mirror of
https://github.com/SheffieldML/GPy.git
synced 2026-05-09 12:02:38 +02:00
Sparse GP serialization
This commit is contained in:
Moreno
parent
d85c9d5379
commit
7b2af57aee
4 changed files with 146 additions and 52 deletions
|
|
@ -117,3 +117,42 @@ class SparseGP(GP):
|
|||
self.Z.gradient = self.kern.gradients_X(self.grad_dict['dL_dKmm'], self.Z)
|
||||
self.Z.gradient += self.kern.gradients_X(self.grad_dict['dL_dKnm'].T, self.Z, self.X)
|
||||
self._Zgrad = self.Z.gradient.copy()
|
||||
|
||||
def to_dict(self, save_data=True):
|
||||
input_dict = super(SparseGP, self).to_dict(save_data)
|
||||
input_dict["class"] = "GPy.core.SparseGP"
|
||||
input_dict["Z"] = self.Z.tolist()
|
||||
return input_dict
|
||||
|
||||
@staticmethod
|
||||
def _from_dict(input_dict, data=None):
|
||||
import GPy
|
||||
if (input_dict['X'] is None) or (input_dict['Y'] is None):
|
||||
assert(data is not None)
|
||||
input_dict["X"], input_dict["Y"] = np.array(data[0]), np.array(data[1])
|
||||
elif data is not None:
|
||||
print("WARNING: The model has been saved with X,Y! The original values are being overriden!")
|
||||
input_dict["X"], input_dict["Y"] = np.array(data[0]), np.array(data[1])
|
||||
else:
|
||||
input_dict["X"], input_dict["Y"] = np.array(input_dict['X']), np.array(input_dict['Y'])
|
||||
|
||||
input_dict["Z"] = np.array(input_dict['Z'])
|
||||
input_dict["kernel"] = GPy.kern.Kern.from_dict(input_dict["kernel"])
|
||||
input_dict["likelihood"] = GPy.likelihoods.likelihood.Likelihood.from_dict(input_dict["likelihood"])
|
||||
mean_function = input_dict.get("mean_function")
|
||||
if mean_function is not None:
|
||||
input_dict["mean_function"] = GPy.core.mapping.Mapping.from_dict(mean_function)
|
||||
else:
|
||||
input_dict["mean_function"] = mean_function
|
||||
input_dict["inference_method"] = GPy.inference.latent_function_inference.LatentFunctionInference.from_dict(input_dict["inference_method"])
|
||||
|
||||
#FIXME: Assumes the Y_metadata is serializable. We should create a Metadata class
|
||||
Y_metadata = input_dict.get("Y_metadata")
|
||||
input_dict["Y_metadata"] = Y_metadata
|
||||
|
||||
normalizer = input_dict.get("normalizer")
|
||||
if normalizer is not None:
|
||||
input_dict["normalizer"] = GPy.util.normalizer._Norm.from_dict(normalizer)
|
||||
else:
|
||||
input_dict["normalizer"] = normalizer
|
||||
return SparseGP(**input_dict)
|
||||
|
|
|
|||
|
|
@ -402,7 +402,7 @@ class EP(EPBase, ExactGaussianInference):
|
|||
|
||||
class EPDTC(EPBase, VarDTC):
|
||||
def inference(self, kern, X, Z, likelihood, Y, mean_function=None, Y_metadata=None, Lm=None, dL_dKmm=None, psi0=None, psi1=None, psi2=None):
|
||||
if self.always_reset:
|
||||
if self.always_reset and not self.loading:
|
||||
self.reset()
|
||||
|
||||
num_data, output_dim = Y.shape
|
||||
|
|
@ -420,11 +420,11 @@ class EPDTC(EPBase, VarDTC):
|
|||
else:
|
||||
Kmn = psi1.T
|
||||
|
||||
if self.ep_mode=="nested":
|
||||
if self.ep_mode=="nested" and not self.loading:
|
||||
#Force EP at each step of the optimization
|
||||
self._ep_approximation = None
|
||||
post_params, ga_approx, log_Z_tilde = self._ep_approximation = self.expectation_propagation(Kmm, Kmn, Y, likelihood, Y_metadata)
|
||||
elif self.ep_mode=="alternated":
|
||||
elif self.ep_mode=="alternated" or self.loading:
|
||||
if getattr(self, '_ep_approximation', None) is None:
|
||||
