SHOGUN
v1.1.0
|
本页面包含了所有Python静态接口的例子。
要运行这些例子只需要
python name_of_example.py
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_multiclass.dat') parameter_list=[[traindat,testdat, train_label,10,2.1,1.2,1e-5,False], [traindat,testdat,train_label,10,2.1,1.3,1e-4,False]] def classifier_gmnpsvm (fm_train_real=traindat,fm_test_real=testdat, label_train_multiclass=train_label, size_cache=10, width=2.1,C=1.2, epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train_multiclass) sg('new_classifier', 'GMNPSVM') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'GMNPSVM' classifier_gmnpsvm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat, train_label,10,2.1,1.2,1e-5,False], [traindat,testdat,train_label,10,2.1,1.3,1e-4,False]] def classifier_gpbtsvm (fm_train_real=traindat,fm_test_real=testdat, label_train_twoclass=train_label, size_cache=10, width=2.1,C=1.2, epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train_twoclass) sg('new_classifier', 'GPBTSVM') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') return result if __name__=='__main__': print 'GPBTSVM' classifier_gpbtsvm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_multiclass.dat') parameter_list=[[traindat,testdat, train_label,3], [traindat,testdat,train_label,4]] def classifier_knn (fm_train_real=traindat,fm_test_real=testdat, label_train_multiclass=train_label,k=3): sg('set_features', 'TRAIN', fm_train_real) sg('set_labels', 'TRAIN', label_train_multiclass) sg('set_distance', 'EUCLIDIAN', 'REAL') sg('new_classifier', 'KNN') sg('train_classifier', k) sg('set_features', 'TEST', fm_test_real) result=sg('classify') return result if __name__=='__main__': print 'KNN' classifier_knn(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat, train_label], [traindat,testdat,train_label]] def classifier_lda (fm_train_real=traindat,fm_test_real=testdat, label_train_twoclass=train_label): sg('set_features', 'TRAIN', fm_train_real) sg('set_labels', 'TRAIN', label_train_twoclass) sg('new_classifier', 'LDA') sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') return result if __name__=='__main__': print 'LDA' classifier_lda(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat, train_label,10,2.1,1.2,1e-5,False], [traindat,testdat,train_label,10,2.1,1.3,1e-4,False]] def classifier_libsvm (fm_train_real=traindat,fm_test_real=testdat, label_train_twoclass=train_label, size_cache=10, width=2.1,C=1.2, epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train_twoclass) sg('new_classifier', 'LIBSVM') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'LibSVM' classifier_libsvm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_multiclass.dat') parameter_list=[[traindat,testdat, train_label,10,2.1,10.,1e-5,False], [traindat,testdat,train_label,10,2.1,11.,1e-4,False]] def classifier_libsvm_multiclass (fm_train_real=traindat,fm_test_real=testdat, label_train_multiclass=train_label, size_cache=10, width=2.1,C=10., epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train_multiclass) sg('new_classifier', 'LIBSVM_MULTICLASS') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'LibSVMMultiClass' classifier_libsvm_multiclass(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,10,2.1,10.,1e-5,False], [traindat,testdat,10,2.1,11.,1e-4,False]] def classifier_libsvm_oneclass (fm_train_real=traindat,fm_test_real=testdat, size_cache=10, width=2.1,C=10., epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('new_classifier', 'LIBSVM_ONECLASS') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'LibSVMOneClass' classifier_libsvm_oneclass(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat, train_label,10,2.1,1.2,1e-5,False], [traindat,testdat,train_label,10,2.1,1.3,1e-4,False]] def classifier_mpdsvm (fm_train_real=traindat,fm_test_real=testdat, label_train_twoclass=train_label, size_cache=10, width=2.1,C=1.2, epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train_twoclass) sg('new_classifier', 'MPDSVM') sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'MPDSVM' classifier_mpdsvm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') train_label=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat, train_label], [traindat,testdat,train_label]] def classifier_perceptron (fm_train_real=traindat,fm_test_real=testdat, label_train_twoclass=train_label): sg('set_features', 'TRAIN', fm_train_real) sg('set_labels', 'TRAIN', label_train_twoclass) sg('new_classifier', 'PERCEPTRON') # often does not converge, mind your data! sg('train_classifier') sg('set_features', 'TEST', fm_test_real) result=sg('classify') return