# spliting train and test set
# print("flag: training sets")
# train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=42)
# print("done")
# export test data if original data is used
# if status == 'o':
# with open("%s/%s-%s.pkl" % (testset_dir, feature_name, "X"), 'wb') as f:
# pickle.dump(test_X, f)
# with open("%s/%s-%s.pkl" % (testset_dir, feature_name, "y"), 'wb') as f:
# pickle.dump(test_y, f)
# print("flag: test set is exported")
print("flag: training model")
if contextual_info:
train_df = fg.queue_level(train_df)
activity_list = fg.get_activities(train_df)
train_context_X = fg.generate_context_feature(train_df, activity_list)
model = net()
if task == 'next_timestamp':
model.train(train_X,
train_y,
regression,
loss,
n_epochs=num_epochs,
batch_size=batch_size,
num_folds=num_folds,
model_name=model_name,
checkpoint_dir=args.checkpoint_dir,
X_train_ctx=train_context_X)
elif task == 'next_activity':
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()
if regression:
model.train(train_X,
train_context_X,
train_Y_Time,
regression,
loss,
batch_size=batch_size,
num_folds=num_folds,