run_TGTSF_weather.py

import argparse
import os
import torch
from exp.exp_TGTSF_weather import Exp_Main
import random
import numpy as np

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

# 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')

# TGTSF dataloader 

parser.add_argument('--news_path', type=str, default='./data/news', help='path to pre-embed news or raw text news. Set to None will use zero embedding')
parser.add_argument('--des_path', type=str, default='./data/ETT/desp.csv', help='channel description, directory to the pre_embed or raw (with pre_embed set 0) set to None will use title of each column')
parser.add_argument('--info_overhead', type=int, default=0, help='number of days of information overhead')
parser.add_argument('--news_pre_embed', type=int, default=1, help='whether to use pre-embedded news')
parser.add_argument('--des_pre_embed', type=int, default=0, help='whether to use pre-embedded description')
parser.add_argument('--add_date', type=int, default=1, help='whether to add date to the description')
parser.add_argument('--text_encoder', type=str, default='paraphrase-MiniLM-L6-v2', help='text encoder for news and description')

parser.add_argument('--zero_news', action='store_true', default=False, help='zero embedding for news')
parser.add_argument('--zero_des', action='store_true', default=False, help='zero embedding for description')

# TGTSF setting
parser.add_argument('--text_dim', type=int, default=384, help='model dim of text encoder')
parser.add_argument('--cross_layers', type=int, default=3, help='cross attention layers')
parser.add_argument('--self_layers', type=int, default=3, help='self attention layers')
parser.add_argument('--finetune', type=int, default=0, help='self attention layers')
parser.add_argument('--out_attn_weights', type=int, default=0, help='whether output the mix attn weights')
parser.add_argument('--mixer_self_layers', type=int, default=0, help='decoder self attention layers')
parser.add_argument('--mixer_cross_layers', type=int, default=0, help='decoder self attention layers')
parser.add_argument('--mixer_type', type=str, default='cross', help='text encoder for news and description')

# 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')


# DLinear
#parser.add_argument('--individual', action='store_true', default=False, help='DLinear: a linear layer for each variate(channel) individually')

# PatchTST
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='end', 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('--notrans', action='store_true', default=False, help='stop using transformer')

# 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')

# optimization
parser.add_argument('--num_workers', type=int, default=2, 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=128, help='batch size of train input data')
parser.add_argument('--patience', type=int, default=100, 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='test', 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)

# 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')

# TGTSF

# Augmentation
parser.add_argument('--aug_method', type=str, default='NA', help='f_mask: Frequency Masking, f_mix: Frequency Mixing')
parser.add_argument('--aug_rate', type=float, default=0.5, help='mask/mix rate')
parser.add_argument('--in_batch_augmentation', action='store_true', help='Augmentation in Batch (save memory cost)', default=False)
parser.add_argument('--in_dataset_augmentation', action='store_true', help='Augmentation in Dataset', default=False)
parser.add_argument('--data_size', type=float, default=1, help='size of dataset, i.e, 0.01 represents uses 1 persent samples in the dataset')
parser.add_argument('--aug_data_size', type=int, default=1, help='size of augmented data, i.e, 1 means double the size of dataset')


if __name__ == '__main__':

    # try:
    #     torch.multiprocessing.set_start_method('spawn')
    # except:
    #     pass

    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]

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

    Exp = Exp_Main

    if args.is_training:
        for ii in range(args.itr):
            # setting record of experiments
            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('>>>>>>>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()