import pandas as pd from data_prepared import read_data, prepare_data_div from testing import test_with_id from pegasos import pegasos_ f = open( "/Users/noch/Documents/workspace/data_challenge/result/Yte_pegasos_13.csv", "a+") nm_char = [6, 6, 5] lmda = [10**(-5), 0.0001, 10**(-5)] epoch = [400000, 300000, 300000] for i in range(3): isTr = 1 Xtr = read_data("Xtr" + str(i), isTr) Ytr = read_data("Ytr" + str(i), isTr) Ytr['Bound'][Ytr['Bound'] == 0] = -1 isTr = 0 Xte = read_data("Xte" + str(i), isTr) Xte['Id'] = pd.DataFrame({'Id': range(i * 1000, (i + 1) * 1000)}) print("preparing data:" + str(i)) Xtr_p = prepare_data_div(Xtr, nm_char[i]) Xtr_p['Bound'] = Ytr['Bound'] Xte_p = prepare_data_div(pd.DataFrame(Xte['DNA']), nm_char[i]) Xte_p['Id'] = Xte['Id'] Xtr_p = Xtr_p.sample(frac=1)
Y_predicted = [] for i, x_i in enumerate(X_te): # print("sum: " + str(np.sum((md.Alpha * md.Y) * kernel(md.X, x_i)))) result = np.sum((md.Alpha * md.Y) * kernel(md.X, x_i)) - md.b #print("result: " + str(result)) if result <= 0: Y_predicted.append(-1) elif result > 0: Y_predicted.append(1) return Y_predicted isTr = 1 for i in range(3): X = read_data("Xtr" + str(i), isTr) Y = read_data("Ytr" + str(i), isTr) max_info = "" max_predic = 0 Y['Bound'][Y['Bound'] == 0] = -1 f = open( "/Users/noch/Documents/workspace/data_challenge/result/console_svm_SMO_ker_linear.txt", "a+") #f= open("/home/jibril/Desktop/data_challenge/result/console_svm_SMO_ker_linear.txt","a+") print("\n testing on Xtr" + str(i) + ", Ytr" + str(i)) for k in range(2, 3):