#if we don't yet have the results of runnign EP, run EP and store the computed factors in self._ep_approximation
|
||||
post_params, ga_approx, log_Z_tilde = self._ep_approximation = self.expectation_propagation(Kmm, Kmn, Y, likelihood, Y_metadata)
|
||||
|
|
@ -434,6 +434,8 @@ class EPDTC(EPBase, VarDTC):
|
|||
else:
|
||||
raise ValueError("ep_mode value not valid")
|
||||
|
||||
self.loading = False
|
||||
|
||||
mu_tilde = ga_approx.v / ga_approx.tau.astype(float)
|
||||
|
||||
return super(EPDTC, self).inference(kern, X, Z, likelihood, ObsAr(mu_tilde[:,None]),
|
||||
|
|
@ -551,8 +553,7 @@ class EPDTC(EPBase, VarDTC):
|
|||
input_dict["_ep_approximation"] = {}
|
||||
input_dict["_ep_approximation"]["post_params"] = self._ep_approximation[0].to_dict()
|
||||
input_dict["_ep_approximation"]["ga_approx"] = self._ep_approximation[1].to_dict()
|
||||
input_dict["_ep_approximation"]["cav_params"] = self._ep_approximation[2].to_dict()
|
||||
input_dict["_ep_approximation"]["log_Z_tilde"] = self._ep_approximation[3].tolist()
|
||||
input_dict["_ep_approximation"]["log_Z_tilde"] = self._ep_approximation[2]
|
||||
|
||||
return input_dict
|
||||
|
||||
|
|
@ -566,8 +567,7 @@ class EPDTC(EPBase, VarDTC):
|
|||
if _ep_approximation is not None:
|
||||
_ep_approximation.append(posteriorParamsDTC.from_dict(_ep_approximation_dict["post_params"]))
|
||||
_ep_approximation.append(gaussianApproximation.from_dict(_ep_approximation_dict["ga_approx"]))
|
||||
_ep_approximation.append(cavityParams.from_dict(_ep_approximation_dict["cav_params"]))
|
||||
_ep_approximation.append(np.array(_ep_approximation_dict["log_Z_tilde"]))
|
||||
_ep_approximation.append(_ep_approximation_dict["log_Z_tilde"])
|
||||
ee = EPDTC(**input_dict)
|
||||
ee.ga_approx_old = ga_approx_old
|
||||
ee._ep_approximation = _ep_approximation
|
||||
|
|
|
|||
|
|
@ -7,6 +7,7 @@ from ..core import SparseGP
|
|||
from .. import likelihoods
|
||||
from .. import kern
|
||||
from ..inference.latent_function_inference import EPDTC
|
||||
from copy import deepcopy
|
||||
|
||||
class SparseGPClassification(SparseGP):
|
||||
"""
|
||||
|
|
@ -40,6 +41,27 @@ class SparseGPClassification(SparseGP):
|
|||
|
||||
SparseGP.__init__(self, X, Y, Z, kernel, likelihood, inference_method=EPDTC(), name='SparseGPClassification',Y_metadata=Y_metadata)
|
||||
|
||||
@staticmethod
|
||||
def from_sparse_gp(sparse_gp):
|
||||
from copy import deepcopy
|
||||
sparse_gp = deepcopy(sparse_gp)
|
||||
SparseGPClassification(sparse_gp.X, sparse_gp.Y, sparse_gp.Z, sparse_gp.kern, sparse_gp.likelihood, sparse_gp.inference_method, sparse_gp.mean_function, name='sparse_gp_classification')
|
||||
|
||||
def to_dict(self, save_data=True):
|
||||
model_dict = super(SparseGPClassification,self).to_dict(save_data)
|
||||
model_dict["class"] = "GPy.models.SparseGPClassification"
|
||||
return model_dict
|
||||
|
||||
@staticmethod
|
||||
def from_dict(input_dict, data=None):
|
||||
import GPy
|
||||
m = GPy.core.model.Model.from_dict(input_dict, data)
|
||||
return GPClassification.from_sparse_gp(m)
|
||||
|
||||
def save_model(self, output_filename, compress=True, save_data=True):
|
||||
self._save_model(output_filename, compress=True, save_data=True)
|
||||
|
||||
|
||||
class SparseGPClassificationUncertainInput(SparseGP):
|
||||
"""
|
||||
Sparse Gaussian Process model for classification with uncertain inputs.
