Benchmark - 2020 March 05¶
[1]:
import datetime
import numpy as np
from matplotlib import pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, random_split
from tqdm import tqdm
import seaborn as sns
from tst.loss import OZELoss
from src.benchmark import LSTM
from src.dataset import OzeDataset
from src.utils import visual_sample, compute_loss
[9]:
# Training parameters
DATASET_PATH = 'datasets/dataset_v6_full.npz'
BATCH_SIZE = 8
NUM_WORKERS = 4
LR = 3e-5
EPOCHS = 30
# Model parameters
d_model = 128 # Lattent dim
N = 8*2 # Number of layers
dropout = 0.2 # Dropout rate
d_input = 38 # From dataset
d_output = 8 # From dataset
# Config
sns.set()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"Using device {device}")
Using device cuda:0
Training¶
Load dataset¶
[3]:
ozeDataset = OzeDataset(DATASET_PATH)
dataset_train, dataset_val, dataset_test = random_split(ozeDataset, (38000, 500, 500))
[4]:
dataloader_train = DataLoader(dataset_train,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=NUM_WORKERS,
pin_memory=False
)
dataloader_val = DataLoader(dataset_val,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=NUM_WORKERS
)
dataloader_test = DataLoader(dataset_test,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=NUM_WORKERS
)
Load network¶
[10]:
# Load transformer with Adam optimizer and MSE loss function
net = LSTM(d_input, d_model, d_output, N, dropout=dropout).to(device)
optimizer = optim.Adam(net.parameters(), lr=LR)
loss_function = OZELoss(alpha=0.3)
Train¶
[11]:
model_save_path = f'models/model_LSTM_{datetime.datetime.now().strftime("%Y_%m_%d__%H%M%S")}.pth'
val_loss_best = np.inf
# Prepare loss history
hist_loss = np.zeros(EPOCHS)
hist_loss_val = np.zeros(EPOCHS)
for idx_epoch in range(EPOCHS):
running_loss = 0
with tqdm(total=len(dataloader_train.dataset), desc=f"[Epoch {idx_epoch+1:3d}/{EPOCHS}]") as pbar:
for idx_batch, (x, y) in enumerate(dataloader_train):
optimizer.zero_grad()
# Propagate input
netout = net(x.to(device))
# Comupte loss
loss = loss_function(y.to(device), netout)
# Backpropage loss
loss.backward()
# Update weights
optimizer.step()
running_loss += loss.item()
pbar.set_postfix({'loss': running_loss/(idx_batch+1)})
pbar.update(x.shape[0])
train_loss = running_loss/len(dataloader_train)
val_loss = compute_loss(net, dataloader_val, loss_function, device).item()
pbar.set_postfix({'loss': train_loss, 'val_loss': val_loss})
hist_loss[idx_epoch] = train_loss
hist_loss_val[idx_epoch] = val_loss
if val_loss < val_loss_best:
val_loss_best = val_loss
torch.save(net.state_dict(), model_save_path)
plt.plot(hist_loss, 'o-', label='train')
plt.plot(hist_loss_val, 'o-', label='val')
plt.legend()
print(f"model exported to {model_save_path} with loss {val_loss_best:5f}")
[Epoch 1/30]: 100%|██████████| 38000/38000 [06:57<00:00, 90.94it/s, loss=0.0318, val_loss=0.0238]
[Epoch 2/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.30it/s, loss=0.0234, val_loss=0.0234]
[Epoch 3/30]: 100%|██████████| 38000/38000 [07:01<00:00, 90.12it/s, loss=0.0189, val_loss=0.0142]
[Epoch 4/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.69it/s, loss=0.0128, val_loss=0.0122]
[Epoch 5/30]: 100%|██████████| 38000/38000 [06:59<00:00, 90.58it/s, loss=0.012, val_loss=0.0119]
[Epoch 6/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.38it/s, loss=0.0118, val_loss=0.0117]
[Epoch 7/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.27it/s, loss=0.0116, val_loss=0.0117]
[Epoch 8/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.89it/s, loss=0.0115, val_loss=0.0115]
[Epoch 9/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.74it/s, loss=0.0114, val_loss=0.0115]
[Epoch 10/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.32it/s, loss=0.0114, val_loss=0.0114]
[Epoch 11/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.45it/s, loss=0.0112, val_loss=0.0112]
[Epoch 12/30]: 100%|██████████| 38000/38000 [06:57<00:00, 90.93it/s, loss=0.0111, val_loss=0.011]
