def results_from_folder(folder_name, file_keyword, acc_keyword, train_time_keyword, test_time_keyword, fold_count=10): file_list = list_files(folder_name) file_count = 0 acc_list = [] train_list = [] test_list = [] for fold_id in range(fold_count): fold_key = "train_" + str(fold_id) + "_" for file_name in file_list: if file_name.startswith('.'): continue if fold_key not in file_name: continue if file_keyword not in file_name: continue print file_name file_count = file_count + 1 acc_value, train_time, test_time = results_from_file( folder_name + file_name, acc_keyword, train_time_keyword, test_time_keyword) if len(acc_list) > fold_id: acc_list[fold_id] = acc_value train_list[fold_id] = train_time test_list[fold_id] = test_time else: acc_list.append(acc_value) train_list.append(train_time) test_list.append(test_time) print np.average(acc_list)
def results_from_folder(folder_name, file_keyword, num_classes, line_keyword, bias=0): file_list = list_files(folder_name) value_matrix = [] file_count = -1 file_count_vector = [] file_count_vector.append(file_count) accuracy_vector = [] train_time_vector = [] test_time_vector = [] for file_name in file_list: if file_name.startswith('.'): continue if file_keyword not in file_name: continue print(file_name) file_count = file_count + 1 file_count_vector.append(file_name.split('_')[2]) value_vector, accuracy, train_time, test_time = results_from_file(folder_name+file_name, line_keyword, bias) print(np.array(value_vector).shape) for add in range(len(value_vector), num_classes): value_vector.append(-1) value_matrix.append(value_vector) accuracy_vector.append(accuracy) train_time_vector.append(train_time) test_time_vector.append(test_time) value_matrix = np.array(value_matrix) #file_count_vector = np.array(file_count_vector).astype(int) acc_time_matrix = [] acc_time_matrix.append(train_time_vector) acc_time_matrix.append(test_time_vector) acc_time_matrix.append(accuracy_vector) return value_matrix, file_count, np.array(acc_time_matrix)
def results_from_folder(folder_name, out_obj_folder, file_keyword, num_classes, line_keyword): file_list = list_files(folder_name) file_count = 0 for file_name in file_list: if file_name.startswith('.'): continue if file_keyword not in file_name: continue print file_name file_count = file_count + 1 feature_matrix = results_from_file(folder_name + file_name, line_keyword) print feature_matrix.shape out_obj_file = file_name.split('.')[0] + "_top15.out" save_obj([feature_matrix], out_obj_folder + out_obj_file)
def iwb_processing_main(data_folder): attr_num = 22 output_folder = data_folder + "raw/" init_folder(output_folder) file_list = list_files(data_folder) train_file = "" test_file = "" for file_name in file_list: if "TRAIN" in file_name: train_file = file_name if "TEST" in file_name: test_file = file_name if train_file == "" or test_file == "": raise Exception("file missing") train_x_matrix, train_y_str_vector = read_iwb_data( data_folder + train_file, attr_num) test_x_matrix, test_y_str_vector = read_iwb_data(data_folder + test_file, attr_num) train_row, train_attr, attr_len = train_x_matrix.shape test_row, attr_num, attr_len = test_x_matrix.shape print(train_x_matrix.shape) print(test_x_matrix.shape) # train_zeros = [] # test_zeros = [] # for i in range(attr_num): # train_data = train_x_matrix[:, i, :] # print(np.amax(train_data)) # if np.amax(train_data) == 0: # train_zeros.append(i) # test_data = test_x_matrix[:, i, :] # if np.amax(test_data) == 0: # test_zeros.append(i) # print(train_zeros) # print(test_zeros) plot_2dmatrix(train_x_matrix[0, 0:2, :].T) train_x_matrix = train_x_matrix.reshape(train_row, (attr_num * attr_len)) test_x_matrix = test_x_matrix.reshape(test_row, (attr_num * attr_len)) label_list = np.unique(train_y_str_vector) train_y_vector = str_v_to_num_vector(train_y_str_vector, label_list) test_y_vector = str_v_to_num_vector(test_y_str_vector, label_list) train_out_file = "train_0.txt" test_out_file = "test_0.txt"
def run_dcpc_main(data_folder, class_column, num_classes, obj_folder, threshold, logger=None): if logger == None: logger = init_logging('') file_list = list_files(data_folder) overall_time = 0 file_count = 0 out_obj_dict = {} for train_file in file_list: if "train_" not in train_file: continue logger.info(train_file) out_obj_file = train_file.replace('.txt', '_dcpc.obj') file_count = file_count + 1 test_file = train_file.replace('train_', 'test_') x_matrix, y_vector = file_read_split(data_folder + train_file) min_class = min(y_vector) max_class = max(y_vector) + 1 #logger.info("x matrix tran after shape: " + str(x_matrix.shape)) #x_matrix = x_matrix.transpose((0, 2, 1)) logger.info("x matrix tran after shape: " + str(x_matrix.shape)) for label in range(min_class, max_class): label_index = np.where(y_vector == label)[0] label_x_matrix = x_matrix[label_index, :, :] logger.info("class: " + str(label)) print "class: " + str(label) logger.info("x matrix tran before shape: " + str(label_x_matrix.shape)) label_dcpc = computeDCPC(label_x_matrix, threshold) logger.info("class: " + str(label) + " dcpc shape: " + str(label_dcpc.shape)) out_obj_dict[label] = label_dcpc logger.info("dcpc out obj: " + str(obj_folder + out_obj_file)) save_obj([out_obj_dict], obj_folder + out_obj_file)
def run_dcpc_processing(dcpc_folder, num_classes, method=0, logger=None): logger.info('obj folder:' + dcpc_folder) dcpc_list = list_files(dcpc_folder) logger.info(dcpc_list) score_folder = dcpc_folder[:-1] + "_score/" score_folder = init_folder(score_folder) for dcpc_obj in dcpc_list: dcpc = load_obj(dcpc_folder + dcpc_obj)[0] if method == 0: out_label_array = [] out_label_dict = {} for label in range(0, num_classes): logger.info('class: ' + str(label)) label_dcpc = dcpc[label] logger.info("dcpc shape: " + str(label_dcpc.shape)) attr_score = clever_rank(label_dcpc, logger) logger.info(attr_score) sorted_dict = sorted(attr_score.items(), key=operator.itemgetter(1), reverse=True) sorted_attr = [] for item in sorted_dict: sorted_attr.append(item[0]) #label_array = [] #for label in range(0, num_classes): # class_array = sorted_attr # label_array.append(class_array) out_label_array.append(sorted_attr) out_label_dict[label] = attr_score logger.info(sorted_attr) logger.info(attr_score) save_obj([out_label_array, out_label_dict], score_folder + dcpc_obj) logger.info("score obj: " + score_folder + dcpc_obj) return score_folder