|
||||
|
|
@ -87,8 +109,3 @@ class SparseGPClassificationUncertainInput(SparseGP):
|
|||
self.psi2 = self.kern.psi2n(self.Z, self.X)
|
||||
self.posterior, self._log_marginal_likelihood, self.grad_dict = self.inference_method.inference(self.kern, self.X, self.Z, self.likelihood, self.Y, self.Y_metadata, psi0=self.psi0, psi1=self.psi1, psi2=self.psi2)
|
||||
self._update_gradients()
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ import tempfile
|
|||
import GPy
|
||||
from nose import SkipTest
|
||||
import numpy as np
|
||||
import os
|
||||
fixed_seed = 11
|
||||
|
||||
|
||||
|
|
@ -116,46 +117,38 @@ class Test(unittest.TestCase):
|
|||
np.testing.assert_array_equal(e1._ep_approximation[2].v[:], e1_r._ep_approximation[2].v[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[3][:], e1_r._ep_approximation[3][:])
|
||||
|
||||
|
||||
e1 = GPy.inference.latent_function_inference.expectation_propagation.EPDTC(ep_mode="nested")
|
||||
e1.ga_approx_old = GPy.inference.latent_function_inference.expectation_propagation.gaussianApproximation(np.random.rand(10),np.random.rand(10))
|
||||
e1._ep_approximation = []
|
||||
e1._ep_approximation.append(GPy.inference.latent_function_inference.expectation_propagation.posteriorParamsDTC(np.random.rand(10),np.random.rand(10)))
|
||||
e1._ep_approximation.append(GPy.inference.latent_function_inference.expectation_propagation.gaussianApproximation(np.random.rand(10),np.random.rand(10)))
|
||||
e1._ep_approximation.append(GPy.inference.latent_function_inference.expectation_propagation.cavityParams(10))
|
||||
e1._ep_approximation[-1].v = np.random.rand(10)
|
||||
e1._ep_approximation[-1].tau = np.random.rand(10)
|
||||
e1._ep_approximation.append(np.random.rand(10))
|
||||
e1_r = GPy.inference.latent_function_inference.LatentFunctionInference.from_dict(e1.to_dict())
|
||||
|
||||
|
||||
assert type(e1) == type(e1_r)
|
||||
assert e1.epsilon==e1_r.epsilon
|
||||
assert e1.eta==e1_r.eta
|
||||
assert e1.delta==e1_r.delta
|
||||
assert e1.always_reset==e1_r.always_reset
|
||||
assert e1.max_iters==e1_r.max_iters
|
||||
assert e1.ep_mode==e1_r.ep_mode
|
||||
assert e1.parallel_updates==e1_r.parallel_updates
|
||||
|
||||
np.testing.assert_array_equal(e1.ga_approx_old.tau[:], e1_r.ga_approx_old.tau[:])
|
||||
np.testing.assert_array_equal(e1.ga_approx_old.v[:], e1_r.ga_approx_old.v[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[0].mu[:], e1_r._ep_approximation[0].mu[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[0].Sigma_diag[:], e1_r._ep_approximation[0].Sigma_diag[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[1].tau[:], e1_r._ep_approximation[1].tau[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[1].v[:], e1_r._ep_approximation[1].v[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[2].tau[:], e1_r._ep_approximation[2].tau[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[2].v[:], e1_r._ep_approximation[2].v[:])
|
||||
np.testing.assert_array_equal(e1._ep_approximation[3][:], e1_r._ep_approximation[3][:])
|
||||
|
||||
|
||||
e2 = GPy.inference.latent_function_inference.exact_gaussian_inference.ExactGaussianInference()
|
||||
e2 = GPy.inference.latent_function_inference.expectation_propagation.EPDTC(ep_mode="nested")
|
||||
e2.ga_approx_old = GPy.inference.latent_function_inference.expectation_propagation.gaussianApproximation(np.random.rand(10),np.random.rand(10))
|
||||
e2._ep_approximation = []
|
||||
e2._ep_approximation.append(GPy.inference.latent_function_inference.expectation_propagation.posteriorParamsDTC(np.random.rand(10),np.random.rand(10)))
|
||||
