import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from torch.utils.data import DataLoader, TensorDataset
import numpy as np

class AdamOptimizer(optim.Optimizer):
    """
    Implementation of the Adam (Adaptive Moment Estimation) algorithm 
    as described in Kingma & Ba (2015).
    """
    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8):
        if not 0.0 <= lr:
            raise ValueError(f"Invalid learning rate: {lr}")
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError(f"Invalid beta1 parameter: {betas[0]}")
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError(f"Invalid beta2 parameter: {betas[1]}")
        if not 0.0 <= eps:
            raise ValueError(f"Invalid epsilon value: {eps}")

        defaults = dict(lr=lr, betas=betas, eps=eps)
        super(AdamOptimizer, self).__init__(params, defaults)

    @torch.no_grad()
    def step(self, closure=None):
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            beta1, beta2 = group['betas']
            eps = group['eps']
            lr = group['lr']

            for p in group['params']:
                if p.grad is None:
                    continue
                
                grad = p.grad
                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    state['step'] = 0
                    state['exp_avg'] = torch.zeros_like(p)
                    state['exp_avg_sq'] = torch.zeros_like(p)

                exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
                state['step'] += 1
                t = state['step']

                # 1. Update biased first moment estimate
                exp_avg.mul_(beta1).add_(grad, alpha=1 - beta1)

                # 2. Update biased second raw moment estimate
                exp_avg_sq.mul_(beta2).addcmul_(grad, grad, value=1 - beta2)

                # 3 & 4. Compute bias-corrected estimates
                bias_correction1 = 1 - beta1 ** t
                bias_correction2 = 1 - beta2 ** t

                # 5. Update parameters
                denom = (exp_avg_sq.sqrt() / np.sqrt(bias_correction2)).add_(eps)
                step_size = lr / bias_correction1
                p.addcdiv_(exp_avg, denom, value=-step_size)

        return loss

# ==========================================
# DEMONSTRATION: Training a Simple MLP
# ==========================================

class SimpleMLP(nn.Module):
    def __init__(self, input_dim):
        super(SimpleMLP, self).__init__()
        self.net = nn.Sequential(
            nn.Linear(input_dim, 32), nn.ReLU(),
            nn.Linear(32, 16), nn.ReLU(),
            nn.Linear(16, 1), nn.Sigmoid()
        )

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

if __name__ == '__main__':
    # Setup Dataset
    X, y = make_classification(n_samples=1000, n_features=20, random_state=42)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
    
    scaler = StandardScaler()
    X_train = torch.FloatTensor(scaler.fit_transform(X_train))
    y_train = torch.FloatTensor(y_train).unsqueeze(1)
    X_test = torch.FloatTensor(scaler.transform(X_test))
    y_test = torch.FloatTensor(y_test).unsqueeze(1)

    train_loader = DataLoader(TensorDataset(X_train, y_train), batch_size=32, shuffle=True)

    model = SimpleMLP(input_dim=20)
    criterion = nn.BCELoss()
    optimizer = AdamOptimizer(model.parameters(), lr=0.001)

    for epoch in range(20):
        model.train()
        for batch_X, batch_y in train_loader:
            optimizer.zero_grad()
            loss = criterion(model(batch_X), batch_y)
            loss.backward()
            optimizer.step()
        
        if (epoch + 1) % 5 == 0:
            print(f"Epoch [{epoch+1}/20] completed.")

    model.eval()
    with torch.no_grad():
        acc = ((model(X_test) > 0.5).float() == y_test).float().mean()
        print(f"\nFinal Test Accuracy: {acc.item():.4f}")