def modelselection_random_search_liblinear_modular(
traindat=traindat, label_traindat=label_traindat):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import ContingencyTableEvaluation, ACCURACY
from shogun.Evaluation import StratifiedCrossValidationSplitting
from shogun.ModelSelection import RandomSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
from shogun.Features import BinaryLabels
from shogun.Features import RealFeatures
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC
# build parameter tree to select C1 and C2
param_tree_root = ModelSelectionParameters()
c1 = ModelSelectionParameters("C1")
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP)
c2 = ModelSelectionParameters("C2")
param_tree_root.append_child(c2)
c2.build_values(-2.0, 2.0, R_EXP)
# training data
features = RealFeatures(traindat)
labels = BinaryLabels(label_traindat)
# classifier
classifier = LibLinear(L2R_L2LOSS_SVC)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#classifier.print_modsel_params()
# splitting strategy for cross-validation
splitting_strategy = StratifiedCrossValidationSplitting(labels, 10)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(classifier, features, labels,
splitting_strategy,
evaluation_criterium)
cross_validation.set_autolock(False)
# model selection instance
model_selection = RandomSearchModelSelection(param_tree_root,
cross_validation, 0.5)
# perform model selection with selected methods
#print "performing model selection of"
#param_tree_root.print_tree()
best_parameters = model_selection.select_model()
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(classifier)
result = cross_validation.evaluate()
def modelselection_parameter_tree_modular(dummy):
from shogun.ModelSelection import ParameterCombination
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.Kernel import PowerKernel
from shogun.Kernel import GaussianKernel
from shogun.Kernel import DistantSegmentsKernel
from shogun.Distance import MinkowskiMetric
root=ModelSelectionParameters()
combinations=root.get_combinations()
combinations.get_num_elements()
c=ModelSelectionParameters('C');
root.append_child(c)
c.build_values(1, 11, R_EXP)
power_kernel=PowerKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#power_kernel.print_modsel_params()
param_power_kernel=ModelSelectionParameters('kernel', power_kernel)
root.append_child(param_power_kernel)
param_power_kernel_degree=ModelSelectionParameters('degree')
param_power_kernel_degree.build_values(1, 1, R_EXP)
param_power_kernel.append_child(param_power_kernel_degree)
metric1=MinkowskiMetric(10)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#metric1.print_modsel_params()
param_power_kernel_metric1=ModelSelectionParameters('distance', metric1)
param_power_kernel.append_child(param_power_kernel_metric1)
param_power_kernel_metric1_k=ModelSelectionParameters('k')
param_power_kernel_metric1_k.build_values(1, 12, R_LINEAR)
param_power_kernel_metric1.append_child(param_power_kernel_metric1_k)
gaussian_kernel=GaussianKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#gaussian_kernel.print_modsel_params()
param_gaussian_kernel=ModelSelectionParameters('kernel', gaussian_kernel)
root.append_child(param_gaussian_kernel)
param_gaussian_kernel_width=ModelSelectionParameters('width')
param_gaussian_kernel_width.build_values(1, 2, R_EXP)
param_gaussian_kernel.append_child(param_gaussian_kernel_width)
ds_kernel=DistantSegmentsKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#ds_kernel.print_modsel_params()
param_ds_kernel=ModelSelectionParameters('kernel', ds_kernel)
root.append_child(param_ds_kernel)
param_ds_kernel_delta=ModelSelectionParameters('delta')
param_ds_kernel_delta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_delta)
param_ds_kernel_theta=ModelSelectionParameters('theta')
param_ds_kernel_theta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_theta)
# root.print_tree()
combinations=root.get_combinations()
# for i in range(combinations.get_num_elements()):
# combinations.get_element(i).print_tree()
return
def modelselection_parameter_tree_modular(dummy):
from shogun.ModelSelection import ParameterCombination
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.Kernel import PowerKernel
from shogun.Kernel import GaussianKernel
from shogun.Kernel import DistantSegmentsKernel
