run_longExp.py

import argparse
import os
import torch
# from exp.exp_main_test import Exp_Main  #This is for ploting eigenvalue
from exp.exp_main import Exp_Main
from exp.exp_short_term_forecasting import Exp_Short_Term_Forecast

import random
import numpy as np

parser = argparse.ArgumentParser(description='Transformer family for Time Series Forecasting')

#For KoopRNN
parser.add_argument('--CI', action='store_true', help='default concatenate all variants before MLP', default=False)
parser.add_argument('--mask_type', type=str, default='global')
parser.add_argument('--shareEncoder', action='store_true', help='default separate mlp for each chain', default=False)

#For m4 dataset；
parser.add_argument('--seasonal_patterns', type=str, default='Monthly', help='subset for M4')
parser.add_argument('--task_name', type=str, default='long_term_forecasting')

#For koopman:
# Koopa
parser.add_argument('--dynamic_dim', type=int, default=128, help='latent dimension of koopman embedding')
parser.add_argument('--hidden_dim', type=int, default=64, help='hidden dimension of en/decoder')
parser.add_argument('--hidden_layers', type=int, default=2, help='number of hidden layers of en/decoder')
parser.add_argument('--seg_len', type=int, default=48, help='segment length of time series')
parser.add_argument('--num_blocks', type=int, default=3, help='number of Koopa blocks')
parser.add_argument('--alpha', type=float, default=0.2, help='spectrum filter ratio')
parser.add_argument('--multistep', action='store_true', help='whether to use approximation for multistep K', default=False)


# random seed
parser.add_argument('--random_seed', type=int, default=2021, help='random seed')

# basic config
parser.add_argument('--is_training', type=int, required=True, default=1, help='status')
parser.add_argument('--model_id', type=str, required=True, default='test', help='model id')
parser.add_argument('--model', type=str, required=True, default='Autoformer',
                    help='model name, options: [Autoformer, Informer, Transformer]')

# data loader
parser.add_argument('--data', type=str, required=True, default='ETTm1', help='dataset type')
parser.add_argument('--root_path', type=str, default='./data/ETT/', help='root path of the data file')
parser.add_argument('--data_path', type=str, default='ETTh1.csv', help='data file')
parser.add_argument('--features', type=str, default='M',
                    help='forecasting task, options:[M, S, MS]; M:multivariate predict multivariate, S:univariate predict univariate, MS:multivariate predict univariate')
parser.add_argument('--target', type=str, default='OT', help='target feature in S or MS task')
parser.add_argument('--freq', type=str, default='h',
                    help='freq for time features encoding, options:[s:secondly, t:minutely, h:hourly, d:daily, b:business days, w:weekly, m:monthly], you can also use more detailed freq like 15min or 3h')
parser.add_argument('--checkpoints', type=str, default='./checkpoints/', help='location of model checkpoints')

# forecasting task
parser.add_argument('--seq_len', type=int, default=96, help='input sequence length')
parser.add_argument('--label_len', type=int, default=0, help='start token length, not used in MTST')
parser.add_argument('--pred_len', type=int, default=96, help='prediction sequence length')


# MTST
parser.add_argument('--n_branches', type=int, default=1, help='num of paralized encoder layers')
parser.add_argument('--patch_len_ls', type=str, default='16', help='list of patch length')
parser.add_argument('--stride_ls', type=str, default='8', help='list of stride')
parser.add_argument('--d_model_ls', type=str, default='128', help='list of d_model for MTST')
parser.add_argument('--n_heads_ls', type=str, default='16', help='list of head number for MTST')
parser.add_argument('--rel_pe', type=str, default='null', help='Type of relative PE: rel_sin')


