File size: 19,186 Bytes
493bf96 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | from data_provider.data_factory import data_provider
from experiments.exp_basic import Exp_Basic
from utils.tools import EarlyStopping, adjust_learning_rate, visual
from utils.metrics import metric
import torch
import torch.nn as nn
from torch import optim
import os
import time
import warnings
import pdb
import numpy as np
import random
warnings.filterwarnings('ignore')
# train on partial variate data and test on the full variates, used for two types of experiments:
# (1) Generalize on unseen variate (Figure 5 of our paper)
# (2) Efficient training strategy (Figure 8 of our paper)
class Exp_Long_Term_Forecast_Partial(Exp_Basic):
def __init__(self, args):
super(Exp_Long_Term_Forecast_Partial, self).__init__(args)
def _build_model(self):
model = self.model_dict[self.args.model].Model(self.args).float()
if self.args.use_multi_gpu and self.args.use_gpu:
model = nn.DataParallel(model, device_ids=self.args.device_ids)
return model
def _get_data(self, flag):
data_set, data_loader = data_provider(self.args, flag)
return data_set, data_loader
def _select_optimizer(self):
model_optim = optim.Adam(self.model.parameters(), lr=self.args.learning_rate)
return model_optim
def _select_criterion(self):
criterion = nn.MSELoss()
return criterion
def vali(self, vali_data, vali_loader, criterion, partial_train=False):
total_loss = []
self.model.eval()
with torch.no_grad():
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(vali_loader):
batch_x = batch_x.float().to(self.device)
batch_y = batch_y.float()
if 'PEMS' in self.args.data or 'Solar' in self.args.data:
batch_x_mark = None
batch_y_mark = None
else:
batch_x_mark = batch_x_mark.float().to(self.device)
batch_y_mark = batch_y_mark.float().to(self.device)
if partial_train: # we train models with only partial variates from the dataset
partial_start = self.args.partial_start_index
partial_end = min(self.args.enc_in + partial_start, batch_x.shape[-1])
batch_x = batch_x[:, :, partial_start:partial_end]
batch_y = batch_y[:, :, partial_start:partial_end]
# decoder input
dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
# encoder - decoder
if self.args.use_amp:
with torch.cuda.amp.autocast():
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
else:
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
elif self.args.channel_independence:
B, Tx, N = batch_x.shape
_, Ty, _ = dec_inp.shape
if batch_x_mark == None:
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1), batch_x_mark, \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1), batch_y_mark).reshape(
B, N, -1).permute(0, 2, 1)
else:
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1),
batch_x_mark.repeat(N, 1, 1), \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1),
batch_y_mark.repeat(N, 1, 1)) \
.reshape(B, N, -1).permute(0, 2, 1)
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
pred = outputs.detach().cpu()
true = batch_y.detach().cpu()
loss = criterion(pred, true)
total_loss.append(loss)
total_loss = np.average(total_loss)
self.model.train()
return total_loss
def train(self, setting):
train_data, train_loader = self._get_data(flag='train')
vali_data, vali_loader = self._get_data(flag='val')
test_data, test_loader = self._get_data(flag='test')
path = os.path.join(self.args.checkpoints, setting)
if not os.path.exists(path):
os.makedirs(path)
time_now = time.time()
train_steps = len(train_loader)
early_stopping = EarlyStopping(patience=self.args.patience, verbose=True)
model_optim = self._select_optimizer()
criterion = self._select_criterion()
if self.args.use_amp:
scaler = torch.cuda.amp.GradScaler()
for epoch in range(self.args.train_epochs):
iter_count = 0
train_loss = []
self.model.train()
epoch_time = time.time()
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(train_loader):
iter_count += 1
model_optim.zero_grad()
batch_x = batch_x.float().to(self.device)
batch_y = batch_y.float().to(self.device)
if 'PEMS' in self.args.data or 'Solar' in self.args.data:
batch_x_mark = None
batch_y_mark = None
else:
batch_x_mark = batch_x_mark.float().to(self.device)
batch_y_mark = batch_y_mark.float().to(self.device)
