def calcprc(output, LTE):
pm = PerformanceMeasures(Labels(numpy.array(LTE)),
Labels(numpy.array(output)))
auPRC = pm.get_auPRC()
return auPRC
def calcprc(output, LTE):
"""The area under the precision recall curve"""
pm = PRCEvaluation()
pm.evaluate(Labels(numpy.array(output)), Labels(numpy.array(LTE)))
auPRC = pm.get_auPRC()
return auPRC
def calcroc(output, LTE):
"""The area under the receiver operating characteristic curve"""
pm = PerformanceMeasures(Labels(numpy.array(LTE)),
Labels(numpy.array(output)))
auROC = pm.get_auROC()
return auROC
def calcroc(output, LTE):
"""The area under the receiver operating characteristic curve"""
pm = ROCEvaluation()
pm.evaluate(Labels(numpy.array(output)), Labels(numpy.array(LTE)))
auROC = pm.get_auROC()
return auROC
def calcprc(output, LTE):
"""The area under the precision recall curve"""
pm = PerformanceMeasures(Labels(numpy.array(LTE)),
Labels(numpy.array(output)))
auPRC = pm.get_auPRC()
return auPRC
def classifier_domainadaptationsvm_modular(fm_train_dna=traindna,fm_test_dna=testdna, \
label_train_dna=label_traindna, \
label_test_dna=label_testdna,fm_train_dna2=traindna2,fm_test_dna2=testdna2, \
label_train_dna2=label_traindna2,label_test_dna2=label_testdna2,C=1,degree=3):
feats_train = StringCharFeatures(fm_train_dna, DNA)
feats_test = StringCharFeatures(fm_test_dna, DNA)
kernel = WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels = Labels(label_train_dna)
svm = SVMLight(C, kernel, labels)
svm.train()
#svm.io.set_loglevel(MSG_DEBUG)
#####################################
#print "obtaining DA SVM from previously trained SVM"
feats_train2 = StringCharFeatures(fm_train_dna, DNA)
feats_test2 = StringCharFeatures(fm_test_dna, DNA)
kernel2 = WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels2 = Labels(label_train_dna)
# we regularize against the previously obtained solution
dasvm = DomainAdaptationSVM(C, kernel2, labels2, svm, 1.0)
dasvm.train()
out = dasvm.classify(feats_test2).get_labels()
return out #,dasvm TODO
def svm_learn(kernel, labels, options):
"""train SVM using SVMLight or LibSVM
Arguments:
kernel -- kernel object from Shogun toolbox
lebels -- list of labels
options -- object containing option data
Return:
trained svm object
"""
try:
svm = SVMLight(options.svmC, kernel,
Labels(numpy.array(labels, dtype=numpy.double)))
except NameError:
svm = LibSVM(options.svmC, kernel,
Labels(numpy.array(labels, dtype=numpy.double)))
if options.quiet == False:
svm.io.set_loglevel(MSG_INFO)
svm.io.set_target_to_stderr()
svm.set_epsilon(options.epsilon)
svm.parallel.set_num_threads(1)
if options.weight != 1.0:
svm.set_C(options.svmC, options.svmC * options.weight)
svm.train()
if options.quiet == False:
svm.io.set_loglevel(MSG_ERROR)
return svm
def plotprc(output, LTE, figure_fname="", prc_label='PRC'):
"""Plot the precision recall curve"""
import pylab
import matplotlib
pylab.figure(2, dpi=150, figsize=(4, 4))
pm = PerformanceMeasures(Labels(numpy.array(LTE)),
Labels(numpy.array(output)))
points = pm.get_PRC()
points = numpy.array(points).T # for pylab.plot
pylab.plot(points[0], points[1], 'b-', label=prc_label)
pylab.axis([0, 1, 0, 1])
ticks = numpy.arange(0., 1., .1, dtype=numpy.float64)
pylab.xticks(ticks, size=10)
pylab.yticks(ticks, size=10)
pylab.xlabel('sensitivity (true positive rate)', size=10)
pylab.ylabel('precision (1 - false discovery rate)', size=10)
pylab.legend(loc='lower right')
if figure_fname != None:
warnings.filterwarnings('ignore', 'Could not match*')
tempfname = figure_fname + '.png'
pylab.savefig(tempfname)
shutil.move(tempfname, figure_fname)
auPRC = pm.get_auPRC()
return auPRC
def plotroc(output, LTE, draw_random=False, figure_fname="", roc_label='ROC'):
"""Plot the receiver operating characteristic curve"""
import pylab
import matplotlib
pylab.figure(1, dpi=150, figsize=(4, 4))
fontdict = dict(family="cursive", weight="bold", size=7, y=1.05)
