def fit_and_predict(load_test_data, train_data, test_feature_matrics,
train_label, test_label_OR_test_data):
features_train = RealFeatures(train_data)
features_test = RealFeatures(test_feature_matrics)
labels_train = BinaryLabels(train_label)
learn_rate = 1.0
max_iter = 1000
perceptron = AveragedPerceptron(features_train, labels_train)
perceptron.set_learn_rate(learn_rate)
perceptron.set_max_iter(max_iter)
perceptron.train()
perceptron.set_features(features_test)
labels_predict = perceptron.apply()
if load_test_data:
del test_label_OR_test_data['question_text']
# import pdb; pdb.set_trace()
test_label_OR_test_data.insert(1, 'prediction', prediction80)
test_label_OR_test_data.to_csv('submission.csv', index=False)
return prediction
else:
labels_test = BinaryLabels(test_label_OR_test_data)
accEval = AccuracyMeasure()
accuracy = accEval.evaluate(labels_predict, labels_test)
f1Eval = F1Measure()
f1_score = f1Eval.evaluate(labels_predict, labels_test)
print('#accuracy is: ', accuracy)
print('#F1 score is: ', f1_score)
def evaluation_thresholds(index):
from shogun import BinaryLabels, ROCEvaluation
import numpy
numpy.random.seed(17)
output = numpy.arange(-1, 1, 0.001)
output = (0.3 * output + 0.7 * (numpy.random.rand(len(output)) - 0.5))
label = [-1.0] * (len(output) // 2)
label.extend([1.0] * (len(output) // 2))
label = numpy.array(label)
pred = BinaryLabels(output)
truth = BinaryLabels(label)
evaluator = ROCEvaluation()
evaluator.evaluate(pred, truth)
[fp, tp] = evaluator.get_ROC()
thresh = evaluator.get_thresholds()
b = thresh[index]
#print("tpr", numpy.mean(output[label>0]>b), tp[index])
#print("fpr", numpy.mean(output[label<0]>b), fp[index])
return tp[index], fp[index], numpy.mean(output[label > 0] > b), numpy.mean(
output[label < 0] > b)
def classifier_domainadaptationsvm (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 = BinaryLabels(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 = BinaryLabels(label_train_dna)
# we regularize against the previously obtained solution
dasvm = DomainAdaptationSVM(C, kernel2, labels2, svm, 1.0)
dasvm.train()
out = dasvm.apply_binary(feats_test2)
return out #,dasvm TODO
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 less variance
cross.set_num_runs(10)
result = cross.evaluate()
casted = CrossValidationResult.obtain_from_generic(result)
#print "result mean:", casted.mean
return classifier, result, casted.get_mean()
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 less variance
cross.set_num_runs(10)
result=cross.evaluate()
casted=CrossValidationResult.obtain_from_generic(result);
#print "result mean:", casted.mean
return classifier,result,casted.get_mean()
def evaluation_rocevaluation(ground_truth, predicted):
from shogun import BinaryLabels
from shogun import ROCEvaluation
ground_truth_labels = BinaryLabels(ground_truth)
predicted_labels = BinaryLabels(predicted)
evaluator = ROCEvaluation()
evaluator.evaluate(predicted_labels, ground_truth_labels)
return evaluator.get_ROC(), evaluator.get_auROC()
def evaluation_cross_validation_classification(traindat=traindat,
label_traindat=label_traindat):
from shogun import CrossValidation, CrossValidationResult
from shogun import ContingencyTableEvaluation, ACCURACY
from shogun import StratifiedCrossValidationSplitting
from shogun import BinaryLabels
from shogun import RealFeatures
from shogun 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 classifier_svmlight(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
C=1.2,
epsilon=1e-5,
num_threads=1):
from shogun import StringCharFeatures, BinaryLabels, DNA
from shogun import WeightedDegreeStringKernel
try:
from shogun 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 = BinaryLabels(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 transfer_multitask_clustered_logistic_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat
):
from shogun import BinaryLabels, RealFeatures, Task, TaskGroup, MSG_DEBUG
try:
from shogun import MultitaskClusteredLogisticRegression
except ImportError:
print("MultitaskClusteredLogisticRegression not available")
exit()
features = RealFeatures(hstack((traindat, sin(traindat), cos(traindat))))
labels = BinaryLabels(hstack((label_train, label_train, label_train)))
n_vectors = features.get_num_vectors()
task_one = Task(0, n_vectors // 3)
task_two = Task(n_vectors // 3, 2 * n_vectors // 3)
task_three = Task(2 * n_vectors // 3, n_vectors)
task_group = TaskGroup()
task_group.append_task(task_one)
task_group.append_task(task_two)
task_group.append_task(task_three)
mtlr = MultitaskClusteredLogisticRegression(1.0, 100.0, features, labels,
task_group, 2)
