run.py

import argparse
import os
import torch
from exp.exp_long_term_forecasting import Exp_Long_Term_Forecast
import random
import numpy as np
import sys

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

if __name__ == '__main__':
    parser = argparse.ArgumentParser()

    # basic config
    parser.add_argument('--task_name', type=str, default='long_term_forecast',
                        help='task name, options:[long_term_forecast, short_term_forecast, imputation, classification, anomaly_detection]')
    parser.add_argument('--is_training', type=int,  default=1, help='status')
    parser.add_argument('--model_id', type=str, default='test', help='model id')
    parser.add_argument('--model', type=str, default='VarFormer', help='model name, options: [VarFormer, Autoformer, Transformer, TimesNet, etc.]')

    # data loader
    parser.add_argument('--data', type=str, 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')
    parser.add_argument('--exp_type', type=str, default='multi', help='experiment type')

    # forecasting setting
    parser.add_argument('--seq_len', type=int, default=96, help='input sequence length')
    parser.add_argument('--label_len', type=int, default=48, help='start token length')
    parser.add_argument('--pred_len', type=int, default=96, help='prediction sequence length')
    parser.add_argument('--seasonal_patterns', type=str, default='Monthly', help='subset for M4')

    # model define - common parameters
    parser.add_argument('--enc_in', type=int, default=7, help='encoder input size')
    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('--dropout', type=float, default=0.1, help='dropout')
    parser.add_argument('--embed', type=str, default='timeF',
                        help='time features encoding, options:[timeF, fixed, learned]')
    parser.add_argument('--output_attention', action='store_true', help='whether to output attention in encoder')

    # model define - VarFormer specific parameters
    parser.add_argument('--inter_dim', type=int, default=128, help='intermediate dimension for VarFormer')
    parser.add_argument('--latent_dim', type=int, default=64, help='latent dimension for VarFormer')
    parser.add_argument('--input_dim', type=int, default=1, help='input dimension for VarFormer')
    parser.add_argument('--beta', type=float, default=1, help='beta for generative model loss')
    parser.add_argument('--alpha', type=float, default=1, help='alpha for transformer NLL model loss')
    parser.add_argument('--nvars', type=int, default=1, help='number of variables')
    parser.add_argument('--revin', type=bool, default=True, help='whether to use RevIN in ModernTCN')
    parser.add_argument('--affine', type=bool, default=True, help='whether to use affine transformation in RevIN')
    parser.add_argument('--subtract_last', type=bool, default=False, help='whether to subtract last value in RevIN')
    parser.add_argument('--c_in', type=int, default=7, help='input size')
    parser.add_argument('--embed_type', type=str, default='timeF',
                        help='time features encoding type, options:[timeF, fixed, learned]')

    # model define - other models specific parameters
    parser.add_argument('--top_k', type=int, default=2, help='for TimesBlock')
    parser.add_argument('--num_kernels', type=int, default=6, help='for Inception')
    parser.add_argument('--fnet_d_model', type=int, default=512, help='dimension of model of fnet')
    parser.add_argument('--fnet_layers', type=int, default=2, help='num of fnet layers')
    parser.add_argument('--fnet_d_ff', type=int, default=2048, help='dimension of fcn of fnet')
    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('--complex_dropout', type=float, default=0.1, help='complex_dropout')
    parser.add_argument('--activation', type=str, default='gelu', help='activation')

    # optimization
    parser.add_argument('--num_workers', type=int, default=10, help='data loader num workers')
    parser.add_argument('--itr', type=int, default=1, 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=3, help='early stopping patience')
    parser.add_argument('--learning_rate', type=float, default=0.0001, help='optimizer learning rate')
    parser.add_argument('--weight_decay', type=float, default=0.01, help='Adam weight decay')
    parser.add_argument('--des', type=str, default='test', help='exp description')
    parser.add_argument('--loss', type=str, default='MSE', help='loss function')
    parser.add_argument('--lradj', type=str, default='type1', help='adjust learning rate')
    parser.add_argument('--use_amp', type=bool, default=False, help='use automatic mixed precision training')
    parser.add_argument('--pct_start', type=float, default=0.1, help='pct_start')

    # 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', type=bool, 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('--device', type=str, default='cpu')

    # de-stationary projector params
    parser.add_argument('--p_hidden_dims', type=int, nargs='+', default=[128, 128],
                        help='hidden layer dimensions of projector (List)')
    parser.add_argument('--p_hidden_layers', type=int, default=2, help='number of hidden layers in projector')

    # additional params
    parser.add_argument('--low_pass', type=bool, default=False)
    parser.add_argument('--low_pass_threshold', type=float, default=3)

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

    if torch.cuda.device_count() <= 1:
        args.use_multi_gpu = False

    if args.use_gpu and args.use_multi_gpu:
        args.device_ids = np.arange(torch.cuda.device_count()).tolist()
        args.gpu = args.device_ids[0]

    # settings
    args.task_name = 'long_term_forecast'
    args.is_training = 1
    args.root_path = './datasets/'
    args.checkpoints = './checkpoints/' + args.exp_type + '/'

    # Set embed_type to match embed for compatibility
    args.embed_type = args.embed

    print('Args in experiment:')
    print(args)
    print(os.getcwd())
    print(os.path.abspath(os.path.join(os.getcwd(), "..")))
    print(os.path.abspath(os.path.join(os.getcwd(), "../..")))

    Exp = Exp_Long_Term_Forecast

    if args.is_training:
        for ii in range(args.itr):
            # setting record of experiments
            if args.model == 'VarFormer':
                setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_eb{}_id{}_ld{}_revin{}_{}_{}'.format(
                    args.task_name,
                    args.model_id,
                    args.model,
                    args.data,
                    args.features,
                    args.seq_len,
                    args.label_len,
                    args.pred_len,
                    args.d_model,
                    args.n_heads,
                    args.e_layers,
                    args.d_layers,
                    args.d_ff,
                    args.embed,
                    args.inter_dim,
                    args.latent_dim,
                    args.revin,
                    args.des, ii)
            else:
                setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(
                    args.task_name,
                    args.model_id,
                    args.model,
                    args.data,
                    args.features,
                    args.seq_len,
                    args.label_len,
                    args.pred_len,
                    args.d_model,
                    args.n_heads,
                    args.e_layers,
                    args.d_layers,
                    args.d_ff,
                    args.factor,
                    args.embed,
                    args.distil,
                    args.des, ii)
            
            if os.path.exists('results/' + args.exp_type + '/'):
                if setting in os.listdir('results/' + args.exp_type + '/'):
                    sys.exit()

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

            print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
            exp.test(setting)
            torch.cuda.empty_cache()
    else:
        ii = 0
        if args.model == 'VarFormer':
            setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_eb{}_id{}_ld{}_revin{}_{}_{}'.format(
                args.task_name,
                args.model_id,
                args.model,
                args.data,
                args.features,
                args.seq_len,
                args.label_len,
                args.pred_len,
                args.d_model,
                args.n_heads,
                args.e_layers,
                args.d_layers,
                args.d_ff,
                args.embed,
                args.inter_dim,
                args.latent_dim,
                args.revin,
                args.des, ii)
        else:
            setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(
                args.task_name,
                args.model_id,
                args.model,
                args.data,
                args.features,
                args.seq_len,
                args.label_len,
                args.pred_len,
                args.d_model,
                args.n_heads,
                args.e_layers,
                args.d_layers,
                args.d_ff,
                args.factor,
                args.embed,
                args.distil,
                args.des, ii)

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