run.py

# Copyright (c) 2019-present, Royal Bank of Canada.
# Copyright (c) 2021 THUML @ Tsinghua University
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
#####################################################################################
# Code is based on the Autoformer (https://arxiv.org/pdf/2106.13008.pdf) implementation
# from https://github.com/thuml/Autoformer by THUML @ Tsinghua University
####################################################################################

import argparse
import torch
from exp.exp_main import Exp_Main
import random
import numpy as np

def main():
    fix_seed = 2021
    random.seed(fix_seed)
    torch.manual_seed(fix_seed)
    np.random.seed(fix_seed)

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

    # basic config
    parser.add_argument('--is_training', type=int, default=1, help='status')
    parser.add_argument('--use_multi_scale', action='store_true', help='using mult-scale')
    parser.add_argument('--prob_forecasting', action='store_true', help='using probabilistic forecasting')
    parser.add_argument('--scales', default=[16, 8, 4, 2, 1], help='scales in mult-scale')
    parser.add_argument('--scale_factor', type=int, default=2, help='scale factor for upsample')
    parser.add_argument('--model', type=str, required=True, default='Autoformer',
            help='model name, options: [Autoformer, Informer, Transformer, Reformer, FEDformer] and their MS versions: [AutoformerMS, InformerMS, etc]')

    # data loader
    parser.add_argument('--data', type=str, default='custom', 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=48, help='start token length')
    parser.add_argument('--pred_len', type=int, default=96, help='prediction sequence length')

    # supplementary config for FiLM model
    parser.add_argument('--modes1', type=int, default=64, help='modes to be selected random 64')
    parser.add_argument('--mode_type',type=int,default=0)

    # supplementary config for FEDformer model
    parser.add_argument('--version', type=str, default='Wavelets',
                        help='for FEDformer, there are two versions to choose, options: [Fourier, Wavelets]')
    parser.add_argument('--mode_select', type=str, default='low',
                        help='for FEDformer, there are two mode selection method, options: [random, low]')
    parser.add_argument('--modes', type=int, default=64, help='modes to be selected random 64')
    parser.add_argument('--L', type=int, default=3, help='ignore level')
    parser.add_argument('--base', type=str, default='legendre', help='mwt base')
    parser.add_argument('--cross_activation', type=str, default='tanh',
                        help='mwt cross atention activation function tanh or softmax')

    # supplementary config for Reformer model
    parser.add_argument('--bucket_size', type=int, default=4, help='for Reformer')
    parser.add_argument('--n_hashes', type=int, default=4, help='for Reformer')
    parser.add_argument('--film_ours', default=True, action='store_true')
    parser.add_argument('--ab', type=int, default=2, help='ablation version')
    parser.add_argument('--ratio', type=float, default=0.5, help='dropout')
    parser.add_argument('--film_version', type=int, default=0, help='compression')

    # model define
    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('--moving_avg', type=int, default=25, help='window size of moving average')
    parser.add_argument('--factor', type=int, default=3, 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')

    # optimization
    parser.add_argument('--num_workers', type=int, default=10, help='data loader num workers')
    parser.add_argument('--itr', type=int, default=3, help='experiments times')
    parser.add_argument('--train_epochs', type=int, default=10, 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('--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='type1', help='adjust learning rate')
    parser.add_argument('--use_amp', action='store_true', help='use automatic mixed precision training', default=False)

    # 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', help='device ids of multile gpus')

    args = parser.parse_args()

    if 'MS' in args.model:
        args.use_multi_scale = True

    args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False
    if args.use_gpu:
        args.devices = '0'
        for i in range(1, torch.cuda.device_count()):
            args.devices = args.devices + f',{i}'
        args.use_multi_gpu = True if torch.cuda.device_count()>1 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]


    if args.data_path=='weather.csv':
        args.root_path = './dataset/weather/' 
        c = 21
        args.enc_in = c
        args.dec_in = c
        args.c_out = c

    if args.data_path=='synthetic':
        args.root_path = ''
        c = 3
        args.enc_in = c
        args.dec_in = c
        args.c_out = c

    elif args.data_path=='traffic.csv':
        args.root_path = './dataset/traffic/' 
        c = 862
        args.enc_in = c
        args.dec_in = c
        args.c_out = c
        args.train_epochs = 3

    elif args.data_path=='electricity.csv':
        args.root_path = './dataset/electricity/' 
        c = 321
        args.enc_in = c
        args.dec_in = c
        args.c_out = c
    elif args.data_path=='exchange_rate.csv':
        args.root_path = './dataset/exchange_rate/' 
        c = 8
        args.enc_in = c
        args.dec_in = c
        args.c_out = c
    elif args.data_path=='national_illness.csv':
        args.root_path = './dataset/illness/'
        c = 7
        args.enc_in = c
        args.dec_in = c
        args.c_out = c
        args.seq_len = 32
        args.label_len = 16
        args.scales = [8, 4, 2, 1]

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

    if args.prob_forecasting:
        assert args.loss == 'mse'

    Exp = Exp_Main

    if args.is_training:
        for ii in range(args.itr):
            setting = f'{args.data_path[:-4]}_{args.model}_{args.pred_len}_{args.loss}'
            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
        setting = '{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_dt{}_{}_{}'.format(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()

if __name__ == "__main__":
    main()