import torch
import torchvision
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset
import time


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5, 2, 2)
        self.pool = nn.MaxPool2d(3, 2)
        self.conv2 = nn.Conv2d(6, 16, 5, 2, 2)
        self.fc1 = nn.Linear(784, 240)
        self.fc2 = nn.Linear(240, 84)
        self.fc3 = nn.Linear(84, 12)
        self.dropout = nn.Dropout(p=0.5)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, self.num_flat_features(x))
        x = self.dropout(x)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


class Memory(Dataset):
    def __init__(self, dataset_array, dataset_labels):
        self.labels = dataset_labels.astype(np.float64)
        self.images = dataset_array.astype(np.float64)
    def __len__(self):
        return self.images.shape[0]
    def __getitem__(self, idx):
        return self.images[idx], self.labels[idx]


def dataloader(batch_size, num_workers=4):
    print("Data loading...")
    training_images = np.load("training_images.npy")
    training_labels = np.load("training_labels.npy")
    trainset = Memory(training_images, training_labels)
    trainset_length = trainset.__len__()
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, num_workers=num_workers, pin_memory=False)
    cv_images = np.load("cv_images.npy")
    cv_labels = np.load("cv_labels.npy")
    cvset = Memory(cv_images, cv_labels)
    cvset_length = cvset.__len__()
    cvloader = torch.utils.data.DataLoader(cvset, batch_size=cvset_length, shuffle=False, num_workers=num_workers, pin_memory=False)
    test_images = np.load("test_images.npy")
    test_labels = np.load("test_labels.npy")
    testset = Memory(test_images, test_labels)
    testset_length = testset.__len__()
    testloader = torch.utils.data.DataLoader(testset, batch_size=testset_length, shuffle=False, num_workers=num_workers, pin_memory=False)
    trainloader2 = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=num_workers, pin_memory=False)
    testloader2 = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=True, num_workers=num_workers, pin_memory=False)
    print("Data loaded.")
    return trainloader, cvloader, testloader, trainset_length, trainloader2, testloader2


def training(trainloader, cvloader, testloader, trainset_length, batch_size, net, opt, epochs, lr, weight_decay, step_size, gamma=0.1):
    criterion = nn.CrossEntropyLoss()
    adam = optim.Adam(net.parameters(), lr=lr, weight_decay=weight_decay)
    adagrad = optim.Adagrad(net.parameters(), lr=lr, weight_decay=weight_decay)
    sgd = optim.SGD(net.parameters(), lr=lr, momentum=0.9, weight_decay=weight_decay)
    if opt == 1:
        optimizer = adam
    elif opt == 2:
        optimizer = adagrad
    else:
        optimizer = sgd
    scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=step_size, gamma=gamma)
    best_acc = 0

#    print("Training started...")
    since = time.time()
    for epoch in range(epochs):  # loop over the dataset multiple times
        net.train()
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # get the inputs
            inputs, labels = data
            inputs = inputs.float().to(device)
            labels = labels.long().to(device)

            # zero the parameter gradients
            optimizer.zero_grad()

            # forward + backward + optimize
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            # print statistics
            running_loss += loss.item()

        running_loss = running_loss / (trainset_length // batch_size)
#        print('Epoch: %d Loss: %.5f' % (epoch + 1, running_loss))

        cv_acc = accshow(cvloader, net)
        if cv_acc > best_acc:
            best_acc = cv_acc
            torch.save(net, "train_model.pth")
            best_epoch = epoch + 1
            best_epoch_lr = epoch + 1
            best_lr = lr

        if (epoch + 1) - best_epoch_lr >= 50:
            lr = lr / 10
            if opt == 1:
                optimizer = adam
            elif opt == 2:
                optimizer = adagrad
            else:
                optimizer = sgd
            best_epoch_lr = best_epoch_lr + 30
#            print("Learning rate changed to %f" % lr)

        if (epoch + 1) - best_epoch >= 100:
             break

#        if epoch % 20 == 19:
#            print('Train images accuracy: %d%s' % (accshow(trainloader, net), "%"))
#            print('Validation images accuracy: %d%s' % (cv_acc, "%"))
#            print('Test images accuracy: %d%s' % (accshow(testloader, net), "%"))

        scheduler.step()
    time_elapsed = time.time() - since
#    print('Training completed in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    best_model = torch.load("train_model.pth")
    return best_model, best_epoch, best_lr


