many x
cdf_x = np.zeros_like(x) # x = np.asarray(x).copy()
N = x.size # cdf_x = np.zeros_like(x)
support_code = "#include <math.h>" # N = x.size
code = """ # support_code = "#include <math.h>"
# code = """
double sign, t, erf; #
for (int i=0; i<N; i++){ # double sign, t, erf;
sign = 1.0; # for (int i=0; i<N; i++){
if (x[i] < 0.0){ # sign = 1.0;
sign = -1.0; # if (x[i] < 0.0){
x[i] = -x[i]; # sign = -1.0;
} # x[i] = -x[i];
x[i] = x[i]/sqrt(2.0); # }
# x[i] = x[i]/sqrt(2.0);
t = 1.0/(1.0 + 0.3275911*x[i]); #
# t = 1.0/(1.0 + 0.3275911*x[i]);
erf = 1. - exp(-x[i]*x[i])*t*(0.254829592 + t*(-0.284496736 + t*(1.421413741 + t*(-1.453152027 + t*(1.061405429))))); #
# erf = 1. - exp(-x[i]*x[i])*t*(0.254829592 + t*(-0.284496736 + t*(1.421413741 + t*(-1.453152027 + t*(1.061405429)))));
//return_val = 0.5*(1.0 + sign*erf); #
cdf_x[i] = 0.5*(1.0 + sign*erf); # //return_val = 0.5*(1.0 + sign*erf);
} # cdf_x[i] = 0.5*(1.0 + sign*erf);
""" # }
weave.inline(code, arg_names=['x', 'cdf_x', 'N'], support_code=support_code) # """
return cdf_x # weave.inline(code, arg_names=['x', 'cdf_x', 'N'], support_code=support_code)
# return cdf_x
def inv_std_norm_cdf(x): def inv_std_norm_cdf(x):
""" """