#mtlr.io.set_loglevel(MSG_DEBUG)
mtlr.set_tolerance(1e-3) # use 1e-2 tolerance
mtlr.set_max_iter(100)
mtlr.train()
mtlr.set_current_task(0)
#print mtlr.get_w()
out = mtlr.apply_regression().get_labels()
return out
def kernel_salzberg_word_string(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
order=3,
gap=0,
reverse=False):
from shogun import StringCharFeatures, StringWordFeatures, DNA, BinaryLabels
from shogun import SalzbergWordStringKernel
from shogun 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 = BinaryLabels(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 classifier_svmocas(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
C=0.9,
epsilon=1e-5,
num_threads=1):
from shogun import RealFeatures, BinaryLabels
from shogun import CSVFile
try:
from shogun import SVMOcas
except ImportError:
print("SVMOcas not available")
return
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
svm = SVMOcas(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(False)
svm.train()
bias = svm.get_bias()
w = svm.get_w()
predictions = svm.apply(feats_test)
return predictions, svm, predictions.get_labels()
def classifier_ssk(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
C=1,
maxlen=1,
decay=1):
from shogun import StringCharFeatures, BinaryLabels
from shogun import LibSVM, SubsequenceStringKernel, DNA
from shogun import ErrorRateMeasure
feats_train = StringCharFeatures(fm_train_dna, DNA)
feats_test = StringCharFeatures(fm_test_dna, DNA)
labels = BinaryLabels(label_train_dna)
kernel = SubsequenceStringKernel(feats_train, feats_train, maxlen, decay)
svm = LibSVM(C, kernel, labels)
svm.train()
out = svm.apply(feats_train)
evaluator = ErrorRateMeasure()
trainerr = evaluator.evaluate(out, labels)
# print(trainerr)
kernel.init(feats_train, feats_test)
predicted_labels = svm.apply(feats_test).get_labels()
# print predicted_labels
return predicted_labels
def transfer_multitask_logistic_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat):
from shogun import BinaryLabels, RealFeatures, Task, TaskGroup
try:
from shogun import MultitaskLogisticRegression
except ImportError:
print("MultitaskLogisticRegression not available")
exit()
features = RealFeatures(hstack((traindat, traindat)))
labels = BinaryLabels(hstack((label_train, label_train)))
n_vectors = features.get_num_vectors()
task_one = Task(0, n_vectors // 2)
task_two = Task(n_vectors // 2, n_vectors)
task_group = TaskGroup()
task_group.append_task(task_one)
task_group.append_task(task_two)
mtlr = MultitaskLogisticRegression(0.1, features, labels, task_group)
mtlr.set_regularization(1) # use regularization ratio
mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
mtlr.train()
mtlr.set_current_task(0)
out = mtlr.apply().get_labels()
return out
def kernel_histogram_word_string(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
order=3,
ppseudo_count=1,
npseudo_count=1):
from shogun import StringCharFeatures, StringWordFeatures, DNA, BinaryLabels
from shogun import HistogramWordStringKernel, AvgDiagKernelNormalizer
from shogun import PluginEstimate #, MSG_DEBUG
charfeat = StringCharFeatures(DNA)
#charfeat.io.set_loglevel(MSG_DEBUG)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, 0, False)
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, 0, False)
pie = PluginEstimate(ppseudo_count, npseudo_count)
labels = BinaryLabels(label_train_dna)
pie.set_labels(labels)
pie.set_features(feats_train)
pie.train()
kernel = HistogramWordStringKernel(feats_train, feats_train, pie)
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 classifier_featureblock_logistic_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat):
from shogun import BinaryLabels, RealFeatures, IndexBlock, IndexBlockGroup
try:
from shogun import FeatureBlockLogisticRegression
except ImportError:
print("FeatureBlockLogisticRegression not available")
exit(0)
features = RealFeatures(hstack((traindat, traindat)))
labels = BinaryLabels(hstack((label_train, label_train)))
n_features = features.get_num_features()
block_one = IndexBlock(0, n_features // 2)
block_two = IndexBlock(n_features // 2, n_features)
block_group = IndexBlockGroup()
block_group.add_block(block_one)
block_group.add_block(block_two)
mtlr = FeatureBlockLogisticRegression(0.1, features, labels, block_group)
mtlr.set_regularization(1) # use regularization ratio
mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
mtlr.train()
out = mtlr.apply().get_labels()
return out
def classifier_svmlight_linear_term (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 import StringCharFeatures, BinaryLabels, DNA
from shogun import WeightedDegreeStringKernel