from shogun.Distance import MinkowskiMetric
root = ModelSelectionParameters()
combinations = root.get_combinations()
combinations.get_num_elements()
c = ModelSelectionParameters('C')
root.append_child(c)
c.build_values(1, 11, R_EXP)
power_kernel = PowerKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#power_kernel.print_modsel_params()
param_power_kernel = ModelSelectionParameters('kernel', power_kernel)
root.append_child(param_power_kernel)
param_power_kernel_degree = ModelSelectionParameters('degree')
param_power_kernel_degree.build_values(1, 1, R_EXP)
param_power_kernel.append_child(param_power_kernel_degree)
metric1 = MinkowskiMetric(10)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#metric1.print_modsel_params()
param_power_kernel_metric1 = ModelSelectionParameters('distance', metric1)
param_power_kernel.append_child(param_power_kernel_metric1)
param_power_kernel_metric1_k = ModelSelectionParameters('k')
param_power_kernel_metric1_k.build_values(1, 12, R_LINEAR)
param_power_kernel_metric1.append_child(param_power_kernel_metric1_k)
gaussian_kernel = GaussianKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#gaussian_kernel.print_modsel_params()
param_gaussian_kernel = ModelSelectionParameters('kernel', gaussian_kernel)
root.append_child(param_gaussian_kernel)
param_gaussian_kernel_width = ModelSelectionParameters('width')
param_gaussian_kernel_width.build_values(1, 2, R_EXP)
param_gaussian_kernel.append_child(param_gaussian_kernel_width)
ds_kernel = DistantSegmentsKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#ds_kernel.print_modsel_params()
param_ds_kernel = ModelSelectionParameters('kernel', ds_kernel)
root.append_child(param_ds_kernel)
param_ds_kernel_delta = ModelSelectionParameters('delta')
param_ds_kernel_delta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_delta)
param_ds_kernel_theta = ModelSelectionParameters('theta')
param_ds_kernel_theta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_theta)
# root.print_tree()
combinations = root.get_combinations()
# for i in range(combinations.get_num_elements()):
# combinations.get_element(i).print_tree()
return
def modelselection_random_search_liblinear_modular (traindat=traindat, label_traindat=label_traindat):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import ContingencyTableEvaluation, ACCURACY
from shogun.Evaluation import StratifiedCrossValidationSplitting
from shogun.ModelSelection import RandomSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
from shogun.Features import BinaryLabels
from shogun.Features import RealFeatures
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC
# build parameter tree to select C1 and C2
param_tree_root=ModelSelectionParameters()
c1=ModelSelectionParameters("C1");
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP);
c2=ModelSelectionParameters("C2");
param_tree_root.append_child(c2);
c2.build_values(-2.0, 2.0, R_EXP);
# training data
features=RealFeatures(traindat)
labels=BinaryLabels(label_traindat)
# classifier
classifier=LibLinear(L2R_L2LOSS_SVC)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#classifier.print_modsel_params()
# splitting strategy for cross-validation
splitting_strategy=StratifiedCrossValidationSplitting(labels, 10)
# evaluation method
evaluation_criterium=ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation=CrossValidation(classifier, features, labels,
splitting_strategy, evaluation_criterium)
cross_validation.set_autolock(False)
# model selection instance
model_selection=RandomSearchModelSelection(param_tree_root,
cross_validation,0.5)
# perform model selection with selected methods
#print "performing model selection of"
#param_tree_root.print_tree()
best_parameters=model_selection.select_model()
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(classifier)
result=cross_validation.evaluate()
def modelselection_parameter_tree_modular():
from shogun.ModelSelection import ParameterCombination
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.ModelSelection import DynamicParameterCombinationArray
from shogun.Kernel import PowerKernel
from shogun.Kernel import GaussianKernel
from shogun.Kernel import DistantSegmentsKernel
from shogun.Distance import MinkowskiMetric
root = ModelSelectionParameters()
combinations = root.get_combinations()
combinations.get_num_elements()