result if __name__=='__main__': print 'Perceptron' classifier_perceptron(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') train_label=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna, train_label,10,20,1.2,1e-5,False], [traindna,testdna,train_label,10,21,1.3,1e-4,False]] def classifier_svmlight (fm_train_dna=traindna,fm_test_dna=testdna,label_train_dna=train_label, size_cache=10, degree=20,C=1.2, epsilon=1e-5,use_bias=False): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_kernel', 'WEIGHTEDDEGREE', 'CHAR', size_cache, degree) sg('set_labels', 'TRAIN', label_train_dna) try: sg('new_classifier', 'SVMLIGHT') except RuntimeError: return sg('svm_epsilon', epsilon) sg('c', C) sg('svm_use_bias', use_bias) sg('train_classifier') sg('set_features', 'TEST', fm_test_dna, 'DNA') result=sg('classify') kernel_matrix = sg('get_kernel_matrix', 'TEST') return result, kernel_matrix if __name__=='__main__': print 'SVMLight' classifier_svmlight(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') parameter_list=[[traindat,10,3],[traindat,11,4]] def clustering_hierarchical (fm_train=traindat, size_cache=10,merges=3): sg('set_features', 'TRAIN', fm_train) sg('set_distance', 'EUCLIDIAN', 'REAL') sg('new_clustering', 'HIERARCHICAL') sg('train_clustering', merges) [merge_distance, pairs]=sg('get_clustering') return [merge_distance, pairs] if __name__=='__main__': print 'Hierarchical' clustering_hierarchical(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') parameter_list=[[traindat,10,3,1000],[traindat,11,4,1500]] def clustering_kmeans (fm_train=traindat, size_cache=10,k=3,iter=1000): sg('set_features', 'TRAIN', fm_train) sg('set_distance', 'EUCLIDIAN', 'REAL') sg('new_clustering', 'KMEANS') sg('train_clustering', k, iter) [radi, centers]=sg('get_clustering') return [radi, centers] if __name__=='__main__': print 'KMeans' clustering_kmeans(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_braycurtis (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'BRAYCURTIS', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'BrayCurtisDistance' distance_braycurtis(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_canberra (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'CANBERRA', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'CanberraMetric' distance_canberra(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,3,0,'n'],[traindna,testdna,4,0,'n']] def distance_canberraword (fm_train_dna=traindna,fm_test_dna=testdna,order=3, gap=0,reverse='n'): sg('set_distance', 'CANBERRA', 'WORD') sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'CanberraWordDistance' distance_canberraword(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_chebyshew (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'CHEBYSHEW', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'ChebyshewMetric' distance_chebyshew(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_chisquare (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'CHISQUARE', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'ChiSquareDistance' distance_chisquare(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_cosine (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'COSINE', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'CosineDistance' distance_cosine(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_euclidian (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'EUCLIDIAN', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'EuclidianDistance' distance_euclidian(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_geodesic (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'GEODESIC', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'GeodesicMetric' distance_geodesic(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,3,0,'n'],[traindna,testdna,4,0,'n']] def distance_hammingword (fm_train_dna=traindna,fm_test_dna=testdna,order=3, gap=0,reverse='n'): sg('set_distance', 'HAMMING', 'WORD') sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'HammingWordDistance' distance_hammingword(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_jensen (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'JENSEN', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'JensenMetric' distance_jensen(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_manhatten (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'MANHATTAN', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'ManhattanMetric' distance_manhatten(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,3,0,'n'],[traindna,testdna,4,0,'n']] def