如何使用 scikit-learn GaussianProcessRegressor 重现 GPy GPRegression 的结果?
How to reproduce results of GPy GPRegression using scikit-learn GaussianProcessRegressor?
GPRegression
(GPy
) 和 GaussianProcessRegressor
(scikit-learn
) 都使用相似的初始值和相同的优化器 (lbfgs
)。为什么结果差异很大?
#!pip -qq install pods
#!pip -qq install GPy
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import RBF, ConstantKernel as C
from sklearn.preprocessing import StandardScaler
import pods
data = pods.datasets.olympic_marathon_men()
X = StandardScaler().fit_transform(data['X'])
y = data['Y']
# scikit-learn
model = GaussianProcessRegressor(C()*RBF(), n_restarts_optimizer=20, random_state=0)
model.fit(X, y)
print(model.kernel_)
# GPy
from GPy.models import GPRegression
from GPy.kern import RBF as GPyRBF
model = GPRegression(X, y, GPyRBF(1))
model.optimize_restarts(20, verbose=0)
print(model.kern)
结果
2.89**2 * RBF(length_scale=0.173)
rbf. | value | constraints | priors
variance | 25.399509298957504 | +ve |
lengthscale | 4.279767394389103 | +ve |
使用 GPy RBF()
内核等同于使用 scikit-learn ConstantKernel()*RBF() + WhiteKernel()
。因为 GPy 库在内部添加了似然噪声。使用这个我能够在两者中获得可比较的结果。
您可以通过将噪声显式设置为 0 来尝试使用 Gpy
的无噪声版本的 GP,您将获得与 skelarn
和 Gpy
相同的超参数调整结果:
# scikit-learn
model = GaussianProcessRegressor(C()*RBF(), n_restarts_optimizer=20, random_state=0) # don't add noise
model.fit(X, y)
print(model.kernel_)
# 2.89**2 * RBF(length_scale=0.173)
# Gpy
model = GPRegression(X, y, GPyRBF(1))
model['.*Gaussian_noise'] = 0 # make noise zero
model['.*noise'].fix()
model.optimize_restarts(20, verbose=0)
print(model.kern)
# rbf. | value | constraints | priors
# variance | 8.343280650322102 | +ve |
# lengthscale | 0.1731764533721659 | +ve |
RBF 方差的最佳值 = 2.89**2 = 8.3521
和长度尺度超参数具有大致相同的值,从上面可以看出。
或使用显式白噪声内核 scikit-learn
:
# scikit-learn
from sklearn.gaussian_process.kernels import WhiteKernel as W
model = GaussianProcessRegressor(C()*RBF()+W(), n_restarts_optimizer=20, random_state=0)
model.fit(X, y)
print(model.kernel_)
# 5.04**2 * RBF(length_scale=4.28) + WhiteKernel(noise_level=0.0485)
# GPy
model = GPRegression(X, y, GPyRBF(1))
model.optimize_restarts(20, verbose=0)
print(model.kern)
# rbf. | value | constraints | priors
# variance | 25.3995066661936 | +ve |
# lengthscale | 4.2797670212128756 | +ve |
RBF 方差的最佳值 = 5.04**2 = 25.4016
和长度尺度超参数具有大致相同的值,从上面可以看出。
GPRegression
(GPy
) 和 GaussianProcessRegressor
(scikit-learn
) 都使用相似的初始值和相同的优化器 (lbfgs
)。为什么结果差异很大?
#!pip -qq install pods
#!pip -qq install GPy
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import RBF, ConstantKernel as C
from sklearn.preprocessing import StandardScaler
import pods
data = pods.datasets.olympic_marathon_men()
X = StandardScaler().fit_transform(data['X'])
y = data['Y']
# scikit-learn
model = GaussianProcessRegressor(C()*RBF(), n_restarts_optimizer=20, random_state=0)
model.fit(X, y)
print(model.kernel_)
# GPy
from GPy.models import GPRegression
from GPy.kern import RBF as GPyRBF
model = GPRegression(X, y, GPyRBF(1))
model.optimize_restarts(20, verbose=0)
print(model.kern)
结果
2.89**2 * RBF(length_scale=0.173)
rbf. | value | constraints | priors
variance | 25.399509298957504 | +ve |
lengthscale | 4.279767394389103 | +ve |
使用 GPy RBF()
内核等同于使用 scikit-learn ConstantKernel()*RBF() + WhiteKernel()
。因为 GPy 库在内部添加了似然噪声。使用这个我能够在两者中获得可比较的结果。
您可以通过将噪声显式设置为 0 来尝试使用 Gpy
的无噪声版本的 GP,您将获得与 skelarn
和 Gpy
相同的超参数调整结果:
# scikit-learn
model = GaussianProcessRegressor(C()*RBF(), n_restarts_optimizer=20, random_state=0) # don't add noise
model.fit(X, y)
print(model.kernel_)
# 2.89**2 * RBF(length_scale=0.173)
# Gpy
model = GPRegression(X, y, GPyRBF(1))
model['.*Gaussian_noise'] = 0 # make noise zero
model['.*noise'].fix()
model.optimize_restarts(20, verbose=0)
print(model.kern)
# rbf. | value | constraints | priors
# variance | 8.343280650322102 | +ve |
# lengthscale | 0.1731764533721659 | +ve |
RBF 方差的最佳值 = 2.89**2 = 8.3521
和长度尺度超参数具有大致相同的值,从上面可以看出。
或使用显式白噪声内核 scikit-learn
:
# scikit-learn
from sklearn.gaussian_process.kernels import WhiteKernel as W
model = GaussianProcessRegressor(C()*RBF()+W(), n_restarts_optimizer=20, random_state=0)
model.fit(X, y)
print(model.kernel_)
# 5.04**2 * RBF(length_scale=4.28) + WhiteKernel(noise_level=0.0485)
# GPy
model = GPRegression(X, y, GPyRBF(1))
model.optimize_restarts(20, verbose=0)
print(model.kern)
# rbf. | value | constraints | priors
# variance | 25.3995066661936 | +ve |
# lengthscale | 4.2797670212128756 | +ve |
RBF 方差的最佳值 = 5.04**2 = 25.4016
和长度尺度超参数具有大致相同的值,从上面可以看出。