def pv_cnn_generation_main(parameter_file, file_keyword, function_keyword="pv_cnn_generation"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_pv_cnn_generation( parameter_file, function_keyword) print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file log_folder = init_folder(log_folder) out_obj_folder = init_folder(out_obj_folder) out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) obj_list = list_files(obj_folder) file_count = 0 class_column = 0 header = True cnn_setting = return_cnn_setting_from_file(cnn_setting_file) cnn_setting.out_obj_folder = out_obj_folder cnn_setting.out_model_folder = out_model_folder cnn_setting.feature_method = 'save' cnn_setting.eval_method = 'f1' init_folder(out_obj_folder) init_folder(out_model_folder) result_obj_folder = obj_folder + method + "_result_folder" result_obj_folder = init_folder(result_obj_folder) delimiter = ' ' loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( class_id) + '_' + method + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) #logger.info('cnn setting:\n ' + cnn_setting.to_string()) logger.info('method: ' + method) logger.info('============') test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) # Call the projected feature function here, just need to set feature_dict = None feature_dict = None top_k = -1 model_save_file = file_key + '_count' + str(file_count) + '_' + method if method == 'fcn': fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_ijcnn_fcn( train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, data_stru, cnn_setting, feature_dict, top_k, model_save_file, class_id, logger) else: fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_cnn( train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, data_stru, cnn_setting, feature_dict, top_k, model_save_file, class_id, logger) logger.info("Fold F1: " + str(fold_f1_value)) logger.info(method + ' fold training time (sec):' + str(fold_train_time)) logger.info(method + ' fold testing time (sec):' + str(fold_test_time)) logger.info(method + ' fold accuracy: ' + str(fold_accuracy)) logger.info("save obj to " + result_obj_folder + file_key + "_all_feature_" + method + "_result.ckpt") save_obj([ fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix ], result_obj_folder + file_key + "_all_feature_" + method + "_result.ckpt")
def cnn_classification_main(parameter_file, file_keyword, function_keyword="cnn_classification"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_all_feature_classification( parameter_file, function_keyword) print(data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file) log_folder = init_folder(log_folder) out_obj_folder = init_folder(out_obj_folder) out_model_folder = init_folder(out_model_folder) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True cnn_setting = return_cnn_setting_from_file(cnn_setting_file) cnn_setting.out_obj_folder = out_obj_folder cnn_setting.out_model_folder = out_model_folder init_folder(out_obj_folder) init_folder(out_model_folder) result_obj_folder = obj_folder + method + "_result_folder" result_obj_folder = init_folder(result_obj_folder) delimiter = ' ' loop_count = -1 saver_file_profix = "" attention_type = 0 attention_type = -1 cnn_setting.attention_type = attention_type trans_bool = False # True: means ins * attr_len * 1 * attr_num # False: means ins * attr_len * attr_num * 1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') saver_file_profix = file_key + "_atten" + str(attention_type) valid_file = data_folder + train_file.replace('train', 'valid') if os.path.isfile(valid_file) is False: valid_file = '' test_file = data_folder + train_file.replace('train', 'test') if os.path.isfile(test_file) is False: test_file = '' data_group, attr_num = train_test_file_reading( data_folder + train_file, test_file, valid_file, class_column, delimiter, header) data_group_processing(data_group, attr_num, trans_bool) data_stru = data_group.gene_data_stru() data_group.data_check(data_stru.num_classes, data_stru.min_class) if cnn_setting.eval_method == "accuracy": cnn_eval_key = "acc" elif num_classes > 2: cnn_eval_key = "acc_batch" else: cnn_eval_key = "f1" log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( data_stru.min_class ) + "_" + str(data_stru.num_classes) + "_act" + str( cnn_setting.activation_fun ) + "_" + cnn_eval_key + "_attention" + str(attention_type) + '.log' print("log file: " + log_file) logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('cnn setting:\n ' + cnn_setting.to_string()) logger.info('method: ' + method) logger.info('============') if file_count == 0: logger.info('train matrix shape: ' + str(data_group.train_x_matrix.shape)) logger.info('train label shape: ' + str(data_group.train_y_vector.shape)) logger.info(data_group.train_x_matrix[0, 0:3, 0:2, 0]) pred_y_prob, train_run_time, test_run_time, cnn_model = run_cnn( cnn_setting, data_group, saver_file_profix, logger) pred_y_vector = np.argmax(pred_y_prob, axis=1) avg_acc, ret_str = averaged_class_based_accuracy( pred_y_vector, data_group.test_y_vector) acc_value = accuracy_score(data_group.test_y_vector, pred_y_vector, True) logger.info("Averaged acc: " + str(acc_value)) logger.info(ret_str) logger.info("Fold eval value: " + str(acc_value)) logger.info(method + ' fold training time (sec):' + str(train_run_time)) logger.info(method + ' fold testing time (sec):' + str(test_run_time)) logger.info("save obj to " + cnn_model.saver_file)
# Our libraries path.append(program_dir) path.append(submission_dir) # path.append (root_dir + "baselines") import data_io # general purpose input/output functions from data_io import vprint # print only in verbose mode from data_manager import DataManager # load/save data and get info about them from internal_rep.complexity import complexity # complexity measure # from best.complexity import complexity should_pass_submission_dir = 'program_dir' in inspect.getfullargspec( complexity).args if debug_mode >= 4: print('File structure') data_io.list_files('..') if debug_mode >= 4: # Show library version and directory structure data_io.show_dir(".") # Move old results and create a new output directory (useful if you run locally) if save_previous_results: data_io.mvdir(output_dir, output_dir + '_' + the_date) data_io.mkdir(output_dir) #### INVENTORY DATA (and sort dataset names alphabetically) datanames = os.listdir(input_dir) # change input dir to compensate for the single file unzipping if 'input_data' in datanames: input_dir = os.path.join(input_dir, 'input_data') datanames = os.listdir(input_dir)
def run_channel_mask_main(data_folder, log_folder, obj_folder, shap_k=10, shap_min=2, shap_max=3, file_key="train_", fun_key="_mask_gene"): file_list = list_files(data_folder) file_count = 0 for train_file in file_list: if file_key not in train_file: continue this_keyword = train_file.replace('.txt', '') log_file = this_keyword + fun_key + "_shapNum" + str( shap_k) + "_shapMin" + str(shap_min) + "_shapMax" + str( shap_max) + "_all_class.log" out_obj_file = this_keyword + fun_key + "_shapNum" + str( shap_k) + "_shapMin" + str(shap_min) + "_shapMax" + str(shap_max) logger = setup_logger(log_folder + log_file) print "log file: " + log_folder + log_file print "obj file: " + obj_folder + out_obj_file logger.info(log_folder + log_file) out_obj_dict = {} file_count = file_count + 1 test_file = train_file.replace('train_', 'test_') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file) train_row, train_col = train_x_matrix.shape test_row, test_col = test_x_matrix.shape attr_len = train_col / attr_num train_x_matrix = train_x_matrix.reshape(train_row, attr_num, attr_len) test_x_matrix = test_x_matrix.reshape(test_row, attr_num, attr_len) logger.info("train x matrix: " + str(train_x_matrix.shape)) logger.info("test x matrix: " + str(test_x_matrix.shape)) train_keep_len = matrix_keep_len_gene(train_x_matrix) test_keep_len = matrix_keep_len_gene(test_x_matrix) min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 num_classes = max_class - min_class logger.info("x matrix tran after shape: " + str(train_x_matrix.shape)) for label in range(min_class, max_class): label = max_class - label - 1 label_train_y_vector = np.where(train_y_vector == label, 1, 0) label_test_y_vector = np.where(test_y_vector == label, 1, 0) label_train_y_matrix = y_vector_to_matrix(label_train_y_vector, 2) label_test_y_matrix = y_vector_to_matrix(label_test_y_vector, 2) logger.info("class: " + str(label)) test_eval_value, mask_value = run_channel_mask( train_x_matrix, label_train_y_matrix, train_keep_len, test_x_matrix, label_test_y_matrix, test_keep_len, shap_k, shap_min, shap_max, logger) logger.info("final for class " + str(label)) logger.info("final acc: " + str(test_eval_value)) logger.info("final mask: " + str(mask_value.shape)) logger.info("out obj saved to " + obj_folder + out_obj_file + "_class" + str(label) + ".obj") save_obj([mask_value], obj_folder + out_obj_file + "_class" + str(label) + ".obj")