e2._ep_approximation.append(GPy.inference.latent_function_inference.expectation_propagation.gaussianApproximation(np.random.rand(10),np.random.rand(10)))
|
||||
e2._ep_approximation.append(100.0)
|
||||
e2_r = GPy.inference.latent_function_inference.LatentFunctionInference.from_dict(e2.to_dict())
|
||||
|
||||
assert type(e2) == type(e2_r)
|
||||
assert e2.epsilon==e2_r.epsilon
|
||||
assert e2.eta==e2_r.eta
|
||||
assert e2.delta==e2_r.delta
|
||||
assert e2.always_reset==e2_r.always_reset
|
||||
assert e2.max_iters==e2_r.max_iters
|
||||
assert e2.ep_mode==e2_r.ep_mode
|
||||
assert e2.parallel_updates==e2_r.parallel_updates
|
||||
|
||||
np.testing.assert_array_equal(e2.ga_approx_old.tau[:], e2_r.ga_approx_old.tau[:])
|
||||
np.testing.assert_array_equal(e2.ga_approx_old.v[:], e2_r.ga_approx_old.v[:])
|
||||
np.testing.assert_array_equal(e2._ep_approximation[0].mu[:], e2_r._ep_approximation[0].mu[:])
|
||||
np.testing.assert_array_equal(e2._ep_approximation[0].Sigma_diag[:], e2_r._ep_approximation[0].Sigma_diag[:])
|
||||
np.testing.assert_array_equal(e2._ep_approximation[1].tau[:], e2_r._ep_approximation[1].tau[:])
|
||||
np.testing.assert_array_equal(e2._ep_approximation[1].v[:], e2_r._ep_approximation[1].v[:])
|
||||
assert(e2._ep_approximation[2] == e2_r._ep_approximation[2])
|
||||
|
||||
e3 = GPy.inference.latent_function_inference.exact_gaussian_inference.ExactGaussianInference()
|
||||
e3_r = GPy.inference.latent_function_inference.LatentFunctionInference.from_dict(e3.to_dict())
|
||||
|
||||
assert type(e3) == type(e3_r)
|
||||
|
||||
|
||||
def test_serialize_deserialize_model(self):
|
||||
def test_serialize_deserialize_GP(self):
|
||||
np.random.seed(fixed_seed)
|
||||
N = 20
|
||||
Nhalf = int(N/2)
|
||||
|
|
@ -165,13 +158,13 @@ class Test(unittest.TestCase):
|
|||
likelihood = GPy.likelihoods.Bernoulli()
|
||||
inference_method=GPy.inference.latent_function_inference.expectation_propagation.EP(ep_mode="nested")
|
||||
mean_function=None
|
||||
|
||||
m = GPy.core.GP(X=X, Y=Y, kernel=kernel, likelihood=likelihood, inference_method=inference_method, mean_function=mean_function, normalizer=True, name='gp_classification')
|
||||
m.optimize()
|
||||
m.save_model("temp_test_gp_with_data.json", compress=True, save_data=True)
|
||||
m.save_model("temp_test_gp_without_data.json", compress=True, save_data=False)
|
||||
m1_r = GPy.core.GP.load_model("temp_test_gp_with_data.json.zip")
|
||||
m2_r = GPy.core.GP.load_model("temp_test_gp_without_data.json.zip", (X,Y))
|
||||
import os
|
||||
os.remove("temp_test_gp_with_data.json.zip")
|
||||
os.remove("temp_test_gp_without_data.json.zip")
|
||||
var = m.predict(X)[0]
|
||||
|
|
@ -180,7 +173,32 @@ class Test(unittest.TestCase):
|
|||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var2_r).flatten())
|
||||
|
||||
def test_serialize_deserialize_inference_GPRegressor(self):
|
||||
def test_serialize_deserialize_SparseGP(self):
|
||||
np.random.seed(fixed_seed)
|
||||
N = 20
|
||||
Nhalf = int(N/2)
|
||||
X = np.hstack([np.random.normal(5, 2, Nhalf), np.random.normal(10, 2, Nhalf)])[:, None]
|
||||
Y = np.hstack([np.ones(Nhalf), np.zeros(Nhalf)])[:, None]
|
||||
kernel = GPy.kern.RBF(1)
|
||||
likelihood = GPy.likelihoods.Bernoulli()
|
||||
inference_method=GPy.inference.latent_function_inference.expectation_propagation.EPDTC(ep_mode="nested")
|
||||
mean_function=None
|
||||
|
||||
sm = GPy.core.SparseGP(X=X, Y=Y, Z=X[0:20,:], kernel=kernel, likelihood=likelihood, inference_method=inference_method, mean_function=mean_function, normalizer=True, name='sparse_gp_classification')
|
||||
sm.optimize()
|
||||
sm.save_model("temp_test_gp_with_data.json", compress=True, save_data=True)
|
||||
