{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Basic Neural Network\n",
        "\n",
        "<!--\n",
        "Project: PyTorch Neural Networks\n",
        "Author: RSK World\n",
        "Website: https://rskworld.in\n",
        "Email: help@rskworld.in\n",
        "Phone: +91 93305 39277\n",
        "-->\n",
        "\n",
        "This notebook demonstrates building and training a basic feedforward neural network.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Basic Neural Network\n",
        "# Project: PyTorch Neural Networks\n",
        "# Author: RSK World\n",
        "# Website: https://rskworld.in\n",
        "# Email: help@rskworld.in\n",
        "# Phone: +91 93305 39277\n",
        "\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.utils.data import DataLoader, TensorDataset\n",
        "import matplotlib.pyplot as plt\n",
        "import sys\n",
        "import os\n",
        "\n",
        "# Add parent directory to path\n",
        "sys.path.append('..')\n",
        "from models.basic_nn import BasicNeuralNetwork\n",
        "from training.utils import generate_sample_data, plot_training_history\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Prepare Data\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Generate sample data\n",
        "X_train, y_train, X_test, y_test = generate_sample_data(\n",
        "    n_samples=1000, n_features=20, n_classes=3\n",
        ")\n",
        "\n",
        "print(f\"Training set: {X_train.shape}, Labels: {y_train.shape}\")\n",
        "print(f\"Test set: {X_test.shape}, Labels: {y_test.shape}\")\n",
        "\n",
        "# Create data loaders\n",
        "train_dataset = TensorDataset(X_train, y_train)\n",
        "test_dataset = TensorDataset(X_test, y_test)\n",
        "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
        "test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Create and Train Model\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Create model\n",
        "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
        "model = BasicNeuralNetwork(input_size=20, hidden_size=64, output_size=3).to(device)\n",
        "\n",
        "# Define loss and optimizer\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
        "\n",
        "# Training loop\n",
        "num_epochs = 20\n",
        "train_losses = []\n",
        "test_losses = []\n",
        "train_accs = []\n",
        "test_accs = []\n",
        "\n",
        "for epoch in range(num_epochs):\n",
        "    # Training\n",
        "    model.train()\n",
        "    train_loss = 0.0\n",
        "    train_correct = 0\n",
        "    train_total = 0\n",
        "    \n",
        "    for inputs, labels in train_loader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        \n",
        "        optimizer.zero_grad()\n",
        "        outputs = model(inputs)\n",
        "        loss = criterion(outputs, labels)\n",
        "        loss.backward()\n",
        "        optimizer.step()\n",
        "        \n",
        "        train_loss += loss.item()\n",
        "        _, predicted = torch.max(outputs.data, 1)\n",
        "        train_total += labels.size(0)\n",
        "        train_correct += (predicted == labels).sum().item()\n",
        "    \n",
        "    # Evaluation\n",
        "    model.eval()\n",
        "    test_loss = 0.0\n",
        "    test_correct = 0\n",
        "    test_total = 0\n",
        "    \n",
        "    with torch.no_grad():\n",
        "        for inputs, labels in test_loader:\n",
        "            inputs, labels = inputs.to(device), labels.to(device)\n",
        "            outputs = model(inputs)\n",
        "            loss = criterion(outputs, labels)\n",
        "            \n",
        "            test_loss += loss.item()\n",
        "            _, predicted = torch.max(outputs.data, 1)\n",
        "            test_total += labels.size(0)\n",
        "            test_correct += (predicted == labels).sum().item()\n",
        "    \n",
        "    train_losses.append(train_loss / len(train_loader))\n",
        "    test_losses.append(test_loss / len(test_loader))\n",
        "    train_accs.append(100 * train_correct / train_total)\n",
        "    test_accs.append(100 * test_correct / test_total)\n",
        "    \n",
        "    if (epoch + 1) % 5 == 0:\n",
        "        print(f'Epoch [{epoch+1}/{num_epochs}]')\n",
        "        print(f'Train Loss: {train_losses[-1]:.4f}, Train Acc: {train_accs[-1]:.2f}%')\n",
        "        print(f'Test Loss: {test_losses[-1]:.4f}, Test Acc: {test_accs[-1]:.2f}%')\n",
        "        print('-' * 50)\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Plot training history\n",
        "history = {\n",
        "    'train_loss': train_losses,\n",
        "    'test_loss': test_losses,\n",
        "    'train_accuracy': train_accs,\n",
        "    'test_accuracy': test_accs\n",
        "}\n",
        "\n",
        "plot_training_history(history)\n",
        "\n"
      ]
    }
  ],
  "metadata": {
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}