I am trying to predict the risk of an event based on patient data such as lab results. Patient might have missing labs or might only have n labs where n<max_observed_months. To handle this I used packed sequences. Also, I want to predict at each month - so the LSTM should be many to many. The problem is the loss is not reducing after a certain point and also auc is stuck around .54.
The data is a n x 5 x 12 matrix where n is the # of patients and 5 features are observed for 12 months or less.
Below is my code, I would really appreciate if you can provide some tips!
class PatientDataset2(Dataset):
def __init__(self, data, target) -> None:
self.data = data
self.targets = target
def __len__(self):
return len(self.data)
def __getitem__(self, index):
sequence = self.data[index]
target = self.targets[index]
return sequence, len(sequence) , target
def collate_fn(data):
data.sort(key=lambda x: x[1], reverse=True)
sequences, lengths, targets = zip(*data)
# sequences, lengths = zip(*data)
sequences_padded = pad_sequence([torch.as_tensor(seq) for seq in sequences], batch_first=True)
targets_padded = pad_sequence([torch.as_tensor(targ) for targ in targets], batch_first=True)
return sequences_padded, torch.LongTensor(lengths), targets_padded
sequence_length = 12
input_size = 5
hidden_size = 25
num_layers = 2
num_classes = 1
batch_size = 100
num_epochs = 500
learning_rate = 0.001
# Recurrent neural network (many-to-many)
class PtLSTM(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(PtLSTM, self).__init__()
self.hidden_size = hidden_size
self.num_layers = num_layers
self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, dropout=.1)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, x, lengths):
packed = pack_padded_sequence(x, lengths, batch_first=True, enforce_sorted=False)
lstm_out, hidden = self.lstm(packed)
outputs = self.fc(lstm_out[0])
# print(outputs.shape)
return outputs.squeeze(1)
model = PtLSTM(input_size, hidden_size, num_layers, num_classes).to(device)
train_dataset = PatientDataset2(x_train, y_train)
train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=False, collate_fn=collate_fn)
# Loss and optimizer
# criterion = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([166]).to(device))
criterion = nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
total_step = len(train_dataloader)
for epoch in range(num_epochs):
for i, (seqs, lengths, labels) in enumerate(train_dataloader):
optimizer.zero_grad()
seqs = seqs.float().to(device)
labels = labels.to(device)
targets = pack_padded_sequence(labels, lengths, batch_first=True)[0]
# Forward pass
outputs = model(seqs, lengths)
# print(labels.shape)
loss = criterion(outputs, targets)
# Backward and optimize
loss.backward()
optimizer.step()
if (i+1) % 1 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))