def multi_proj_feature_classification( parameter_file, file_keyword, function_keyword="multi_proj_feature_classification"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification( parameter_file, function_keyword) log_folder = init_folder(log_folder) if method == 'cnn': return projected_cnn_classification_main(parameter_file, file_keyword) else: # Need to check the rest return False print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) print obj_folder file_list = list_files(data_folder) obj_list = list_files(obj_folder) class_column = 0 header = True save_obj_folder = obj_folder[:-1] + "_" + method + "_out" save_obj_folder = init_folder(save_obj_folder) delimiter = ' ' loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( class_id) + '_top' + str(top_k) + '_' + method + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('method: ' + method) logger.info('============') found_obj_file = '' for obj_file in obj_list: if file_key in obj_file: found_obj_file = obj_file break if found_obj_file == '': raise Exception('No obj file found') print found_obj_file found_obj_file = obj_folder + found_obj_file feature_array = load_obj(found_obj_file)[0] feature_array = np.array(feature_array) logger.info("feature array shape: " + str(feature_array.shape)) test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) if loop_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) data_stru.attr_num = top_k fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_classification( train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, feature_array, top_k, method, class_id, logger) logger.info("Fold F1: " + str(fold_f1_value)) logger.info(method + ' fold training time (sec):' + str(fold_train_time)) logger.info(method + ' fold testing time (sec):' + str(fold_test_time)) logger.info(method + ' fold accuracy: ' + str(fold_accuracy)) logger.info("save obj to " + save_obj_folder + file_key + "_" + method + "_project_" + method + "_result.ckpt") save_obj([ fold_accuracy, fold_f1_value, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix ], save_obj_folder + file_key + "_" + method + "_project_" + method + "_result.ckpt")
def cnn_load_main(parameter_file, file_keyword, function_keyword="cnn_classification"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_all_feature_classification(parameter_file, function_keyword) print(data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file) log_folder = init_folder(log_folder) out_obj_folder = init_folder(out_obj_folder) out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True cnn_setting = return_cnn_setting_from_file(cnn_setting_file) cnn_setting.out_obj_folder = out_obj_folder cnn_setting.out_model_folder = out_model_folder cnn_setting.full_feature_num = 400 init_folder(out_obj_folder) init_folder(out_model_folder) print (out_model_folder) model_file_list = list_files(out_model_folder) result_obj_folder = obj_folder + method +"_result_folder" result_obj_folder = init_folder(result_obj_folder) logger = setup_logger('') delimiter = ' ' loop_count = -1 saver_file_profix = "" for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') saver_file_profix = file_key test_file = train_file.replace('train', 'test') #train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading(data_folder + train_file, data_folder + test_file, '', class_column, delimiter, header) data_group, attr_num = train_test_file_reading(data_folder + train_file, data_folder + test_file, '', class_column, delimiter, header) train_x_matrix = data_group.train_x_matrix train_y_vector = data_group.train_y_vector test_x_matrix = data_group.test_x_matrix test_y_vector = data_group.test_y_vector train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes) test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes) found_model_file = "" for model_file in model_file_list: if model_file.startswith(file_key): model_file = model_file.split('.')[0] found_model_file = out_model_folder + model_file + ".ckpt" break if found_model_file == "": raise Exception("No model object file found!!!") print(found_model_file) cnn_session, logits_out, train_x_placeholder, keep_prob_placeholder, keeped_feature_list = load_model(found_model_file, data_stru, cnn_setting, logger) last_conv_tensor = keeped_feature_list[0] train_last_conv = cnn_session.run(last_conv_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) test_last_conv = cnn_session.run(last_conv_tensor, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0}) drop_num = 10 print(np.squeeze(test_last_conv[1, :, :, :])) test_last_conv = top_attr_x_matrix(test_last_conv, drop_num) print(np.squeeze(test_last_conv[1, :, :, :])) train_last_conv = top_attr_x_matrix(train_last_conv, drop_num) output_y_placeholder = tf.placeholder(tf.float32, [None, num_classes]) actual = tf.argmax(output_y_placeholder, axis=1) prediction = tf.argmax(logits_out, axis=1) correct_prediction = tf.equal(actual, prediction) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) ori_pred_y_vector = cnn_session.run(prediction, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0}) test_accuracy = cnn_session.run(accuracy, feed_dict={train_x_placeholder: test_x_matrix, keep_prob_placeholder: 1.0, output_y_placeholder: test_y_matrix}) cnn_session.close() kernel_eval_matrix, ref_kernel_eval_matrix = last_conv_analysis(train_last_conv, train_y_vector) print(kernel_eval_matrix.shape) print(kernel_eval_matrix) train_ins_len = len(train_y_vector) test_ins_len = len(test_y_vector) batch_size = 100 layer_list = np.array([400]) max_epoch = 10 stop_threshold = 0.99 activation_fun = 3 std_value = 0.02 eval_method = "acc" saver_file = './test_1.save' nn_setting = nn_parameters(layer_list, batch_size, max_epoch, stop_threshold, activation_fun, std_value, eval_method, saver_file) all_pred_prob = [] for c in range(num_classes): train_y_vector_class = np.zeros((train_ins_len)) index_class = np.where(train_y_vector==c)[0] train_y_vector_class[index_class] = 1 train_y_m_class = y_vector_to_matrix(train_y_vector_class, 2) test_y_vector_class = np.zeros((test_ins_len)) index_class = np.where(test_y_vector==c)[0] test_y_vector_class[index_class] = 1 test_y_m_class = y_vector_to_matrix(test_y_vector_class, 2) keep_num = 5 kernel_index = kernel_eval_matrix[c, 0:keep_num] ref_kernel_index = ref_kernel_eval_matrix[c, 0:keep_num] print("kernel index " + str(kernel_index)) print("ref kernel index " + str(ref_kernel_index)) kernel_index = np.concatenate((kernel_index, ref_kernel_index), axis=0) print("union index " + str(kernel_index)) kernel_index = np.unique(kernel_index) print("unique index " + str(kernel_index)) kernel_index = ref_kernel_eval_matrix[c, 0:keep_num] train_x_class = train_last_conv[:, :, :, kernel_index] test_x_class = test_last_conv[:, :, :, kernel_index] print(train_x_class.shape) reshape_col = 45 * len(kernel_index) train_x_class = train_x_class.reshape((train_ins_len, reshape_col)) test_x_class = test_x_class.reshape((test_ins_len, reshape_col)) c_eval_value, c_train_time, c_test_time, c_predict_proba = run_nn(train_x_class, train_y_m_class, test_x_class, test_y_m_class, nn_setting) all_pred_prob.append(c_predict_proba[:, 1]-c_predict_proba[:, 0]) all_pred_prob = np.array(all_pred_prob) print(all_pred_prob.shape) pred_vector = np.argmax(all_pred_prob, axis=0) print(pred_vector) print(all_pred_prob[:, 0]) print(all_pred_prob[:, 1]) print(all_pred_prob[:, 2]) final_accuracy = accuracy_score(pred_vector, test_y_vector) avg_acc, ret_str = averaged_class_based_accuracy(ori_pred_y_vector, test_y_vector) print("original avg acc" + str(avg_acc)) print("original accuracy: " + str(test_accuracy)) print(ret_str) avg_acc, ret_str = averaged_class_based_accuracy(pred_vector, test_y_vector) print("avg acc" + str(avg_acc)) print("new accuracy: " + str(final_accuracy)) print(ret_str) load_result_analysis(all_pred_prob, test_y_vector) sdfds output_y_placeholder = tf.placeholder(tf.float32, [None, num_classes]) actual = tf.argmax(output_y_placeholder, axis=1) prediction = tf.argmax(logits_out, axis=1) correct_prediction = tf.equal(actual, prediction) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) test_eval_value = accuracy.eval(feed_dict={train_x_placeholder: test_x_matrix, output_y_placeholder: test_y_matrix, keep_prob_placeholder: 1.0}) print("fisrt") print(test_eval_value) conv_count = 1 drop_ratio = 0.1 #conv_variable_up_main(cnn_session, conv_count, drop_ratio) weight_name = "conv_w_" + str(0) + ":0" bias_name = "conv_b_" + str(0) + ":0" ori_weight_variable = tf.get_default_graph().get_tensor_by_name(weight_name) ori_bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name) weight_variable = tf.get_default_graph().get_tensor_by_name(weight_name) bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name) ori_weight_variable = cnn_session.run(weight_variable) ori_bias_variable = cnn_session.run(bias_variable) train_drop_acc = [] test_drop_acc = [] for drop_i in range(50): drop_weight_variable = np.copy(ori_weight_variable) drop_bias_variable = np.copy(ori_bias_variable) drop_index = [] drop_index.append(drop_i) up_fir_weight, up_fir_bias = conv_variable_up(drop_weight_variable, drop_bias_variable, drop_index) weight_assign = tf.assign(weight_variable, up_fir_weight) bias_assign = tf.assign(bias_variable, up_fir_bias) cnn_session.run(weight_assign) cnn_session.run(bias_assign) up_bias_variable = tf.get_default_graph().get_tensor_by_name(bias_name) up_bias_variable_val = cnn_session.run(bias_variable) train_eval_value = accuracy.eval(feed_dict={train_x_placeholder: train_x_matrix, output_y_placeholder: train_y_matrix, keep_prob_placeholder: 1.0}) train_drop_acc.append(train_eval_value) test_eval_value = accuracy.eval(feed_dict={train_x_placeholder: test_x_matrix, output_y_placeholder: test_y_matrix, keep_prob_placeholder: 1.0}) test_drop_acc.append(test_eval_value) print ("Drop " + str(drop_i)) print(train_eval_value) print(test_eval_value) print(train_drop_acc) print(train_drop_acc.argsort()) print(test_drop_acc) print(test_drop_acc.argsort()) sdfs print("HERE") fir_weight_variable_val = np.squeeze(fir_weight_variable_val) kernel_dist_val = cnn_session.run(kernel_dist) keep_index_val = cnn_session.run(keep_index) print(fir_weight_variable_val.shape) print(np.amax(fir_weight_variable_val, axis=1)) print(np.amin(fir_weight_variable_val, axis=1)) print(np.mean(fir_weight_variable_val, axis=1)) mean_row = np.mean(fir_weight_variable_val, axis=-1) print(mean_row.shape) dist_list = [] for r in range(40): row = fir_weight_variable_val[:, r] dist_list.append(np.linalg.norm(row-mean_row)) print (dist_list) print(kernel_dist_val) print(keep_index_val) print(sorted(dist_list)) print("!!!") #conv_variable_up(fir_weight_variable_val, fir_bias_variable_val) sdfsd train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading(data_folder + train_file, data_folder + test_file, class_column, delimiter, header) train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) train_x_matrix = test_x_matrix[0:1, :, :, :] #plot_2dmatrix(np.squeeze(train_x_matrix)[:, 0:5]) fir_out_tensor = tf.nn.conv2d(train_x_placeholder, fir_weight_variable, strides=[1, 1, 1, 1], padding='VALID') + fir_bias_variable fir_out_tensor = tf.nn.relu(fir_out_tensor) print(fir_out_tensor.get_shape()) fir_analysis_tensor = tf.reduce_max(fir_out_tensor, [1]) print(fir_analysis_tensor.get_shape()) fir_analysis_tensor = tf.reduce_max(fir_analysis_tensor, [1]) fir_analysis_tensor = tf.reduce_mean(fir_analysis_tensor, [0]) top_k_indices = tf.nn.top_k(fir_analysis_tensor, 10).indices top_k_values = tf.nn.top_k(fir_analysis_tensor, 10).values top_fir_out_tensor = tf.gather(fir_out_tensor, top_k_indices, axis=3) sec_weight_variable = tf.get_default_graph().get_tensor_by_name("conv_w_1:0") sec_bias_variable = tf.get_default_graph().get_tensor_by_name("conv_b_1:0") sec_out_tensor = tf.nn.conv2d(fir_out_tensor, sec_weight_variable, strides=[1, 1, 1, 1], padding='VALID') + sec_bias_variable sec_out_tensor = tf.nn.relu(sec_out_tensor) sec_weight_var_val = cnn_session.run(sec_weight_variable) #print(np.squeeze(sec_weight_var_val)) #sdfds #plot_2dmatrix(fir_weight_var_val[:, 4]) #sdf #print(fir_weight_var_val.T) fir_out_tensor_val = cnn_session.run(fir_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) print(fir_out_tensor_val.shape) top_fir_out_tensor = cnn_session.run(top_fir_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) print(top_fir_out_tensor.shape) fir_analysis_tensor_val = cnn_session.run(fir_analysis_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) print(fir_analysis_tensor.shape) top_k_indices_val = cnn_session.run(top_k_indices, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) top_k_values_val = cnn_session.run(top_k_values, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) fir_weight_variable_val = cnn_session.run(fir_weight_variable) fir_weight_variable_val = np.squeeze(fir_weight_variable_val) print(fir_weight_variable_val.shape) print(fir_analysis_tensor_val) fir_sort_in = np.argsort(fir_analysis_tensor_val) print(fir_sort_in) print(top_k_indices_val) print(top_k_values_val) plot_2dmatrix(fir_weight_variable_val[:, fir_sort_in[-10:]]) sdfd for n in range(len(fir_out_tensor_val)): for k in range(50): ret_str = "k" + str(k) + ": " kernel_max = -1 max_attr = -1 max_attr_list = [] for a in range(attr_num): attr_max = max(fir_out_tensor_val[n, :, a, k]) max_attr_list.append(attr_max) if attr_max > kernel_max: kernel_max = attr_max max_attr = a if attr_max == 0: ret_str = ret_str + str(a) + " " print(ret_str) print("max attr " + str(max_attr)) print(sorted(range(len(max_attr_list)), key=lambda k: max_attr_list[k])) print("======") print("label " + str(train_y_vector[0])) fir_out_tensor_val = cnn_session.run(sec_out_tensor, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) print(fir_out_tensor_val.shape) sdf for n in range(len(fir_out_tensor_val)): for k in range(40): ret_str = "k" + str(k) + ": " kernel_max = -1 max_attr = -1 max_attr_list = [] for a in range(attr_num): attr_max = max(fir_out_tensor_val[n, :, a, k]) max_attr_list.append(attr_max) if attr_max > kernel_max: kernel_max = attr_max max_attr = a if attr_max == 0: ret_str = ret_str + str(a) + " " print(ret_str) print("max attr " + str(max_attr)) print(sorted(range(len(max_attr_list)), key=lambda k: max_attr_list[k])) print("======") sdf fir_out_mean_val = cnn_session.run(fir_out_mean, feed_dict={train_x_placeholder: train_x_matrix, keep_prob_placeholder: 1.0}) #fir_out_mean_val = np.squeeze(fir_out_mean_val) print(fir_out_mean_val.shape) plot_2dmatrix(np.squeeze(fir_out_mean_val[:, :, 0:5])) sdfd plot_2dmatrix(fir_weight_var_val) min_class = min(train_y_vector) max_class = max(train_y_vector) num_classes = max_class - min_class + 1 if cnn_setting.eval_method == "accuracy": cnn_eval_key = "acc" elif num_classes > 2: cnn_eval_key = "acc_batch" else: cnn_eval_key = "f1" log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(min_class)+"_" + str(max_class) + "_act" + str(cnn_setting.activation_fun) + "_" + cnn_eval_key + '.log' print("log file: " + log_file) logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('cnn setting:\n ' + cnn_setting.to_string()) logger.info('method: ' + method) logger.info('============') train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) logger.info(train_x_matrix[0, 0:3, 0:2, 0]) logger.info(test_x_matrix[0, 0:3, 0:2, 0]) train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes) test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes) cnn_eval_value, train_run_time, test_run_time, cnn_predict_proba, saver_file, feature_list_obj_file = run_cnn(train_x_matrix, train_y_matrix, test_x_matrix, test_y_matrix, data_stru, cnn_setting, saver_file_profix, logger) logger.info("Fold eval value: " + str(cnn_eval_value)) logger.info(method + ' fold training time (sec):' + str(train_run_time)) logger.info(method + ' fold testing time (sec):' + str(test_run_time)) logger.info("save obj to " + saver_file)
def backward_multitime_main(parameter_file="../../parameters/", file_keyword="train_", n_selected_features=15): function_keyword = "backward_wrapper" data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_all_feature_classification( parameter_file, function_keyword) print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file log_folder = init_folder(log_folder) out_obj_folder = init_folder(out_obj_folder) out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True delimiter = ' ' loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( class_id) + '_' + method + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('method: ' + method) logger.info('============') test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) n_samples, n_col = train_x_matrix.shape train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len) n_samples, n_col = test_x_matrix.shape test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) if class_id == -1: min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 else: min_class = class_id max_class = class_id + 1 for c in range(min_class, max_class): logger.info("Class: " + str(c)) temp_train_y_vector = np.where(train_y_vector == c, 1, 0) temp_test_y_vector = np.where(test_y_vector == c, 1, 0) top_features = backward_multitime( train_x_matrix, temp_train_y_vector, test_x_matrix, temp_test_y_vector, n_selected_features, data_keyword, method, cnn_setting_file, logger) logger.info("Top Features For Class " + str(c) + ": " + str(top_features)) logger.info("End Of Class: " + str(c))
def mask_evaluation_main(log_folder, obj_folder, out_obj_folder, obj_keyword, shap_k=-1, shap_min=-1, shap_max=-1, func_key="arxiv_mask_gene"): log_folder = log_folder + func_key log_folder = init_folder(log_folder) log_file = obj_keyword + "_allclass_" + func_key + ".log" #logger = setup_logger('') logger = setup_logger(log_folder + log_file) logger.info("log folder: " + log_folder) logger.info("obj folder: " + obj_folder) obj_file_list = list_files(obj_folder) if shap_k != -1: obj_sec_key = "shapNum" + str(shap_k) + "_shapMin" + str( shap_min) + "_shapMax" + str(shap_max) else: obj_sec_key = ".obj" min_class = 100 max_class = -1 output_array = [] for obj_file in obj_file_list: if obj_keyword not in obj_file: continue if "_class" not in obj_file: continue if obj_sec_key not in obj_file: continue class_key = obj_file.split('_')[-1] class_key = class_key.replace('class', '').replace('.obj', '') logger.info("obj file:" + obj_file) logger.info("class key: " + class_key) class_key = int(class_key) if min_class > class_key: min_class = class_key if max_class < class_key: max_class = class_key shap_mask = load_obj(obj_folder + obj_file)[0] if len(shap_mask) == 0: continue shap_mask = numpy.array(shap_mask) shap_mask = numpy.squeeze(shap_mask) logger.info("shap_mask shape: " + str(shap_mask.shape)) #shap_num, attr_num = shap_mask.shape shap_mask = numpy.absolute(shap_mask) shap_mask = numpy.sum(shap_mask, axis=0) logger.info(shap_mask) sort_index = numpy.argsort(shap_mask) imp_value = 0 norm_imp = numpy.zeros(len(shap_mask)) for index in sort_index: norm_imp[index] = imp_value imp_value = imp_value + 1 shap_mask_index = numpy.argsort(norm_imp)[::-1] logger.info(shap_mask_index) logger.info("====") output_array.append(shap_mask_index) logger.info("shap_mask final shape: " + str(shap_mask.shape)) output_array = numpy.array(output_array) obj_file = obj_keyword + "_min" + str(min_class) + "_max" + str( max_class) + "out.obj" logger.info("final output obj shape: " + str(output_array.shape)) logger.info(output_array) save_obj([output_array], out_obj_folder + obj_file)
def forward_multitime_main(parameter_file="../../parameters/", file_keyword="train_"): function_keyword = "forward_wrapper" #data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword) data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification( parameter_file, function_keyword) print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file if data_keyword == "dsa" or data_keyword == "toy": n_selected_features = 15 num_classes = 19 elif data_keyword == "rar": n_selected_features = 30 num_classes = 33 elif data_keyword == "arc" or data_keyword == "fixed_arc": n_selected_features = 30 num_classes = 18 elif data_keyword == "asl": n_selected_features = 6 num_classes = 95 else: raise Exception("Please fullfill the data basic information first!") log_folder = init_folder(log_folder) #out_obj_folder = init_folder(out_obj_folder) #out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True delimiter = ' ' loop_count = -1 ########## ###already remove later #already_obj_folder = "../../object/" + data_keyword + "/forward_wrapper/" #already_obj_list = list_files(already_obj_folder) ###end of already remove later for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') #already_obj_file = "" already = False #for already_obj_file in already_obj_list: # if file_key in already_obj_file and method in already_obj_file: # already = True # break ########## ###already part #if already is True: # already_class_feature = load_obj(already_obj_folder + already_obj_file)[0] #else: # log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_' + method + '.log' # already_class_feature = None ###end of already part log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( class_id) + '_' + method + "_top" + str( n_selected_features) + '_already' + str(already) + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('method: ' + method) logger.info('============') test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) n_samples, n_col = train_x_matrix.shape train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len) n_samples, n_col = test_x_matrix.shape test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 for c in range(min_class, max_class): logger.info("Class: " + str(c)) already_feature = [] #if already_class_feature is not None: # class_already = already_class_feature[c, :] # for already_f in class_already: # already_feature.append(already_f) # logger.info("already features: " +file_key + " with class " + str(c) + ": " + str(already_feature)) temp_train_y_vector = np.where(train_y_vector == c, 1, 0) temp_test_y_vector = np.where(test_y_vector == c, 1, 0) #print already_feature top_features = forward_multitime( train_x_matrix, temp_train_y_vector, test_x_matrix, temp_test_y_vector, n_selected_features, data_keyword, file_key, method, cnn_setting_file, logger, already_feature) logger.info("Top Features For Class " + str(c) + ": " + str(top_features)) logger.info("End Of Class: " + str(c))
