def evaluation_cross_validation_classification(traindat=traindat,
label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import ContingencyTableEvaluation, ACCURACY
from modshogun import StratifiedCrossValidationSplitting
from modshogun import BinaryLabels
from modshogun import RealFeatures
from modshogun import LibLinear, L2R_L2LOSS_SVC
# training data
features = RealFeatures(traindat)
labels = BinaryLabels(label_traindat)
# classifier
classifier = LibLinear(L2R_L2LOSS_SVC)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "CrossValidationSplitting" is also available
splitting_strategy = StratifiedCrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(classifier, features, labels,
splitting_strategy,
evaluation_criterium)
cross_validation.set_autolock(False)
# (optional) repeat x-val 10 times
cross_validation.set_num_runs(10)
# perform cross-validation and print(results)
result = cross_validation.evaluate()
def evaluation_multiclassovrevaluation_modular(traindat, label_traindat,
testdat, label_testdat):
from shogun.Features import MulticlassLabels
from shogun.Evaluation import MulticlassOVREvaluation, ROCEvaluation
from modshogun import MulticlassLibLinear, RealFeatures, ContingencyTableEvaluation, ACCURACY
from shogun.Mathematics import Math
Math.init_random(1)
ground_truth_labels = MulticlassLabels(label_traindat)
svm = MulticlassLibLinear(1.0, RealFeatures(traindat),
MulticlassLabels(label_traindat))
svm.train()
predicted_labels = svm.apply()
binary_evaluator = ROCEvaluation()
evaluator = MulticlassOVREvaluation(binary_evaluator)
mean_roc = evaluator.evaluate(predicted_labels, ground_truth_labels)
#print mean_roc
binary_evaluator = ContingencyTableEvaluation(ACCURACY)
evaluator = MulticlassOVREvaluation(binary_evaluator)
mean_accuracy = evaluator.evaluate(predicted_labels, ground_truth_labels)
#print mean_accuracy
return mean_roc, mean_accuracy
def modelselection_random_search_liblinear_modular (traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import ContingencyTableEvaluation, ACCURACY
from modshogun import StratifiedCrossValidationSplitting
from modshogun import RandomSearchModelSelection
from modshogun import ModelSelectionParameters, R_EXP
from modshogun import ParameterCombination
from modshogun import BinaryLabels
from modshogun import RealFeatures
from modshogun 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(cross_validation, param_tree_root, 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_grid_search_kernel(num_subsets, num_vectors, dim_vectors):
# init seed for reproducability
Math.init_random(1)
random.seed(1)
# create some (non-sense) data
matrix = random.rand(dim_vectors, num_vectors)
# create num_feautres 2-dimensional vectors
features = RealFeatures()
features.set_feature_matrix(matrix)
# create labels, two classes
labels = BinaryLabels(num_vectors)
for i in range(num_vectors):
labels.set_label(i, 1 if i % 2 == 0 else -1)
# create svm
classifier = LibSVM()
# splitting strategy
splitting_strategy = StratifiedCrossValidationSplitting(
labels, num_subsets)
# accuracy evaluation
evaluation_criterion = ContingencyTableEvaluation(ACCURACY)
# cross validation class for evaluation in model selection
cross = CrossValidation(classifier, features, labels, splitting_strategy,
evaluation_criterion)
cross.set_num_runs(1)
# print all parameter available for modelselection
# Dont worry if yours is not included, simply write to the mailing list
#classifier.print_modsel_params()
# model parameter selection
param_tree = create_param_tree()
#param_tree.print_tree()
grid_search = GridSearchModelSelection(cross, param_tree)
print_state = False
best_combination = grid_search.select_model(print_state)
#print("best parameter(s):")
#best_combination.print_tree()
best_combination.apply_to_machine(classifier)
# larger number of runs to have tighter confidence intervals
cross.set_num_runs(10)
cross.set_conf_int_alpha(0.01)
result = cross.evaluate()
casted = CrossValidationResult.obtain_from_generic(result)
#print "result mean:", casted.mean
return classifier, result, casted.mean
def evaluation_cross_validation_mkl_weight_storage(
traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import CrossValidationPrintOutput
from modshogun import CrossValidationMKLStorage
from modshogun import ContingencyTableEvaluation, ACCURACY
from modshogun import StratifiedCrossValidationSplitting
from modshogun import BinaryLabels
from modshogun import RealFeatures, CombinedFeatures
from modshogun import GaussianKernel, CombinedKernel
from modshogun import LibSVM, MKLClassification
# training data, combined features all on same data
features = RealFeatures(traindat)
comb_features = CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels = BinaryLabels(label_traindat)
# kernel, different Gaussians combined
kernel = CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm = MKLClassification(LibSVM())
svm.set_interleaved_optimization_enabled(False)
svm.set_kernel(kernel)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy = StratifiedCrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(svm, comb_features, labels,
splitting_strategy,
evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
mkl_storage = CrossValidationMKLStorage()
cross_validation.add_cross_validation_output(mkl_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result = cross_validation.evaluate()
# print mkl weights
weights = mkl_storage.get_mkl_weights()
def evaluation_contingencytableevaluation_modular(ground_truth, predicted):
from modshogun import BinaryLabels
from modshogun import ContingencyTableEvaluation
from modshogun import AccuracyMeasure, ErrorRateMeasure, BALMeasure
from modshogun import WRACCMeasure, F1Measure, CrossCorrelationMeasure
from modshogun import RecallMeasure, PrecisionMeasure, SpecificityMeasure
ground_truth_labels = BinaryLabels(ground_truth)
predicted_labels = BinaryLabels(predicted)
base_evaluator = ContingencyTableEvaluation()
base_evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = AccuracyMeasure()
accuracy = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = ErrorRateMeasure()
errorrate = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = BALMeasure()
bal = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = WRACCMeasure()
wracc = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = F1Measure()
f1 = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = CrossCorrelationMeasure()
crosscorrelation = evaluator.evaluate(predicted_labels,
ground_truth_labels)
evaluator = RecallMeasure()
recall = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = PrecisionMeasure()
precision = evaluator.evaluate(predicted_labels, ground_truth_labels)
evaluator = SpecificityMeasure()
specificity = evaluator.evaluate(predicted_labels, ground_truth_labels)
return accuracy, errorrate, bal, wracc, f1, crosscorrelation, recall, precision, specificity
def evaluation_contingencytableevaluation_modular (ground_truth, predicted): from modshogun import BinaryLabels from modshogun import ContingencyTableEvaluation from modshogun import AccuracyMeasure,ErrorRateMeasure,BALMeasure from modshogun import WRACCMeasure,F1Measure,CrossCorrelationMeasure from modshogun import RecallMeasure,PrecisionMeasure,SpecificityMeasure ground_truth_labels = BinaryLabels(ground_truth) predicted_labels = BinaryLabels(predicted) base_evaluator = ContingencyTableEvaluation() base_evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = AccuracyMeasure() accuracy = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = ErrorRateMeasure() errorrate = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = BALMeasure() bal = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = WRACCMeasure() wracc = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = F1Measure() f1 = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = CrossCorrelationMeasure() crosscorrelation = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = RecallMeasure() recall = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = PrecisionMeasure() precision = evaluator.evaluate(predicted_labels,ground_truth_labels) evaluator = SpecificityMeasure() specificity = evaluator.evaluate(predicted_labels,ground_truth_labels) return accuracy, errorrate, bal, wracc, f1, crosscorrelation, recall, precision, specificity