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 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 classifier_multiclassmachine (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,width=2.1,C=1,epsilon=1e-5): from shogun import RealFeatures, MulticlassLabels from shogun import GaussianKernel from shogun import LibSVM, KernelMulticlassMachine, MulticlassOneVsRestStrategy feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) kernel=GaussianKernel(feats_train, feats_train, width) labels=MulticlassLabels(label_train_multiclass) classifier = LibSVM() 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
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 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_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 svm_train(kernel, labels, C1, C2=None):
"""Trains a SVM with the given kernel"""
num_threads = 1
kernel.io.disable_progress()
svm = LibSVM(C1, kernel, labels)
if C2:
svm.set_C(C1, C2)
svm.parallel.set_num_threads(num_threads)
svm.io.disable_progress()
svm.train()
return svm
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
class svm_splice_model(object): def __init__(self, order, traindat, alphas, b, (window_left,offset,window_right), consensus): f=StringCharFeatures(traindat, DNA) wd_kernel = WeightedDegreeStringKernel(f,f, int(order)) wd_kernel.io.set_target_to_stdout() self.svm=LibSVM() self.svm.set_kernel(wd_kernel) self.svm.set_alphas(alphas) self.svm.set_support_vectors(numpy.arange(len(alphas), dtype=numpy.int32)) self.svm.set_bias(b) self.svm.io.set_target_to_stdout() self.svm.parallel.set_num_threads(self.svm.parallel.get_num_cpus()) self.svm.set_linadd_enabled(True) self.svm.set_batch_computation_enabled(True) self.window_left=int(window_left) self.window_right=int(window_right) self.consensus=consensus self.wd_kernel=wd_kernel self.traindat=f self.offset=offset
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
(datasetSize,trainingSize,testSize,TEST_SIZE)
print_to_console_log(data_info)
## Codify Labels (1,-1)
y_train[np.where(y_train==0)] = -1
y_test [np.where(y_test==0)] = -1
## Set up Subsequence string Kernel
features = StringCharFeatures(X_train, RAWBYTE)
test_features = StringCharFeatures(X_test, RAWBYTE)
labels = BinaryLabels(y_train)
sk = SubsequenceStringKernel(features, features, SUBSEQUENCE_SIZE, LAMBDA)
## Fitting Kernel SVM to the Training set
startTime1 = time.time()
svm = LibSVM(C, sk, labels)
svm.train()
endTime1 = time.time()
## Print Training Time
formatedTime = time.strftime('%H:%M:%S', time.gmtime(endTime1-startTime1))
print_to_console_log("Training Time\nTime:{:010.4f}s\nTime:{:s}\n".format(endTime1-startTime1,formatedTime))
# save the model to disk
pickle.dump(svm, open(FILE_NAME, 'wb'))
# Model Evaluation
print_to_console_log("Evaluate Model...\n")
startTime2 = time.time()
predicted_labels = svm.apply(test_features).get_labels()
y_predicted = np.array(predicted_labels)
from shogun import LibSVM, LDA
from shogun import ROCEvaluation
import util
util.set_title('ROC example')
util.DISTANCE=0.5
subplots_adjust(hspace=0.3)
pos=util.get_realdata(True)
neg=util.get_realdata(False)
features=util.get_realfeatures(pos, neg)
labels=util.get_labels()
# classifiers
gk=GaussianKernel(features, features, 1.0)
svm = LibSVM(1000.0, gk, labels)
svm.train()
lda=LDA(1,features,labels)
lda.train()
## plot points
subplot(211)
plot(pos[0,:], pos[1,:], "r.")
plot(neg[0,:], neg[1,:], "b.")
grid(True)
title('Data',size=10)
# plot ROC for SVM
subplot(223)
ROC_evaluation=ROCEvaluation()
ROC_evaluation.evaluate(svm.apply(),labels)
from shogun import LibSVM, LDA
from shogun import ROCEvaluation
import util
util.set_title('ROC example')
util.DISTANCE = 0.5
subplots_adjust(hspace=0.3)
pos = util.get_realdata(True)
neg = util.get_realdata(False)
features = util.get_realfeatures(pos, neg)
labels = util.get_labels()
# classifiers
gk = GaussianKernel(features, features, 1.0)
svm = LibSVM(1000.0, gk, labels)
svm.train()
lda = LDA(1, features, labels)
lda.train()
## plot points
subplot(211)
plot(pos[0, :], pos[1, :], "r.")
plot(neg[0, :], neg[1, :], "b.")
grid(True)
title('Data', size=10)
# plot ROC for SVM
subplot(223)
ROC_evaluation = ROCEvaluation()
ROC_evaluation.evaluate(svm.apply(), labels)