sm.save_model("temp_test_gp_without_data.json", compress=True, save_data=False)
|
||||
sm1_r = GPy.core.GP.load_model("temp_test_gp_with_data.json.zip")
|
||||
sm2_r = GPy.core.GP.load_model("temp_test_gp_without_data.json.zip", (X,Y))
|
||||
os.remove("temp_test_gp_with_data.json.zip")
|
||||
os.remove("temp_test_gp_without_data.json.zip")
|
||||
var = sm.predict(X)[0]
|
||||
var1_r = sm1_r.predict(X)[0]
|
||||
var2_r = sm2_r.predict(X)[0]
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var2_r).flatten())
|
||||
|
||||
def test_serialize_deserialize_GPRegressor(self):
|
||||
np.random.seed(fixed_seed)
|
||||
N = 50
|
||||
N_new = 50
|
||||
|
|
@ -195,7 +213,6 @@ class Test(unittest.TestCase):
|
|||
m.save_model("temp_test_gp_regressor_without_data.json", compress=True, save_data=False)
|
||||
m1_r = GPy.models.GPRegression.load_model("temp_test_gp_regressor_with_data.json.zip")
|
||||
m2_r = GPy.models.GPRegression.load_model("temp_test_gp_regressor_without_data.json.zip", (X,Y))
|
||||
import os
|
||||
os.remove("temp_test_gp_regressor_with_data.json.zip")
|
||||
os.remove("temp_test_gp_regressor_without_data.json.zip")
|
||||
|
||||
|
|
@ -208,7 +225,7 @@ class Test(unittest.TestCase):
|
|||
np.testing.assert_array_equal(var.flatten(), var1_r.flatten())
|
||||
np.testing.assert_array_equal(var.flatten(), var2_r.flatten())
|
||||
|
||||
def test_serialize_deserialize_inference_GPClassifier(self):
|
||||
def test_serialize_deserialize_GPClassification(self):
|
||||
np.random.seed(fixed_seed)
|
||||
N = 50
|
||||
Nhalf = int(N/2)
|
||||
|
|
@ -221,7 +238,6 @@ class Test(unittest.TestCase):
|
|||
m.save_model("temp_test_gp_classifier_without_data.json", compress=True, save_data=False)
|
||||
m1_r = GPy.models.GPClassification.load_model("temp_test_gp_classifier_with_data.json.zip")
|
||||
m2_r = GPy.models.GPClassification.load_model("temp_test_gp_classifier_without_data.json.zip", (X,Y))
|
||||
import os
|
||||
os.remove("temp_test_gp_classifier_with_data.json.zip")
|
||||
os.remove("temp_test_gp_classifier_without_data.json.zip")
|
||||
|
||||
|
|
@ -231,6 +247,28 @@ class Test(unittest.TestCase):
|
|||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
|
||||
def test_serialize_deserialize_SparseGPClassification(self):
|
||||
np.random.seed(fixed_seed)
|
||||
N = 50
|
||||
Nhalf = int(N/2)
|
||||
X = np.hstack([np.random.normal(5, 2, Nhalf), np.random.normal(10, 2, Nhalf)])[:, None]
|
||||
Y = np.hstack([np.ones(Nhalf), np.zeros(Nhalf)])[:, None]
|
||||
kernel = GPy.kern.RBF(1)
|
||||
m = GPy.models.SparseGPClassification(X, Y, num_inducing=3, kernel=kernel)
|
||||
m.optimize()
|
||||
m.save_model("temp_test_sparse_gp_classifier_with_data.json", compress=True, save_data=True)
|
||||
m.save_model("temp_test_sparse_gp_classifier_without_data.json", compress=True, save_data=False)
|
||||
m1_r = GPy.models.SparseGPClassification.load_model("temp_test_sparse_gp_classifier_with_data.json.zip")
|
||||
m2_r = GPy.models.SparseGPClassification.load_model("temp_test_sparse_gp_classifier_without_data.json.zip", (X,Y))
|
||||
os.remove("temp_test_sparse_gp_classifier_with_data.json.zip")
|
||||
os.remove("temp_test_sparse_gp_classifier_without_data.json.zip")
|
||||
|
||||
var = m.predict(X)[0]
|
||||
var1_r = m1_r.predict(X)[0]
|
||||
var2_r = m2_r.predict(X)[0]
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
np.testing.assert_array_equal(np.array(var).flatten(), np.array(var1_r).flatten())
|
||||
|
||||
if __name__ == "__main__":
|
||||
#import sys;sys.argv = ['', 'Test.test_parameter_index_operations']
|
||||
unittest.main()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue