import os.path as osp

import torch
import torch.nn.functional as F
from sklearn.metrics import f1_score
from torch import Tensor
from torch.nn import BatchNorm1d

from torch_geometric.datasets import PPI
from torch_geometric.loader import DataLoader
from torch_geometric.nn import FiLMConv

path = osp.join(osp.dirname(osp.realpath(__file__)), 'data', 'PPI')
train_dataset = PPI(path, split='train')
val_dataset = PPI(path, split='val')
test_dataset = PPI(path, split='test')
train_loader = DataLoader(train_dataset, batch_size=2, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=2, shuffle=False)
test_loader = DataLoader(test_dataset, batch_size=2, shuffle=False)


class FiLM(torch.nn.Module):
    def __init__(self, in_channels: int, hidden_channels: int,
                 out_channels: int, num_layers: int, dropout: float = 0.0):
        super().__init__()
        self.dropout = dropout

        self.convs = torch.nn.ModuleList()
        self.convs.append(FiLMConv(in_channels, hidden_channels))
        for _ in range(num_layers - 2):
            conv = FiLMConv(hidden_channels, hidden_channels)
            self.convs.append(conv)
        self.last_conv = FiLMConv(hidden_channels, out_channels, act=None)

        self.norms = torch.nn.ModuleList()
        for _ in range(num_layers - 1):
            self.norms.append(BatchNorm1d(hidden_channels))

    def forward(self, x: Tensor, edge_index: Tensor) -> Tensor:
        for conv, norm in zip(self.convs, self.norms):
            x = norm(conv(x, edge_index))
            x = F.dropout(x, p=self.dropout, training=self.training)
        x = self.last_conv(x, edge_index)
        return x


device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = FiLM(train_dataset.num_features, 320, train_dataset.num_classes,
             num_layers=4, dropout=0.1)
model = torch.jit.script(model).to(device)
criterion = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)


def train():
    model.train()

    total_loss = 0
    for data in train_loader:
        data = data.to(device)
        optimizer.zero_grad()
        loss = criterion(model(data.x, data.edge_index), data.y)
        total_loss += loss.item() * data.num_graphs
        loss.backward()
        optimizer.step()
    return total_loss / len(train_loader.dataset)


@torch.no_grad()
def test(loader):
    model.eval()

    ys, preds = [], []
    for data in loader:
        ys.append(data.y)
        out = model(data.x.to(device), data.edge_index.to(device))
        preds.append((out > 0).float().cpu())

    y, pred = torch.cat(ys, dim=0).numpy(), torch.cat(preds, dim=0).numpy()
    return f1_score(y, pred, average='micro') if pred.sum() > 0 else 0


for epoch in range(1, 501):
    loss = train()
    val_f1 = test(val_loader)
    test_f1 = test(test_loader)
    print(f'Epoch: {epoch:02d}, Loss: {loss:.4f}, Val: {val_f1:.4f}, '
          f'Test: {test_f1:.4f}')