distance_manhattenword (fm_train_dna=traindna,fm_test_dna=testdna,order=3, gap=0,reverse='n'): sg('set_distance', 'MANHATTAN', 'WORD') sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'ManhattanWordDistance' distance_manhattenword(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,3.],[traindat,testdat,4.]] def distance_minkowski (fm_train_real=traindat,fm_test_real=testdat,k=3.): sg('set_distance', 'MINKOWSKI', 'REAL', k) sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'MinkowskiMetric' distance_minkowski(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat],[traindat,testdat]] def distance_tanimoto (fm_train_real=traindat,fm_test_real=testdat): sg('set_distance', 'TANIMOTO', 'REAL') sg('set_features', 'TRAIN', fm_train_real) dm=sg('get_distance_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) dm=sg('get_distance_matrix', 'TEST') return dm if __name__=='__main__': print 'TanimotoDistance' distance_tanimoto(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') cubedna=lm.load_cubes('../data/fm_train_cube.dat') parameter_list=[[traindna,cubedna,3,0,'n'],[traindna,cubedna,4,0,'n']] def distribution_histogram(fm_train=traindna,fm_cube=cubedna,order=3, gap=0,reverse='n'): # sg('new_distribution', 'HISTOGRAM') sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') # sg('train_distribution') # histo=sg('get_histogram') # num_examples=11 # num_param=sg('get_histogram_num_model_parameters') # for i in xrange(num_examples): # for j in xrange(num_param): # sg('get_log_derivative %d %d' % (j, i)) # sg('get_log_likelihood') # return sg('get_log_likelihood_sample') if __name__=='__main__': print 'Histogram' distribution_histogram(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') cubedna=lm.load_cubes('../data/fm_train_cube.dat') parameter_list=[[traindna,cubedna,3,6,1,list(),list()], [traindna,cubedna,3,6,1,list(),list()]] def distribution_hmm(fm_train=traindna,fm_cube=cubedna,N=3,M=6, order=1,hmms=list(),links=list()): sg('new_hmm',N, M) sg('set_features', 'TRAIN', fm_cube, 'CUBE') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order) sg('bw') hmm=sg('get_hmm') sg('new_hmm', N, M) sg('set_hmm', hmm[0], hmm[1], hmm[2], hmm[3]) likelihood=sg('hmm_likelihood') return likelihood if __name__=='__main__': print 'HMM' distribution_hmm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') cubedna=lm.load_cubes('../data/fm_train_cube.dat') parameter_list=[[traindna,cubedna,3,0,'n'], [traindna,cubedna,3,0,'n']] def distribution_linearhmm (fm_train=traindna,fm_cube=cubedna, order=3,gap=0,reverse='n'): # sg('new_distribution', 'LinearHMM') sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') # sg('train_distribution') # histo=sg('get_histogram') # num_examples=11 # num_param=sg('get_histogram_num_model_parameters') # for i in xrange(num_examples): # for j in xrange(num_param): # sg('get_log_derivative %d %d' % (j, i)) # sg('get_log_likelihood_sample') if __name__=='__main__': print 'LinearHMM' distribution_linearhmm(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.4,10],[traindat,testdat,1.5,11]] def kernel_chi2 (fm_train_real=traindat,fm_test_real=testdat, width=1.4,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'CHI2', 'REAL', size_cache, width) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Chi2' kernel_chi2(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.,10],[traindat,testdat,1.5,11]] def kernel_combined(fm_train_real=traindat,fm_test_real=testdat, weight=1.,size_cache=10): sg('clean_kernel') sg('clean_features', 'TRAIN') sg('clean_features', 'TEST') sg('set_kernel', 'COMBINED', size_cache) sg('add_kernel', weight, 'LINEAR', 'REAL', size_cache) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', size_cache, 1.) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) sg('add_kernel', weight, 'POLY', 'REAL', size_cache, 3, False) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Combined' kernel_combined(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,0,'n',False,'FULL'], [traindna,testdna,11,4,0,'n',False,'FULL']] def kernel_commulongstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10, order=3,gap=0,reverse='n', use_sign=False,normalization='FULL'): sg('add_preproc', 'SORTULONGSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'ULONG', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'ULONG', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'COMMSTRING', 