# Variate Generalization training:
# We train with partial variates (args.enc_in < number of dataset variates)
# and test the obtained model directly on all variates.
partial_start = self.args.partial_start_index
partial_end = min(self.args.enc_in + partial_start, batch_x.shape[-1])
batch_x = batch_x[:, :, partial_start:partial_end]
batch_y = batch_y[:, :, partial_start:partial_end]
# Efficient training strategy: randomly choose part of the variates
# and only train the model with selected variates in each batch
if self.args.efficient_training:
_, _, N = batch_x.shape
index = np.stack(random.sample(range(N), N))[-self.args.enc_in:]
batch_x = batch_x[:, :, index]
batch_y = batch_y[:, :, index]
# decoder input
dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
# encoder - decoder
if self.args.use_amp:
with torch.cuda.amp.autocast():
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
loss = criterion(outputs, batch_y)
train_loss.append(loss.item())
else:
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
elif self.args.channel_independence:
B, Tx, N = batch_x.shape
_, Ty, _ = dec_inp.shape
if batch_x_mark == None:
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1), batch_x_mark, \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1), batch_y_mark).reshape(
B, N, -1).permute(0, 2, 1)
else:
a = batch_x.permute(0, 2, 1)
b = batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1)
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1),
batch_x_mark.repeat(N, 1, 1), \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1),
batch_y_mark.repeat(N, 1, 1)) \
.reshape(B, N, -1).permute(0, 2, 1)
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
loss = criterion(outputs, batch_y)
train_loss.append(loss.item())
if (i + 1) % 100 == 0:
print("\titers: {0}, epoch: {1} | loss: {2:.7f}".format(i + 1, epoch + 1, loss.item()))
speed = (time.time() - time_now) / iter_count
left_time = speed * ((self.args.train_epochs - epoch) * train_steps - i)
print('\tspeed: {:.4f}s/iter; left time: {:.4f}s'.format(speed, left_time))
iter_count = 0
time_now = time.time()
if self.args.use_amp:
scaler.scale(loss).backward()
scaler.step(model_optim)
scaler.update()
else:
loss.backward()
model_optim.step()
print("Epoch: {} cost time: {}".format(epoch + 1, time.time() - epoch_time))
train_loss = np.average(train_loss)
vali_loss = self.vali(vali_data, vali_loader, criterion, partial_train=True)
test_loss = self.vali(test_data, test_loader, criterion, partial_train=False)
print("Epoch: {0}, Steps: {1} | Train Loss: {2:.7f} Vali Loss: {3:.7f} Test Loss: {4:.7f}".format(
epoch + 1, train_steps, train_loss, vali_loss, test_loss))
early_stopping(vali_loss, self.model, path)
if early_stopping.early_stop:
print("Early stopping")
break
adjust_learning_rate(model_optim, epoch + 1, self.args)
best_model_path = path + '/' + 'checkpoint.pth'
self.model.load_state_dict(torch.load(best_model_path))
return self.model
def test(self, setting, test=0):
test_data, test_loader = self._get_data(flag='test')
if test:
print('loading model')
self.model.load_state_dict(torch.load(os.path.join('./checkpoints/' + setting, 'checkpoint.pth')))
preds = []
trues = []
folder_path = './test_results/' + setting + '/'
if not os.path.exists(folder_path):
os.makedirs(folder_path)
self.model.eval()
with torch.no_grad():
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(test_loader):
# During model inference, test the obtained model directly on all variates.
batch_x = batch_x.float().to(self.device)
batch_y = batch_y.float().to(self.device)
if 'PEMS' in self.args.data or 'Solar' in self.args.data:
batch_x_mark = None
batch_y_mark = None
else:
batch_x_mark = batch_x_mark.float().to(self.device)
batch_y_mark = batch_y_mark.float().to(self.device)
# decoder input
dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
# encoder - decoder
if self.args.use_amp:
with torch.cuda.amp.autocast():
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
else:
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
elif self.args.channel_independence: # compare the result with channel_independence
B, Tx, N = batch_x.shape
_, Ty, _ = dec_inp.shape
if batch_x_mark == None:
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1), batch_x_mark, \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1), batch_y_mark).reshape(
B, N, -1).permute(0, 2, 1)
else:
outputs = self.model(batch_x.permute(0, 2, 1).reshape(B * N, Tx, 1),
batch_x_mark.repeat(N, 1, 1), \
dec_inp.permute(0, 2, 1).reshape(B * N, Ty, 1),
batch_y_mark.repeat(N, 1, 1)) \
.reshape(B, N, -1).permute(0, 2, 1)
else:
# directly test the trained model on all variates without fine-tuning.
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, -self.args.pred_len:, f_dim:]
batch_y = batch_y[:, -self.args.pred_len:, f_dim:].to(self.device)
outputs = outputs.detach().cpu().numpy()
batch_y = batch_y.detach().cpu().numpy()
if test_data.scale and self.args.inverse:
shape = outputs.shape
outputs = test_data.inverse_transform(outputs.squeeze(0)).reshape(shape)
batch_y = test_data.inverse_transform(batch_y.squeeze(0)).reshape(shape)
pred = outputs
true = batch_y
preds.append(pred)
trues.append(true)
if i % 20 == 0:
input = batch_x.detach().cpu().numpy()
if test_data.scale and self.args.inverse:
shape = input.shape
input = test_data.inverse_transform(input.squeeze(0)).reshape(shape)
gt = np.concatenate((input[0, :, -1], true[0, :, -1]), axis=0)
pd = np.concatenate((input[0, :, -1], pred[0, :, -1]), axis=0)
visual(gt, pd, os.path.join(folder_path, str(i) + '.pdf'))
preds = np.array(preds)
trues = np.array(trues)
print('test shape:', preds.shape, trues.shape)
preds = preds.reshape(-1, preds.shape[-2], preds.shape[-1])
trues = trues.reshape(-1, trues.shape[-2], trues.shape[-1])
print('test shape:', preds.shape, trues.shape)
# result save
folder_path = './results/' + setting + '/'
if not os.path.exists(folder_path):
os.makedirs(folder_path)
mae, mse, rmse, mape, mspe = metric(preds, trues)
print('mse:{}, mae:{}'.format(mse, mae))
f = open("result_long_term_forecast.txt", 'a')
f.write(setting + " \n")
f.write('mse:{}, mae:{}'.format(mse, mae))
f.write('\n')
f.write('\n')
f.close()
np.save(folder_path + 'metrics.npy', np.array([mae, mse, rmse, mape, mspe]))
np.save(folder_path + 'pred.npy', preds)
np.save(folder_path + 'true.npy', trues)
return
def predict(self, setting, load=False):
pred_data, pred_loader = self._get_data(flag='pred')
if load:
path = os.path.join(self.args.checkpoints, setting)
best_model_path = path + '/' + 'checkpoint.pth'
self.model.load_state_dict(torch.load(best_model_path))
preds = []
self.model.eval()
with torch.no_grad():
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(pred_loader):
batch_x = batch_x.float().to(self.device)
batch_y = batch_y.float()
batch_x_mark = batch_x_mark.float().to(self.device)
batch_y_mark = batch_y_mark.float().to(self.device)
# decoder input
dec_inp = torch.zeros_like(batch_y[:, -self.args.pred_len:, :]).float()
dec_inp = torch.cat([batch_y[:, :self.args.label_len, :], dec_inp], dim=1).float().to(self.device)
# encoder - decoder
if self.args.use_amp:
with torch.cuda.amp.autocast():
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
else:
if self.args.output_attention:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
outputs = outputs.detach().cpu().numpy()
if pred_data.scale and self.args.inverse:
shape = outputs.shape
outputs = pred_data.inverse_transform(outputs.squeeze(0)).reshape(shape)
preds.append(outputs)
preds = np.array(preds)
preds = preds.reshape(-1, preds.shape[-2], preds.shape[-1])
# result save
folder_path = './results/' + setting + '/'
if not os.path.exists(folder_path):
os.makedirs(folder_path)
np.save(folder_path + 'real_prediction.npy', preds)
return
|