def best_forward_multitime_main(parameter_file="../../parameters/", file_keyword="train_", function_keyword="best_forward_multitime"): #data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_all_feature_classification(parameter_file, function_keyword) data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword) print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, cnn_setting_file function_keyword = function_keyword + "_" + method if data_keyword == "dsa" or data_keyword == "toy": n_selected_features = 15 num_classes = 19 elif data_keyword == "rar": n_selected_features = 30 num_classes = 33 elif data_keyword == "arc" or data_keyword == "fixed_arc": n_selected_features = 30 num_classes = 18 elif data_keyword == "asl": n_selected_features = 6 num_classes = 95 else: raise Exception("Please fullfill the data basic information first!") keep_k = 5 log_folder = init_folder(log_folder) #out_obj_folder = init_folder(out_obj_folder) #out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True delimiter = ' ' loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_' + method + "_top" + str(n_selected_features) +'.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('method: ' + method) logger.info('============') test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector = train_test_file_reading( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) n_samples, n_col = train_x_matrix.shape train_x_matrix = train_x_matrix.reshape(n_samples, attr_num, attr_len) n_samples, n_col = test_x_matrix.shape test_x_matrix = test_x_matrix.reshape(n_samples, attr_num, attr_len) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 for c in range(min_class, max_class): logger.info("Class: " + str(c)) temp_train_y_vector = np.where(train_y_vector == c, 1, 0) temp_test_y_vector = np.where(test_y_vector == c, 1, 0) top_features = fixed_width_forward_multitime(train_x_matrix, temp_train_y_vector, test_x_matrix, temp_test_y_vector, n_selected_features, keep_k, data_keyword, file_key, method, cnn_setting_file, logger) logger.info("Top Features For Class " +str(c) + ": " + str(top_features)) logger.info("End Of Class: " + str(c))
def run_load_predict_cnn(fold_keyword, model_saved_folder, feature_array, top_k, test_x_matrix, test_y_vector, data_stru, cnn_setting, group_all=True, save_obj_folder="./", logger=None): if logger is None: logger = init_logging('') real_num_classes = data_stru.num_classes model_list = list_files(model_saved_folder) data_stru.num_classes = 2 load_time = 0 test_time = 0 multi_predict = [] for c in range(real_num_classes): logger.info("Class: " + str(c)) class_keyword = "class" + str(c) + "_" found_model_file = "" for model_file in model_list: if ".index" not in model_file: continue if fold_keyword not in model_file: continue if class_keyword not in model_file: continue found_model_file = model_file.replace(".index", "") print (found_model_file) break if found_model_file == "": raise Exception("Model for " + class_keyword + " and " + fold_keyword + " Not Found!!!") else: found_model_file = model_saved_folder + found_model_file class_feature = feature_array[c] class_feature = class_feature[0:top_k] logger.info("model file: " + str(model_saved_folder + found_model_file)) logger.info("feature list: " + str(class_feature)) temp_test_x_matrix = test_x_matrix[:, :, class_feature, :] logger.info("In run_load_predict_cnn: " + str(temp_test_x_matrix.shape)) start_time = time.time() cnn_session, predict_y_proba, train_x_placeholder, keep_prob_placeholder = load_model(found_model_file, data_stru, cnn_setting, group_all, logger) load_time = load_time + time.time() - start_time start_time = time.time() cnn_predict_proba = load_model_predict(cnn_session, temp_test_x_matrix, predict_y_proba, train_x_placeholder, keep_prob_placeholder) #print (cnn_predict_proba[0:10, :]) test_time = test_time + time.time() - start_time multi_predict.append(cnn_predict_proba[:, 1]) cnn_session.close() multi_predict = np.array(multi_predict) #print multi_predict[0:2, 5:11] multi_predict_vector = np.argmax(multi_predict, axis=0) save_obj_file = save_obj_folder + fold_keyword + "_" + str(top_k) + ".out" save_obj([multi_predict], save_obj_file) logger.info("output obj saved to: " + save_obj_file) logger.info("multi predict matrix shape: " + str(multi_predict.shape)) logger.info("multi predict vector shape: " + str(multi_predict_vector.shape)) #print (str(multi_predict_vector[0:10])) logger.info("test y vector: " + str(test_y_vector.shape)) #print (str(test_y_vector[0:10])) acc = accuracy_score(test_y_vector, multi_predict_vector) data_stru.num_classes = real_num_classes acc1, f1_list = multiple_f1_value_precision_recall_accuracy(multi_predict_vector, test_y_vector, logger) if acc != acc1: raise Exception("check accuracy") return acc, f1_list, load_time, test_time
def multi_projected_cnn_classification_main(parameter_file, file_keyword, function_keyword="multi_proj_classification"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification(parameter_file, function_keyword) obj_keyword = obj_folder.split('/')[-2] model_saved_folder = "../../object/" + data_keyword + "/projected_classification/" + obj_keyword + "_top" + str(top_k) + "_cnn_model_folder/" print obj_keyword print cnn_obj_folder print model_saved_folder top_keyword = "_top" + str(top_k) + "." group_all = False log_folder = init_folder(log_folder) #cnn_obj_folder = init_folder(cnn_obj_folder) #cnn_temp_folder = init_folder(cnn_temp_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) obj_list = list_files(obj_folder) file_count = 0 class_column = 0 header = True cnn_setting = return_cnn_setting_from_file(cnn_setting_file) cnn_setting.save_obj_folder = cnn_obj_folder cnn_setting.temp_obj_folder = cnn_temp_folder cnn_setting.eval_method = 'f1' #init_folder(cnn_obj_folder) #init_folder(cnn_temp_folder) save_obj_folder = "../../object/" + data_keyword + "/" + function_keyword + "/" + obj_keyword + "/" save_obj_folder = init_folder(save_obj_folder) delimiter = ' ' loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str(class_id) + '_top' + str(top_k) + '_' + method + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('cnn setting:\n ' + cnn_setting.to_string()) logger.info('method: ' + method) logger.info('============') found_obj_file = '' for obj_file in obj_list: if file_key in obj_file: found_obj_file = obj_file break if found_obj_file == '': raise Exception('No obj file found') # found_obj_file = obj_folder + found_obj_file feature_dict = load_obj(found_obj_file)[0] feature_dict = np.array(feature_dict) logger.info("feature array shape: " + str(feature_dict.shape)) test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) logger.info("topk: " + str(top_k) ) data_stru.attr_num = top_k fold_accuracy, fold_f1_list, fold_load_time, fold_test_time = run_load_predict_cnn(file_key, model_saved_folder, feature_dict, top_k, test_x_matrix, test_y_vector, data_stru, cnn_setting, group_all, save_obj_folder, logger) logger.info("Fold ACC: " + str(fold_accuracy)) logger.info("Fold F1 list: " + str(fold_f1_list)) logger.info(method + ' fold training time (sec):' + str(fold_load_time)) logger.info(method + ' fold testing time (sec):' + str(fold_test_time))
