-
Notifications
You must be signed in to change notification settings - Fork 1
/
run.py
173 lines (154 loc) · 8.81 KB
/
run.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
import argparse
import os
import torch
from exp.exp_long_term_forecasting import Exp_Long_Term_Forecast
from exp.exp_short_term_forecasting import Exp_Short_Term_Forecast
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 = 47
random.seed(fix_seed)
torch.manual_seed(fix_seed)
np.random.seed(fix_seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(fix_seed) # For current GPU
torch.cuda.manual_seed_all(fix_seed) # For all GPUs, if you are using more than one
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, classification]')
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='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, 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=False)
parser.add_argument('--d_state', type=int, default=16, help='d_state for Mamba')
parser.add_argument('--d_conv', type=int, default=4, help='d_conv for Mamba')
parser.add_argument('--expand', type=int, default=3, help='expand for Mamba')
parser.add_argument('--patch_len', type=int, default=16, help='size of the patch')
parser.add_argument('--stride', type=int, default=8, help='stride for patching')
parser.add_argument('--moe_hidden_factor', type=int, default=2, help='factor for scaling the hidden dim in MoE')
parser.add_argument('--num_experts', type=int, default=16, help='number of experts')
parser.add_argument('--num_gates', type=int, default=2, help='number of experts')
parser.add_argument('--revin', action='store_true', help='inverse normalization', default=False)
parser.add_argument('--use_norm', type=int, default=True, help='use norm and denorm')
# 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('--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('--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('--moving_avg', type=int, default=25, help='window size of moving average')
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('--channel_independence', type=int, default=0,
help='1: channel dependence 0: channel independence for FreTS model')
# 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=5, 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')
args = parser.parse_args()
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.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{}_eb{}_{}_{}'.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.embed,
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{}_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.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()