'ULONG', size_cache, use_sign, normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'CommUlongString' kernel_commulongstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,0,'n',False,'FULL'], [traindna,testdna,11,4,0,'n',False,'FULL']] def kernel_commwordstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10, order=3,gap=0,reverse='n', use_sign=False,normalization='FULL'): sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'COMMSTRING', 'WORD', size_cache, use_sign, normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'CommWordString' kernel_commwordstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,23.,10],[traindat,testdat,24.,11]] def kernel_const (fm_train_real=traindat,fm_test_real=testdat,c=23.,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'CONST', 'REAL', size_cache, c) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Const' kernel_const(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,23.,10],[traindat,testdat,24.,11]] def kernel_diag (fm_train_real=traindat,fm_test_real=testdat,diag=23., size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'DIAG', 'REAL', size_cache, diag) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Diag' kernel_diag(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,3,10],[traindna,testdna,4,11]] def kernel_fixeddegreestring (fm_train_dna=traindna,fm_test_dna=testdna,degree=3, size_cache=10): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'FIXEDDEGREE', 'CHAR', size_cache, degree) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'FixedDegreeString' kernel_fixeddegreestring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.4,10],[traindat,testdat,1.9,11]] def kernel_gaussian (fm_train_real=traindat,fm_test_real=testdat, width=1.4,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Gaussian' kernel_gaussian(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.9,2,1,10],[traindat,testdat,1.5,2,1,11]] def kernel_gaussianshift (fm_train_real=traindat,fm_test_real=testdat, width=1.4,max_shift=2,shift_step=1,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'GAUSSIANSHIFT', 'REAL', size_cache, width, max_shift, shift_step) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'GaussianShift' kernel_gaussianshift(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.2,10],[traindat,testdat,1.5,11]] def kernel_linear (fm_train_real=traindat,fm_test_real=testdat, scale=1.2,size_cache=10): from sg import sg sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'LINEAR', 'REAL', size_cache, scale) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Linear' kernel_linear(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10], [traindna,testdna,11]] def kernel_linearstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'LINEAR', 'CHAR', size_cache) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'LinearString' kernel_linearstring(*parameter_list[0])
from tools.load import LoadMatrix from numpy import ushort from sg import sg lm=LoadMatrix() trainword=ushort(lm.load_numbers('../data/fm_test_word.dat')) testword=ushort(lm.load_numbers('../data/fm_test_word.dat')) parameter_list=[[trainword,testword,10,1.4], [trainword,testword,11,1.5]] def kernel_linearword (fm_train_word=trainword,fm_test_word=testword, size_cache=10, scale=1.4): sg('set_features', 'TRAIN', fm_train_word) sg('set_features', 'TEST', fm_test_word) sg('set_kernel', 'LINEAR', 'WORD', size_cache, scale) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'LinearWord' kernel_linearword(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10], [traindna,testdna,11]] def kernel_localalignmentstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'LOCALALIGNMENT', 'CHAR', size_cache) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'LocalAlignmentString' kernel_localalignmentstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,5,5,7], [traindna,testdna,trainlabel,11,6,6,8]] def kernel_localityimprovedstring (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, length=5,inner_degree=5,outer_degree=7): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'LIK', 'CHAR', size_cache, length, inner_degree, outer_degree) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'LocalityImprovedString' kernel_localityimprovedstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,1.2], [traindna,testdna,11,4,1.3]] def kernel_oligostring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,k=3,width=1.2): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'OLIGO', 'CHAR', size_cache, k, width) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'OligoString' kernel_oligostring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,3,0,'n'], [traindna,testdna,trainlabel,11,4,0,'n']] def