Upload 7 files

checkpoints

@@ -0,0 +1,20 @@
+<script>start("/Users/inertia/Desktop/tide_prediction_project/TimeXer-main/checkpoints/");</script>
+<script>onHasParentDirectory();</script>
+<script>addRow("long_term_forecast_DT_0001_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0001_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0002_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0002_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0003_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0003_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0008_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0008_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0017_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0017_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0018_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0018_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0024_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0024_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0025_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0025_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0037_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0037_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0043_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0043_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0050_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0050_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0051_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0051_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0052_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0052_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0065_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0065_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0066_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0066_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0067_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0067_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow("long_term_forecast_DT_0068_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0","long_term_forecast_DT_0068_144_72_TimeXer_TIDE_ftMS_sl144_ll96_pl72_dm256_nh8_el1_dl1_df512_expand2_dc4_fc3_ebtimeF_dtTrue_Exp_0",1,128,"128 B",1753578822,"7/27/25, 10:13:42 AM");</script>
+<script>addRow(".DS_Store",".DS_Store",0,6148,"6.0 kB",1753578849,"7/27/25, 10:14:09 AM");</script>

data_provider

@@ -0,0 +1,8 @@
+<script>start("/Users/inertia/Desktop/tide_prediction_project/TimeXer-main/data_provider/");</script>
+<script>onHasParentDirectory();</script>
+<script>addRow("__pycache__","__pycache__",1,224,"224 B",1752058048,"7/9/25, 7:47:28 PM");</script>
+<script>addRow("__init__.py","__init__.py",0,1,"1 B",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("data_factory.py","data_factory.py",0,1953,"1.9 kB",1753163478,"7/22/25, 2:51:18 PM");</script>
+<script>addRow("data_loader.py","data_loader.py",0,43957,"42.9 kB",1753164809,"7/22/25, 3:13:29 PM");</script>
+<script>addRow("m4.py","m4.py",0,4451,"4.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("uea.py","uea.py",0,5036,"4.9 kB",1732692345,"11/27/24, 4:25:45 PM");</script>

layers

@@ -0,0 +1,16 @@
+<script>start("/Users/inertia/Desktop/tide_prediction_project/TimeXer-main/layers/");</script>
+<script>onHasParentDirectory();</script>
+<script>addRow("__pycache__","__pycache__",1,480,"480 B",1752058061,"7/9/25, 7:47:41 PM");</script>
+<script>addRow("__init__.py","__init__.py",0,0,"0 B",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("AutoCorrelation.py","AutoCorrelation.py",0,6440,"6.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Autoformer_EncDec.py","Autoformer_EncDec.py",0,6831,"6.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Conv_Blocks.py","Conv_Blocks.py",0,2376,"2.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Crossformer_EncDec.py","Crossformer_EncDec.py",0,4333,"4.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Embed.py","Embed.py",0,7025,"6.9 kB",1752042645,"7/9/25, 3:30:45 PM");</script>
+<script>addRow("ETSformer_EncDec.py","ETSformer_EncDec.py",0,11433,"11.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("FourierCorrelation.py","FourierCorrelation.py",0,7346,"7.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("MultiWaveletCorrelation.py","MultiWaveletCorrelation.py",0,23039,"22.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Pyraformer_EncDec.py","Pyraformer_EncDec.py",0,7433,"7.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("SelfAttention_Family.py","SelfAttention_Family.py",0,12001,"11.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("StandardNorm.py","StandardNorm.py",0,2184,"2.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Transformer_EncDec.py","Transformer_EncDec.py",0,4929,"4.8 kB",1732692345,"11/27/24, 4:25:45 PM");</script>

models

@@ -0,0 +1,31 @@
+<script>start("/Users/inertia/Desktop/tide_prediction_project/TimeXer-main/models/");</script>
+<script>onHasParentDirectory();</script>
+<script>addRow("__pycache__","__pycache__",1,928,"928 B",1752058061,"7/9/25, 7:47:41 PM");</script>
+<script>addRow("__init__.py","__init__.py",0,0,"0 B",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Autoformer.py","Autoformer.py",0,6815,"6.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Crossformer.py","Crossformer.py",0,6363,"6.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("DLinear.py","DLinear.py",0,4501,"4.4 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("ETSformer.py","ETSformer.py",0,4599,"4.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("FEDformer.py","FEDformer.py",0,8449,"8.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("FiLM.py","FiLM.py",0,11567,"11.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("FreTS.py","FreTS.py",0,4630,"4.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Informer.py","Informer.py",0,6395,"6.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("iTransformer.py","iTransformer.py",0,5735,"5.6 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Koopa.py","Koopa.py",0,13374,"13.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("LightTS.py","LightTS.py",0,5671,"5.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Mamba.py","Mamba.py",0,1590,"1.6 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("MambaSimple.py","MambaSimple.py",0,5493,"5.4 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("MICN.py","MICN.py",0,9901,"9.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Nonstationary_Transformer.py","Nonstationary_Transformer.py",0,9719,"9.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("PatchTST.py","PatchTST.py",0,9071,"8.9 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Pyraformer.py","Pyraformer.py",0,4215,"4.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("Reformer.py","Reformer.py",0,5090,"5.0 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("SCINet.py","SCINet.py",0,7357,"7.2 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("SegRNN.py","SegRNN.py",0,4215,"4.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TemporalFusionTransformer.py","TemporalFusionTransformer.py",0,14027,"13.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TiDE.py","TiDE.py",0,7222,"7.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TimeMixer.py","TimeMixer.py",0,20024,"19.6 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TimesNet.py","TimesNet.py",0,8684,"8.5 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TimeXer.py","TimeXer.py",0,9259,"9.0 kB",1752469382,"7/14/25, 2:03:02 PM");</script>
+<script>addRow("Transformer.py","Transformer.py",0,5561,"5.4 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("TSMixer.py","TSMixer.py",0,1814,"1.8 kB",1732692345,"11/27/24, 4:25:45 PM");</script>

