import torch
import torch.nn as nn
import torch.optim as optim
import time
import copy

from save_model import save_model
from early_stopping import EarlyStopping

def train_model(model, dataloaders, criterion, optimizer, lr_scheduler, device, snapshot_path, model_name = 'model_ft', num_epochs=25, early_stop = False, patience = 7):
    since = time.time()

    val_acc_history = []
    model = model.to(device)
    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0
  
    # initialize the early_stopping object
    early_stopping = EarlyStopping(model_name, patience=patience, verbose=True, path = snapshot_path)

    
    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    # Get model outputs and calculate loss
                    outputs = model(inputs)
                    loss = criterion(outputs, labels)
                    _, preds = torch.max(outputs, 1)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / len(dataloaders[phase].dataset)
            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
            
            
            # deep copy the model
            if phase == 'val' and epoch_acc >= best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
            if phase == 'val':
                val_acc_history.append(epoch_acc)
                lr_scheduler.step(epoch_acc)

        print()
       
        if early_stop:
            early_stopping(epoch_loss, model, epoch)
            if early_stopping.early_stop:
                print("Early stopping")
                break
        elif epoch%10 == 9:
            save_model(model, model_name, snapshot_path, epoch, device)
            
    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model, val_acc_history