kernel_pluginestimatehistogram (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, order=3,gap=0,reverse='n',): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) pseudo_pos=1e-1 pseudo_neg=1e-1 sg('new_plugin_estimator', pseudo_pos, pseudo_neg) sg('set_labels', 'TRAIN', label_train_dna) sg('train_estimator') sg('set_kernel', 'HISTOGRAM', 'WORD', size_cache) km=sg('get_kernel_matrix', 'TRAIN') # not supported yet # lab=sg('plugin_estimate_classify') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'PluginEstimate w/ HistogramWord' kernel_pluginestimatehistogram(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,4,False,True,10], [traindat,testdat,5,False,True,11]] def kernel_poly (fm_train_real=traindat,fm_test_real=testdat, degree=4,inhomogene=False,use_normalization=True,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'POLY', 'REAL', size_cache, degree, inhomogene, use_normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Poly' kernel_poly(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,False], [traindna,testdna,11,4,False]] def kernel_polymatchstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,degree=3,inhomogene=False): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'POLYMATCH', 'CHAR', size_cache, degree, inhomogene) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'PolyMatchString' kernel_polymatchstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,2,True,True,3,0,'n'], [traindna,testdna,trainlabel,11,3,True,True,4,0,'n']] def kernel_polymatchword (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, degree=2,inhomogene=True,normalize=True, order=3,gap=0,reverse='n'): sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'POLYMATCH', 'WORD', size_cache, degree, inhomogene, normalize) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'PolyMatchWord' kernel_polymatchword(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,3,0,'n',False,'FULL'], [traindna,testdna,trainlabel,11,4,0,'n',False,'FULL']] def kernel_salzbergstring (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, order=3,gap=0,reverse='n',use_sign=False, normalization='FULL'): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) pseudo_pos=1e-1 pseudo_neg=1e-1 sg('new_plugin_estimator', pseudo_pos, pseudo_neg) sg('set_labels', 'TRAIN', label_train_dna) sg('train_estimator') sg('set_kernel', 'SALZBERG', 'WORD', size_cache) #sg('set_prior_probs', 0.4, 0.6) sg('set_prior_probs_from_labels', label_train_dna) km=sg('get_kernel_matrix', 'TRAIN') # not supported yet # lab=sg('plugin_estimate_classify') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'PluginEstimate w/ SalzbergWord' kernel_salzbergstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,11,1.2,1.3,10],[traindat,testdat,12,1.3,1.4,11]] def kernel_sigmoid (fm_train_real=traindat,fm_test_real=testdat, num_feats=11,gamma=1.2,coef0=1.3,size_cache=10): sg('set_features', 'TRAIN', fm_train_real) sg('set_features', 'TEST', fm_test_real) sg('set_kernel', 'SIGMOID', 'REAL', size_cache, gamma, coef0) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'Sigmoid' kernel_sigmoid(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,5,5,7], [traindna,testdna,trainlabel,11,6,6,8]] def kernel_simplelocalityimprovedstring (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, length=5,inner_degree=5,outer_degree=7): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'SLIK', 'CHAR', size_cache, length, inner_degree, outer_degree) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'SimpleLocalityImprovedString' kernel_simplelocalityimprovedstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') trainlabel=lm.load_labels('../data/label_train_dna.dat') parameter_list=[[traindna,testdna,trainlabel,10,3,0,'n',False,'FULL'], [traindna,testdna,trainlabel,11,4,0,'n',False,'FULL']] def kernel_weightedcommwordstring (fm_train_dna=traindna,fm_test_dna=testdna, label_train_dna=trainlabel,size_cache=10, order=3,gap=0,reverse='n',use_sign=False, normalization='FULL'): sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'WEIGHTEDCOMMSTRING', 'WORD', size_cache, use_sign, normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'WeightedCommWordString' kernel_weightedcommwordstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,20], [traindna,testdna,11,21]] def kernel_weighteddegreepositonstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,degree=20): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'WEIGHTEDDEGREEPOS', 