requirements.txt

@@ -0,0 +1,13 @@
+einops
+joblib
+matplotlib==3.7.0
+numpy==1.23.5
+pandas==1.5.3
+patool==1.12
+reformer-pytorch==1.4.4
+scikit-learn==1.2.2
+scipy==1.10.1
+sktime==0.16.1
+sympy==1.11.1
+torch==2.0.0
+tqdm==4.64.1

run.py

@@ -0,0 +1,227 @@
+import argparse
+import os
+import torch
+from exp.exp_long_term_forecasting import Exp_Long_Term_Forecast
+from exp.exp_imputation import Exp_Imputation
+from exp.exp_short_term_forecasting import Exp_Short_Term_Forecast
+from exp.exp_anomaly_detection import Exp_Anomaly_Detection
+from exp.exp_classification import Exp_Classification
+from utils.print_args import print_args
+import random
+import numpy as np
+
+if __name__ == '__main__':
+    fix_seed = 2021
+    random.seed(fix_seed)
+    torch.manual_seed(fix_seed)
+    np.random.seed(fix_seed)
+
+    parser = argparse.ArgumentParser(description='TimesNet')
+
+    # basic config
+    parser.add_argument('--task_name', type=str, required=True, default='long_term_forecast',
+                        help='task name, options:[long_term_forecast, short_term_forecast, imputation, classification, anomaly_detection]')
+    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, Transformer, TimesNet]')
+
+    # 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='residual', help='target feature in S or MS task')
+    parser.add_argument('--freq', type=str, default='t',
+                        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')
+    parser.add_argument('--seasonal_patterns', type=str, default='Monthly', help='subset for M4')
+    parser.add_argument('--inverse', action='store_true', help='inverse output data', default=True)
+
+    # inputation task
+    parser.add_argument('--mask_rate', type=float, default=0.25, help='mask ratio')
+
+    # anomaly detection task
+    parser.add_argument('--anomaly_ratio', type=float, default=0.25, help='prior anomaly ratio (%)')
+
+    # model define
+    parser.add_argument('--expand', type=int, default=2, help='expansion factor for Mamba')
+    parser.add_argument('--d_conv', type=int, default=4, help='conv kernel size for Mamba')
+    parser.add_argument('--top_k', type=int, default=5, help='for TimesBlock')
+    parser.add_argument('--num_kernels', type=int, default=6, help='for Inception')
+    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=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=0.1, 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('--channel_independence', type=int, default=1,
+                        help='0: channel dependence 1: channel independence for FreTS model')
+    parser.add_argument('--decomp_method', type=str, default='moving_avg',
+                        help='method of series decompsition, only support moving_avg or dft_decomp')
+    parser.add_argument('--use_norm', type=int, default=1, help='whether to use normalize; True 1 False 0')
+    parser.add_argument('--down_sampling_layers', type=int, default=0, help='num of down sampling layers')
+    parser.add_argument('--down_sampling_window', type=int, default=1, help='down sampling window size')
+    parser.add_argument('--down_sampling_method', type=str, default=None,
+                        help='down sampling method, only support avg, max, conv')
+    parser.add_argument('--seg_len', type=int, default=48,
+                        help='the length of segmen-wise iteration of SegRNN')
+
+    # optimization
+    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=20, 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')
+
+    # de-stationary projector params
+    parser.add_argument('--p_hidden_dims', type=int, nargs='+', default=[128, 128],
+                        help='hidden layer dimensions of projector (List)')
+    parser.add_argument('--p_hidden_layers', type=int, default=2, help='number of hidden layers in projector')
+
+    # metrics (dtw)
+    parser.add_argument('--use_dtw', type=bool, default=False,
+                        help='the controller of using dtw metric (dtw is time consuming, not suggested unless necessary)')
+
+    # Augmentation
+    parser.add_argument('--augmentation_ratio', type=int, default=0, help="How many times to augment")
+    parser.add_argument('--seed', type=int, default=2, help="Randomization seed")
+    parser.add_argument('--jitter', default=False, action="store_true", help="Jitter preset augmentation")
+    parser.add_argument('--scaling', default=False, action="store_true", help="Scaling preset augmentation")
+    parser.add_argument('--permutation', default=False, action="store_true",
+                        help="Equal Length Permutation preset augmentation")
+    parser.add_argument('--randompermutation', default=False, action="store_true",