pm = PerformanceMeasures(Labels(numpy.array(LTE)),
Labels(numpy.array(output)))
points = pm.get_ROC()
points = numpy.array(points).T # for pylab.plot
pylab.plot(points[0], points[1], 'b-', label=roc_label)
if draw_random:
pylab.plot([0, 1], [0, 1], 'r-', label='random guessing')
pylab.axis([0, 1, 0, 1])
ticks = numpy.arange(0., 1., .1, dtype=numpy.float64)
pylab.xticks(ticks, size=10)
pylab.yticks(ticks, size=10)
pylab.xlabel('1 - specificity (false positive rate)', size=10)
pylab.ylabel('sensitivity (true positive rate)', size=10)
pylab.legend(loc='lower right',
prop=matplotlib.font_manager.FontProperties('tiny'))
if figure_fname != None:
warnings.filterwarnings('ignore', 'Could not match*')
tempfname = figure_fname + '.png'
pylab.savefig(tempfname)
shutil.move(tempfname, figure_fname)
auROC = pm.get_auROC()
return auROC
def modelselection_grid_search_kernel():
num_subsets = 3
num_vectors = 20
dim_vectors = 3
# create some (non-sense) data
matrix = rand(dim_vectors, num_vectors)
# create num_feautres 2-dimensional vectors
features = RealFeatures()
features.set_feature_matrix(matrix)
# create labels, two classes
labels = Labels(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(param_tree, cross)
print_state = True
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()
print("result: ")
result.print_result()
return 0
def modelselection_grid_search_kernel():
num_subsets=3
num_vectors=20
dim_vectors=3
# create some (non-sense) data
matrix=rand(dim_vectors, num_vectors)
# create num_feautres 2-dimensional vectors
features=RealFeatures()
features.set_feature_matrix(matrix)
# create labels, two classes
labels=Labels(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(param_tree, cross)
print_state=True
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()
print("result: ")
result.print_result()
return 0
def evaluation_multiclassaccuracy_modular(ground_truth, predicted):
from shogun.Features import Labels
from shogun.Evaluation import MulticlassAccuracy
ground_truth_labels = Labels(ground_truth)
predicted_labels = Labels(predicted)
evaluator = MulticlassAccuracy()
accuracy = evaluator.evaluate(predicted_labels, ground_truth_labels)
return accuracy
def knn_train(train_data=None, train_label = None, k=1):
train_data = RealFeatures(train_data)
distance = EuclidianDistance(train_data, train_data)
try:
train_label = Labels(array(train_label.tolist(), dtype=float64))
except Exception as e:
print e
raise Exception
knn_model = KNN(k, distance, train_label)
knn_train = knn_model.train()
return knn_model
def evaluation_meansquarederror_modular(ground_truth, predicted): from shogun.Features import Labels from shogun.Evaluation import MeanSquaredError ground_truth_labels = Labels(ground_truth) predicted_labels = Labels(predicted) evaluator = MeanSquaredError() mse = evaluator.evaluate(predicted_labels,ground_truth_labels) return mse
def evaluation_rocevaluation_modular(ground_truth, predicted): from shogun.Features import Labels from shogun.Evaluation import ROCEvaluation ground_truth_labels = Labels(ground_truth) predicted_labels = Labels(predicted) evaluator = ROCEvaluation() evaluator.evaluate(predicted_labels,ground_truth_labels) return evaluator.get_ROC(), evaluator.get_auROC()
def classifier_mpdsvm_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import MPDSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
labels = Labels(label_train_twoclass)
svm = MPDSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
kernel.init(feats_train, feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def regression_svrlight_modular(fm_train=traindat,fm_test=testdat,label_train=label_traindat, \
width=1.2,C=1,epsilon=1e-5,tube_epsilon=1e-2,num_threads=3):
from shogun.Features import Labels, RealFeatures
from shogun.Kernel import GaussianKernel
try:
from shogun.Regression import SVRLight
except ImportError:
print 'No support for SVRLight available.'
