def cross_validation_test(): glogger.setLoggingLevel(glogger.nothing) filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt" #try: # columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n") #except SyntaxError: columns = (2, -4, -3, -2, -1) print('\nIncluding columns: ' + str(columns)) P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True) #remove tail censored P, T = copy_without_tailcensored(P, T) #try: # comsize = input("Number of networks to cross-validate [10]: ") #except SyntaxError: comsize = 10 print('Number of networks to cross-validate: ' + str(comsize)) #try: # netsize = input('Number of hidden nodes [3]: ') #except SyntaxError as e: if len(sys.argv) < 2: netsize = 3 else: netsize = sys.argv[1] print("Number of hidden nodes: " + str(netsize)) #try: # pop_size = input('Population size [50]: ') #except SyntaxError as e: pop_size = 50 print("Population size: " + str(pop_size)) #try: # mutation_rate = input('Please input a mutation rate (0.25): ') #except SyntaxError as e: mutation_rate = 0.25 print("Mutation rate: " + str(mutation_rate)) #try: # epochs = input("Number of generations (200): ") #except SyntaxError as e: epochs = 200 print("Epochs: " + str(epochs)) com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear') #1 is the column in the target array which holds teh binary censoring information test_errors, vald_errors = train_committee(com, train_evolutionary, P, T, 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate) print('\nTest Errors, Validation Errors:') for terr, verr in zip(test_errors.values(), vald_errors.values()): print(str(terr) + ", " + str(verr)) print('\nTest average, Validation average:') print(str(sum(test_errors.values()) / len(test_errors.values())) + ', ' + str(sum(vald_errors.values()) / len(vald_errors.values())))
def committee_test(): try: netsize = input('Number of hidden nodes? [1]: ') except SyntaxError as e: netsize = 1 try: comsize = input('Committee size? [1]: ') except SyntaxError as e: comsize = 1 try: pop_size = input('Population size? [100]: ') except SyntaxError as e: pop_size = 100 try: mutation_rate = input('Please input a mutation rate (0.05): ') except SyntaxError as e: mutation_rate = 0.05 filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt" try: columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n") except SyntaxError: columns = (2, -4, -3, -2, -1) P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True) #remove tail censored try: cutoff = input('Cutoff for censored data? [9999 years]: ') except SyntaxError as e: cutoff = 9999 P, T = copy_without_censored(P, T, cutoff) #Divide into validation sets try: test_size = float(input('Size of test set (not used in training)? Input in fractions. Default is [0.0]: ')) except: test_size = 0.0 ((TP, TT), (VP, VT)) = get_validation_set(P, T, validation_size = test_size, binary_column = 1) print("Length of training set: " + str(len(TP))) print("Length of test set: " + str(len(VP))) try: epochs = input("\nNumber of generations (1): ") except SyntaxError as e: epochs = 1 com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear') #1 is the column in the target array which holds the binary censoring information test_errors, vald_errors, data_sets = train_committee(com, train_evolutionary, P, T, 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate) com.set_training_sets([set[0][0] for set in data_sets]) #first 0 gives training sets, second 0 gives inputs. print('\nTest C_indices, Validation C_indices:') for terr, verr in zip(test_errors.values(), vald_errors.values()): print(str(1 / terr) + ", " + str(1 / verr)) if plt: outputs = numpy.array([[com.risk_eval(inputs)] for inputs in TP]) #Need double brackets for dimensions to be right for numpy kaplanmeier(time_array = TT[:, 0], event_array = TT[:, 1], output_array = outputs[:, 0], threshold = 0.5) train_c_index = get_C_index(TT, outputs) print("\nC-index on the training set: " + str(train_c_index)) if len(VP) > 0: outputs = numpy.array([[com.risk_eval(inputs)] for inputs in VP]) #Need double brackets for dimensions to be right for numpy test_c_index = get_C_index(VT, outputs) kaplanmeier(time_array = VT[:, 0], event_array = VT[:, 1], output_array = outputs[:, 0], threshold = 0.5) print("C-index on the test set: " + str(test_c_index)) #raw_input("\nPress enter to show plots...") plt.show() try: answer = input("\nDo you wish to print committee risk output? ['n']: ") except (SyntaxError, NameError): answer = 'n' if answer != 'n' and answer != 'no': inputs = read_data_file(filename) P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True) outputs = [[com.risk_eval(patient)] for patient in P] while len(inputs) > len(outputs): outputs.insert(0, ["net_output"]) print("\n") for rawline in zip(inputs, outputs): line = '' for col in rawline[0]: line += str(col) line += ',' for col in rawline[1]: line += str(col) print(line)