c = ModelSelectionParameters("C")
root.append_child(c)
c.build_values(1, 11, R_EXP)
power_kernel = PowerKernel()
param_power_kernel = ModelSelectionParameters("kernel", power_kernel)
root.append_child(param_power_kernel)
param_power_kernel_degree = ModelSelectionParameters("degree")
param_power_kernel_degree.build_values(1, 1, R_EXP)
param_power_kernel.append_child(param_power_kernel_degree)
metric1 = MinkowskiMetric(10)
param_power_kernel_metric1 = ModelSelectionParameters("distance", metric1)
param_power_kernel.append_child(param_power_kernel_metric1)
param_power_kernel_metric1_k = ModelSelectionParameters("k")
param_power_kernel_metric1_k.build_values(1, 12, R_LINEAR)
param_power_kernel_metric1.append_child(param_power_kernel_metric1_k)
gaussian_kernel = GaussianKernel()
param_gaussian_kernel = ModelSelectionParameters("kernel", gaussian_kernel)
root.append_child(param_gaussian_kernel)
param_gaussian_kernel_width = ModelSelectionParameters("width")
param_gaussian_kernel_width.build_values(1, 2, R_EXP)
param_gaussian_kernel.append_child(param_gaussian_kernel_width)
ds_kernel = DistantSegmentsKernel()
param_ds_kernel = ModelSelectionParameters("kernel", ds_kernel)
root.append_child(param_ds_kernel)
param_ds_kernel_delta = ModelSelectionParameters("delta")
param_ds_kernel_delta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_delta)
param_ds_kernel_theta = ModelSelectionParameters("theta")
param_ds_kernel_theta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_theta)
root.print_tree()
combinations = root.get_combinations()
for i in range(combinations.get_num_elements()):
combinations.get_element(i).print_tree()
return
#nu=ModelSelectionParameters("nu");
#param_tree_root.append_child(nu);
#nu.build_values(-2.0, 2.0, R_EXP);
# training data
features=RealFeatures(traindat)
labels=Labels(label_traindat)
# kernel
# width for the kernel
width = 2.0
kernel = GaussianKernel(features, features, width)
# Generate parameter tree
param_tree_root=ModelSelectionParameters()
# Add SVM margin
c1=ModelSelectionParameters("C1");
c1.build_values(-2.0, 2.0, R_EXP);
param_tree_root.append_child(c1)
c2=ModelSelectionParameters("C2");
c2.build_values(-2.0, 2.0, R_EXP);
param_tree_root.append_child(c2)
# Add kernel width parameter
param_gaussian_kernel=ModelSelectionParameters('kernel', kernel)
param_gaussian_kernel_width=ModelSelectionParameters('width')
param_gaussian_kernel_width.build_values(-2.0, 2.0, R_EXP)
param_gaussian_kernel.append_child(param_gaussian_kernel_width)
def create_param_tree():
root=ModelSelectionParameters()
c1=ModelSelectionParameters("C1")
root.append_child(c1)
c1.build_values(-1.0, 1.0, R_EXP)
c2=ModelSelectionParameters("C2")
root.append_child(c2)
c2.build_values(-1.0, 1.0, R_EXP)
gaussian_kernel=GaussianKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
gaussian_kernel.print_modsel_params()
param_gaussian_kernel=ModelSelectionParameters("kernel", gaussian_kernel)
gaussian_kernel_width=ModelSelectionParameters("width")
gaussian_kernel_width.build_values(-1.0, 1.0, R_EXP, 1.0, 2.0)
param_gaussian_kernel.append_child(gaussian_kernel_width)
root.append_child(param_gaussian_kernel)
power_kernel=PowerKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
power_kernel.print_modsel_params()
param_power_kernel=ModelSelectionParameters("kernel", power_kernel)
root.append_child(param_power_kernel)
param_power_kernel_degree=ModelSelectionParameters("degree")
param_power_kernel_degree.build_values(1.0, 2.0, R_LINEAR)
param_power_kernel.append_child(param_power_kernel_degree)
metric=MinkowskiMetric(10)
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
metric.print_modsel_params()
param_power_kernel_metric1=ModelSelectionParameters("distance", metric)
param_power_kernel.append_child(param_power_kernel_metric1)
param_power_kernel_metric1_k=ModelSelectionParameters("k")
param_power_kernel_metric1_k.build_values(1.0, 2.0, R_LINEAR)
param_power_kernel_metric1.append_child(param_power_kernel_metric1_k)
return root
def create_param_tree():
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.ModelSelection import ParameterCombination
from shogun.Kernel import GaussianKernel, PolyKernel
root = ModelSelectionParameters()
tau = ModelSelectionParameters("tau")
root.append_child(tau)
# also R_LINEAR/R_LOG is available as type
min = -1
max = 1
type = R_EXP
