# AUTOGENERATED! DO NOT EDIT! File to edit: ../../modules/source/04_networks/networks_dev.ipynb.

# %% auto 0
__all__ = ['Sequential', 'create_mlp']

# %% ../../modules/source/04_networks/networks_dev.ipynb 1
import numpy as np
import sys
import os
from typing import List, Union, Optional, Callable
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from matplotlib.patches import FancyBboxPatch, ConnectionPatch
import seaborn as sns

# Import all the building blocks we need - try package first, then local modules
try:
    from tinytorch.core.tensor import Tensor
    from tinytorch.core.layers import Dense
    from tinytorch.core.activations import ReLU, Sigmoid, Tanh, Softmax
except ImportError:
    # For development, import from local modules
    sys.path.append(os.path.join(os.path.dirname(__file__), '..', '01_tensor'))
    sys.path.append(os.path.join(os.path.dirname(__file__), '..', '02_activations'))
    sys.path.append(os.path.join(os.path.dirname(__file__), '..', '03_layers'))
    from tensor_dev import Tensor
    from activations_dev import ReLU, Sigmoid, Tanh, Softmax
    from layers_dev import Dense

# %% ../../modules/source/04_networks/networks_dev.ipynb 2
def _should_show_plots():
    """Check if we should show plots (disable during testing)"""
    # Check multiple conditions that indicate we're in test mode
    is_pytest = (
        'pytest' in sys.modules or
        'test' in sys.argv or
        os.environ.get('PYTEST_CURRENT_TEST') is not None or
        any('test' in arg for arg in sys.argv) or
        any('pytest' in arg for arg in sys.argv)
    )
    
    # Show plots in development mode (when not in test mode)
    return not is_pytest

# %% ../../modules/source/04_networks/networks_dev.ipynb 7
class Sequential:
    """
    Sequential Network: Composes layers in sequence
    
    The most fundamental network architecture.
    Applies layers in order: f(x) = layer_n(...layer_2(layer_1(x)))
    """
    
    def __init__(self, layers: List):
        """
        Initialize Sequential network with layers.
        
        Args:
            layers: List of layers to compose in order
            
        TODO: Store the layers and implement forward pass
        
        APPROACH:
        1. Store the layers list as an instance variable
        2. This creates the network architecture ready for forward pass
        
        EXAMPLE:
        Sequential([Dense(3,4), ReLU(), Dense(4,2)])
        creates a 3-layer network: Dense → ReLU → Dense
        
        HINTS:
        - Store layers in self.layers
        - This is the foundation for all network architectures
        """
        ### BEGIN SOLUTION
        self.layers = layers
        ### END SOLUTION
    
    def forward(self, x: Tensor) -> Tensor:
        """
        Forward pass through all layers in sequence.
        
        Args:
            x: Input tensor
            
        Returns:
            Output tensor after passing through all layers
            
        TODO: Implement sequential forward pass through all layers
        
        APPROACH:
        1. Start with the input tensor
        2. Apply each layer in sequence
        3. Each layer's output becomes the next layer's input
        4. Return the final output
        
        EXAMPLE:
        Input: Tensor([[1, 2, 3]])
        Layer1 (Dense): Tensor([[1.4, 2.8]])
        Layer2 (ReLU): Tensor([[1.4, 2.8]])
        Layer3 (Dense): Tensor([[0.7]])
        Output: Tensor([[0.7]])
        
        HINTS:
        - Use a for loop: for layer in self.layers:
        - Apply each layer: x = layer(x)
        - The output of one layer becomes input to the next
        - Return the final result
        """
        ### BEGIN SOLUTION
        # Apply each layer in sequence
        for layer in self.layers:
            x = layer(x)
        return x
        ### END SOLUTION
    
    def __call__(self, x: Tensor) -> Tensor:
        """Make network callable: network(x) same as network.forward(x)"""
        return self.forward(x)

# %% ../../modules/source/04_networks/networks_dev.ipynb 11
def create_mlp(input_size: int, hidden_sizes: List[int], output_size: int, 
               activation=ReLU, output_activation=Sigmoid) -> Sequential:
    """
    Create a Multi-Layer Perceptron (MLP) network.
    
    Args:
        input_size: Number of input features
        hidden_sizes: List of hidden layer sizes
        output_size: Number of output features
        activation: Activation function for hidden layers (default: ReLU)
        output_activation: Activation function for output layer (default: Sigmoid)
        
    Returns:
        Sequential network with MLP architecture
        
    TODO: Implement MLP creation with alternating Dense and activation layers.
    
    APPROACH:
    1. Start with an empty list of layers
    2. Add layers in this pattern:
       - Dense(input_size → first_hidden_size)
       - Activation()
       - Dense(first_hidden_size → second_hidden_size)
       - Activation()
       - ...
       - Dense(last_hidden_size → output_size)
       - Output_activation()
    3. Return Sequential(layers)
    
    EXAMPLE:
    create_mlp(3, [4, 2], 1) creates:
    Dense(3→4) → ReLU → Dense(4→2) → ReLU → Dense(2→1) → Sigmoid
    
    HINTS:
    - Start with layers = []
    - Track current_size starting with input_size
    - For each hidden_size: add Dense(current_size, hidden_size), then activation
    - Finally add Dense(last_hidden_size, output_size), then output_activation
    - Return Sequential(layers)
    """
    ### BEGIN SOLUTION
    layers = []
    current_size = input_size
    
    # Add hidden layers with activations
    for hidden_size in hidden_sizes:
        layers.append(Dense(current_size, hidden_size))
        layers.append(activation())
        current_size = hidden_size
    
    # Add output layer with output activation
    layers.append(Dense(current_size, output_size))
    layers.append(output_activation())
    
    return Sequential(layers)
    ### END SOLUTION