{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import cupy as cp\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from itertools import product"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GPU is available. Using CuPy for GPU acceleration.\n"
     ]
    }
   ],
   "source": [
    "try:\n",
    "    import cupy as cp\n",
    "    if cp.cuda.is_available():\n",
    "        print(\"GPU is available. Using CuPy for GPU acceleration.\")\n",
    "        xp = cp\n",
    "    else:\n",
    "        print(\"GPU is not available. Falling back to NumPy on CPU.\")\n",
    "        xp = np\n",
    "except ImportError:\n",
    "    print(\"CuPy not found. Using NumPy on CPU.\")\n",
    "    xp = np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('data/bel_data_test.csv')\n",
    "data = xp.array(data)\n",
    "\n",
    "# Split data\n",
    "X = data[:, 1:].T\n",
    "Y = data[:, 0].astype(int)\n",
    "\n",
    "# Separate test set (first 1000 rows)\n",
    "X_test = X[:, :1000]\n",
    "Y_test = Y[:1000]\n",
    "\n",
    "# Remaining data for training and validation\n",
    "X_remain = X[:, 1000:]\n",
    "Y_remain = Y[1000:]\n",
    "\n",
    "# Split remaining data into training and validation sets\n",
    "X_train, X_val, Y_train, Y_val = train_test_split(X_remain.T, Y_remain, test_size=0.2, random_state=42)\n",
    "X_train, X_val = X_train.T, X_val.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Input layer size: 1024\n",
      "Output layer size: 61\n"
     ]
    }
   ],
   "source": [
    "# Determine input and output layer sizes\n",
    "input_size = X_train.shape[0]\n",
    "output_size = len(np.unique(Y))-1\n",
    "\n",
    "print(f\"Input layer size: {input_size}\")\n",
    "print(f\"Output layer size: {output_size}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, Y_train = xp.array(X_train), xp.array(Y_train)\n",
    "X_val, Y_val = xp.array(X_val), xp.array(Y_val)\n",
    "X_test, Y_test = xp.array(X_test), xp.array(Y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def init_params(layer_dims):\n",
    "    params = {}\n",
    "    L = len(layer_dims)\n",
    "    \n",
    "    for l in range(1, L):\n",
    "        params[f'W{l}'] = xp.random.randn(layer_dims[l], layer_dims[l-1]) * xp.sqrt(2. / layer_dims[l-1])\n",
    "        params[f'b{l}'] = xp.zeros((layer_dims[l], 1))\n",
    "    \n",
    "    return params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def ReLU(Z):\n",
    "    return xp.maximum(Z, 0)\n",
    "\n",
    "def softmax(Z):\n",
    "    A = xp.exp(Z) / sum(xp.exp(Z))\n",
    "    return A\n",
    "\n",
    "def forward_prop(X, params):\n",
    "    caches = []\n",
    "    A = X\n",
    "    L = len(params) // 2\n",
    "\n",
    "    for l in range(1, L):\n",
    "        A_prev = A\n",
    "        W = params[f'W{l}']\n",
    "        b = params[f'b{l}']\n",
    "        Z = xp.dot(W, A_prev) + b\n",
    "        A = ReLU(Z)\n",
    "        caches.append((A_prev, W, b, Z))\n",
    "\n",
    "    WL = params[f'W{L}']\n",
    "    bL = params[f'b{L}']\n",
    "    ZL = xp.dot(WL, A) + bL\n",
    "    AL = softmax(ZL)\n",
    "    caches.append((A, WL, bL, ZL))\n",
    "\n",
    "    return AL, caches\n",
    "\n",
    "def ReLU_deriv(Z):\n",
    "    return Z > 0\n",
    "\n",
    "def one_hot(Y):\n",
    "    # one_hot_Y = xp.zeros((Y.size, Y.max() + 1))\n",
    "    # one_hot_Y[xp.arange(Y.size), Y] = 1\n",
    "    # one_hot_Y = one_hot_Y.T\n",
    "    # return one_hot_Y\n",
    "    Y = Y.astype(int)\n",
    "    one_hot_Y = xp.zeros((Y.size, int(xp.max(Y)) + 1))\n",
    "    one_hot_Y[xp.arange(Y.size), Y] = 1\n",
    "    return one_hot_Y.T\n",
    "\n",
    "def backward_prop(AL, Y, caches):\n",
    "    grads = {}\n",
    "    L = len(caches)\n",
    "    m = AL.shape[1]\n",
    "    Y = one_hot(Y)\n",
    "\n",
    "    dAL = AL - Y\n",
    "    current_cache = caches[L-1]\n",
    "    grads[f\"dW{L}\"] = 1 / m * xp.dot(dAL, current_cache[0].T)\n",
    "    grads[f\"db{L}\"] = 1 / m * xp.sum(dAL, axis=1, keepdims=True)\n",
    "    dA_prev = xp.dot(current_cache[1].T, dAL)\n",
    "\n",
    "    for l in reversed(range(L-1)):\n",
    "        current_cache = caches[l]\n",
    "        dZ = dA_prev * ReLU_deriv(current_cache[3])\n",
    "        grads[f\"dW{l+1}\"] = 1 / m * xp.dot(dZ, current_cache[0].T)\n",
    "        grads[f\"db{l+1}\"] = 1 / m * xp.sum(dZ, axis=1, keepdims=True)\n",
    "        if l > 0:\n",
    "            dA_prev = xp.dot(current_cache[1].T, dZ)\n",
    "\n",
    "    return grads\n",
    "\n",
    "def update_params(params, grads, alpha):\n",
    "    L = len(params) // 2\n",
    "\n",
    "    for l in range(1, L + 1):\n",
    "        params[f\"W{l}\"] -= alpha * grads[f\"dW{l}\"]\n",
    "        params[f\"b{l}\"] -= alpha * grads[f\"db{l}\"]\n",