def checking(trainloader, cvloader, testloader, trainset_length, batch_size, epochs, initial_lr, step_size, loops):
    cv_score, test_score = [0, 0]
    opt_list = [1, 2, 3]
    decay_list = [0.05, 0.03, 0.01, 0.005, 0.003, 0.001, 0.0005, 0.0003, 0.0001]
    print("Checking started...")
    since = time.time()
    for opt in opt_list:
        for weight in decay_list:
            for i in range(loops):
                net = Net()
                net = net.to(device)
                trained_net, best_epoch, lr = training(trainloader, cvloader, testloader, trainset_length, batch_size, net, opt, epochs, initial_lr, weight, step_size)
                trained_net = trained_net.to(device)
                train_acc = accshow(trainloader, trained_net)
                cv_acc = accshow(cvloader, trained_net)
                test_acc = accshow(testloader, trained_net)
                print("Train: %d%s CV: %d%s Test: %d%s Opt: %d Rate: %.4f Decay: %.4f Loop: %d Epoch: %d" % (train_acc, "%", cv_acc, "%", test_acc, "%", opt, lr, weight, i+1, best_epoch))
                if cv_acc > cv_score:
                    cv_score = cv_acc
                    cv_train = train_acc
                    cv_test = test_acc
                    cv_opt = opt
                    cv_rate = lr
                    cv_decay = weight
                    cv_epoch = best_epoch
                    torch.save(trained_net, "check_model_val.pth")
                if test_acc > test_score:
                    test_score = test_acc
                    test_train = train_acc
                    test_cv = cv_acc
                    test_opt = opt
                    test_rate = lr
                    test_decay = weight
                    test_epoch = best_epoch
                    torch.save(trained_net, "check_model_test.pth")
    time_elapsed = time.time() - since
    print('Checking completed in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print("Best cross-validation set accuracy:")
    print("Train: %d%s CV: %d%s Test: %d%s Opt: %d Rate: %.4f Decay: %.4f Epoch: %d" % (cv_train, "%", cv_score, "%", cv_test, "%", cv_opt, cv_rate, cv_decay, cv_epoch))
    print("Best test set accuracy:")
    print("Train: %d%s CV: %d%s Test: %d%s Opt: %d Rate: %.4f Decay: %.4f Epoch: %d" % (test_train, "%", test_cv, "%", test_score, "%", test_opt, test_rate, test_decay, test_epoch))
    cv_net = torch.load("check_model_val.pth")
    test_net = torch.load("check_model_test.pth")
    return cv_net, test_net


def accshow(loader, net):
    net.eval()
    correct = 0
    total = 0
    with torch.no_grad():
        for data in loader:
            inputs, labels = data
            inputs = inputs.float().to(device)
            labels = labels.long().to(device)
            outputs = net(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    return (100 * correct / total)


def classaccshow(loader, net, classes, classes_length):
    net.eval()
    class_correct = list(0. for i in range(classes_length))
    class_total = list(0. for i in range(classes_length))
    with torch.no_grad():
        for data in loader:
            inputs, labels = data
            inputs = inputs.float().to(device)
            labels = labels.long().to(device)
            outputs = net(inputs)
            _, predicted = torch.max(outputs, 1)
            c = (predicted == labels).squeeze()
            try:
                for i in range(100):
                    label = labels[i]
                    class_correct[label] += c[i].item()
                    class_total[label] += 1
            except IndexError:
                pass
    for i in range(classes_length):
        print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))


def imshow(img):
    img = img * 0.13 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


def imgshow(loader, net, classes):
    net.eval()
    dataiter = iter(loader)
    inputs, labels = dataiter.next()
    imshow(torchvision.utils.make_grid(inputs))
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    inputs = inputs.to(device)
    outputs = net(inputs)
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))



if __name__ == '__main__':

    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    classes = ('alder', 'beech', 'birch', 'chestnut', 'gingko biloba', 'hornbeam', 'horse chestnut', 'linden', 'oak', 'oriental plane', 'pine', 'spruce')
    classes_length = len(classes)
    batch_size = 35
    trainloader, cvloader, testloader, trainset_length, trainloader2, testloader2 = dataloader(batch_size)

    net = Net()
    net = net.to(device)
    epochs = 999
    step_size = epochs
    opt = 2
    learning_rate = 0.01
    weight_decay = 0.0005

#    model, best_epoch, best_lr = training(trainloader, cvloader, testloader, trainset_length, batch_size, net, opt, epochs, learning_rate, weight_decay, step_size)
#    print("Best net score was in %d epoch with %f learning rate." % (best_epoch, best_lr))
    model, model_test = checking(trainloader, cvloader, testloader, trainset_length, batch_size, epochs, learning_rate, step_size, loops=3)
#    model = torch.load("best_val.pth", map_location=device)
    model = model.to(device)
    print("Final model:")
    print('Train images accuracy: %d%s' % (accshow(trainloader, model), "%"))
    print('Validation images accuracy: %d%s' % (accshow(cvloader, model), "%"))
    print('Test images accuracy: %d%s' % (accshow(testloader, model), "%"))


#    classaccshow(cvloader, model, classes, classes_length)
#    classaccshow(testloader, model, classes, classes_length)
#    imgshow(testloader2, model, classes)