import torch
import numpy as np
import pandas as pd
import torch.nn as nn

class TabularTransformer(nn.Module):
    def __init__(self, input_dim=7, output_dim=1, embedding_dim=64, num_heads=8, hidden_dim=128):
        super().__init__()
        self.embedding = nn.Linear(input_dim, embedding_dim)
        self.attention = nn.MultiheadAttention(embed_dim=embedding_dim, num_heads=num_heads)
        self.fc = nn.Sequential(
            nn.Linear(embedding_dim, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, output_dim)
        )
    
    def forward(self, x):
        x = self.embedding(x)
        x = x.unsqueeze(0)     # Add sequence dimension for attention
        attn_out, _ = self.attention(x, x, x)
        x = attn_out.squeeze(0)  # Remove sequence dimension
        return self.fc(x)

def model_predict(model, X_input, scaler_X, scaler_y):
    # Convert to tensor
    X_scaled = scaler_X.transform(X_input)
    X_tensor = torch.FloatTensor(X_scaled)
    
    # Make prediction
    with torch.no_grad():
        scaled_pred = model(X_tensor).numpy()
    
    # Inverse transform to get original scale prediction
    prediction = scaler_y.inverse_transform(scaled_pred)
    return prediction.flatten()