return
feats_train = RealFeatures(fm_train)
feats_test = RealFeatures(fm_test)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = Labels(label_train)
svr = SVRLight(C, epsilon, kernel, labels)
svr.set_tube_epsilon(tube_epsilon)
svr.parallel.set_num_threads(num_threads)
svr.train()
kernel.init(feats_train, feats_test)
out = svr.classify().get_labels()
return out, kernel
def classifier_svmsgd_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
C=0.9,
num_threads=1,
num_iter=5):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import SVMSGD
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
labels = Labels(label_train_twoclass)
svm = SVMSGD(C, feats_train, labels)
svm.set_epochs(num_iter)
#svm.io.set_loglevel(0)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,width=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCOVREncoder, ECOCHDDecoder, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsRestStrategy(), feats_train, classifier, labels)
mc_classifier.train()
out_mc = mc_classifier.apply(feats_test).get_labels()
ecoc_strategy = ECOCStrategy(ECOCOVREncoder(), ECOCHDDecoder())
ecoc_classifier = LinearMulticlassMachine(ecoc_strategy, feats_train, classifier, labels)
ecoc_classifier.train()
out_ecoc = ecoc_classifier.apply(feats_test).get_labels()
n_diff = (out_mc != out_ecoc).sum()
if n_diff == 0:
print("Same results for OvR and ECOCOvR")
else:
print("Different results for OvR and ECOCOvR (%d out of %d are different)" % (n_diff, len(out_mc)))
return out_ecoc, out_mc
def classifier_svmlight_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,C=1.2,epsilon=1e-5,num_threads=1): from shogun.Features import StringCharFeatures, Labels, DNA from shogun.Kernel import WeightedDegreeStringKernel try: from shogun.Classifier import SVMLight except ImportError: print 'No support for SVMLight available.' return feats_train=StringCharFeatures(DNA) feats_train.set_features(fm_train_dna) feats_test=StringCharFeatures(DNA) feats_test.set_features(fm_test_dna) degree=20 kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree) labels=Labels(label_train_dna) svm=SVMLight(C, kernel, labels) svm.set_epsilon(epsilon) svm.parallel.set_num_threads(num_threads) svm.train() kernel.init(feats_train, feats_test) svm.apply().get_labels() return kernel
def classifier_svmlight_linear_term_modular(fm_train_dna=traindna,fm_test_dna=testdna, \
label_train_dna=label_traindna,degree=3, \
C=10,epsilon=1e-5,num_threads=1):
from shogun.Features import StringCharFeatures, Labels, DNA
from shogun.Kernel import WeightedDegreeStringKernel
from shogun.Classifier import SVMLight
feats_train = StringCharFeatures(DNA)
feats_train.set_features(fm_train_dna)
feats_test = StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
kernel = WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels = Labels(label_train_dna)
svm = SVMLight(C, kernel, labels)
svm.set_qpsize(3)
svm.set_linear_term(
-numpy.array([1, 2, 3, 4, 5, 6, 7, 8, 7, 6], dtype=numpy.double))
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.train()
kernel.init(feats_train, feats_test)
out = svm.apply().get_labels()
return out, kernel
def mlprocess(task_filename, data_filename, pred_filename, verbose=True):
"""Demo of creating machine learning process."""