[Epoch 13/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.79it/s, loss=0.0109, val_loss=0.0109]
[Epoch 14/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.44it/s, loss=0.0108, val_loss=0.0108]
[Epoch 15/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.44it/s, loss=0.0107, val_loss=0.0107]
[Epoch 16/30]: 100%|██████████| 38000/38000 [06:57<00:00, 90.93it/s, loss=0.0107, val_loss=0.0107]
[Epoch 17/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.80it/s, loss=0.0106, val_loss=0.0106]
[Epoch 18/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.40it/s, loss=0.0106, val_loss=0.0107]
[Epoch 19/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.29it/s, loss=0.0105, val_loss=0.0105]
[Epoch 20/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.82it/s, loss=0.0104, val_loss=0.0105]
[Epoch 21/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.82it/s, loss=0.0104, val_loss=0.0105]
[Epoch 22/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.45it/s, loss=0.0103, val_loss=0.0104]
[Epoch 23/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.32it/s, loss=0.0103, val_loss=0.0103]
[Epoch 24/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.86it/s, loss=0.0103, val_loss=0.0104]
[Epoch 25/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.72it/s, loss=0.0102, val_loss=0.0103]
[Epoch 26/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.46it/s, loss=0.0102, val_loss=0.0103]
[Epoch 27/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.41it/s, loss=0.0101, val_loss=0.0103]
[Epoch 28/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.82it/s, loss=0.0101, val_loss=0.0102]
[Epoch 29/30]: 100%|██████████| 38000/38000 [06:58<00:00, 90.90it/s, loss=0.0101, val_loss=0.0101]
[Epoch 30/30]: 100%|██████████| 38000/38000 [07:00<00:00, 90.42it/s, loss=0.01, val_loss=0.0101]
model exported to models/model_LSTM_2020_03_04__211137.pth with loss 0.010125
Validation¶
[ ]:
_ = net.eval()
Plot results on a sample¶
[8]:
visual_sample(dataloader_test, net, device)
plt.savefig("fig")
Evaluate on the test dataset¶
[ ]:
predictions = np.empty(shape=(len(dataloader_test.dataset), 168, 8))
idx_prediction = 0
with torch.no_grad():
for x, y in tqdm(dataloader_test, total=len(dataloader_test)):
netout = net(x.to(device)).cpu().numpy()
predictions[idx_prediction:idx_prediction+x.shape[0]] = netout
idx_prediction += x.shape[0]
[ ]:
fig, axes = plt.subplots(8, 1)
fig.set_figwidth(20)
fig.set_figheight(40)
plt.subplots_adjust(bottom=0.05)
occupancy = (dataloader_test.dataset.dataset._x.numpy()[..., dataloader_test.dataset.dataset.labels["Z"].index("occupancy")].mean(axis=0)>0.5).astype(float)
y_true_full = dataloader_test.dataset.dataset._y[dataloader_test.dataset.indices].numpy()
for idx_label, (label, ax) in enumerate(zip(dataloader_test.dataset.dataset.labels['X'], axes)):
# Select output to plot
y_true = y_true_full[..., idx_label]
y_pred = predictions[..., idx_label]
# Rescale
y_true = dataloader_test.dataset.dataset.rescale(y_true, idx_label)
y_pred = dataloader_test.dataset.dataset.rescale(y_pred, idx_label)
if label.startswith('Q_'):
# Convert kJ/h to kW
y_true /= 3600
y_pred /= 3600
# Compute delta, mean and std
delta = np.abs(y_true - y_pred)
mean = delta.mean(axis=0)
std = delta.std(axis=0)
# Plot
# Labels for consumption and temperature
if label.startswith('Q_'):
y_label_unit = 'kW'
else:
y_label_unit = '°C'
# Occupancy
occupancy_idxes = np.where(np.diff(occupancy) != 0)[0]
for idx in range(0, len(occupancy_idxes), 2):
ax.axvspan(occupancy_idxes[idx], occupancy_idxes[idx+1], facecolor='green', alpha=.15)
# Std
ax.fill_between(np.arange(mean.shape[0]), (mean - std), (mean + std), alpha=.4, label='std')
# Mean
ax.plot(mean, label='mean')
# Title and labels
ax.set_title(label)
ax.set_xlabel('time', fontsize=16)
ax.set_ylabel(y_label_unit, fontsize=16)
ax.legend()
plt.savefig('error_mean_std')