Spaces:
Sleeping
Sleeping
File size: 8,648 Bytes
e1ccef5 |
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 |
from data_provider.data_factory import data_provider
from exp.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 numpy as np
warnings.filterwarnings('ignore')
class Exp_Imputation(Exp_Basic):
def __init__(self, args):
super(Exp_Imputation, 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):
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_x_mark = batch_x_mark.float().to(self.device)
# random mask
B, T, N = batch_x.shape
"""
B = batch size
T = seq len
N = number of features
"""
mask = torch.rand((B, T, N)).to(self.device)
mask[mask <= self.args.mask_rate] = 0 # masked
mask[mask > self.args.mask_rate] = 1 # remained
inp = batch_x.masked_fill(mask == 0, 0)
outputs = self.model(inp, batch_x_mark, None, None, mask)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, :, f_dim:]
# add support for MS
batch_x = batch_x[:, :, f_dim:]
mask = mask[:, :, f_dim:]
pred = outputs.detach().cpu()
true = batch_x.detach().cpu()
mask = mask.detach().cpu()
loss = criterion(pred[mask == 0], true[mask == 0])
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()
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_x_mark = batch_x_mark.float().to(self.device)
# random mask
B, T, N = batch_x.shape
mask = torch.rand((B, T, N)).to(self.device)
mask[mask <= self.args.mask_rate] = 0 # masked
mask[mask > self.args.mask_rate] = 1 # remained
inp = batch_x.masked_fill(mask == 0, 0)
outputs = self.model(inp, batch_x_mark, None, None, mask)
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, :, f_dim:]
# add support for MS
batch_x = batch_x[:, :, f_dim:]
mask = mask[:, :, f_dim:]
loss = criterion(outputs[mask == 0], batch_x[mask == 0])
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()
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)
test_loss = self.vali(test_data, test_loader, criterion)
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 = []
masks = []
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):
batch_x = batch_x.float().to(self.device)
batch_x_mark = batch_x_mark.float().to(self.device)
# random mask
B, T, N = batch_x.shape
mask = torch.rand((B, T, N)).to(self.device)
mask[mask <= self.args.mask_rate] = 0 # masked
mask[mask > self.args.mask_rate] = 1 # remained
inp = batch_x.masked_fill(mask == 0, 0)
# imputation
outputs = self.model(inp, batch_x_mark, None, None, mask)
# eval
f_dim = -1 if self.args.features == 'MS' else 0
outputs = outputs[:, :, f_dim:]
# add support for MS
batch_x = batch_x[:, :, f_dim:]
mask = mask[:, :, f_dim:]
outputs = outputs.detach().cpu().numpy()
pred = outputs
true = batch_x.detach().cpu().numpy()
preds.append(pred)
trues.append(true)
masks.append(mask.detach().cpu())
if i % 20 == 0:
filled = true[0, :, -1].copy()
filled = filled * mask[0, :, -1].detach().cpu().numpy() + \
pred[0, :, -1] * (1 - mask[0, :, -1].detach().cpu().numpy())
visual(true[0, :, -1], filled, os.path.join(folder_path, str(i) + '.pdf'))
preds = np.concatenate(preds, 0)
trues = np.concatenate(trues, 0)
masks = np.concatenate(masks, 0)
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[masks == 0], trues[masks == 0])
print('mse:{}, mae:{}'.format(mse, mae))
f = open("result_imputation.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
|