resource_p, data_p, transition) testset_dir = "../testsets" log_config = { "control_flow_p": control_flow_p, "time_p": time_p, "resource_p": resource_p, "data_p": data_p, "transition": transition } # load data print("flag: loading data") fg = FeatureGenerator() df = fg.create_initial_log(filename, log_config) print("done") num_events = len(df) num_cases = len(set(df["id"])) # feature generation print("flag: generating features") if task == 'next_activity': loss = 'categorical_crossentropy' regression = False feature_type_list = ["activity_history"] df = fg.add_activity_history(df) df = fg.add_next_activity(df) elif task == 'next_timestamp':
model_name = args.data_set + args.task contextual_info = args.contextual_info if args.task == 'next_activity': loss = 'categorical_crossentropy' regression = False elif args.task == 'next_timestamp': loss = 'mae' regression = True batch_size = args.batch_size_train num_folds = args.num_folds # load data FG = FeatureGenerator() df = FG.create_initial_log(filename) #split train and test #train_df, test_df = FG.train_test_split(df, 0.7, 0.3) train_df = df test_df = train_df #create train train_df = FG.order_csv_time(train_df) train_df = FG.queue_level(train_df) train_df.to_csv('./training_data.csv') state_list = FG.get_states(train_df) train_X, train_Y_Event, train_Y_Time = FG.one_hot_encode_history( train_df, args.checkpoint_dir + args.data_set) if contextual_info: train_context_X = FG.generate_context_feature(train_df, state_list) model = net()