step = 1.5
base = 2
tau.build_values(min, max, type, step, base)
# gaussian kernel with width
gaussian_kernel = GaussianKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#gaussian_kernel.print_modsel_params()
param_gaussian_kernel = ModelSelectionParameters("kernel", gaussian_kernel)
gaussian_kernel_width = ModelSelectionParameters("width")
gaussian_kernel_width.build_values(5.0, 8.0, R_EXP, 1.0, 2.0)
param_gaussian_kernel.append_child(gaussian_kernel_width)
root.append_child(param_gaussian_kernel)
# polynomial kernel with degree
poly_kernel = PolyKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#poly_kernel.print_modsel_params()
param_poly_kernel = ModelSelectionParameters("kernel", poly_kernel)
root.append_child(param_poly_kernel)
# note that integers are used here
param_poly_kernel_degree = ModelSelectionParameters("degree")
param_poly_kernel_degree.build_values(1, 2, R_LINEAR)
param_poly_kernel.append_child(param_poly_kernel_degree)
return root
def modelselection_grid_search_simple(traindat=traindat,
label_traindat=label_traindat):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import ContingencyTableEvaluation, ACCURACY
from shogun.Evaluation import StratifiedCrossValidationSplitting
from shogun.ModelSelection import GridSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
from shogun.Features import Labels
from shogun.Features import RealFeatures
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC
# build parameter tree to select C1 and C2
param_tree_root = ModelSelectionParameters()
c1 = ModelSelectionParameters("C1")
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP)
c2 = ModelSelectionParameters("C2")
param_tree_root.append_child(c2)
c2.build_values(-2.0, 2.0, R_EXP)
# training data
features = RealFeatures(traindat)
labels = Labels(label_traindat)
# classifier
classifier = LibLinear(L2R_L2LOSS_SVC)
# splitting strategy for cross-validation
splitting_strategy = StratifiedCrossValidationSplitting(labels, 10)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(classifier, features, labels,
splitting_strategy,
evaluation_criterium)
# model selection instance
model_selection = GridSearchModelSelection(param_tree_root,
cross_validation)
# perform model selection with selected methods
print "performing model selection of"
param_tree_root.print_tree()
best_parameters = model_selection.select_model()
# print best parameters
print "best parameters:"
best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(classifier)
result = cross_validation.evaluate()
result.print_result()
def run_demo():
LG.basicConfig(level=LG.INFO)
random.seed(572)
#1. create toy data
[x, y] = create_toy_data()
feat_train = RealFeatures(transpose(x))
labels = RegressionLabels(y)
n_dimensions = 1
#2. location of unispaced predictions
X = SP.linspace(0, 10, 10)[:, SP.newaxis]
#new interface with likelihood parametres being decoupled from the covaraince function
likelihood = GaussianLikelihood()
covar_parms = SP.log([2])
hyperparams = {'covar': covar_parms, 'lik': SP.log([1])}
#construct covariance function
SECF = GaussianKernel(feat_train, feat_train, 2)
covar = SECF
zmean = ZeroMean()
inf = ExactInferenceMethod(SECF, feat_train, zmean, labels, likelihood)
gp = GaussianProcessRegression(inf, feat_train, labels)
root = ModelSelectionParameters()
c1 = ModelSelectionParameters("inference_method", inf)
root.append_child(c1)
c2 = ModelSelectionParameters("scale")
c1.append_child(c2)
c2.build_values(0.01, 4.0, R_LINEAR)
c3 = ModelSelectionParameters("likelihood_model", likelihood)
c1.append_child(c3)
c4 = ModelSelectionParameters("sigma")
c3.append_child(c4)
c4.build_values(0.001, 4.0, R_LINEAR)
c5 = ModelSelectionParameters("kernel", SECF)
c1.append_child(c5)
c6 = ModelSelectionParameters("width")
c5.append_child(c6)
c6.build_values(0.001, 4.0, R_LINEAR)
crit = GradientCriterion()
grad = GradientEvaluation(gp, feat_train, labels, crit)
grad.set_function(inf)
gp.print_modsel_params()
root.print_tree()
grad_search = GradientModelSelection(root, grad)
grad.set_autolock(0)
best_combination = grad_search.select_model(1)
gp.set_return_type(GaussianProcessRegression.GP_RETURN_COV)
St = gp.apply_regression(feat_train)
St = St.get_labels()
gp.set_return_type(GaussianProcessRegression.GP_RETURN_MEANS)
M = gp.apply_regression()
M = M.get_labels()
#create plots
