apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-01 07:46:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

crescent data example is better organized

Browse source
This commit is contained in:
Ricardo 2013-09-20 11:40:00 +01:00
parent 99c3af63c4
commit c8fec98071
1 changed files with 33 additions and 71 deletions
Download patch file Download diff file Expand all files Collapse all files

104
GPy/examples/classification.py
View file

@ -10,27 +10,6 @@ import numpy as np
import GPy
default_seed = 10000
def crescent_data(seed=default_seed, kernel=None): # FIXME
"""Run a Gaussian process classification on the crescent data. The demonstration calls the basic GP classification model and uses EP to approximate the likelihood.
:param model_type: type of model to fit ['Full', 'FITC', 'DTC'].
:param seed : seed value for data generation.
:type seed: int
:param inducing : number of inducing variables (only used for 'FITC' or 'DTC').
:type inducing: int
"""
data = GPy.util.datasets.crescent_data(seed=seed)
Y = data['Y']
Y[Y.flatten()==-1] = 0
m = GPy.models.GPClassification(data['X'], Y)
#m.update_likelihood_approximation()
#m.optimize()
m.pseudo_EM()
print(m)
m.plot()
return m
def oil(num_inducing=50, max_iters=100, kernel=None):
"""
@ -118,56 +97,6 @@ def sparse_toy_linear_1d_classification(num_inducing=10,seed=default_seed):
return m
def sparse_crescent_data(num_inducing=10, seed=default_seed, kernel=None):
"""
Run a Gaussian process classification with DTC approxiamtion on the crescent data. The demonstration calls the basic GP classification model and uses EP to approximate the likelihood.
:param model_type: type of model to fit ['Full', 'FITC', 'DTC'].
:param seed : seed value for data generation.
:type seed: int
:param inducing : number of inducing variables (only used for 'FITC' or 'DTC').
:type inducing: int
"""
data = GPy.util.datasets.crescent_data(seed=seed)
Y = data['Y']
Y[Y.flatten()==-1]=0
m = GPy.models.SparseGPClassification(data['X'], Y, kernel=kernel, num_inducing=num_inducing)
m['.*len'] = 10.
#m.update_likelihood_approximation()
#m.optimize()
m.pseudo_EM()
print(m)
m.plot()
return m
def FITC_crescent_data(num_inducing=10, seed=default_seed):
"""
Run a Gaussian process classification with FITC approximation on the crescent data. The demonstration uses EP to approximate the likelihood.
:param model_type: type of model to fit ['Full', 'FITC', 'DTC'].
:param seed : seed value for data generation.
:type seed: int
:param inducing : number of inducing variables (only used for 'FITC' or 'DTC').
:type num_inducing: int
"""
data = GPy.util.datasets.crescent_data(seed=seed)
Y = data['Y']
Y[Y.flatten()==-1]=0
m = GPy.models.FITCClassification(data['X'], Y,num_inducing=num_inducing)
m.constrain_bounded('.*len',1.,1e3)
m['.*len'] = 3.
#m.update_likelihood_approximation()
#m.optimize()
m.pseudo_EM()
print(m)
m.plot()
return m
def toy_heaviside(seed=default_seed):
"""
Simple 1D classification example using a heavy side gp transformation
@ -198,3 +127,36 @@ def toy_heaviside(seed=default_seed):
return m
def crescent_data(model_type='Full', num_inducing=10, seed=default_seed, kernel=None):
"""
Run a Gaussian process classification on the crescent data. The demonstration calls the basic GP classification model and uses EP to approximate the likelihood.
:param model_type: type of model to fit ['Full', 'FITC', 'DTC'].
:param inducing: number of inducing variables (only used for 'FITC' or 'DTC').
:type inducing: int
:param seed: seed value for data generation.
:type seed: int
:param kernel: kernel to use in the model
:type kernel: a GPy kernel
"""
data = GPy.util.datasets.crescent_data(seed=seed)
Y = data['Y']
Y[Y.flatten()==-1] = 0
if model_type == 'Full':
m = GPy.models.GPClassification(data['X'], Y,kernel=kernel)
elif model_type == 'DTC':
m = GPy.models.SparseGPClassification(data['X'], Y, kernel=kernel, num_inducing=num_inducing)
m['.*len'] = 10.
elif model_type == 'FITC':
m = GPy.models.FITCClassification(data['X'], Y, kernel=kernel, num_inducing=num_inducing)
m.constrain_bounded('.*len',1.,1e3)
m['.*len'] = 3.
m.pseudo_EM()
print(m)
m.plot()
return m