# PatchTST
parser.add_argument('--res_attn', action='store_true', help='res_attention, default False')
parser.add_argument('--head_type', type=str, default='flatten', help='linear head type')
parser.add_argument('--fc_dropout', type=float, default=0.05, help='fully connected dropout')
parser.add_argument('--head_dropout', type=float, default=0.0, help='head dropout')
parser.add_argument('--patch_len', type=int, default=16, help='patch length')
parser.add_argument('--stride', type=int, default=8, help='stride')
parser.add_argument('--padding_patch', default='None', help='None: None; end: padding on the end')
parser.add_argument('--revin', type=int, default=1, help='RevIN; True 1 False 0')
parser.add_argument('--affine', type=int, default=0, help='RevIN-affine; True 1 False 0')
parser.add_argument('--subtract_last', type=int, default=0, help='0: subtract mean; 1: subtract last')
parser.add_argument('--decomposition', type=int, default=0, help='decomposition; True 1 False 0')
parser.add_argument('--kernel_size', type=int, default=25, help='decomposition-kernel')
parser.add_argument('--individual', type=int, default=0, help='individual head; True 1 False 0')
parser.add_argument('--store_attn', action='store_true', help='save and print attn scores')
parser.add_argument('--pre_norm', action='store_true', help='pre normalization')
parser.add_argument('--pe', type=str, default='zeros', help='try sincos absolute pe')
parser.add_argument('--no_learn_pe', action='store_false', help='when try sincos absolute pe, act it and the learn_pe is False')

# Formers 
parser.add_argument('--embed_type', type=int, default=0, help='0: default 1: value embedding + temporal embedding + positional embedding 2: value embedding + temporal embedding 3: value embedding + positional embedding 4: value embedding')
parser.add_argument('--enc_in', type=int, default=7, help='encoder input size') # DLinear with --individual, use this hyperparameter as the number of channels
parser.add_argument('--dec_in', type=int, default=7, help='decoder input size')
parser.add_argument('--c_out', type=int, default=7, help='output size')
parser.add_argument('--d_model', type=int, default=512, help='dimension of model')
parser.add_argument('--n_heads', type=int, default=8, help='num of heads')
parser.add_argument('--e_layers', type=int, default=2, help='num of encoder layers')
parser.add_argument('--d_layers', type=int, default=1, help='num of decoder layers')
parser.add_argument('--d_ff', type=int, default=2048, help='dimension of fcn')
parser.add_argument('--moving_avg', type=int, default=25, help='window size of moving average')
parser.add_argument('--factor', type=int, default=1, help='attn factor')
parser.add_argument('--distil', action='store_false',
                    help='whether to use distilling in encoder, using this argument means not using distilling',
                    default=True)
parser.add_argument('--dropout', type=float, default=0.05, help='dropout')
parser.add_argument('--embed', type=str, default='timeF',
                    help='time features encoding, options:[timeF, fixed, learned]')
parser.add_argument('--activation', type=str, default='gelu', help='activation')
parser.add_argument('--output_attention', action='store_true', help='whether to output attention in ecoder')
parser.add_argument('--do_predict', action='store_true', help='whether to predict unseen future data')


# Linear RNNs
parser.add_argument('--inv_loss', type=int, default=0, help='default 0: not adding inverse loss; 1: adding inverse loss.')
parser.add_argument('--inv_loss_alpha', type=float, default=0.1, help='default 0: not adding inverse loss; 1: adding inverse loss.')



# optimization
parser.add_argument('--num_workers', type=int, default=0, help='data loader num workers')
parser.add_argument('--itr', type=int, default=2, help='experiments times')
parser.add_argument('--train_epochs', type=int, default=100, help='train epochs')
parser.add_argument('--batch_size', type=int, default=32, help='batch size of train input data')
parser.add_argument('--patience', type=int, default=20, help='early stopping patience')
parser.add_argument('--learning_rate', type=float, default=0.0001, help='optimizer learning rate')
parser.add_argument('--des', type=str, default='Exp', help='exp description')
parser.add_argument('--loss', type=str, default='MSE', help='loss function')
parser.add_argument('--lradj', type=str, default='type3', help='adjust learning rate')
parser.add_argument('--pct_start', type=float, default=0.3, help='pct_start')
parser.add_argument('--use_amp', action='store_true', help='use automatic mixed precision training', default=False)
parser.add_argument('--l2', type=float, default=0., help='weight decay factor in Optimizer')
parser.add_argument('--warmup_steps', type=int, default=0, help='num of warmup epoch')