try:
from shogun import SVMLight
except ImportError:
print("SVMLight is not available")
exit(0)
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=BinaryLabels(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 classifier_gpbtsvm(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun import RealFeatures, BinaryLabels
from shogun import GaussianKernel
from shogun import CSVFile
try:
from shogun import GPBTSVM
except ImportError:
print("GPBTSVM not available")
exit(0)
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
svm = GPBTSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
predictions = svm.apply(feats_test)
return predictions, svm, predictions.get_labels()
def evaluation_contingencytableevaluation(ground_truth, predicted):
from shogun import BinaryLabels
from shogun import ContingencyTableEvaluation
from shogun import AccuracyMeasure, ErrorRateMeasure, BALMeasure
from shogun import WRACCMeasure, F1Measure, CrossCorrelationMeasure
from shogun 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 kernel_auc (train_fname=traindat,label_fname=label_traindat,width=1.7): from shogun import GaussianKernel, AUCKernel, RealFeatures from shogun import BinaryLabels, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) subkernel=GaussianKernel(feats_train, feats_train, width) kernel=AUCKernel(0, subkernel) kernel.setup_auc_maximization(BinaryLabels(CSVFile(label_fname))) km_train=kernel.get_kernel_matrix() return kernel
def get_labels(raw=False, type='binary'):
data = concatenate(
array(
(-ones(NUM_EXAMPLES, dtype=double), ones(NUM_EXAMPLES,
dtype=double))))
if raw:
return data
else:
if type == 'binary':
return BinaryLabels(data)
if type == 'regression':
return RegressionLabels(data)
return None
def evaluation_director_contingencytableevaluation (ground_truth, predicted):
try:
from shogun import DirectorContingencyTableEvaluation, ED_MAXIMIZE
except ImportError:
print("recompile shogun with --enable-swig-directors")
return
class SimpleWeightedBinaryEvaluator(DirectorContingencyTableEvaluation):
def __init__(self):
DirectorContingencyTableEvaluation.__init__(self)
def get_custom_direction(self):
return ED_MAXIMIZE
def get_custom_score(self):
return self.get_WRACC()+self.get_BAL()
from shogun import BinaryLabels
evaluator = SimpleWeightedBinaryEvaluator()
r = evaluator.evaluate(BinaryLabels(ground_truth), BinaryLabels(predicted))
r2 = evaluator.get_custom_score()
print(r,r2)
return r,r2
def features_from_file(fileName):
fileHandle = open(fileName)
fileHandle.readline()
features = []
labels = []
for line in fileHandle:
tokens = line.split(',')
labels.append(float(tokens[1]))
features.append([float(token) for token in tokens[2:]])
return RealFeatures(numpy.transpose(
numpy.array(features))), features, BinaryLabels(
numpy.array(labels, numpy.float))
def classifier_svmsgd (train_fname=traindat,test_fname=testdat,label_fname=label_traindat,C=0.9,num_threads=1,num_iter=5): from shogun import RealFeatures, SparseRealFeatures, BinaryLabels from shogun import SVMSGD, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) labels=BinaryLabels(CSVFile(label_fname)) svm=SVMSGD(C, feats_train, labels) svm.set_epochs(num_iter) #svm.io.set_loglevel(0) svm.train() bias=svm.get_bias() w=svm.get_w() predictions = svm.apply(feats_test) return predictions, svm, predictions.get_labels()
def kernel_combined_custom_poly(train_fname=traindat,
test_fname=testdat,
train_label_fname=label_traindat):
from shogun import CombinedFeatures, RealFeatures, BinaryLabels
from shogun import CombinedKernel, PolyKernel, CustomKernel
from shogun import LibSVM, CSVFile
kernel = CombinedKernel()
feats_train = CombinedFeatures()
tfeats = RealFeatures(CSVFile(train_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, tfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_train = RealFeatures(CSVFile(train_fname))
feats_train.append_feature_obj(subkfeats_train)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
labels = BinaryLabels(CSVFile(train_label_fname))
svm = LibSVM(1.0, kernel, labels)
svm.train()
kernel = CombinedKernel()
feats_pred = CombinedFeatures()
pfeats = RealFeatures(CSVFile(test_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, pfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_test = RealFeatures(CSVFile(test_fname))
feats_pred.append_feature_obj(subkfeats_test)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_pred)
svm.set_kernel(kernel)
svm.apply()
km_train = kernel.get_kernel_matrix()
return km_train, kernel
def classifier_lda(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
gamma=3,
num_threads=1):
