apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-05 01:32:40 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'devel' into params

Browse source
This commit is contained in:
Max Zwiessele 2013-10-07 08:20:29 +01:00
commit 4f56506aa6
60 changed files with 1944 additions and 596 deletions
Download patch file Download diff file Expand all files Collapse all files

116
GPy/examples/classification.py
View file

@ -10,31 +10,11 @@ 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):
"""
Run a Gaussian process classification on the three phase oil data. The demonstration calls the basic GP classification model and uses EP to approximate the likelihood.
"""
data = GPy.util.datasets.oil()
X = data['X']
@ -64,8 +44,10 @@ def oil(num_inducing=50, max_iters=100, kernel=None):
def toy_linear_1d_classification(seed=default_seed):
"""
Simple 1D classification example
:param seed : seed value for data generation (default is 4).
:param seed: seed value for data generation (default is 4).
:type seed: int
"""
data = GPy.util.datasets.toy_linear_1d_classification(seed=seed)
@ -92,8 +74,10 @@ def toy_linear_1d_classification(seed=default_seed):
def sparse_toy_linear_1d_classification(num_inducing=10,seed=default_seed):
"""
Sparse 1D classification example
:param seed : seed value for data generation (default is 4).
:param seed: seed value for data generation (default is 4).
:type seed: int
"""
data = GPy.util.datasets.toy_linear_1d_classification(seed=seed)
@ -118,61 +102,13 @@ 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
:param seed : seed value for data generation (default is 4).
:param seed: seed value for data generation (default is 4).
:type seed: int
"""
data = GPy.util.datasets.toy_linear_1d_classification(seed=seed)
@ -198,3 +134,35 @@ 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['.*len'] = 3.
m.pseudo_EM()
print(m)
m.plot()
return m

2
GPy/examples/regression.py
View file

@ -132,7 +132,7 @@ def multiple_optima(gene_number=937, resolution=80, model_restarts=10, seed=1000
length_scales = np.linspace(0.1, 60., resolution)
log_SNRs = np.linspace(-3., 4., resolution)
data = GPy.util.datasets.della_gatta_TRP63_gene_expression(gene_number)
data = GPy.util.datasets.della_gatta_TRP63_gene_expression(data_set='della_gatta',gene_number=gene_number)
# data['Y'] = data['Y'][0::2, :]
# data['X'] = data['X'][0::2, :]