plot_sausage(transpose(x), transpose(M), transpose(SP.sqrt(St)))
plot_training_data(x, y)
PL.show()
def modelselection_parameter_tree_modular():
from shogun.ModelSelection import ParameterCombination
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.ModelSelection import DynamicParameterCombinationArray
from shogun.Kernel import PowerKernel
from shogun.Kernel import GaussianKernel
from shogun.Kernel import DistantSegmentsKernel
from shogun.Distance import MinkowskiMetric
root = ModelSelectionParameters()
combinations = root.get_combinations()
combinations.get_num_elements()
c = ModelSelectionParameters('C')
root.append_child(c)
c.build_values(1, 11, R_EXP)
power_kernel = PowerKernel()
param_power_kernel = ModelSelectionParameters('kernel', power_kernel)
root.append_child(param_power_kernel)
param_power_kernel_degree = ModelSelectionParameters('degree')
param_power_kernel_degree.build_values(1, 1, R_EXP)
param_power_kernel.append_child(param_power_kernel_degree)
metric1 = MinkowskiMetric(10)
param_power_kernel_metric1 = ModelSelectionParameters('distance', metric1)
param_power_kernel.append_child(param_power_kernel_metric1)
param_power_kernel_metric1_k = ModelSelectionParameters('k')
param_power_kernel_metric1_k.build_values(1, 12, R_LINEAR)
param_power_kernel_metric1.append_child(param_power_kernel_metric1_k)
gaussian_kernel = GaussianKernel()
param_gaussian_kernel = ModelSelectionParameters('kernel', gaussian_kernel)
root.append_child(param_gaussian_kernel)
param_gaussian_kernel_width = ModelSelectionParameters('width')
param_gaussian_kernel_width.build_values(1, 2, R_EXP)
param_gaussian_kernel.append_child(param_gaussian_kernel_width)
ds_kernel = DistantSegmentsKernel()
param_ds_kernel = ModelSelectionParameters('kernel', ds_kernel)
root.append_child(param_ds_kernel)
param_ds_kernel_delta = ModelSelectionParameters('delta')
param_ds_kernel_delta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_delta)
param_ds_kernel_theta = ModelSelectionParameters('theta')
param_ds_kernel_theta.build_values(1, 2, R_EXP)
param_ds_kernel.append_child(param_ds_kernel_theta)
root.print_tree()
combinations = root.get_combinations()
for i in range(combinations.get_num_elements()):
combinations.get_element(i).print_tree()
return
def run_demo():
LG.basicConfig(level=LG.INFO)
random.seed(572)
#1. create toy data
[x,y] = create_toy_data()
feat_train = RealFeatures(transpose(x));
labels = RegressionLabels(y);
n_dimensions = 1
#2. location of unispaced predictions
X = SP.linspace(0,10,10)[:,SP.newaxis]
#new interface with likelihood parametres being decoupled from the covaraince function
likelihood = GaussianLikelihood()
covar_parms = SP.log([2])
hyperparams = {'covar':covar_parms,'lik':SP.log([1])}
#construct covariance function
SECF = GaussianKernel(feat_train, feat_train,2)
covar = SECF
zmean = ZeroMean();
inf = ExactInferenceMethod(SECF, feat_train, zmean, labels, likelihood);
gp = GaussianProcessRegression(inf, feat_train, labels);
root=ModelSelectionParameters();
c1=ModelSelectionParameters("inference_method", inf);
root.append_child(c1);
c2 = ModelSelectionParameters("scale");
c1.append_child(c2);
c2.build_values(0.01, 4.0, R_LINEAR);
c3 = ModelSelectionParameters("likelihood_model", likelihood);
c1.append_child(c3);
c4=ModelSelectionParameters("sigma");
c3.append_child(c4);
c4.build_values(0.001, 4.0, R_LINEAR);
c5 =ModelSelectionParameters("kernel", SECF);
c1.append_child(c5);
c6 =ModelSelectionParameters("width");
c5.append_child(c6);
c6.build_values(0.001, 4.0, R_LINEAR);
crit = GradientCriterion();
grad=GradientEvaluation(gp, feat_train, labels,
crit);
grad.set_function(inf);
gp.print_modsel_params();
root.print_tree();
grad_search=GradientModelSelection(
root, grad);
grad.set_autolock(0);
best_combination=grad_search.select_model(1);
gp.set_return_type(GaussianProcessRegression.GP_RETURN_COV);
St = gp.apply_regression(feat_train);
St = St.get_labels();
gp.set_return_type(GaussianProcessRegression.GP_RETURN_MEANS);
M = gp.apply_regression();
M = M.get_labels();
#create plots
plot_sausage(transpose(x),transpose(M),transpose(SP.sqrt(St)));
plot_training_data(x,y);
PL.show();
def modelselection_grid_search_libsvr_modular (fm_train=traindat,fm_test=testdat,label_train=label_traindat,\
width=2.1,C=1,epsilon=1e-5,tube_epsilon=1e-2):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import MeanSquaredError