def run_pure_pv_evaluation( file_keyword, parameter_file='../../parameters/pv_baseline_evaluation.txt', function_keyword="pure_pv_evaluation"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, method, log_folder, out_obj_folder = read_pure_feature_generation( parameter_file, function_keyword) print data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, method, log_folder, out_obj_folder file_list = list_files(data_folder) file_count = 0 for train_file in file_list: if file_keyword not in train_file: continue train_key = train_file.replace('.txt', '') file_count = file_count + 1 data_matrix, attr_num = file_reading(data_folder + train_file) train_x_matrix, train_y_vector = x_y_spliting(data_matrix, class_column) train_row, train_col = train_x_matrix.shape train_x_matrix = train_x_matrix.reshape(train_row, attr_num, attr_len) if class_id < 0: min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 else: min_class = class_id max_class = min_class + 1 log_file = train_key + "_" + method + "_min" + str( min_class) + "_max" + str(max_class) + "_pure_projected.log" #logger = setup_logger('') logger = setup_logger(log_folder + log_file) print "log file: " + log_folder + log_file logger.info(train_file) out_obj_file = train_key + "_" + method + "_min" + str( min_class) + "_max" + str(max_class) + "_pure_projected.obj" out_obj_matrix = [] logger.info("min class: " + str(min_class)) logger.info("max class: " + str(max_class)) for label in range(min_class, max_class): class_train_y = np.where(train_y_vector == label, 1, 0) logger.info("label: " + str(label)) if method == 'rf_lda': class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_rf_lda_analysis( train_x_matrix, class_train_y, logger) elif method == "rf": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_rf_analysis( train_x_matrix, class_train_y, logger) elif method == "lda": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_lda_analysis( train_x_matrix, class_train_y, logger) logger.info("class attr imp matrix shape: " + str(class_attr_imp_matrix.shape)) class_attr_list = map_attr_imp_analysis(class_attr_imp_matrix, logger) logger.info(class_attr_list) logger.info(class_attr_list.shape) out_obj_matrix.append(class_attr_list) out_obj_matrix = np.array(out_obj_matrix) logger.info("out obj to: " + out_obj_folder + out_obj_file) logger.info(out_obj_matrix.shape) save_obj([out_obj_matrix], out_obj_folder + out_obj_file)
def nn_classification_main(parameter_file, file_keyword, function_keyword="nn_classification"): data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, nn_setting_file = read_all_feature_classification( parameter_file, function_keyword) print(data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, method, log_folder, out_obj_folder, out_model_folder, nn_setting_file) log_folder = init_folder(log_folder) out_obj_folder = init_folder(out_obj_folder) out_model_folder = init_folder(out_model_folder) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) file_count = 0 class_column = 0 header = True nn_setting_file = "../../parameters/nn_model_parameter.txt" nn_setting, nn_key = return_nn_setting_from_file(nn_setting_file) result_obj_folder = obj_folder + method + "_result_folder" result_obj_folder = init_folder(result_obj_folder) delimiter = ' ' loop_count = -1 saver_file_profix = "" for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') saver_file_profix = file_key test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) min_class = min(train_y_vector) max_class = max(train_y_vector) num_classes = max_class - min_class + 1 if nn_setting.eval_method == "accuracy": nn_eval_key = "acc" elif num_classes > 2: nn_eval_key = "acc_batch" else: nn_eval_key = "f1" log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( min_class) + "_" + str(max_class) + "_act" + str( nn_setting.activation_fun) + "_" + nn_eval_key + '.log' print("log file: " + log_file) logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('nn setting:\n ' + nn_setting.to_string()) logger.info('method: ' + method) logger.info('============') #train_y_vector[50:80] = 1 #test_y_vector[30:40] = 1 if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) logger.info(train_x_matrix[0, 0:3]) logger.info(test_x_matrix[0, 0:3]) train_y_matrix = y_vector_to_matrix(train_y_vector, num_classes) test_y_matrix = y_vector_to_matrix(test_y_vector, num_classes) feature_dict = None top_k = -1 #model_save_file = file_key + '_count' + str(file_count) + '_' + method nn_eval_value, train_run_time, test_run_time, nn_predict_proba = run_nn( train_x_matrix, train_y_matrix, test_x_matrix, test_y_matrix, nn_setting, logger) logger.info("Fold eval value: " + str(nn_eval_value)) logger.info(method + ' fold training time (sec):' + str(train_run_time)) logger.info(method + ' fold testing time (sec):' + str(test_run_time))
def run_cnn_projected_feature_analysis(feature_folder, class_id, data_folder, data_file_keyword, method="rf_lda", log_folder='./'): data_file_list = list_files(data_folder) feature_file_list = list_files(feature_folder) out_obj_folder = feature_folder[:-1] + "_" + method out_obj_folder = init_folder(out_obj_folder) class_column = 0 for train_file in data_file_list: if data_file_keyword not in train_file: continue data_key = train_file.replace('.txt', '') data_matrix, attr_num = file_reading(data_folder + train_file) train_x_matrix, train_y_vector = x_y_spliting(data_matrix, class_column) #train_y_vector = np.array([0, 0, 1, 1, 1, 1, 2, 2, 2, 3]) if class_id < 0: min_class = min(train_y_vector) max_class = max(train_y_vector) + 1 else: min_class = class_id max_class = min_class + 1 log_file = data_key + "_" + method + "_min" + str( min_class) + "_max" + str(max_class) + ".log" logger = setup_logger(log_folder + log_file) logger.info('data file: ' + train_file) out_obj_file = data_key + "_" + method + "_min" + str( min_class) + "_max" + str(max_class) + ".obj" out_obj_matrix = [] for label in range(min_class, max_class): logger.info("class: " + str(label)) feature_key = "_class" + str(label) + "_" for feature_file in feature_file_list: if data_key not in feature_file or feature_key not in feature_file: continue logger.info("feature file: " + feature_file) feature_obj = load_obj(feature_folder + feature_file) train_feature = obj_processing(feature_obj[0]) logger.info("train feature shape: " + str(train_feature.shape)) class_train_y = np.where(train_y_vector == label, 1, 0) logger.info("feature method: " + str(method)) if method == "rf_lda_sum": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_rf_lda_analysis( train_feature, class_train_y, logger) elif method == "rf": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_rf_analysis( train_feature, class_train_y, logger) elif method == "lda": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_lda_analysis( train_feature, class_train_y, logger) elif method == "cpca": class_attr_imp_matrix, class_run_time = project_cnn_feature_combined_cpca_analysis( train_feature, class_train_y, logger) if method == "cpca": class_attr_list = class_attr_imp_matrix else: logger.info("class attr imp matrix shape: " + str(class_attr_imp_matrix.shape)) class_attr_list = map_attr_imp_analysis( class_attr_imp_matrix, logger) logger.info(class_attr_list) out_obj_matrix.append(class_attr_list) out_obj_matrix = np.array(out_obj_matrix) logger.info("out obj to: " + out_obj_folder + out_obj_file) logger.info(out_obj_matrix.shape) save_obj([out_obj_matrix], out_obj_folder + out_obj_file)