from shogun import RealFeatures, BinaryLabels, LDA, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
lda = LDA(gamma, feats_train, labels)
lda.train()
bias = lda.get_bias()
w = lda.get_w()
predictions = lda.apply(feats_test).get_labels()
return lda, predictions
def classifier_svmlin (train_fname=traindat,test_fname=testdat,label_fname=label_traindat,C=0.9,epsilon=1e-5,num_threads=1): from shogun import RealFeatures, SparseRealFeatures, BinaryLabels from shogun import SVMLin, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) labels=BinaryLabels(CSVFile(label_fname)) svm=SVMLin(C, feats_train, labels) svm.set_epsilon(epsilon) svm.parallel.set_num_threads(num_threads) svm.set_bias_enabled(True) svm.train() bias=svm.get_bias() w=svm.get_w() predictions = svm.apply(feats_test) return predictions, svm, predictions.get_labels()
def classifier_custom_kernel(C=1, dim=7):
from shogun import RealFeatures, BinaryLabels, CustomKernel, LibSVM
from numpy import diag, ones, sign
from numpy.random import rand, seed
seed((C, dim))
lab = sign(2 * rand(dim) - 1)
data = rand(dim, dim)
symdata = data * data.T + diag(ones(dim))
kernel = CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels = BinaryLabels(lab)
svm = LibSVM(C, kernel, labels)
svm.train()
predictions = svm.apply()
out = svm.apply().get_labels()
return svm, out
def runShogunSVMDNASpectrumKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up SVM
charfeat_train = StringCharFeatures(train_xt, DNA)
feats_train = StringWordFeatures(DNA)
feats_train.obtain_from_char(charfeat_train, K-1, K, GAP, False)
preproc=SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test=StringWordFeatures(DNA)
feats_test.obtain_from_char(charfeat_test, K-1, K, GAP, False)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
kernel=CommWordStringKernel(feats_train, feats_train, False)
kernel.io.set_loglevel(MSG_DEBUG)
# init kernel
labels = BinaryLabels(train_lt)
# run svm model
print "Ready to train!"
svm=LibSVM(SVMC, kernel, labels)
svm.io.set_loglevel(MSG_DEBUG)
svm.train()
# predictions
print "Making predictions!"
out1DecisionValues = svm.apply(feats_train)
out1=out1DecisionValues.get_labels()
kernel.init(feats_train, feats_test)
out2DecisionValues = svm.apply(feats_test)
out2=out2DecisionValues.get_labels()
return out1,out2,out1DecisionValues,out2DecisionValues
def classifier_svmlight_batch_linadd(fm_train_dna, fm_test_dna,
label_train_dna, degree, C, epsilon,
num_threads):
from shogun import StringCharFeatures, BinaryLabels, DNA
from shogun import WeightedDegreeStringKernel, MSG_DEBUG
try:
from shogun import SVMLight
except ImportError:
print('No support for SVMLight available.')
return
feats_train = StringCharFeatures(DNA)
#feats_train.io.set_loglevel(MSG_DEBUG)
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 = BinaryLabels(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)
#print('SVMLight Objective: %f num_sv: %d' % \)
# (svm.get_objective(), svm.get_num_support_vectors())
svm.set_batch_computation_enabled(False)
svm.set_linadd_enabled(False)
svm.apply().get_labels()
svm.set_batch_computation_enabled(True)
labels = svm.apply().get_labels()
return labels, svm
def classifier_mpdsvm(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
C=1,
epsilon=1e-5):
from shogun import RealFeatures, BinaryLabels
from shogun import GaussianKernel
from shogun import MPDSVM, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
svm = MPDSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
predictions = svm.apply(feats_test)
return predictions, svm, predictions.get_labels()
def classifier_perceptron(n=100,
dim=2,
distance=5,
learn_rate=1.,
max_iter=1000,
num_threads=1,
seed=1):
from shogun import RealFeatures, BinaryLabels
from shogun import Perceptron
random.seed(seed)
# produce some (probably) linearly separable training data by hand
# Two Gaussians at a far enough distance
X = array(random.randn(dim, n)) + distance
Y = array(random.randn(dim, n)) - distance
X_test = array(random.randn(dim, n)) + distance
Y_test = array(random.randn(dim, n)) - distance
label_train_twoclass = hstack((ones(n), -ones(n)))
#plot(X[0,:], X[1,:], 'x', Y[0,:], Y[1,:], 'o')
fm_train_real = hstack((X, Y))
fm_test_real = hstack((X_test, Y_test))
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = BinaryLabels(label_train_twoclass)
perceptron = Perceptron(feats_train, labels)
perceptron.set_learn_rate(learn_rate)
perceptron.set_max_iter(max_iter)
# only guaranteed to converge for separable data
perceptron.train()
perceptron.set_features(feats_test)
out_labels = perceptron.apply().get_labels()
return perceptron, out_labels