from shogun.Evaluation import CrossValidationSplitting
from shogun.Features import RegressionLabels
from shogun.Features import RealFeatures
from shogun.Kernel import GaussianKernel
from shogun.Regression import LibSVR
from shogun.ModelSelection import GridSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
# training data
features_train = RealFeatures(traindat)
labels = RegressionLabels(label_traindat)
# kernel
kernel = GaussianKernel(features_train, features_train, width)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#kernel.print_modsel_params()
labels = RegressionLabels(label_train)
# predictor
predictor = LibSVR(C, tube_epsilon, kernel, labels)
predictor.set_epsilon(epsilon)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy = CrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = MeanSquaredError()
# cross-validation instance
cross_validation = CrossValidation(predictor, features_train, labels,
splitting_strategy,
evaluation_criterium)
# (optional) repeat x-val 10 times
cross_validation.set_num_runs(10)
# (optional) request 95% confidence intervals for results (not actually needed
# for this toy example)
cross_validation.set_conf_int_alpha(0.05)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#predictor.print_modsel_params()
# build parameter tree to select C1 and C2
param_tree_root = ModelSelectionParameters()
c1 = ModelSelectionParameters("C1")
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP)
c2 = ModelSelectionParameters("C2")
param_tree_root.append_child(c2)
c2.build_values(-2.0, 2.0, R_EXP)
# model selection instance
model_selection = GridSearchModelSelection(param_tree_root,
cross_validation)
# perform model selection with selected methods
#print "performing model selection of"
#print "parameter tree"
#param_tree_root.print_tree()
#print "starting model selection"
# print the current parameter combination, if no parameter nothing is printed
print_state = False
# lock data before since model selection will not change the kernel matrix
# (use with care) This avoids that the kernel matrix is recomputed in every
# iteration of the model search
predictor.data_lock(labels, features_train)
best_parameters = model_selection.select_model(print_state)
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(predictor)
result = cross_validation.evaluate()
def run_demo():
LG.basicConfig(level=LG.INFO)
random.seed(572)
x = np.linspace(0.0, 1.0, 80)
y = np.sin(3.0 * np.pi * x)
x = x[:, np.newaxis]
feat_train = RealFeatures(transpose(x));
labels = RegressionLabels(y);
n_dimensions = 1
#new interface with likelihood parametres being decoupled from the covaraince function
likelihood = GaussianLikelihood()
covar_parms = SP.log([2])
hyperparams = {'covar':covar_parms,'lik':SP.log([1])}
#construct covariance function
SECF = GaussianKernel(feat_train, feat_train,2)
covar = SECF
zmean = ZeroMean();
inf = ExactInferenceMethod(SECF, feat_train, zmean, labels, likelihood);
gp = GaussianProcessRegression(inf, feat_train, labels);
root = ModelSelectionParameters();
c1 = ModelSelectionParameters("inference_method", inf);
root.append_child(c1);
c2 = ModelSelectionParameters("scale");
c1.append_child(c2);
c2.build_values(0.01, 4.0, R_LINEAR);
c3 = ModelSelectionParameters("likelihood_model", likelihood);
c1.append_child(c3);
c4 = ModelSelectionParameters("sigma");
c3.append_child(c4);
c4.build_values(0.001, 4.0, R_LINEAR);
c5 = ModelSelectionParameters("kernel", SECF);
c1.append_child(c5);
c6 = ModelSelectionParameters("width");
c5.append_child(c6);
c6.build_values(0.001, 4.0, R_LINEAR);
crit = GradientCriterion();
grad = GradientEvaluation(gp, feat_train, labels, crit);
grad.set_function(inf);
gp.print_modsel_params();
root.print_tree();
grad_search=GradientModelSelection(root, grad)
grad.set_autolock(0)
best_combination=grad_search.select_model(1);
x_test = np.linspace(0.0, 1.0, 100)
x_test = x_test[:, np.newaxis]
feat_test = RealFeatures(transpose(x_test));
gp.set_return_type(GaussianProcessRegression.GP_RETURN_COV)
St = gp.apply_regression(feat_test);
St = St.get_labels();
gp.set_return_type(GaussianProcessRegression.GP_RETURN_MEANS);
M = gp.apply_regression();
M = M.get_labels();
#create plots
pylab.figure()
# pylab.plot(x, y, 'rx')
pylab.plot(x_test, M, 'ro')
pylab.show()
