def _run_lda ():
"""Run Linear Discriminant Analysis classifier."""
params={
'name': 'LDA',
'type': 'lda',
'gamma': 0.1,
'num_threads': 1,
'data': dataop.get_clouds(2),
'feature_class': 'simple',
'feature_type': 'Real',
'label_type': 'twoclass',
'accuracy': 1e-7
}
feats=featop.get_features(
params['feature_class'], params['feature_type'], params['data'])
params['labels'], labels=dataop.get_labels(
feats['train'].get_num_vectors(), params['label_type'])
lda=classifier.LDA(params['gamma'], feats['train'], labels)
lda.parallel.set_num_threads(params['num_threads'])
lda.train()
lda.set_features(feats['test'])
params['classified']=lda.classify().get_labels()
output=fileop.get_output(category.CLASSIFIER, params)
fileop.write(category.CLASSIFIER, output)
def _run_perceptron ():
"""Run Perceptron classifier."""
params={
'name': 'Perceptron',
'type': 'perceptron',
'num_threads': 1,
'learn_rate': .1,
'max_iter': 1000,
'data': dataop.get_clouds(2),
'feature_class': 'simple',
'feature_type': 'Real',
'label_type': 'twoclass',
'accuracy': 1e-7
}
feats=featop.get_features(
params['feature_class'], params['feature_type'], params['data'])
num_vec=feats['train'].get_num_vectors()
params['labels'], labels=dataop.get_labels(num_vec, params['label_type'])
perceptron=classifier.Perceptron(feats['train'], labels)
perceptron.parallel.set_num_threads(params['num_threads'])
perceptron.set_learn_rate(params['learn_rate'])
perceptron.set_max_iter(params['max_iter'])
perceptron.train()
params['bias']=perceptron.get_bias()
perceptron.set_features(feats['test'])
params['classified']=perceptron.classify().get_labels()
output=fileop.get_output(category.CLASSIFIER, params)
fileop.write(category.CLASSIFIER, output)
def _run (name, first_arg):
"""
Run generator for a specific clustering method.
@param name Name of the clustering method to run.
@param first_arg First argument to the clustering's constructor; so far, only this distinguishes the instantion of the different methods.
"""
# put some constantness into randomness
Math_init_random(dataop.INIT_RANDOM)
num_clouds=3
params={
'name': 'EuclidianDistance',
'data': dataop.get_clouds(num_clouds, 5),
'feature_class': 'simple',
'feature_type': 'Real'
}
feats=featop.get_features(
params['feature_class'], params['feature_type'], params['data'])
dfun=eval(params['name'])
distance=dfun(feats['train'], feats['train'])
output=fileop.get_output(category.DISTANCE, params)
params={
'name': name,
'accuracy': 1e-8,
first_arg: num_clouds
}
fun=eval('clustering.'+name)
clustering=fun(params[first_arg], distance)
clustering.train()
distance.init(feats['train'], feats['test'])
if name=='KMeans':
params['radi']=clustering.get_radiuses()
params['centers']=clustering.get_cluster_centers()
elif name=='Hierarchical':
params['merge_distance']=clustering.get_merge_distances()
params['pairs']=clustering.get_cluster_pairs()
output.update(fileop.get_output(category.CLUSTERING, params))
fileop.write(category.CLUSTERING, output)
def _run_svm_linear ():
"""Run all SVMs based on (Sparse) Linear Classifiers."""
params={
'type': 'linear',
'bias_enabled': False,
'data': dataop.get_clouds(2),
'feature_class': 'simple',
'feature_type': 'Real',
'label_type': 'twoclass'
}
feats=featop.get_features(
params['feature_class'], params['feature_type'],
params['data'], sparse=True)
svms=('LibLinear', 'SVMLin', 'SVMSGD')
params['bias_enabled']=True
_loop_svm(svms, params, feats)
# SubGradientSVM needs max_train_time to terminate
svms=('SubGradientSVM',)
params['bias_enabled']=False
params['max_train_time']=.5 # up to 2. does not improve test results :(
_loop_svm(svms, params, feats)
svms=('SVMOcas',)
_loop_svm(svms, params, feats)
params={
'type': 'linear',
'bias_enabled': False,
'label_type': 'twoclass',
'feature_class': 'wd',
'feature_type': 'Byte',
'data': dataop.get_dna(),
'alphabet': 'RAWDNA',
'order': 1
}
feats=featop.get_features(
params['feature_class'], params['feature_type'],
params['data'], params['order'])
_loop_svm(svms, params, feats)
def _run(name, first_arg):
"""
Run generator for a specific clustering method.
@param name Name of the clustering method to run.
@param first_arg First argument to the clustering's constructor; so far, only this distinguishes the instantion of the different methods.
