# -*- coding: utf-8 -*-

import os
import torch
import torch.nn.functional as F
import torch.nn as nn
from torch_geometric.datasets import Planetoid
import torch_geometric.nn as pyg_nn
import torch_geometric.transforms as T


# load dataset
def get_data(folder="node_classify/cora", data_name="cora"):
    # dataset = Planetoid(root=folder, name=data_name)
    dataset = Planetoid(root=folder, name=data_name,
                        transform=T.NormalizeFeatures())
    return dataset


# create the graph cnn model
class GraphCNN(nn.Module):
    def __init__(self, in_c, hid_c, out_c):
        super(GraphCNN, self).__init__()
        self.conv1 = pyg_nn.GCNConv(in_channels=in_c, out_channels=hid_c)
        self.conv2 = pyg_nn.GCNConv(in_channels=hid_c, out_channels=out_c)

    def forward(self, data):
        # data.x data.edge_index
        x = data.x  # [N, C]
        edge_index = data.edge_index  # [2 ,E]

        hid = self.conv1(x=x, edge_index=edge_index)  # [N, D]
        hid = F.relu(hid)

        out = self.conv2(x=hid, edge_index=edge_index)  # [N, out_c]

        out = F.log_softmax(out, dim=1)  # [N, out_c]

        return out


class OwnGCN(nn.Module):
    def __init__(self, in_c, hid_c, out_c):
        super(OwnGCN, self).__init__()
        self.in_ = pyg_nn.SGConv(in_c, hid_c, K=2)

        self.conv1 = pyg_nn.APPNP(K=2, alpha=0.1)
        self.conv2 = pyg_nn.APPNP(K=2, alpha=0.1)

        self.out_ = pyg_nn.SGConv(hid_c, out_c, K=2)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index

        x = self.in_(x, edge_index)
        x = F.dropout(x, p=0.1, training=self.training)

        x = F.relu(self.conv1(x, edge_index))
        x = F.dropout(x, p=0.1, training=self.training)

        x = F.relu(self.conv2(x, edge_index))
        x = F.dropout(x, p=0.1, training=self.training)

        x = self.out_(x, edge_index)

        return F.log_softmax(x, dim=1)


# todo list
class YourOwnGCN(nn.Module):
    pass


def analysis_data(dataset):
    print("Basic Info:      ", dataset[0])
    print("# Nodes:         ", dataset[0].num_nodes)
    print("# Features:      ", dataset[0].num_features)
    print("# Edges:         ", dataset[0].num_edges)
    print("# Classes:       ", dataset.num_classes)
    print("# Train samples: ", dataset[0].train_mask.sum().item())
    print("# Valid samples: ", dataset[0].val_mask.sum().item())
    print("# Test samples:  ", dataset[0].test_mask.sum().item())
    print("Undirected:      ", dataset[0].is_undirected())


def main():
    os.environ["CUDA_VISIBLE_DEVICES"] = "0"
    cora_dataset = get_data()

    # todo list
    # my_net = GraphCNN(in_c=cora_dataset.num_features, hid_c=150, out_c=cora_dataset.num_classes)
    my_net = OwnGCN(in_c=cora_dataset.num_features, hid_c=300, out_c=cora_dataset.num_classes)

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

    my_net = my_net.to(device)
    data = cora_dataset[0].to(device)

    optimizer = torch.optim.Adam(my_net.parameters(), lr=1e-2, weight_decay=1e-3)
    """
    # model train
    my_net.train()
    for epoch in range(500):
        optimizer.zero_grad()

        output = my_net(data)
        loss = F.nll_loss(output[data.train_mask], data.y[data.train_mask])
        loss.backward()
        optimizer.step()

        _, prediction = output.max(dim=1)

        valid_correct = prediction[data.val_mask].eq(data.y[data.val_mask]).sum().item()
        valid_number = data.val_mask.sum().item()

        valid_acc = valid_correct / valid_number
        print("Epoch: {:03d}".format(epoch + 1), "Loss: {:.04f}".format(loss.item()),
              "Valid Accuracy:: {:.4f}".format(valid_acc))
    """

    # model test
    my_net = torch.load("node_classify/best.pth")
    my_net.eval()

    _, prediction = my_net(data).max(dim=1)

    target = data.y

    test_correct = prediction[data.test_mask].eq(target[data.test_mask]).sum().item()
    test_number = data.test_mask.sum().item()

    train_correct = prediction[data.train_mask].eq(target[data.train_mask]).sum().item()
    train_number = data.train_mask.sum().item()

    print("==" * 20)

    print("Accuracy of Train Samples: {:.04f}".format(train_correct / train_number))

    print("Accuracy of Test  Samples: {:.04f}".format(test_correct / test_number))


def test_main():
    os.environ["CUDA_VISIBLE_DEVICES"] = "0"

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

    cora_dataset = get_data()
    data = cora_dataset[0].to(device)

    my_net = torch.load("node_classify/best.pth")

    my_net.eval()
    _, prediction = my_net(data).max(dim=1)

    target = data.y

    test_correct = prediction[data.test_mask].eq(target[data.test_mask]).sum().item()
    test_number = data.test_mask.sum().item()

    train_correct = prediction[data.train_mask].eq(target[data.train_mask]).sum().item()
    train_number = data.train_mask.sum().item()

    print("==" * 20)

    print("Accuracy of Train Samples: {:.04f}".format(train_correct / train_number))

    print("Accuracy of Test  Samples: {:.04f}".format(test_correct / test_number))


if __name__ == '__main__':
    test_main()
    # main()
    # dataset = get_data()
    # analysis_data(dataset)

def main():
    print("hello world")
main()

import os.path as osp
import argparse

import torch
import torch.nn.functional as F
from torch_geometric.datasets import Planetoid
import torch_geometric.transforms as T
from torch_geometric.nn import GCNConv, ChebConv  # noqa

