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


def set_seed(seed):
    random.seed(seed)
    seed += 1
    np.random.seed(seed)
    seed += 1
    torch.manual_seed(seed)


def get_args(argv=None):
    parser = argparse.ArgumentParser(description='ETSformer: Exponential Smoothing Transformers for Time-series Forecasting')

    # basic config
    parser.add_argument('--model_id', type=str, required=True, default='test', help='model id')
    parser.add_argument('--model', type=str, required=True, default='ETSformer',
                        help='model name, options: [ETSformer]')

    # 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, required=True, help='input sequence length')
    parser.add_argument('--label_len', type=int, default=0, help='start token length')
    parser.add_argument('--pred_len', type=int, required=True, help='prediction sequence length')

    # 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('--K', type=int, default=1, help='Top-K Fourier bases')
    parser.add_argument('--dropout', type=float, default=0.2, 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='sigmoid', help='activation')

    parser.add_argument('--min_lr', type=float, default=1e-30)
    parser.add_argument('--warmup_epochs', type=int, default=3)
    parser.add_argument('--std', type=float, default=0.2)

    parser.add_argument('--smoothing_learning_rate', type=float, default=0, help='optimizer learning rate')
    parser.add_argument('--damping_learning_rate', type=float, default=0, help='optimizer learning rate')
    parser.add_argument('--output_attention', type=bool, default=False)

    # optimization
    parser.add_argument('--optim', type=str, default='adam', help='optimizer')
    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=15, 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=5, help='early stopping patience')
    parser.add_argument('--learning_rate', type=float, default=1e-4, help='optimizer learning rate')
    parser.add_argument('--des', type=str, default='test', help='exp description')
    parser.add_argument('--lradj', type=str, default='exponential_with_warmup', help='adjust learning rate')

    # 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')

    args = parser.parse_args(argv)

    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)
    return args

if __name__=="__main__":
    
    args = get_args()

    Exp = Exp_Main

    for ii in range(args.itr):
        set_seed(ii)
        # setting record of experiments
        setting = '{}_{}_{}_ft{}_sl{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_K{}_lr{}_{}_{}'.format(
            args.model_id,
            args.model,
            args.data,
            args.features,
            args.seq_len,
            args.pred_len,
            args.d_model,
            args.n_heads,
            args.e_layers,
            args.d_layers,
            args.d_ff,
            args.K,
            args.learning_rate,
            args.des, ii)

        if os.path.exists(os.path.join(args.checkpoints, setting)):
            continue

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

        print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
        exp.test(setting, data='val')
        exp.test(setting, data='test')

        torch.cuda.empty_cache()