import torch
import torch.nn as nn
import torch.nn.functional as F

"""
含残差的双层 空间->时间->空间 结构模型 无效
"""


class DynamicGraphConstructor(nn.Module):
    def __init__(self, node_num, embed_dim):
        super().__init__()
        self.nodevec1 = nn.Parameter(
            torch.randn(node_num, embed_dim), requires_grad=True
        )
        self.nodevec2 = nn.Parameter(
            torch.randn(node_num, embed_dim), requires_grad=True
        )

    def forward(self):
        # 构造动态邻接矩阵 (N, N)
        adj = torch.matmul(self.nodevec1, self.nodevec2.T)
        adj = F.relu(adj)
        adj = F.softmax(adj, dim=-1)
        return adj


class GraphConvBlock(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.theta = nn.Linear(input_dim, output_dim)
        self.residual = input_dim == output_dim
        if not self.residual:
            self.res_proj = nn.Linear(input_dim, output_dim)

    def forward(self, x, adj):
        # x: (B, N, C)
        res = x
        x = torch.matmul(adj, x)
        x = self.theta(x)
        x = x + (res if self.residual else self.res_proj(res))
        return F.relu(x)


class MANBA_Block(nn.Module):
    def __init__(self, input_dim, hidden_dim):
        super().__init__()
        self.attn = nn.MultiheadAttention(
            embed_dim=input_dim, num_heads=4, batch_first=True
        )
        self.ffn = nn.Sequential(
            nn.Linear(input_dim, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, input_dim),
        )
        self.norm1 = nn.LayerNorm(input_dim)
        self.norm2 = nn.LayerNorm(input_dim)

    def forward(self, x):
        # x: (B, N, C) 当 N 视为时间序列长度
        res = x
        x_attn, _ = self.attn(x, x, x)
        x = self.norm1(res + x_attn)
        res2 = x
        x_ffn = self.ffn(x)
        x = self.norm2(res2 + x_ffn)
        return x


class SandwichBlock(nn.Module):
    """
    空间 -> 时间 -> 空间 三明治结构
    输入/输出： (B, N, hidden_dim)
    """

    def __init__(self, num_nodes, embed_dim, hidden_dim):
        super().__init__()
        self.graph_constructor = DynamicGraphConstructor(num_nodes, embed_dim)
        self.gc1 = GraphConvBlock(hidden_dim, hidden_dim)
        self.manba = MANBA_Block(hidden_dim, hidden_dim * 2)
        self.gc2 = GraphConvBlock(hidden_dim, hidden_dim)

    def forward(self, h):
        # 第一步：空间卷积
        adj = self.graph_constructor()
        h1 = self.gc1(h, adj)
        # 第二步：时间注意力
        h2 = self.manba(h1)
        # 第三步：空间卷积
        h3 = self.gc2(h2, adj)
        return h3


class EXP(nn.Module):
    def __init__(self, args):
        super().__init__()
        self.horizon = args["horizon"]
        self.output_dim = args["output_dim"]
        self.seq_len = args.get("in_len", 12)
        self.hidden_dim = args.get("hidden_dim", 64)
        self.num_nodes = args["num_nodes"]
        self.embed_dim = args.get("embed_dim", 16)

        # 输入映射
        self.input_proj = nn.Linear(self.seq_len, self.hidden_dim)
        # 两层 空间-时间-空间 三明治块
        self.sandwich1 = SandwichBlock(self.num_nodes, self.embed_dim, self.hidden_dim)
        self.sandwich2 = SandwichBlock(self.num_nodes, self.embed_dim, self.hidden_dim)
        # 输出映射
        self.out_proj = nn.Linear(self.hidden_dim, self.horizon * self.output_dim)

    def forward(self, x):
        # x: (B, T, N, D)
        x_main = x[..., 0]  # (B, T, N)
        B, T, N = x_main.shape
        assert T == self.seq_len

        # 投影到隐藏维 (B,N,hidden)
        x_flat = x_main.permute(0, 2, 1).reshape(B * N, T)
        h0 = self.input_proj(x_flat).view(B, N, self.hidden_dim)

        # 第一层三明治 + 残差
        h1 = self.sandwich1(h0)
        h1 = h1 + h0
        # 第二层三明治
        h2 = self.sandwich2(h1)

        # 输出
        out = self.out_proj(h2)  # (B, N, H*D_out)
        out = out.view(B, N, self.horizon, self.output_dim)
        out = out.permute(0, 2, 1, 3)  # (B, horizon, N, output_dim)
        return out