if 'num_mpi' in params.keys():
T_input = np.loadtxt(T_data_path + 'training_input0.dat')
T_output = np.loadtxt(T_data_path + 'training_output0.dat')
for i in range(params['num_mpi'] - 1):
file_name = T_data_path + 'training_input' + str(i + 1) + '.dat'
file_name1 = T_data_path + 'training_output' + str(i + 1) + '.dat'
T_input = np.append(T_input, np.loadtxt(file_name), axis=0)
T_output = np.append(T_output, np.loadtxt(file_name1), axis=0)
else:
T_input = np.loadtxt(T_data_path + 'training_input.dat')
T_output = np.loadtxt(T_data_path + 'training_output.dat')
if (training_type == 'Neural_Network'):
ml = MLPRegressor()
elif (training_type == 'Random_Forest'):
ml = RandomForestRegressor()
elif (training_type == 'Decision_Tree'):
ml = tree.DecisionTreeRegressor()
ml.fit(T_input, T_output)
ml.type = training_type
ml.output_param_path = param_path
sk2f(ml)
print('-------------------------------\n')
print('training_completed\n\n')
print('training_type:\n')
print(training_type + '\n')
print('-------------------------------\n')
