"""
This code was modified from the GCN implementation in DGL examples.
Simplifying Graph Convolutional Networks
Paper: https://arxiv.org/abs/1902.07153
Code: https://github.com/Tiiiger/SGC
SGC implementation in DGL.
"""
import argparse, time, math
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import dgl.function as fn
import dgl
from dgl.data import register_data_args
from dgl.data import CoraGraphDataset, CiteseerGraphDataset, PubmedGraphDataset
from dgl.nn.pytorch.conv import SGConv


def evaluate(model, g, features, labels, mask):
    model.eval()
    with torch.no_grad():
        logits = model(g, features)[mask] # only compute the evaluation set
        labels = labels[mask]
        _, indices = torch.max(logits, dim=1)
        correct = torch.sum(indices == labels)
        return correct.item() * 1.0 / len(labels)

def main(args):
    # load and preprocess dataset
    if args.dataset == 'cora':
        data = CoraGraphDataset()
    elif args.dataset == 'citeseer':
        data = CiteseerGraphDataset()
    elif args.dataset == 'pubmed':
        data = PubmedGraphDataset()
    else:
        raise ValueError('Unknown dataset: {}'.format(args.dataset))

    g = data[0]
    if args.gpu < 0:
        cuda = False
    else:
        cuda = True
        g = g.int().to(args.gpu)

    features = g.ndata['feat']
    labels = g.ndata['label']
    train_mask = g.ndata['train_mask']
    val_mask = g.ndata['val_mask']
    test_mask = g.ndata['test_mask']
    in_feats = features.shape[1]
    n_classes = data.num_labels
    n_edges = g.number_of_edges()
    print("""----Data statistics------'
      #Edges %d
      #Classes %d
      #Train samples %d
      #Val samples %d
      #Test samples %d""" %
          (n_edges, n_classes,
              train_mask.int().sum().item(),
              val_mask.int().sum().item(),
              test_mask.int().sum().item()))

    n_edges = g.number_of_edges()
    # add self loop
    g = dgl.remove_self_loop(g)
    g = dgl.add_self_loop(g)

    # create SGC model
    model = SGConv(in_feats,
                   n_classes,
                   k=2,
                   cached=True,
                   bias=args.bias)

    if cuda:
        model.cuda()
    loss_fcn = torch.nn.CrossEntropyLoss()

    # use optimizer
    optimizer = torch.optim.Adam(model.parameters(),
                                 lr=args.lr,
                                 weight_decay=args.weight_decay)

    # initialize graph
    dur = []
    for epoch in range(args.n_epochs):
        model.train()
        if epoch >= 3:
            t0 = time.time()
        # forward
        logits = model(g, features) # only compute the train set
        loss = loss_fcn(logits[train_mask], labels[train_mask])

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if epoch >= 3:
            dur.append(time.time() - t0)

        acc = evaluate(model, g, features, labels, val_mask)
        print("Epoch {:05d} | Time(s) {:.4f} | Loss {:.4f} | Accuracy {:.4f} | "
              "ETputs(KTEPS) {:.2f}". format(epoch, np.mean(dur), loss.item(),
                                             acc, n_edges / np.mean(dur) / 1000))

    print()
    acc = evaluate(model, g, features, labels, test_mask)
    print("Test Accuracy {:.4f}".format(acc))


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='SGC')
    register_data_args(parser)
    parser.add_argument("--gpu", type=int, default=-1,
            help="gpu")
    parser.add_argument("--lr", type=float, default=0.2,
            help="learning rate")
    parser.add_argument("--bias", action='store_true', default=False,
            help="flag to use bias")
    parser.add_argument("--n-epochs", type=int, default=100,
            help="number of training epochs")
    parser.add_argument("--weight-decay", type=float, default=5e-6,
            help="Weight for L2 loss")
    args = parser.parse_args()
    print(args)

    main(args)