def com_cross(): filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt" #try: # columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n") #except SyntaxError: #if len(sys.argv) < 3: columns = (2, -4, -3, -2, -1) #else: # columns = [int(col) for col in sys.argv[2:]] print('\nIncluding columns: ' + str(columns)) P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True) #remove tail censored #print('\nRemoving tail censored...') #P, T = copy_without_censored(P, T) #Divide into validation sets #test_size = 0.33 #print('Size of test set (not used in training): ' + str(test_size)) #((TP, TT), (VP, VT)) = get_validation_set(P, T, validation_size = test_size, binary_column = 1) print("\nData set:") print("Number of patients with events: " + str(T[:, 1].sum())) print("Number of censored patients: " + str((1 - T[:, 1]).sum())) #print("Length of training set: " + str(len(TP))) #print("Length of test set: " + str(len(VP))) #try: # comsize = input("Number of networks to cross-validate [10]: ") #except SyntaxError: if len(sys.argv) < 2: netsize = 1 else: netsize = int(sys.argv[1]) print("\nNumber of hidden nodes: " + str(netsize)) comsize = 4 print('Number of members in each committee: ' + str(comsize)) comnum = 5 print('Number of committees to cross-validate: ' + str(comnum)) times_to_cross = 3 print('Number of times to repeat cross-validation: ' + str(times_to_cross)) #try: # pop_size = input('Population size [50]: ') #except SyntaxError as e: pop_size = 100 print("Population size: " + str(pop_size)) #try: # mutation_rate = input('Please input a mutation rate (0.25): ') #except SyntaxError as e: mutation_rate = 0.05 print("Mutation rate: " + str(mutation_rate)) #try: # epochs = input("Number of generations (200): ") #except SyntaxError as e: epochs = 100 print("Epochs: " + str(epochs)) for _cross_time in xrange(times_to_cross): data_sets = get_cross_validation_sets(P, T, comnum , binary_column = 1) print('\nTest Errors, Validation Errors:') for _com_num, (TS, VS) in zip(xrange(comnum), data_sets): com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear') #1 is the column in the target array which holds the binary censoring information test_errors, vald_errors, internal_sets = train_committee(com, train_evolutionary, TS[0], TS[1], 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate) com.set_training_sets([set[0][0] for set in internal_sets]) #first 0 gives training sets, second 0 gives inputs. outputs = numpy.array([[com.risk_eval(inputs)] for inputs in TS[0]]) #Need double brackets for dimensions to be right for numpy train_c_index = get_C_index(TS[1], outputs) outputs = numpy.array([[com.risk_eval(inputs)] for inputs in VS[0]]) #Need double brackets for dimensions to be right for numpy val_c_index = get_C_index(VS[1], outputs) print(str(1.0 / train_c_index) + ", " + str(1.0 / val_c_index))
def cross_validation_test(): filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt" #try: # columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n") #except SyntaxError: if len(sys.argv) < 3: columns = (2, -4, -3, -2, -1) else: columns = [int(col) for col in sys.argv[2:]] print('\nIncluding columns: ' + str(columns)) P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True) #remove tail censored #print('\nRemoving tail censored...') #P, T = copy_without_censored(P, T) print("\nData set:") print("Number of patients with events: " + str(T[:, 1].sum())) print("Number of censored patients: " + str((1 - T[:, 1]).sum())) #try: # comsize = input("Number of networks to cross-validate [10]: ") #except SyntaxError: comsize = 5 print('\nNumber of networks to cross-validate: ' + str(comsize)) times_to_cross = 3 print('\nNumber of times to repeat cross-validation: ' + str(times_to_cross)) #try: # netsize = input('Number of hidden nodes [3]: ') #except SyntaxError as e: if len(sys.argv) < 2: netsize = 1 else: netsize = int(sys.argv[1]) print("Number of hidden nodes: " + str(netsize)) #try: # pop_size = input('Population size [50]: ') #except SyntaxError as e: pop_size = 100 print("Population size: " + str(pop_size)) #try: # mutation_rate = input('Please input a mutation rate (0.25): ') #except SyntaxError as e: mutation_rate = 0.05 print("Mutation rate: " + str(mutation_rate)) #try: # epochs = input("Number of generations (200): ") #except SyntaxError as e: epochs = 400 print("Epochs: " + str(epochs)) for _ in xrange(times_to_cross): com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear') #1 is the column in the target array which holds the binary censoring information test_errors, vald_errors, data_sets = train_committee(com, train_evolutionary, P, T, 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate) print('\nTest Errors, Validation Errors:') for terr, verr in zip(test_errors.values(), vald_errors.values()): print(str(terr) + ", " + str(verr))