def modelselection_grid_search_libsvr_modular(fm_train=traindat,fm_test=testdat,label_train=label_traindat,\
width=2.1,C=1,epsilon=1e-5,tube_epsilon=1e-2):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import MeanSquaredError
from shogun.Evaluation import CrossValidationSplitting
from shogun.Features import Labels
from shogun.Features import RealFeatures
from shogun.Kernel import GaussianKernel
from shogun.Regression import LibSVR
from shogun.ModelSelection import GridSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
# training data
features_train=RealFeatures(traindat)
labels=Labels(label_traindat)
# kernel
kernel=GaussianKernel(features_train, features_train, width)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#kernel.print_modsel_params()
labels=Labels(label_train)
# predictor
predictor=LibSVR(C, tube_epsilon, kernel, labels)
predictor.set_epsilon(epsilon)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy=CrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium=MeanSquaredError()
# cross-validation instance
cross_validation=CrossValidation(predictor, features_train, labels,
splitting_strategy, evaluation_criterium)
# (optional) repeat x-val 10 times
cross_validation.set_num_runs(10)
# (optional) request 95% confidence intervals for results (not actually needed
# for this toy example)
cross_validation.set_conf_int_alpha(0.05)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#predictor.print_modsel_params()
# build parameter tree to select C1 and C2
param_tree_root=ModelSelectionParameters()
c1=ModelSelectionParameters("C1");
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP);
c2=ModelSelectionParameters("C2");
param_tree_root.append_child(c2);
c2.build_values(-2.0, 2.0, R_EXP);
# model selection instance
model_selection=GridSearchModelSelection(param_tree_root,
cross_validation)
# perform model selection with selected methods
#print "performing model selection of"
#print "parameter tree"
#param_tree_root.print_tree()
#print "starting model selection"
# print the current parameter combination, if no parameter nothing is printed
print_state=False
# lock data before since model selection will not change the kernel matrix
# (use with care) This avoids that the kernel matrix is recomputed in every
# iteration of the model search
predictor.data_lock(labels, features_train)
best_parameters=model_selection.select_model(print_state)
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(predictor)
result=cross_validation.evaluate()
def create_param_tree():
from shogun.ModelSelection import ModelSelectionParameters, R_EXP, R_LINEAR
from shogun.ModelSelection import ParameterCombination
from shogun.Kernel import GaussianKernel, PolyKernel
root=ModelSelectionParameters()
tau=ModelSelectionParameters("tau")
root.append_child(tau)
# also R_LINEAR/R_LOG is available as type
min=-1
max=1
type=R_EXP
step=1.5
base=2
tau.build_values(min, max, type, step, base)
# gaussian kernel with width
gaussian_kernel=GaussianKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#gaussian_kernel.print_modsel_params()
param_gaussian_kernel=ModelSelectionParameters("kernel", gaussian_kernel)
gaussian_kernel_width=ModelSelectionParameters("width");
gaussian_kernel_width.build_values(5.0, 8.0, R_EXP, 1.0, 2.0)
param_gaussian_kernel.append_child(gaussian_kernel_width)
root.append_child(param_gaussian_kernel)
# polynomial kernel with degree
poly_kernel=PolyKernel()
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#poly_kernel.print_modsel_params()
param_poly_kernel=ModelSelectionParameters("kernel", poly_kernel)
root.append_child(param_poly_kernel)
# note that integers are used here
param_poly_kernel_degree=ModelSelectionParameters("degree")
param_poly_kernel_degree.build_values(1, 2, R_LINEAR)
param_poly_kernel.append_child(param_poly_kernel_degree)
return root
def modelselection_grid_search_linear_modular(traindat=traindat, label_traindat=label_traindat):
from shogun.Evaluation import CrossValidation, CrossValidationResult
from shogun.Evaluation import ContingencyTableEvaluation, ACCURACY
from shogun.Evaluation import StratifiedCrossValidationSplitting
from shogun.ModelSelection import GridSearchModelSelection
from shogun.ModelSelection import ModelSelectionParameters, R_EXP
from shogun.ModelSelection import ParameterCombination