'CHAR', size_cache, degree) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'WeightedDegreePositionString' kernel_weighteddegreepositonstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,20], [traindna,testdna,11,21]] def kernel_weighteddegreestring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,degree=20): sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('set_kernel', 'WEIGHTEDDEGREE', 'CHAR', size_cache, degree) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'WeightedDegreeString' kernel_weighteddegreestring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') trainlabel=lm.load_labels('../data/label_train_multiclass.dat') parameter_list=[[traindat,testdat,trainlabel,10,1.2,1.2,1e-5,0.001,1.5,1.0], [traindat,testdat,trainlabel,11,1.3,1.3,1e-5,0.002,1.6,1.1]] def mkl_multiclass (fm_train_real=traindat,fm_test_real=testdat, label_train_multiclass=trainlabel, size_cache=10,width=1.2,C=1.2,epsilon=1e-5, mkl_eps=0.001,mkl_norm=1.5,weight=1.0): sg('clean_kernel') sg('clean_features', 'TRAIN') sg('clean_features', 'TEST') sg('set_kernel', 'COMBINED', size_cache) sg('add_kernel', weight, 'LINEAR', 'REAL', size_cache) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', size_cache, width) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) sg('add_kernel', weight, 'POLY', 'REAL', size_cache, 2) sg('add_features', 'TRAIN', fm_train_real) sg('add_features', 'TEST', fm_test_real) sg('set_labels', 'TRAIN', label_train_multiclass) sg('new_classifier', 'MKL_MULTICLASS') sg('svm_epsilon', epsilon) sg('c', C) sg('mkl_parameters', mkl_eps, 0.0, mkl_norm) sg('train_classifier') #sg('set_features', 'TEST', fm_test_real) result=sg('classify') return result if __name__=='__main__': print 'mkl_multiclass' mkl_multiclass(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg from numpy import * num=100 labelstrain=concatenate((-ones([1,num]), ones([1,num])),1)[0] featuretrain=concatenate((random.normal(size=(2,num))-1,random.normal(size=(2,num))+1),1) parameter_list=[[1.,labelstrain,featuretrain,1e-2], [1.,labelstrain,featuretrain,1e-2]] def mkl_regression (weight=1., labels=labelstrain,features=featuretrain, tube_epsilon=1e-2): sg('new_classifier', 'MKL_REGRESSION') sg('c', 1.) sg('svr_tube_epsilon', tube_epsilon) sg('set_labels', 'TRAIN', labels) sg('add_features', 'TRAIN', features) sg('add_features', 'TRAIN', features) sg('add_features', 'TRAIN', features) sg('set_kernel', 'COMBINED', 100) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 100.) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 10.) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 1.) sg('train_classifier') [bias, alphas]=sg('get_svm'); km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'MKL_REGRESSION' mkl_regression(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg from numpy import * num=100 labelstrain=concatenate((-ones([1,num]), ones([1,num])),1)[0] featuretrain=concatenate((random.normal(size=(2,num))-1,random.normal(size=(2,num))+1),1) parameter_list=[[1.,labelstrain,featuretrain], [1.,labelstrain,featuretrain]] def mkl_twoclass (weight=1., labels=labelstrain,features=featuretrain): sg('c', 10.) sg('new_classifier', 'MKL_CLASSIFICATION') sg('set_labels', 'TRAIN', labels) sg('add_features', 'TRAIN', features) sg('add_features', 'TRAIN', features) sg('add_features', 'TRAIN', features) sg('set_kernel', 'COMBINED', 100) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 100.) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 10.) sg('add_kernel', weight, 'GAUSSIAN', 'REAL', 100, 1.) sg('train_classifier') [bias, alphas]=sg('get_svm'); km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'MKL_TWOCLASS' mkl_twoclass(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.4,10],[traindat,testdat,1.5,11]] def preproc_logplusone (fm_train_real=traindat,fm_test_real=testdat, width=1.4,size_cache=10): sg('add_preproc', 'LOGPLUSONE') sg('set_kernel', 'CHI2', 'REAL', size_cache, width) sg('set_features', 'TRAIN', fm_train_real) sg('attach_preproc', 'TRAIN') km=sg('get_kernel_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) sg('attach_preproc', 'TEST') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'LogPlusOne' preproc_logplusone(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.4,10],[traindat,testdat,1.5,11]] def preproc_normone (fm_train_real=traindat,fm_test_real=testdat, width=1.4,size_cache=10): sg('add_preproc', 'NORMONE') sg('set_kernel', 'CHI2', 'REAL', size_cache, width) sg('set_features', 'TRAIN', fm_train_real) sg('attach_preproc', 