# model/InformerOnlyX/embed.py
import torch
import torch.nn as nn
import math


class PositionalEmbedding(nn.Module):
    def __init__(self, d_model, max_len=5000):
        super().__init__()
        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len).unsqueeze(1).float()
        div_term = torch.exp(
            torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model)
        )
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        self.register_buffer("pe", pe.unsqueeze(0))  # [1, L, D]

    def forward(self, x):
        return self.pe[:, :x.size(1)]


class DataEmbedding(nn.Module):
    """
    Informer-style embedding without time covariates
    """

    def __init__(self, c_in, d_model, dropout):
        super().__init__()
        self.value_embedding = nn.Linear(c_in, d_model)
        self.position_embedding = PositionalEmbedding(d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        x = self.value_embedding(x) + self.position_embedding(x)
        return self.dropout(x)