from shogun.Features import Labels
from shogun.Features import RealFeatures
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC
# build parameter tree to select C1 and C2
param_tree_root = ModelSelectionParameters()
c1 = ModelSelectionParameters("C1")
param_tree_root.append_child(c1)
c1.build_values(-2.0, 2.0, R_EXP)
c2 = ModelSelectionParameters("C2")
param_tree_root.append_child(c2)
c2.build_values(-2.0, 2.0, R_EXP)
# training data
features = RealFeatures(traindat)
labels = Labels(label_traindat)
# classifier
classifier = LibLinear(L2R_L2LOSS_SVC)
# splitting strategy for cross-validation
splitting_strategy = StratifiedCrossValidationSplitting(labels, 10)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(classifier, features, labels, splitting_strategy, evaluation_criterium)
# model selection instance
model_selection = GridSearchModelSelection(param_tree_root, cross_validation)
# perform model selection with selected methods
# print "performing model selection of"
# param_tree_root.print_tree()
best_parameters = model_selection.select_model()
# print best parameters
# print "best parameters:"
# best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(classifier)
result = cross_validation.evaluate()
def regression_gaussian_process_modelselection (n=100,n_test=100, \
x_range=6,x_range_test=10,noise_var=0.5,width=1, seed=1):
from shogun.Features import RealFeatures, RegressionLabels
from shogun.Kernel import GaussianKernel
from shogun.ModelSelection import GradientModelSelection, ModelSelectionParameters, R_LINEAR
from shogun.Regression import GaussianLikelihood, ZeroMean, \
ExactInferenceMethod, GaussianProcessRegression, GradientCriterion, \
GradientEvaluation
# Reproducable results
random.seed(seed)
# Easy regression data: one dimensional noisy sine wave
X_train=random.rand(1,n)*x_range
X_test=array([[float(i)/n_test*x_range_test for i in range(n_test)]])
Y_test=sin(X_test)
Y_train=sin(X_train)+random.randn(n)*noise_var
# shogun representation
labels=RegressionLabels(Y_train[0])
feats_train=RealFeatures(X_train)
feats_test=RealFeatures(X_test)
# GP specification
width=1
shogun_width=width*width*2
kernel=GaussianKernel(10,shogun_width)
kernel.init(feats_train,feats_train)
zmean = ZeroMean()
likelihood = GaussianLikelihood()
inf = ExactInferenceMethod(kernel, feats_train, zmean, labels, likelihood)
gp = GaussianProcessRegression(inf, feats_train, labels)
# Paramter tree for model selection
root = ModelSelectionParameters()
c1 = ModelSelectionParameters("inference_method", inf)
root.append_child(c1)
c2 = ModelSelectionParameters("scale")
c1.append_child(c2)
c2.build_values(0.01, 4.0, R_LINEAR)
c3 = ModelSelectionParameters("likelihood_model", likelihood)
c1.append_child(c3)
c4 = ModelSelectionParameters("sigma")
c3.append_child(c4)
c4.build_values(0.001, 4.0, R_LINEAR)
c5 = ModelSelectionParameters("kernel", kernel)
c1.append_child(c5)
c6 = ModelSelectionParameters("width")
c5.append_child(c6)
c6.build_values(0.001, 4.0, R_LINEAR)
# Criterion for Gradient Search
crit = GradientCriterion()
# Evaluate our inference method for its derivatives
grad = GradientEvaluation(gp, feats_train, labels, crit)
grad.set_function(inf)
gp.print_modsel_params()
root.print_tree()
# Handles all of the above structures in memory
grad_search = GradientModelSelection(root, grad)
# Set autolocking to false to get rid of warnings
grad.set_autolock(False)
# Search for best parameters
best_combination = grad_search.select_model(True)
# Outputs all result and information
best_combination.print_tree()
best_combination.apply_to_machine(gp)
result = grad.evaluate()
result.print_result()
#inference
gp.set_return_type(GaussianProcessRegression.GP_RETURN_COV)
covariance = gp.apply_regression(feats_test)
covariance = covariance.get_labels()
gp.set_return_type(GaussianProcessRegression.GP_RETURN_MEANS)
mean = gp.apply_regression(feats_test)
mean = mean.get_labels()
# some things we can do
alpha = inf.get_alpha()
diagonal = inf.get_diagonal_vector()
cholesky = inf.get_cholesky()
# plot results
plot(X_train[0],Y_train[0],'x') # training observations
plot(X_test[0],Y_test[0],'-') # ground truth of test
plot(X_test[0],mean, '-') # mean predictions of test
legend(["training", "ground truth", "mean predictions"])
show()
return gp, alpha, labels, diagonal, covariance, mean, cholesky
