def lda (): print 'LDA' from shogun.Features import RealFeatures, Labels from shogun.Classifier import LDA feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) gamma=3 num_threads=1 labels=Labels(label_train_twoclass) lda=LDA(gamma, feats_train, labels) lda.train() lda.get_bias() lda.get_w() #lda.set_features(feats_train) result = lda.classify() prediction_labels = result.get_labels() print prediction_labels>0 lda.set_features(feats_test) result = lda.classify() prediction_labels = result.get_labels() print prediction_labels>0
def classifier_lda_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_twoclass=label_traindat,gamma=3,num_threads=1): from shogun.Features import RealFeatures, Labels from shogun.Classifier import LDA feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) labels=Labels(label_train_twoclass) lda=LDA(gamma, feats_train, labels) lda.train() lda.get_bias() lda.get_w() lda.set_features(feats_test) lda.classify().get_labels() return lda,lda.classify().get_labels()
def classifier_lda_modular(fm_train_real=traindat, fm_test_real=testdat, label_train_twoclass=label_traindat, gamma=3, num_threads=1): from shogun.Features import RealFeatures, Labels from shogun.Classifier import LDA feats_train = RealFeatures(fm_train_real) feats_test = RealFeatures(fm_test_real) labels = Labels(label_train_twoclass) lda = LDA(gamma, feats_train, labels) lda.train() lda.get_bias() lda.get_w() lda.set_features(feats_test) lda.classify().get_labels() return lda, lda.classify().get_labels()
title('Data',size=10) # plot PRC for SVM subplot(223) PRC_evaluation=PRCEvaluation() PRC_evaluation.evaluate(svm.classify(),labels) PRC = PRC_evaluation.get_PRC() plot(PRC[:,0], PRC[:,1]) fill_between(PRC[:,0],PRC[:,1],0,alpha=0.1) text(0.55,mean(PRC[:,1])/3,'auPRC = %.5f' % PRC_evaluation.get_auPRC()) grid(True) xlabel('Precision') ylabel('Recall') title('LibSVM (Gaussian kernel, C=%.3f) PRC curve' % svm.get_C1(),size=10) # plot PRC for LDA subplot(224) PRC_evaluation.evaluate(lda.classify(),labels) PRC = PRC_evaluation.get_PRC() plot(PRC[:,0], PRC[:,1]) fill_between(PRC[:,0],PRC[:,1],0,alpha=0.1) text(0.55,mean(PRC[:,1])/3,'auPRC = %.5f' % PRC_evaluation.get_auPRC()) grid(True) xlabel('Precision') ylabel('Recall') title('LDA (gamma=%.3f) PRC curve' % lda.get_gamma(),size=10) connect('key_press_event', util.quit) show()