import os.path as osp

import torch
import torch.nn.functional as F

from torch_geometric.datasets import Planetoid
from torch_geometric.explain import Explainer, GraphMaskExplainer
from torch_geometric.nn import GATConv, GCNConv

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

path = osp.join(osp.dirname(osp.realpath(__file__)), 'data', 'Planetoid')
dataset = Planetoid(path, name='Cora')
data = dataset[0].to(device)

# GCN Node Classification =====================================================


class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GCNConv(dataset.num_features, 16)
        self.conv2 = GCNConv(16, dataset.num_classes)

    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index).relu()
        x = F.dropout(x, training=self.training)
        x = self.conv2(x, edge_index)
        return F.log_softmax(x, dim=1)


model = GCN().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

for epoch in range(1, 201):
    model.train()
    optimizer.zero_grad()
    out = model(data.x, data.edge_index)
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()

explainer = Explainer(
    model=model,
    algorithm=GraphMaskExplainer(2, epochs=5),
    explanation_type='model',
    node_mask_type='attributes',
    edge_mask_type='object',
    model_config=dict(
        mode='multiclass_classification',
        task_level='node',
        return_type='log_probs',
    ),
)

node_index = 10
explanation = explainer(data.x, data.edge_index, index=node_index)
print(f'Generated explanations in {explanation.available_explanations}')

# GAT Node Classification =====================================================


class GAT(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GATConv(dataset.num_features, 8, heads=8)
        self.conv2 = GATConv(64, dataset.num_classes, heads=1, concat=False)

    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index).relu()
        x = F.dropout(x, training=self.training)
        x = self.conv2(x, edge_index)
        return F.log_softmax(x, dim=1)


model = GAT().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

for epoch in range(1, 201):
    model.train()
    optimizer.zero_grad()
    out = model(data.x, data.edge_index)
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()

explainer = Explainer(
    model=model,
    algorithm=GraphMaskExplainer(2, epochs=5),
    explanation_type='model',
    node_mask_type='attributes',
    edge_mask_type='object',
    model_config=dict(
        mode='multiclass_classification',
        task_level='node',
        return_type='log_probs',
    ),
)

node_index = torch.tensor([10, 20])
explanation = explainer(data.x, data.edge_index, index=node_index)
print(f'Generated explanations in {explanation.available_explanations}')