from torch import nn


class CNNLSTM(nn.Module):
    def __init__(self,
                 input_dim: int,
                 output_dim: int,
                 embed_dim: int,
                 lstm_hidden_size=64,
                 num_layers=1):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv1d(in_channels=input_dim, out_channels=input_dim, kernel_size=9, stride=2),  # 288 → ~140
            nn.ReLU(),
            nn.AdaptiveAvgPool1d(output_size=128),  # force to 128
            nn.Conv1d(input_dim, input_dim, kernel_size=5, stride=2),  # 128 → ~62
            nn.ReLU(),
            nn.AdaptiveAvgPool1d(output_size=48),  # final fixed length
        )

        # linear projection to embed dim
        self.input_proj = nn.Linear(input_dim, embed_dim)

        self.lstm = nn.LSTM(
            input_size=embed_dim,
            hidden_size=lstm_hidden_size,
            num_layers=num_layers,
            batch_first=True,
            dropout=0.4,
        )
        self.head = nn.Sequential(
            nn.Linear(lstm_hidden_size, output_dim)  # Output is a scalar Δt
        )

    def forward(self, x):
        # x: (batch_size, seq_len, input_size)
        x = x.permute(0, 2, 1)
        # x: (batch_size, input_size, seq_len)
        x = self.conv(x)
        # x: (batch_size, embed_dim, seq_len)
        x = x.permute(0, 2, 1)
        # x: (batch_size, seq_len, embed_dim)
        # project to embed dim
        x = self.input_proj(x)
        # x: (batch_size, seq_len, embed_dim)
        x, _ = self.lstm(x)
        # x: (batch_size, seq_len, lstm_hidden_size)
        x = x[:, -1, :]  # Get the last time step
        # x: (batch_size, lstm_hidden_size)
        x = self.head(x)
        # x: (batch_size, output_size)
        return x