from collections import OrderedDict

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader

from tests.base.datasets import TrialMNIST

try:
    from test_tube import HyperOptArgumentParser
except ImportError:
    # TODO: this should be discussed and moved out of this package
    raise ImportError('Missing test-tube package.')

from pytorch_lightning.core.lightning import LightningModule


class Generator(nn.Module):
    def __init__(self, latent_dim: tuple, img_shape: tuple):
        super().__init__()
        self.img_shape = img_shape

        def block(in_feat, out_feat, normalize=True):
            layers = [nn.Linear(in_feat, out_feat)]
            if normalize:
                layers.append(nn.BatchNorm1d(out_feat, 0.8))
            layers.append(nn.LeakyReLU(0.2, inplace=True))
            return layers

        self.model = nn.Sequential(
            *block(latent_dim, 128, normalize=False),
            *block(128, 256),
            *block(256, 512),
            *block(512, 1024),
            nn.Linear(1024, int(np.prod(img_shape))),
            nn.Tanh()
        )

    def forward(self, z):
        img = self.model(z)
        img = img.view(img.size(0), *self.img_shape)
        return img


class Discriminator(nn.Module):
    def __init__(self, img_shape: tuple):
        super().__init__()

        self.model = nn.Sequential(
            nn.Linear(int(np.prod(img_shape)), 512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(512, 256),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Linear(256, 1),
            nn.Sigmoid(),
        )

    def forward(self, img):
        img_flat = img.view(img.size(0), -1)
        validity = self.model(img_flat)

        return validity


class TestGAN(LightningModule):
    """Implements a basic GAN for the purpose of illustrating multiple optimizers."""

    def __init__(self, hidden_dim, learning_rate, b1, b2, **kwargs):
        super().__init__()
        self.hidden_dim = hidden_dim
        self.learning_rate = learning_rate
        self.b1 = b1
        self.b2 = b2

        # networks
        mnist_shape = (1, 28, 28)
        self.generator = Generator(latent_dim=self.hidden_dim, img_shape=mnist_shape)
        self.discriminator = Discriminator(img_shape=mnist_shape)

        # cache for generated images
        self.generated_imgs = None
        self.last_imgs = None

    def forward(self, z):
        return self.generator(z)

    def adversarial_loss(self, y_hat, y):
        return F.binary_cross_entropy(y_hat, y)

    def training_step(self, batch, batch_idx, optimizer_idx=None):
        imgs, _ = batch
        self.last_imgs = imgs

        # train generator
        if optimizer_idx == 0:
            # sample noise
            z = torch.randn(imgs.shape[0], self.hidden_dim)
            z = z.type_as(imgs)

            # generate images
            self.generated_imgs = self(z)

            # ground truth result (ie: all fake)
            # put on GPU because we created this tensor inside training_loop
            valid = torch.ones(imgs.size(0), 1)
            valid = valid.type_as(imgs)

            # adversarial loss is binary cross-entropy
            g_loss = self.adversarial_loss(self.discriminator(self.generated_imgs), valid)
            tqdm_dict = {'g_loss': g_loss}
            output = OrderedDict({
                'loss': g_loss,
                'progress_bar': tqdm_dict,
                'log': tqdm_dict
            })
            return output

        # train discriminator
        if optimizer_idx == 1:
            # Measure discriminator's ability to classify real from generated samples

            # how well can it label as real?
            valid = torch.ones(imgs.size(0), 1)
            valid = valid.type_as(imgs)

            real_loss = self.adversarial_loss(self.discriminator(imgs), valid)

            # how well can it label as fake?
            fake = torch.zeros(imgs.size(0), 1)
            fake = fake.type_as(fake)

            fake_loss = self.adversarial_loss(self.discriminator(self.generated_imgs.detach()), fake)

            # discriminator loss is the average of these
            d_loss = (real_loss + fake_loss) / 2
            tqdm_dict = {'d_loss': d_loss}
            output = OrderedDict({
                'loss': d_loss,
                'progress_bar': tqdm_dict,
                'log': tqdm_dict
            })
            return output

    def configure_optimizers(self):
        lr = self.learning_rate
        b1 = self.b1
        b2 = self.b2

        opt_g = torch.optim.Adam(self.generator.parameters(), lr=lr, betas=(b1, b2))
        opt_d = torch.optim.Adam(self.discriminator.parameters(), lr=lr, betas=(b1, b2))
        return [opt_g, opt_d], []

    def train_dataloader(self):
        return DataLoader(TrialMNIST(train=True, download=True), batch_size=16)