    "\n",
    "    return params\n",
    "\n",
    "def get_predictions(AL):\n",
    "    return xp.argmax(AL, axis=0)\n",
    "\n",
    "def get_accuracy(predictions, Y):\n",
    "    return xp.sum(predictions == Y) / Y.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def gradient_descent(X_train, Y_train, X_val, Y_val, layer_dims, alpha, iterations, accuracy_threshold=0.85):\n",
    "    params = init_params(layer_dims)\n",
    "    best_val_accuracy = 0\n",
    "    acc_store = []\n",
    "    \n",
    "    for i in range(iterations):\n",
    "        AL, caches = forward_prop(X_train, params)\n",
    "        grads = backward_prop(AL, Y_train, caches)\n",
    "        params = update_params(params, grads, alpha)\n",
    "\n",
    "        if i % 100 == 0:\n",
    "            train_predictions = get_predictions(AL)\n",
    "            train_accuracy = get_accuracy(train_predictions, Y_train)\n",
    "            \n",
    "            val_AL, _ = forward_prop(X_val, params)\n",
    "            val_predictions = get_predictions(val_AL)\n",
    "            val_accuracy = get_accuracy(val_predictions, Y_val)\n",
    "            \n",
    "            print(f\"Iteration {i}: Train Accuracy: {train_accuracy:.4f}, Validation Accuracy: {val_accuracy:.4f}\")\n",
    "            acc_store.append((train_accuracy, val_accuracy))\n",
    "            \n",
    "            if val_accuracy > best_val_accuracy:\n",
    "                best_val_accuracy = val_accuracy\n",
    "                best_params = params.copy()\n",
    "            \n",
    "            # Early stopping condition based on validation accuracy threshold\n",
    "            if val_accuracy >= accuracy_threshold:\n",
    "                print(f\"Validation accuracy threshold of {accuracy_threshold:.2f} reached. Stopping training.\")\n",
    "                break\n",
    "\n",
    "    return best_params, best_val_accuracy, acc_store"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def grid_search(X_train, Y_train, X_val, Y_val, layer_configs, alpha, iterations, accuracy_threshold=0.85):\n",
    "    results = []\n",
    "    \n",
    "    for layer_config in layer_configs:\n",
    "        layer_dims = [input_size] + list(layer_config) + [output_size]\n",
    "        print(f\"Training architecture: {layer_dims}\")\n",
    "        best_params, accuracy, acc_store = gradient_descent(X_train, Y_train, X_val, Y_val, layer_dims, alpha, iterations, accuracy_threshold)\n",
    "        results.append((layer_config, accuracy, best_params, acc_store))\n",
    "        print(f\"Architecture {layer_dims}: Best Validation Accuracy: {accuracy:.4f}\\n\")\n",
    "    \n",
    "    return sorted(results, key=lambda x: x[1], reverse=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# def predict(X, parameters):\n",
    "#     AL, _ = forward_propagation(X, parameters)\n",
    "#     predictions = (AL > 0.5)  # Classify as 1 if greater than 0.5\n",
    "#     return predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "hidden_layers = [1, 2]\n",
    "neurons_per_layer = [64, 128, 256]\n",
    "layer_configs = list(product(*[neurons_per_layer] * max(hidden_layers)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Performing grid search...\n",
      "Training architecture: [1024, 64, 64, 61]\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "'ndarray' object cannot be interpreted as an integer",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[12], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# Perform grid search\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPerforming grid search...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 3\u001b[0m best_configs \u001b[38;5;241m=\u001b[39m \u001b[43mgrid_search\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlayer_configs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malpha\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.01\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43miterations\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m4000\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mTop 5 Architectures:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m config, accuracy, _, _ \u001b[38;5;129;01min\u001b[39;00m best_configs[:\u001b[38;5;241m5\u001b[39m]:\n",
