def init_svm(task_type, kernel, labels):
"""A factory for creating the right svm type"""
C=1
epsilon=1e-5
if task_type == 'Binary Classification':
svm = LibSVM(C, kernel, labels)
elif task_type == 'Multi Class Classification':
svm = LibSVMMultiClass(C, kernel, labels)
elif task_type == 'Regression':
tube_epsilon=1e-2
svm=LibSVR(C, epsilon, kernel, labels)
svm.set_tube_epsilon(tube_epsilon)
else:
print(task_type + ' unknown!')
return svm
def regression_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.Features import Labels, RealFeatures
from shogun.Kernel import GaussianKernel
from shogun.Regression import LibSVR
feats_train = RealFeatures(fm_train)
feats_test = RealFeatures(fm_test)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = Labels(label_train)
svr = LibSVR(C, tube_epsilon, kernel, labels)
svr.set_epsilon(epsilon)
svr.train()
kernel.init(feats_train, feats_test)
out1 = svr.apply().get_labels()
out2 = svr.apply(feats_test).get_labels()
return out1, out2, kernel
def regression_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.Features import Labels, RealFeatures from shogun.Kernel import GaussianKernel from shogun.Regression import LibSVR feats_train=RealFeatures(fm_train) feats_test=RealFeatures(fm_test) kernel=GaussianKernel(feats_train, feats_train, width) labels=Labels(label_train) svr=LibSVR(C, tube_epsilon, kernel, labels) svr.set_epsilon(epsilon) svr.train() kernel.init(feats_train, feats_test) out1=svr.apply().get_labels() out2=svr.apply(feats_test).get_labels() return out1,out2,kernel
def __init__(self, traininput,testinput,traintarget,width=0.5,C=1,epsilon=0.1,tube_epsilon=0.1):
train = matrix(traininput, dtype=float64)
test = matrix(testinput, dtype=float64)
label_train = array(traintarget, dtype=float64)
self.feats_train=RealFeatures(train)
feats_test=RealFeatures(test)
trainstart = time.time()
self.kernel=GaussianKernel(self.feats_train, self.feats_train, width)
# self.kernel = PolyKernel(self.feats_train, self.feats_train, 2, False)
labels=Labels(label_train)
self.svr=LibSVR(C, epsilon, self.kernel, labels)
self.svr.set_tube_epsilon(tube_epsilon)
self.svr.train()
trainend = time.time()
print 'SVR train time'
print trainend-trainstart
def libsvr (): print 'LibSVR' from shogun.Features import Labels, RealFeatures from shogun.Kernel import GaussianKernel from shogun.Regression import LibSVR feats_train=RealFeatures(fm_train) feats_test=RealFeatures(fm_test) width=2.1 kernel=GaussianKernel(feats_train, feats_train, width) C=1 epsilon=1e-5 tube_epsilon=1e-2 labels=Labels(label_train) svr=LibSVR(C, epsilon, kernel, labels) svr.set_tube_epsilon(tube_epsilon) svr.train() kernel.init(feats_train, feats_test) out1=svr.classify().get_labels() out2=svr.classify(feats_test).get_labels()
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 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 regression_libsvr_modular (svm_c=1, svr_param=0.1, n=100,n_test=100, \ x_range=6,x_range_test=10,noise_var=0.5,width=1, seed=1): from shogun.Features import RegressionLabels, RealFeatures from shogun.Kernel import GaussianKernel from shogun.Regression import LibSVR, LIBSVR_NU_SVR, LIBSVR_EPSILON_SVR # reproducable results random.seed(seed) # easy regression data: one dimensional noisy sine wave n=15 n_test=100 x_range_test=10 noise_var=0.5; X=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=sin(X)+random.randn(n)*noise_var # shogun representation labels=RegressionLabels(Y[0]) feats_train=RealFeatures(X) feats_test=RealFeatures(X_test) kernel=GaussianKernel(feats_train, feats_train, width) # two svr models: epsilon and nu svr_epsilon=LibSVR(svm_c, svr_param, kernel, labels, LIBSVR_EPSILON_SVR) svr_epsilon.train() svr_nu=LibSVR(svm_c, svr_param, kernel, labels, LIBSVR_NU_SVR) svr_nu.train() # predictions kernel.init(feats_train, feats_test) out1_epsilon=svr_epsilon.apply().get_labels() out2_epsilon=svr_epsilon.apply(feats_test).get_labels() out1_nu=svr_epsilon.apply().get_labels() out2_nu=svr_epsilon.apply(feats_test).get_labels() return out1_epsilon,out2_epsilon,out1_nu,out2_nu ,kernel
class SVR:
svr = None
kernel = None
feats_train = None
def __init__(self, traininput,testinput,traintarget,width=0.5,C=1,epsilon=0.1,tube_epsilon=0.1):
train = matrix(traininput, dtype=float64)
test = matrix(testinput, dtype=float64)
label_train = array(traintarget, dtype=float64)
self.feats_train=RealFeatures(train)
feats_test=RealFeatures(test)
trainstart = time.time()
self.kernel=GaussianKernel(self.feats_train, self.feats_train, width)
# self.kernel = PolyKernel(self.feats_train, self.feats_train, 2, False)
labels=Labels(label_train)
self.svr=LibSVR(C, epsilon, self.kernel, labels)
self.svr.set_tube_epsilon(tube_epsilon)
self.svr.train()
trainend = time.time()
print 'SVR train time'
print trainend-trainstart
def svr_req(self,inputs):
feat_inputs = RealFeatures(matrix(inputs, dtype=float64))
teststart = time.time()
self.kernel.init(self.feats_train, feat_inputs)
out = self.svr.classify(feat_inputs).get_labels()
# feat_input0 = RealFeatures(matrix(inputs[0], dtype=float64))
# feat_input1 = RealFeatures(matrix(inputs[1], dtype=float64))
# feat_input2 = RealFeatures(matrix(inputs[2], dtype=float64))
# feat_input3 = RealFeatures(matrix(inputs[3], dtype=float64))
#
# out.append(self.svr.classify(feat_input0).get_labels())
# out.append(self.svr.classify(feat_input1).get_labels())
# out.append(self.svr.classify(feat_input2).get_labels())
# out.append(self.svr.classify(feat_input3).get_labels())
testend = time.time()
print 'SVR query response '
print testend-teststart
return out
def calc_sme(self, testtarget, realtarget):
result = 0.0
for i in range(len(testtarget)):
result += pow((realtarget[i] - testtarget[i]),2)
result /= len(testtarget)
return result
def calc_mape(self, testtarget, realtarget):
result = 0.0
for i in range(len(testtarget)):
result = abs(testtarget[i] - realtarget[i])/testtarget[i]
return result/len(testtarget)
def calc_rsqr(self, testtarget, realtarget):
result_up = 0.0
result_down = 0.0
avg = sum(realtarget)/len(realtarget)
for i in range(len(testtarget)):
result_up += pow((realtarget[i] - testtarget[i]),2)
result_down += (realtarget[i] - avg)
return 1 - (result_up / result_down)
def calc_pred(self, testtarget, realtarget, x):
countx = 0.0
for i in range(len(testtarget)):
if ((testtarget[i]/realtarget[i]) - 1 < (realtarget[i] * (1-x))):
countx += 1
return countx / len(realtarget)