#GCN用于提取圖的特征參數(shù)然后用于分類

#數(shù)據(jù)集初始化部分
parser = argparse.ArgumentParser()
parser.add_argument('--use_gdc', action='store_true',
                    help='Use GDC preprocessing.')
args = parser.parse_args()#是否使用GDC優(yōu)化
dataset = 'CiteSeer'#訓(xùn)練用的數(shù)據(jù)集
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', dataset)#數(shù)據(jù)集存放位置
dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())#數(shù)據(jù)初始化類，其dataset的基類是一個torch.utils.data.Dataset對象
data = dataset[0]#只有一個圖作為訓(xùn)練數(shù)據(jù)
#print(data)

#預(yù)處理和模型定義
if args.use_gdc:
    gdc = T.GDC(self_loop_weight=1, normalization_in='sym',
                normalization_out='col',
                diffusion_kwargs=dict(method='ppr', alpha=0.05),
                sparsification_kwargs=dict(method='topk', k=128,
                                           dim=0), exact=True)
    data = gdc(data)#圖擴(kuò)散卷積用于預(yù)處理

#搭建模型
class Net(torch.nn.Module):
    #放置參數(shù)層(一般為可學(xué)習(xí)層，不可學(xué)習(xí)層也可放置，若不放置，則在forward中用functional實現(xiàn))
    def __init__(self):
        super(Net, self).__init__()#在不覆蓋Module的Init函數(shù)的情況下設(shè)置Net的init函數(shù)
        self.conv1 = GCNConv(dataset.num_features, 16, cached=True,
                             normalize=not args.use_gdc)#第一層GCN卷積運算輸入特征向量大小為num_features輸出大小為16
        #GCNConv的def init需要in_channel和out_channel(卷積核的數(shù)量)的參數(shù)，并對in_channel和out_channel調(diào)用linear函數(shù)，而該函數(shù)的作用為構(gòu)建全連接層
        self.conv2 = GCNConv(16, dataset.num_classes, cached=True,
                             normalize=not args.use_gdc)#第二層GCN卷積運算輸入為16(第一層的輸出)輸出為num_class
        # self.conv1 = ChebConv(data.num_features, 16, K=2)
        # self.conv2 = ChebConv(16, data.num_features, K=2)

    #實現(xiàn)模型的功能各個層之間的連接關(guān)系(具體實現(xiàn))
    def forward(self):
        x, edge_index, edge_weight = data.x, data.edge_index, data.edge_attr#賦值data.x特征向量edge_index圖的形狀，edge_attr權(quán)重矩陣
        x = F.relu(self.conv1(x, edge_index, edge_weight))#第一層用非線性激活函數(shù)relu
        #x,edge_index,edge_weight特征矩陣，鄰接矩陣，權(quán)重矩陣組成GCN核心公式
        x = F.dropout(x, training=self.training)#用dropout函數(shù)防止過擬合
        x = self.conv2(x, edge_index, edge_weight)#第二層輸出
        return F.log_softmax(x, dim=1)#log_softmax激活函數(shù)用于最后一層返回分類結(jié)果
#Z=log_softmax(A*RELU(A*X*W0)*W1)A連接關(guān)系X特征矩陣W參數(shù)矩陣
#得到Z后即可用于分類
#softmax(dim=1)行和為1再取log  x為節(jié)點的embedding

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')#指定設(shè)備
model, data = Net().to(device), data.to(device)#copy model,data到device上

#優(yōu)化算法
optimizer = torch.optim.Adam([
    dict(params=model.conv1.parameters(), weight_decay=5e-4),#權(quán)重衰減避免過擬合
    dict(params=model.conv2.parameters(), weight_decay=0)#需要優(yōu)化的參數(shù)
], lr=0.01)  # Only perform weight-decay on first convolution.
#lr步長因子或者是學(xué)習(xí)率

#模型訓(xùn)練
def train():
    model.train()#設(shè)置成train模式
    optimizer.zero_grad()#清空所有被優(yōu)化的變量的梯度
    F.nll_loss(model()[data.train_mask], data.y[data.train_mask]).backward()#損失函數(shù)訓(xùn)練參數(shù)用于節(jié)點分類
    optimizer.step()#步長
     
@torch.no_grad()#不需要計算梯度，也不進(jìn)行反向傳播

#測試
def test():
    model.eval()#設(shè)置成evaluation模式
    logits, accs = model(), []
    for _, mask in data('train_mask', 'val_mask', 'test_mask'):#mask矩陣，掩膜作用與之相應(yīng)的部分不會被更新
        pred = logits[mask].max(1)[1]#mask對應(yīng)點的輸出向量最大值并取序號1
        acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()#判斷是否相等計算準(zhǔn)確度
        accs.append(acc)
    return accs

best_val_acc = test_acc = 0

#執(zhí)行
for epoch in range(1, 201):
    train()
    train_acc, val_acc, tmp_test_acc = test()#訓(xùn)練準(zhǔn)確率，實際輸入的準(zhǔn)確率，測試準(zhǔn)確率
    if val_acc > best_val_acc:
        best_val_acc = val_acc
        test_acc = tmp_test_acc
    log = 'Epoch: {:03d}, Train: {:.4f}, Val: {:.4f}, Test: {:.4f}'#類型及保留位數(shù)
    print(log.format(epoch, train_acc, best_val_acc, test_acc))#輸出格式化函數(shù)'''