'TRAIN') km=sg('get_kernel_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) sg('attach_preproc', 'TEST') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'NormOne' preproc_normone(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') parameter_list=[[traindat,testdat,1.4,10,True],[traindat,testdat,1.5,11,True]] def preproc_prunevarsubmean (fm_train_real=traindat,fm_test_real=testdat, width=1.4,size_cache=10,divide_by_std=True): sg('add_preproc', 'PRUNEVARSUBMEAN', divide_by_std) sg('set_kernel', 'CHI2', 'REAL', size_cache, width) sg('set_features', 'TRAIN', fm_train_real) sg('attach_preproc', 'TRAIN') km=sg('get_kernel_matrix', 'TRAIN') sg('set_features', 'TEST', fm_test_real) sg('attach_preproc', 'TEST') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'PruneVarSubMean' preproc_prunevarsubmean(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,0,'n',False,'FULL'], [traindna,testdna,11,4,0,'n',False,'FULL']] def preproc_sortulongstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,order=3,gap=0,reverse='n', use_sign=False,normalization='FULL'): sg('add_preproc', 'SORTULONGSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'ULONG', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'ULONG', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'COMMSTRING', 'ULONG', size_cache, use_sign, normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'CommUlongString' preproc_sortulongstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindna=lm.load_dna('../data/fm_train_dna.dat') testdna=lm.load_dna('../data/fm_test_dna.dat') parameter_list=[[traindna,testdna,10,3,0,'n',False,'FULL'], [traindna,testdna,11,4,0,'n',False,'FULL']] def preproc_sortwordstring (fm_train_dna=traindna,fm_test_dna=testdna, size_cache=10,order=3,gap=0,reverse='n', use_sign=False,normalization='FULL'): sg('add_preproc', 'SORTWORDSTRING') sg('set_features', 'TRAIN', fm_train_dna, 'DNA') sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TRAIN') sg('set_features', 'TEST', fm_test_dna, 'DNA') sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse) sg('attach_preproc', 'TEST') sg('set_kernel', 'COMMSTRING', 'WORD', size_cache, use_sign, normalization) km=sg('get_kernel_matrix', 'TRAIN') km=sg('get_kernel_matrix', 'TEST') return km if __name__=='__main__': print 'CommWordString' preproc_sortwordstring(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') trainlabel=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat,trainlabel,10,2.1,1.2,1e-6], [traindat,testdat,trainlabel,11,2.3,1.3,1e-6]] def regression_krr (fm_train=traindat,fm_test=testdat, label_train=trainlabel,size_cache=10,width=2.1, C=1.2,tau=1e-6): sg('set_features', 'TRAIN', fm_train) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train) sg('new_regression', 'KRR') sg('krr_tau', tau) sg('c', C) sg('train_regression') sg('set_features', 'TEST', fm_test) result=sg('classify') return result if __name__=='__main__': print 'KRR' regression_krr(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') trainlabel=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat,trainlabel,10,2.1,1.2,1e-5,1e-2], [traindat,testdat,trainlabel,11,2.3,1.3,1e-6,1e-3]] def regression_libsvr (fm_train=traindat,fm_test=testdat, label_train=trainlabel,size_cache=10,width=2.1, C=1.2,epsilon=1e-5,tube_epsilon=1e-2): sg('set_features', 'TRAIN', fm_train) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train) sg('new_regression', 'LIBSVR') sg('svr_tube_epsilon', tube_epsilon) sg('c', C) sg('train_regression') sg('set_features', 'TEST', fm_test) result=sg('classify') return result if __name__=='__main__': print 'LibSVR' regression_libsvr(*parameter_list[0])
from tools.load import LoadMatrix from sg import sg lm=LoadMatrix() traindat=lm.load_numbers('../data/fm_train_real.dat') testdat=lm.load_numbers('../data/fm_test_real.dat') trainlabel=lm.load_labels('../data/label_train_twoclass.dat') parameter_list=[[traindat,testdat,trainlabel,10,2.1,1.2,1e-5,1e-2], [traindat,testdat,trainlabel,11,2.3,1.3,1e-6,1e-3]] def regression_svrlight (fm_train=traindat,fm_test=testdat, label_train=trainlabel,size_cache=10,width=2.1, C=1.2,epsilon=1e-5,tube_epsilon=1e-2): sg('set_features', 'TRAIN', fm_train) sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width) sg('set_labels', 'TRAIN', label_train) try: sg('new_regression', 'SVRLIGHT') except RuntimeError: return sg('svr_tube_epsilon', tube_epsilon) sg('c', C) sg('train_regression') sg('set_features', 'TEST', fm_test) result=sg('classify') return result if __name__=='__main__': print 'SVRLight' regression_svrlight(*parameter_list[0])