+                        help="Random Length Permutation preset augmentation")
+    parser.add_argument('--magwarp', default=False, action="store_true", help="Magnitude warp preset augmentation")
+    parser.add_argument('--timewarp', default=False, action="store_true", help="Time warp preset augmentation")
+    parser.add_argument('--windowslice', default=False, action="store_true", help="Window slice preset augmentation")
+    parser.add_argument('--windowwarp', default=False, action="store_true", help="Window warp preset augmentation")
+    parser.add_argument('--rotation', default=False, action="store_true", help="Rotation preset augmentation")
+    parser.add_argument('--spawner', default=False, action="store_true", help="SPAWNER preset augmentation")
+    parser.add_argument('--dtwwarp', default=False, action="store_true", help="DTW warp preset augmentation")
+    parser.add_argument('--shapedtwwarp', default=False, action="store_true", help="Shape DTW warp preset augmentation")
+    parser.add_argument('--wdba', default=False, action="store_true", help="Weighted DBA preset augmentation")
+    parser.add_argument('--discdtw', default=False, action="store_true",
+                        help="Discrimitive DTW warp preset augmentation")
+    parser.add_argument('--discsdtw', default=False, action="store_true",
+                        help="Discrimitive shapeDTW warp preset augmentation")
+    parser.add_argument('--extra_tag', type=str, default="", help="Anything extra")
+
+    # TimeXer
+    parser.add_argument('--patch_len', type=int, default=16, help='patch length')
+
+    args = parser.parse_args()
+    # args.use_gpu = True if torch.cuda.is_available() and args.use_gpu else False
+    args.use_gpu = True if torch.cuda.is_available() else False
+
+    print(torch.cuda.is_available())
+
+    if args.use_gpu and args.use_multi_gpu:
+        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]
+
+    print('Args in experiment:')
+    print_args(args)
+
+    if args.task_name == 'long_term_forecast':
+        Exp = Exp_Long_Term_Forecast
+    elif args.task_name == 'short_term_forecast':
+        Exp = Exp_Short_Term_Forecast
+    elif args.task_name == 'imputation':
+        Exp = Exp_Imputation
+    elif args.task_name == 'anomaly_detection':
+        Exp = Exp_Anomaly_Detection
+    elif args.task_name == 'classification':
+        Exp = Exp_Classification
+    else:
+        Exp = Exp_Long_Term_Forecast
+
+    if args.is_training:
+        for ii in range(args.itr):
+            # setting record of experiments
+            exp = Exp(args)  # set experiments
+            setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_expand{}_dc{}_fc{}_eb{}_dt{}_{}_{}'.format(
+                args.task_name,
+                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.expand,
+                args.d_conv,
+                args.factor,
+                args.embed,
+                args.distil,
+                args.des, ii)
+
+            print('>>>>>>>start training : {}>>>>>>>>>>>>>>>>>>>>>>>>>>'.format(setting))
+            exp.train(setting)
+
+            print('>>>>>>>testing : {}<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<'.format(setting))
+            exp.test(setting)
+            torch.cuda.empty_cache()
+    else:
+        ii = 0
+        setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_expand{}_dc{}_fc{}_eb{}_dt{}_{}_{}'.format(
+            args.task_name,
+            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.expand,
+            args.d_conv,
+            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()

utils

@@ -0,0 +1,12 @@
+<script>start("/Users/inertia/Desktop/tide_prediction_project/TimeXer-main/utils/");</script>
+<script>onHasParentDirectory();</script>
+<script>addRow("__pycache__","__pycache__",1,352,"352 B",1752058061,"7/9/25, 7:47:41 PM");</script>
+<script>addRow("__init__.py","__init__.py",0,0,"0 B",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("augmentation.py","augmentation.py",0,20122,"19.7 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("losses.py","losses.py",0,3459,"3.4 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("m4_summary.py","m4_summary.py",0,6174,"6.0 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("masking.py","masking.py",0,11384,"11.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("metrics.py","metrics.py",0,930,"930 B",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("print_args.py","print_args.py",0,3139,"3.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("timefeatures.py","timefeatures.py",0,4369,"4.3 kB",1732692345,"11/27/24, 4:25:45 PM");</script>
+<script>addRow("tools.py","tools.py",0,6236,"6.1 kB",1732692345,"11/27/24, 4:25:45 PM");</script>