import argparse
import os
import torch
import json

from exp.exp_informer import Exp_Informer

from distutils.dir_util import copy_tree
import shutil

import dist.sm_dist as sm_dist

def arg_setting():
    parser = argparse.ArgumentParser(description='[Informer] Long Sequences Forecasting')

    parser.add_argument('--model', type=str, required=True, default='informer',help='model of experiment, options: [informer, informerstack, informerlight(TBD)]')

    parser.add_argument('--data', type=str, required=True, default='ETTh1', help='data')
    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('--seq_len', type=int, default=96, help='input sequence length of Informer encoder')
    parser.add_argument('--label_len', type=int, default=48, help='start token length of Informer decoder')
    parser.add_argument('--pred_len', type=int, default=24, help='prediction sequence length')
    # Informer decoder input: concat[start token series(label_len), zero padding series(pred_len)]

    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('--s_layers', type=str, default='3,2,1', help='num of stack encoder layers')
    parser.add_argument('--d_ff', type=int, default=2048, help='dimension of fcn')
    parser.add_argument('--factor', type=int, default=5, help='probsparse attn factor')
    parser.add_argument('--padding', type=int, default=0, help='padding type')
    parser.add_argument('--distil', type=lambda s:s.lower() in ['false', 'f', 'no', '0'], 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('--attn', type=str, default='prob', help='attention used in encoder, options:[prob, full]')
    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', type=lambda s:s.lower() in ['true', 't', 'yes', '1'], help='whether to output attention in ecoder', default=False)
    parser.add_argument('--do_predict', type=lambda s:s.lower() in ['true', 't', 'yes', '1'], help='whether to predict unseen future data', default=False)
    parser.add_argument('--mix', type=lambda s:s.lower() in ['false', 'f', 'no', '0'], help='use mix attention in generative decoder', default=True)
    parser.add_argument('--cols', type=str, nargs='+', help='certain cols from the data files as the input features')
    parser.add_argument('--num_workers', type=int, default=0, help='data loader num workers')
    parser.add_argument('--itr', type=int, default=2, help='experiments times')
    parser.add_argument('--train_epochs', type=int, default=6, 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', type=lambda s:s.lower() in ['true', 't', 'yes', '1'], help='use automatic mixed precision training', default=False)
    parser.add_argument('--inverse', type=lambda s:s.lower() in ['true', 't', 'yes', '1'], help='inverse output data', default=False)

    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=lambda s:s.lower() in ['true', 't', 'yes', '1'], 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()
    return args


def check_sagemaker(args):
    ## SageMaker
    print(f"os.environ.get('SM_CHANNEL_TRAINING') : {os.environ['SM_CHANNEL_TRAINING']}")
    print(f"os.environ['SM_MODEL_DIR'] : {os.environ['SM_MODEL_DIR']}")
    print(f"os.environ['SM_NUM_GPUS'] : {os.environ['SM_NUM_GPUS']}")
    print(f"json.loads(os.environ['SM_HOSTS']) : {json.loads(os.environ['SM_HOSTS'])}")
    print(f" os.environ['SM_CURRENT_HOST'] : {os.environ['SM_CURRENT_HOST']}")

    if os.environ.get('SM_MODEL_DIR') is not None:
        args.root_path = os.environ['SM_CHANNEL_TRAINING']+args.root_path
        args.checkpoints = "/opt/ml/checkpoints"
    return args


def main(args):
        
    args.use_gpu = True if torch.cuda.is_available() else False
    args.device = torch.device("cuda" if args.use_gpu else "cpu")
    
    if args.use_gpu:
        print(f"args.use_multi_gpu : {args.use_multi_gpu}")
        if args.use_multi_gpu:
            ## 1. dist_set
            args = sm_dist.dist_set(args)
        else:
#             args.devices = args.devices.replace(' ','')
#             device_ids = args.devices.split(',')
#             args.device_ids = [int(id_) for id_ in device_ids]
#             args.gpu = args.device_ids[0]
#             args.devices = '0,1,2,3,4,5,6,7'
            args.local_rank = 0
            args.rank = 0
            args.gpu = 0
    else:
        print("No GPU")
        args.local_rank = 0
        args.rank = 0
        
        
    data_parser = {
        'bikeshare':{'data':'informer_dataset.csv','T':'demand','M':[11,11,11],'S':[1,1,1],'MS':[7,7,1]},
        'ETTh1':{'data':'ETTh1.csv','T':'OT','M':[7,7,7],'S':[1,1,1],'MS':[7,7,1]},
        'ETTh2':{'data':'ETTh2.csv','T':'OT','M':[7,7,7],'S':[1,1,1],'MS':[7,7,1]},
        'ETTm1':{'data':'ETTm1.csv','T':'OT','M':[7,7,7],'S':[1,1,1],'MS':[7,7,1]},
        'ETTm2':{'data':'ETTm2.csv','T':'OT','M':[7,7,7],'S':[1,1,1],'MS':[7,7,1]},
        'WTH':{'data':'WTH.csv','T':'WetBulbCelsius','M':[12,12,12],'S':[1,1,1],'MS':[12,12,1]},
        'ECL':{'data':'ECL.csv','T':'MT_320','M':[321,321,321],'S':[1,1,1],'MS':[321,321,1]},
        'Solar':{'data':'solar_AL.csv','T':'POWER_136','M':[137,137,137],'S':[1,1,1],'MS':[137,137,1]},
    }
    if args.data in data_parser.keys():
        data_info = data_parser[args.data]
        args.data_path = data_info['data']
        args.target = data_info['T']
        args.enc_in, args.dec_in, args.c_out = data_info[args.features]

    args.s_layers = [int(s_l) for s_l in args.s_layers.replace(' ','').split(',')]
    args.detail_freq = args.freq
    args.freq = args.freq[-1:]

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

    Exp = Exp_Informer

    for ii in range(args.itr):
        # setting record of experiments
        setting = '{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_at{}_fc{}_eb{}_dt{}_mx{}_{}_{}'.format(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.attn, args.factor, 
                    args.embed, args.distil, args.mix, 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()
    print("End of Exp")
    ## copy code to model.tar.gz for predictor/inference
    
    if args.rank==0:
        copy_tree(f"/opt/ml/checkpoints/{setting}", os.path.join(os.environ['SM_MODEL_DIR'],setting))
        copy_tree("/opt/ml/checkpoints/results", os.path.join(os.environ['SM_MODEL_DIR'],"results"))
        shutil.copyfile("/opt/ml/checkpoints/test_report.json", os.environ['SM_MODEL_DIR'] + "/test_report.json")
        copy_tree("/opt/ml/code", os.environ['SM_MODEL_DIR'])
if __name__ == '__main__':
    args = arg_setting()
    args = check_sagemaker(args)

    main(args)