task_type, fidx, lidx, train_idx, test_idx = parse_task(task_filename)
outputs = init_output(task_type)
all_data = parse_data(data_filename)
train_ex, train_lab, test_ex, test_lab = split_data(all_data, fidx, lidx, train_idx, test_idx)
label_train = outputs.str2label(train_lab)
if verbose:
print('Number of features: %d' % train_ex.shape[0])
print('%d training examples, %d test examples' % (len(train_lab), len(test_lab)))
feats_train = RealFeatures(train_ex)
feats_test = RealFeatures(test_ex)
width=1.0
kernel=GaussianKernel(feats_train, feats_train, width)
labels=Labels(label_train)
svm = init_svm(task_type, kernel, labels)
svm.train()
kernel.init(feats_train, feats_test)
preds = svm.classify().get_labels()
pred_label = outputs.label2str(preds)
pf = open(pred_filename, 'w')
for pred in pred_label:
pf.write(pred+'\n')
pf.close()
def libsvm():
print 'LibSVM'
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Evaluation import PerformanceMeasures
from shogun.Classifier import LibSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
C = 1
epsilon = 1e-5
labels = Labels(label_train_twoclass)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
#kernel.init(feats_train, feats_test)
output = svm.classify(feats_test) #.get_labels()
#output_vector = output.get_labels()
out = svm.classify().get_labels()
testerr = mean(sign(out) != testlab)
print testerr
def classifier_subgradientsvm_modular(fm_train_real, fm_test_real,
label_train_twoclass, C, epsilon,
max_train_time):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import SubGradientSVM
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
labels = Labels(label_train_twoclass)
svm = SubGradientSVM(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.set_max_train_time(max_train_time)
svm.train()
svm.set_features(feats_test)
labels = svm.apply().get_labels()
return labels, svm
def classifier_libsvm_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LibSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = Labels(label_train_twoclass)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
kernel.init(feats_train, feats_test)
labels = svm.classify().get_labels()
supportvectors = sv_idx = svm.get_support_vectors()
alphas = svm.get_alphas()
predictions = svm.classify()
return predictions, svm, predictions.get_labels()
def classifier_svmlin_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
C=0.9,
epsilon=1e-5,
num_threads=1):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import SVMLin
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
labels = Labels(label_train_twoclass)
svm = SVMLin(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.get_bias()
svm.get_w()
svm.classify().get_labels()
predictions = svm.classify()
return predictions, svm, predictions.get_labels()
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)
# 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)
# 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 classifier_larank_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
C=0.9,
num_threads=1,
num_iter=5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LaRank
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
epsilon = 1e-5
labels = Labels(label_train_multiclass)
svm = LaRank(C, kernel, labels)
#svm.set_tau(1e-3)
svm.set_batch_mode(False)
#svm.io.enable_progress()
svm.set_epsilon(epsilon)
svm.train()
out = svm.apply(feats_train).get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def kernel_salzberg_word_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
order=3,
gap=0,
reverse=False):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA, Labels
from shogun.Kernel import SalzbergWordStringKernel
from shogun.Classifier import PluginEstimate
charfeat = StringCharFeatures(fm_train_dna, DNA)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
charfeat = StringCharFeatures(fm_test_dna, DNA)
feats_test = StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
pie = PluginEstimate()
labels = Labels(label_train_dna)
pie.set_labels(labels)
pie.set_features(feats_train)
pie.train()
kernel = SalzbergWordStringKernel(feats_train, feats_train, pie, labels)
km_train = kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
pie.set_features(feats_test)
pie.apply().get_labels()
km_test = kernel.get_kernel_matrix()
return km_train, km_test, kernel
def get_labels(raw=False):
data = concatenate(
array(
