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


"""
使用多层感知机替换输入输出的proj层
"""


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):
        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):
        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):
        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):
    def __init__(self, num_nodes, embed_dim, hidden_dim):
        super().__init__()
        self.manba1 = MANBA_Block(hidden_dim, hidden_dim * 2)
        self.graph_constructor = DynamicGraphConstructor(num_nodes, embed_dim)
        self.gc = GraphConvBlock(hidden_dim, hidden_dim)
        self.manba2 = MANBA_Block(hidden_dim, hidden_dim * 2)

    def forward(self, h):
        h1 = self.manba1(h)
        adj = self.graph_constructor()
        h2 = self.gc(h1, adj)
        h3 = self.manba2(h2)
        return h3


class MLP(nn.Module):
    def __init__(self, in_dim, hidden_dims, out_dim, activation=nn.ReLU):
        super().__init__()
        dims = [in_dim] + hidden_dims + [out_dim]
        layers = []
        for i in range(len(dims) - 2):
            layers += [nn.Linear(dims[i], dims[i + 1]), activation()]
        layers += [nn.Linear(dims[-2], dims[-1])]
        self.net = nn.Sequential(*layers)

    def forward(self, x):
        return self.net(x)


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)

        # 替换为MLP: input_proj(seq_len -> hidden_dim -> hidden_dim)
        self.input_proj = MLP(self.seq_len, [self.hidden_dim], self.hidden_dim)

        self.sandwich1 = SandwichBlock(self.num_nodes, self.embed_dim, self.hidden_dim)
        self.sandwich2 = SandwichBlock(self.num_nodes, self.embed_dim, self.hidden_dim)

        # 替换为MLP: out_proj(hidden_dim -> 2*hidden_dim -> horizon*output_dim)
        self.out_proj = MLP(
            self.hidden_dim, [2 * self.hidden_dim], self.horizon * self.output_dim
        )

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

        # (B, T, N) -> (B, N, T) -> (B*N, T) -> MLP -> (B, N, hidden_dim)
        x_flat = x_main.permute(0, 2, 1).reshape(B * N, T)
        h0 = self.input_proj(x_flat).view(B, N, self.hidden_dim)

        h1 = self.sandwich1(h0)
        h1 = h1 + h0
        h2 = self.sandwich2(h1)

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