def createSpectrumData(testSeqFile, resultsConf): filename_list = string.split(testSeqFile, "_") list_len = len(filename_list) testPosLen = int(filename_list[list_len - 3]) testNegLen = int(filename_list[list_len - 2]) k1 = int(resultsConf["results"]["k1"]) k2 = int(resultsConf["results"]["k2"]) testSpectrumData = demo_utils.get_spectrum_data(testSeqFile, k1, k2, testPosLen, testNegLen, True); return testSpectrumData;
Cs = [ 10**x for x in xrange( -3, 4 ) ] k1 = int(sys.argv[1]) k2 = int(sys.argv[2]) trainFile = sys.argv[3]; testFile = sys.argv[4]; trainPosLen = int(sys.argv[5]) trainNegLen = int(sys.argv[6]) testPosLen = int(sys.argv[7]) testNegLen = int(sys.argv[8]) trainFeatureData = sys.argv[9]; testFeatureData = sys.argv[10]; trainData = demo_utils.get_spectrum_data(trainFile, k1, k2, trainPosLen, trainNegLen, True); trainData.save(featureData); for C in Cs: print C; #print "Train for C : " + str(C); s = svm.SVM(C=C); s.train(trainData); testData = demo_utils.get_spectrum_data(testFile, k1, k2, testPosLen, testNegLen, True); results = s.test(testData); exit(1); for C in Cs: print "Train for C : " + C;
bestTP = None K1 = [7, 8, 9, 10, 11, 12, 13] K2 = [7, 8, 9, 10, 11, 12, 13] result_file = open("K-spectrum.txt", "w") for k1 in K1: for k2 in K2: for C in Cs: print "**** Train/Test with K1: " + str(k1) + ", k2: " + str(k2) + ", C: " + str(C) trainData = generate_model.get_spectrum_data(trainSeqFile, k1, k2, trainLen, trainLen, True) folds = [] s = svm.SVM(C=C) s.train(trainData) # testData = SparseDataSet(testFeatureFile); testData = demo_utils.get_spectrum_data(testSeqFile, k1, k2, testLen, testLen, True) results = s.test(testData) labels = results.getGivenClass() dvals = results.getDecisionFunction() folds.append((dvals, labels)) demo_utils.print_results(results) print "Results Log: " results.getLog() fpc, tpc, area = roc_mod.roc_VA(folds, None) print "Area: " + str(area) if area > bestAUC: bestAUC = area bestFP = fpc bestTP = tpc