(-ones(NUM_EXAMPLES, dtype=double), ones(NUM_EXAMPLES,
dtype=double))))
if raw:
return data
else:
return Labels(data)
def regression_least_squares_modular (fm_train=traindat,fm_test=testdat,label_train=label_traindat,tau=1e-6): from shogun.Features import Labels, RealFeatures from shogun.Kernel import GaussianKernel from shogun.Regression import LeastSquaresRegression ls=LeastSquaresRegression(RealFeatures(traindat), Labels(label_train)) ls.train() out = ls.apply(RealFeatures(fm_test)).get_labels() return out,ls
def evaluation_contingencytableevaluation_modular(ground_truth, predicted):
from shogun.Features import Labels
from shogun.Evaluation import ContingencyTableEvaluation
from shogun.Evaluation import AccuracyMeasure, ErrorRateMeasure, BALMeasure
from shogun.Evaluation import WRACCMeasure, F1Measure, CrossCorrelationMeasure
from shogun.Evaluation import RecallMeasure, PrecisionMeasure, SpecificityMeasure
ground_truth_labels = Labels(ground_truth)
predicted_labels = Labels(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 classifier_multiclassmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,width=2.1,C=1,epsilon=1e-5): from shogun.Features import RealFeatures, Labels from shogun.Kernel import GaussianKernel from shogun.Classifier import LibSVM, KernelMulticlassMachine, MulticlassOneVsRestStrategy feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) kernel=GaussianKernel(feats_train, feats_train, width) labels=Labels(label_train_multiclass) classifier = LibSVM(C, kernel, labels) classifier.set_epsilon(epsilon) print labels.get_labels() mc_classifier = KernelMulticlassMachine(MulticlassOneVsRestStrategy(),kernel,classifier,labels) mc_classifier.train() kernel.init(feats_train, feats_test) out = mc_classifier.apply().get_labels() return out
num=10 dist=1 width=2.1 traindata_real=concatenate((randn(2,num)-dist, randn(2,num)+dist), axis=1) testdata_real=concatenate((randn(2,num)-dist, randn(2,num)+dist), axis=1); trainlab=concatenate((-ones(num), ones(num))); testlab=concatenate((-ones(num), ones(num))); feats_train=RealFeatures(traindata_real); feats_test=RealFeatures(testdata_real); kernel=GaussianKernel(feats_train, feats_train, width); kernel.io.set_loglevel(MSG_DEBUG) labels=Labels(trainlab); svm=SVMLight(2, kernel, labels) svm.train() svm.io.set_loglevel(MSG_DEBUG) ################################################## print "labels:" print labels.to_string() print "features" print feats_train.to_string() print "kernel" print kernel.to_string()
def features_io_modular(fm_train_real, label_train_twoclass):
import numpy
from shogun.Features import SparseRealFeatures, RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.IO import AsciiFile, BinaryFile, HDF5File
feats=SparseRealFeatures(fm_train_real)
feats2=SparseRealFeatures()
f=BinaryFile("fm_train_sparsereal.bin","w")
feats.save(f)
f=AsciiFile("fm_train_sparsereal.ascii","w")
feats.save(f)
f=BinaryFile("fm_train_sparsereal.bin")
feats2.load(f)
f=AsciiFile("fm_train_sparsereal.ascii")
feats2.load(f)
feats=RealFeatures(fm_train_real)
feats2=RealFeatures()
f=BinaryFile("fm_train_real.bin","w")
feats.save(f)
f=HDF5File("fm_train_real.h5","w", "/data/doubles")
feats.save(f)
f=AsciiFile("fm_train_real.ascii","w")
feats.save(f)
f=BinaryFile("fm_train_real.bin")
feats2.load(f)
#print "diff binary", numpy.max(numpy.abs(feats2.get_feature_matrix().flatten()-fm_train_real.flatten()))
f=AsciiFile("fm_train_real.ascii")
feats2.load(f)
#print "diff ascii", numpy.max(numpy.abs(feats2.get_feature_matrix().flatten()-fm_train_real.flatten()))
lab=Labels(numpy.array([1.0,2.0,3.0]))
lab2=Labels()
f=AsciiFile("label_train_twoclass.ascii","w")
lab.save(f)
f=BinaryFile("label_train_twoclass.bin","w")
lab.save(f)
f=HDF5File("label_train_real.h5","w", "/data/labels")
lab.save(f)
f=AsciiFile("label_train_twoclass.ascii")
lab2.load(f)
f=BinaryFile("label_train_twoclass.bin")
lab2.load(f)
f=HDF5File("fm_train_real.h5","r", "/data/doubles")
feats2.load(f)
#print feats2.get_feature_matrix()
f=HDF5File("label_train_real.h5","r", "/data/labels")
lab2.load(f)
#print lab2.get_labels()
#clean up
import os
for f in ['fm_train_sparsereal.bin','fm_train_sparsereal.ascii',
'fm_train_real.bin','fm_train_real.h5','fm_train_real.ascii',
'label_train_real.h5', 'label_train_twoclass.ascii','label_train_twoclass.bin']:
os.unlink(f)
return feats, feats2, lab, lab2