# GPU
parser.add_argument('--use_gpu', type=bool, default=True, help='use gpu')
parser.add_argument('--gpu', type=int, default=0, help='gpu')
parser.add_argument('--use_multi_gpu', action='store_true', help='use multiple gpus', default=False)
parser.add_argument('--devices', type=str, default='0,1,2,3', help='device ids of multile gpus')
parser.add_argument('--test_flop', action='store_true', default=False, help='See utils/tools for usage')


# MLFLOW:
parser.add_argument('--use_mlflow',action='store_true', help='use mlflow')
parser.add_argument('--mlflow_project',type=str, default='exp', help='project name of mlflow')

args = parser.parse_args()

# # random seed
# fix_seed = args.random_seed
# random.seed(fix_seed)
# torch.manual_seed(fix_seed)
# np.random.seed(fix_seed)


args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False

if args.use_gpu and args.use_multi_gpu:
    args.dvices = args.devices.replace(' ', '')
    device_ids = args.devices.split(',')
    args.device_ids = [int(id_) for id_ in device_ids]
    args.gpu = args.device_ids[0]

args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False


print('Args in experiment:')
print(args)

if args.task_name == 'short_term_forecast':
    Exp = Exp_Short_Term_Forecast
else:
    Exp = Exp_Main

rel_pe = args.rel_pe

import multiprocessing
import os

if __name__ == '__main__':
    multiprocessing.freeze_support()
    if args.is_training:
        for ii in range(args.itr):
            # random seed
            fix_seed = args.random_seed + ii
            random.seed(fix_seed)
            torch.manual_seed(fix_seed)
            np.random.seed(fix_seed)
            print('random seed:', fix_seed)
            # setting record of experiments
            setting = '{}_{}_msk{}_CI{}_hl{}_pl{}_dm{}_hd{}_el{}_dr{}_bn{}_sl{}_shareE{}_{}'.format(
                args.model_id,
                args.model,
                args.mask_type,
                args.CI,
                args.seq_len,
                args.pred_len,
                args.dynamic_dim,
                args.hidden_dim,
                args.hidden_layers,
                args.dropout,
                args.num_blocks,
                args.seg_len,
                args.shareEncoder,
                ii
                )

            exp = Exp(args)  # set experiments
            print('>>>>>>>start training : {}>>>>>>>>>>>>>>>>>>>>>>>>>>'.format(setting))
            exp.train(setting)

            print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
            exp.test(setting)

            if args.do_predict:
                print('>>>>>>>predicting : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
                exp.predict(setting, True)

            torch.cuda.empty_cache()
    else:
        ii=0
        # random seed
        fix_seed = args.random_seed
        random.seed(fix_seed)
        torch.manual_seed(fix_seed)
        np.random.seed(fix_seed)
        print('random seed:', fix_seed)
        setting = '{}_{}_msk{}_CI{}_hl{}_pl{}_dm{}_hd{}_el{}_dr{}_bn{}_sl{}_shareE{}_{}'.format(
            args.model_id,
            args.model,
            args.mask_type,
            args.CI,
            args.seq_len,
            args.pred_len, # changed for extending test horizon!!!! change it back
            args.dynamic_dim,
            args.hidden_dim,
            args.hidden_layers,
            args.dropout,
            args.num_blocks,
            args.seg_len,
            args.shareEncoder,
            ii
            )

        exp = Exp(args)  # set experiments
        print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
        exp.test(setting, test=1)
        torch.cuda.empty_cache()