#obj_folder = '../../object/dsa/all_feature_classification/fcn_obj_folder/' #obj_file = 'train_0_count0_fcn_class0_c8_1_c5_1_c3_1global_p112_1.ckpt' #obj_vector = load_obj(obj_folder + obj_file) obj_vector = load_obj(obj_file)[0] print obj_vector.shape print obj_vector sdfs print np.array(obj_vector[0]).shape print np.array(obj_vector[0]).shape print len(obj_vector) print np.array(obj_vector[0]).shape #print np.array(obj_vector[0][1]).shape #print np.array(obj_vector[0][8]).shape #print np.array(obj_vector[1]).shape sdfds obj_list = list_files(obj_folder) acc_vector = [] train_vector = [] test_vector = [] obj_count = 0 for obj_file in obj_list: print obj_file obj_vector = load_obj(obj_folder + obj_file) #print obj_vector[0] #print obj_vector[3] acc_vector.append(float(obj_vector[0])) train_vector.append((obj_vector[3])) test_vector.append((obj_vector[4])) obj_count = obj_count + 1 acc_vector = np.array(acc_vector)
def run_z_norm_main(data_folder, file_keyword="train_", logger=None, class_column=0, delimiter=' ', header=True): if logger is None: logger = setup_logger('') if data_folder.endswith('/'): out_folder = data_folder[:-1] + "_z_norm/" else: out_folder = data_folder + "_z_norm/" out_folder = init_folder(out_folder) file_list = list_files(data_folder) file_count = 0 for train_file in file_list: if file_keyword not in train_file: continue logger.info(train_file) test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) #train_x_matrix = train_x_matrix[0:20, :] #test_x_matrix = test_x_matrix[0:20, :] #train_y_vector = train_y_vector[0:20] #test_y_vector = test_y_vector[0:20] train_row, train_col = train_x_matrix.shape test_row, test_col = test_x_matrix.shape attr_len = train_col / attr_num train_x_matrix = train_x_matrix.reshape(train_row, attr_num, attr_len) test_x_matrix = test_x_matrix.reshape(test_row, attr_num, attr_len) norm_train_matrix = run_z_normalization(train_x_matrix) norm_test_matrix = run_z_normalization(test_x_matrix) if file_count == 0: logger.info("Before norm") logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info("After norm") logger.info('train matrix shape: ' + str(norm_train_matrix.shape)) logger.info('test matrix shape: ' + str(norm_test_matrix.shape)) norm_train_matrix = norm_train_matrix.reshape(train_row, train_col) norm_test_matrix = norm_test_matrix.reshape(test_row, test_col) train_y_vector = train_y_vector.reshape(len(train_y_vector), 1) test_y_vector = test_y_vector.reshape(len(test_y_vector), 1) norm_train_matrix = np.hstack((train_y_vector, norm_train_matrix)) norm_test_matrix = np.hstack((test_y_vector, norm_test_matrix)) if file_count == 0: logger.info("before write to file") logger.info('train matrix shape: ' + str(norm_train_matrix.shape)) logger.info('test matrix shape: ' + str(norm_test_matrix.shape)) file_writing(norm_train_matrix, out_folder + train_file, attr_num) file_writing(norm_test_matrix, out_folder + test_file, attr_num) if norm_checking(out_folder + train_file) is False or norm_checking( out_folder + test_file) is False: logger.info("ERROR!!!") raise Exception("ERROR!!!") return False file_count = file_count + 1
def global_classification_main(parameter_file, file_keyword): function_keyword = "global_classification" data_keyword, data_folder, attr_num, attr_len, num_classes, start_class, class_column, class_id, obj_folder, top_k, method, log_folder, cnn_obj_folder, cnn_temp_folder, cnn_setting_file = read_feature_classification( parameter_file, function_keyword) data_stru = return_data_stru(num_classes, start_class, attr_num, attr_len, class_column) file_list = list_files(data_folder) obj_list = list_files(obj_folder) file_count = 0 class_column = 0 header = True cnn_setting = return_cnn_setting_from_file(cnn_setting_file) cnn_setting.save_obj_folder = cnn_obj_folder cnn_setting.temp_obj_folder = cnn_temp_folder cnn_setting.eval_method = 'f1' init_folder(cnn_obj_folder) init_folder(cnn_temp_folder) all_result_matrix = np.zeros((10, num_classes)) train_file_vector = [] prediction_matrix = [] f1_value_matrix = [] accuracy_vector = [] delimiter = ' ' all_accuracy = 0 all_train_time = 0 all_test_time = 0 loop_count = -1 for train_file in file_list: if file_keyword not in train_file: continue loop_count = loop_count + 1 file_key = train_file.replace('.txt', '') log_file = log_folder + data_keyword + '_' + file_key + '_' + function_keyword + '_class' + str( class_id) + '_top' + str(top_k) + '_' + method + '.log' print "log file: " + log_file logger = setup_logger(log_file, 'logger_' + str(loop_count)) logger.info('\nlog file: ' + log_file) logger.info(train_file) logger.info('cnn setting:\n ' + cnn_setting.to_string()) logger.info('method: ' + method) logger.info('============') continue found_obj_file = '' for obj_file in obj_list: if file_key in obj_file: found_obj_file = obj_file break if found_obj_file == '': raise Exception('No obj file found') print found_obj_file print cnn_setting.save_obj_folder + file_key + "_" + method + "_projected_result.ckpt" # found_obj_file = obj_folder + found_obj_file feature_dict = load_obj(found_obj_file)[0] feature_dict = np.array(feature_dict) logger.info("feature array shape: " + str(feature_dict.shape)) test_file = train_file.replace('train', 'test') train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, attr_num = train_test_file_reading_with_attrnum( data_folder + train_file, data_folder + test_file, class_column, delimiter, header) if file_count == 0: logger.info('train matrix shape: ' + str(train_x_matrix.shape)) logger.info('train label shape: ' + str(train_y_vector.shape)) logger.info('test matrix shape: ' + str(test_x_matrix.shape)) logger.info('test label shape: ' + str(test_y_vector.shape)) train_x_matrix = train_test_transpose(train_x_matrix, attr_num, attr_len, False) test_x_matrix = train_test_transpose(test_x_matrix, attr_num, attr_len, False) data_stru.attr_num = top_k fold_accuracy, fold_avg_eval, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix = run_feature_projected_cnn( train_x_matrix, train_y_vector, test_x_matrix, test_y_vector, data_stru, cnn_setting, feature_dict, top_k, file_key + '_count' + str(file_count), class_id, logger) prediction_matrix.append(fold_predict_y) logger.info("Fold F1: " + str(fold_f1_value_list)) accuracy_vector.append(fold_accuracy) all_accuracy = all_accuracy + fold_accuracy all_train_time = all_train_time + fold_train_time all_test_time = all_test_time + fold_test_time logger.info(method + ' fold accuracy: ' + str(fold_accuracy)) logger.info(method + ' fold training time (sec):' + str(fold_train_time)) logger.info(method + ' fold testing time (sec):' + str(fold_test_time)) save_obj([ fold_accuracy, fold_avg_eval, fold_predict_y, fold_train_time, fold_test_time, fold_predict_matrix ], save_obj_folder + file_key + "_" + method + "_global_cnn_result.ckpt")