"""
# put some constantness into randomness
Math_init_random(dataop.INIT_RANDOM)
num_clouds = 3
params = {
'name': 'EuclidianDistance',
'data': dataop.get_clouds(num_clouds, 5),
'feature_class': 'simple',
'feature_type': 'Real'
}
feats = featop.get_features(params['feature_class'],
params['feature_type'], params['data'])
dfun = eval(params['name'])
distance = dfun(feats['train'], feats['train'])
output = fileop.get_output(category.DISTANCE, params)
params = {'name': name, 'accuracy': 1e-8, first_arg: num_clouds}
fun = eval('clustering.' + name)
clustering = fun(params[first_arg], distance)
clustering.train()
distance.init(feats['train'], feats['test'])
if name == 'KMeans':
params['radi'] = clustering.get_radiuses()
params['centers'] = clustering.get_cluster_centers()
elif name == 'Hierarchical':
params['merge_distance'] = clustering.get_merge_distances()
params['pairs'] = clustering.get_cluster_pairs()
output.update(fileop.get_output(category.CLUSTERING, params))
fileop.write(category.CLUSTERING, output)
def _run_knn ():
"""Run K-Nearest-Neighbour classifier.
"""
params={
'name': 'EuclidianDistance',
'data': dataop.get_clouds(2),
'feature_class': 'simple',
'feature_type': 'Real'
}
feats=featop.get_features(
params['feature_class'], params['feature_type'], params['data'])
dfun=eval(params['name'])
distance=dfun(feats['train'], feats['train'])
output=fileop.get_output(category.DISTANCE, params)
params={
'name': 'KNN',
'type': 'knn',
'num_threads': 1,
'k': 3,
'label_type': 'twoclass',
'accuracy': 1e-8
}
params['labels'], labels=dataop.get_labels(
feats['train'].get_num_vectors(), params['label_type'])
knn=classifier.KNN(params['k'], distance, labels)
knn.parallel.set_num_threads(params['num_threads'])
knn.train()
distance.init(feats['train'], feats['test'])
params['classified']=knn.classify().get_labels()
output.update(fileop.get_output(category.CLASSIFIER, params))
fileop.write(category.CLASSIFIER, output)
def _run_svm_kernel ():
"""Run all kernel-based SVMs."""
kparams={
'name': 'Gaussian',
'args': {'key': ('width',), 'val': (1.5,)},
'feature_class': 'simple',
'feature_type': 'Real',
'data': dataop.get_clouds(2)
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=GaussianKernel(10, *kparams['args']['val'])
output=fileop.get_output(category.KERNEL, kparams)
svms=('SVMLight', 'LibSVM', 'GPBTSVM', 'MPDSVM')
params={
'type': 'kernel',
'label_type': 'twoclass'
}
_loop_svm(svms, params, feats, kernel, output)
svms=('LibSVMOneClass',)
params['label_type']=None
_loop_svm(svms, params, feats, kernel, output)
svms=('LibSVMMultiClass', 'GMNPSVM')
params['label_type']='series'
kparams['data']=dataop.get_clouds(3)
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
output=fileop.get_output(category.KERNEL, kparams)
_loop_svm(svms, params, feats, kernel, output)
svms=('SVMLight', 'GPBTSVM')
params['label_type']='twoclass'
kparams={
'name': 'Linear',
'feature_class': 'simple',
'feature_type': 'Real',
'data': dataop.get_clouds(2),
'normalizer': AvgDiagKernelNormalizer()
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=LinearKernel()
kernel.set_normalizer(kparams['normalizer'])
output=fileop.get_output(category.KERNEL, kparams)
_loop_svm(svms, params, feats, kernel, output)
kparams={
'name': 'CommWordString',
'args': {'key': ('use_sign',), 'val': (False,)},
'data': dataop.get_dna(),
'feature_class': 'string_complex',
'feature_type': 'Word'
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=CommWordStringKernel(10, *kparams['args']['val'])
output=fileop.get_output(category.KERNEL, kparams)
_loop_svm(svms, params, feats, kernel, output)
kparams={
'name': 'CommUlongString',
'args': {'key': ('use_sign',), 'val': (False,)},
'data': dataop.get_dna(),
'feature_class': 'string_complex',
'feature_type': 'Ulong'
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=CommUlongStringKernel(10, *kparams['args']['val'])
output=fileop.get_output(category.KERNEL, kparams)
_loop_svm(svms, params, feats, kernel, output)
kparams={
'name': 'WeightedDegreeString',
'args': {'key': ('degree',), 'val': (3,)},
'data': dataop.get_dna(),
'feature_class': 'string',
'feature_type': 'Char'
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=WeightedDegreeStringKernel(*kparams['args']['val'])
output=fileop.get_output(category.KERNEL, kparams)
_loop_svm(svms, params, feats, kernel, output)
params['linadd_enabled']=True
_loop_svm(svms, params, feats, kernel, output)
params['batch_enabled']=True
_loop_svm(svms, params, feats, kernel, output)
kparams={
'name': 'WeightedDegreePositionString',
'args': {'key': ('degree',), 'val': (20,)},
'data': dataop.get_dna(),
'feature_class': 'string',
'feature_type': 'Char'
}
feats=featop.get_features(
kparams['feature_class'], kparams['feature_type'], kparams['data'])
kernel=WeightedDegreePositionStringKernel(10, *kparams['args']['val'])
output=fileop.get_output(category.KERNEL, kparams)
del params['linadd_enabled']
del params['batch_enabled']
_loop_svm(svms, params, feats, kernel, output)
params['linadd_enabled']=True
_loop_svm(svms, params, feats, kernel, output)
params['batch_enabled']=True
_loop_svm(svms, params, feats, kernel, output)
