#      Hyperparameter Settings
#     parser.add_argument('--window_size', type=int, default=5, help='Size of the sliding window')
# 
#     # 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='Transformer',
#                         help='model name, options: [Autoformer, Informer, Transformer]')
# 
#     # data loader
#     parser.add_argument('--data', type=str, required=True, default='aaa', help='dataset type')
#     parser.add_argument('--root_path', type=str, default='./data/', help='root path of the data file')
#     parser.add_argument('--data_path', type=str, default='aaa.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='t', help='target feature in S or MS task')
#     parser.add_argument('--freq', type=str, default='s',
#                         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('--gnn_out_channels', type=int, default=64, help='input sequence length')
#     parser.add_argument('--gnn_layer_type', type=str, default='GCN', help='input sequence length')
#     # forecasting task   #    ITransformer  回望窗口大小
# 
#     parser.add_argument('--seq_len', type=int, default=384, 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')
#     # 分块
#     parser.add_argument('--patch_len', type=int, default=112, help='prediction sequence length')
#     parser.add_argument('--stride', type=int, default=3, help='prediction sequence length')
#     parser.add_argument('--patch_size_list', nargs='+', type=int, default=[6, 4, 3, 2, 1])
# 
#     # model define
#     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('--enc_in', type=int, default=3, help='encoder input size')
#     parser.add_argument('--dec_in', type=int, default=3, help='decoder input size')
#     parser.add_argument('--c_out', type=int, default=3, 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 encoder')
#     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=2, 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='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', 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')