      "Cell \u001b[0;32mIn[9], line 7\u001b[0m, in \u001b[0;36mgrid_search\u001b[0;34m(X_train, Y_train, X_val, Y_val, layer_configs, alpha, iterations, accuracy_threshold)\u001b[0m\n\u001b[1;32m      5\u001b[0m layer_dims \u001b[38;5;241m=\u001b[39m [input_size] \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mlist\u001b[39m(layer_config) \u001b[38;5;241m+\u001b[39m [output_size]\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTraining architecture: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlayer_dims\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 7\u001b[0m best_params, accuracy, acc_store \u001b[38;5;241m=\u001b[39m \u001b[43mgradient_descent\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlayer_dims\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malpha\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43miterations\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maccuracy_threshold\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      8\u001b[0m results\u001b[38;5;241m.\u001b[39mappend((layer_config, accuracy, best_params, acc_store))\n\u001b[1;32m      9\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mArchitecture \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlayer_dims\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: Best Validation Accuracy: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00maccuracy\u001b[38;5;132;01m:\u001b[39;00m\u001b[38;5;124m.4f\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
      "Cell \u001b[0;32mIn[8], line 8\u001b[0m, in \u001b[0;36mgradient_descent\u001b[0;34m(X_train, Y_train, X_val, Y_val, layer_dims, alpha, iterations, accuracy_threshold)\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(iterations):\n\u001b[1;32m      7\u001b[0m     AL, caches \u001b[38;5;241m=\u001b[39m forward_prop(X_train, params)\n\u001b[0;32m----> 8\u001b[0m     grads \u001b[38;5;241m=\u001b[39m \u001b[43mbackward_prop\u001b[49m\u001b[43m(\u001b[49m\u001b[43mAL\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaches\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      9\u001b[0m     params \u001b[38;5;241m=\u001b[39m update_params(params, grads, alpha)\n\u001b[1;32m     11\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m i \u001b[38;5;241m%\u001b[39m \u001b[38;5;241m100\u001b[39m \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
      "Cell \u001b[0;32mIn[7], line 42\u001b[0m, in \u001b[0;36mbackward_prop\u001b[0;34m(AL, Y, caches)\u001b[0m\n\u001b[1;32m     40\u001b[0m L \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(caches)\n\u001b[1;32m     41\u001b[0m m \u001b[38;5;241m=\u001b[39m AL\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m---> 42\u001b[0m Y \u001b[38;5;241m=\u001b[39m \u001b[43mone_hot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mY\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     44\u001b[0m dAL \u001b[38;5;241m=\u001b[39m AL \u001b[38;5;241m-\u001b[39m Y\n\u001b[1;32m     45\u001b[0m current_cache \u001b[38;5;241m=\u001b[39m caches[L\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
      "Cell \u001b[0;32mIn[7], line 33\u001b[0m, in \u001b[0;36mone_hot\u001b[0;34m(Y)\u001b[0m\n\u001b[1;32m     32\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mone_hot\u001b[39m(Y):\n\u001b[0;32m---> 33\u001b[0m     one_hot_Y \u001b[38;5;241m=\u001b[39m \u001b[43mxp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mzeros\u001b[49m\u001b[43m(\u001b[49m\u001b[43m(\u001b[49m\u001b[43mY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     34\u001b[0m     one_hot_Y[xp\u001b[38;5;241m.\u001b[39marange(Y\u001b[38;5;241m.\u001b[39msize), Y] \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m     35\u001b[0m     one_hot_Y \u001b[38;5;241m=\u001b[39m one_hot_Y\u001b[38;5;241m.\u001b[39mT\n",
      "File \u001b[0;32m~/.pyenv/versions/semantics/lib/python3.12/site-packages/cupy/_creation/basic.py:248\u001b[0m, in \u001b[0;36mzeros\u001b[0;34m(shape, dtype, order)\u001b[0m\n\u001b[1;32m    229\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mzeros\u001b[39m(\n\u001b[1;32m    230\u001b[0m         shape: _ShapeLike,\n\u001b[1;32m    231\u001b[0m         dtype: DTypeLike \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mfloat\u001b[39m,\n\u001b[1;32m    232\u001b[0m         order: _OrderCF \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mC\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m    233\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m NDArray[Any]:\n\u001b[1;32m    234\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Returns a new array of given shape and dtype, filled with zeros.\u001b[39;00m\n\u001b[1;32m    235\u001b[0m \n\u001b[1;32m    236\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    246\u001b[0m \n\u001b[1;32m    247\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 248\u001b[0m     a \u001b[38;5;241m=\u001b[39m \u001b[43mcupy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mndarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mshape\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    249\u001b[0m     a\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mmemset_async(\u001b[38;5;241m0\u001b[39m, a\u001b[38;5;241m.\u001b[39mnbytes)\n\u001b[1;32m    250\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m a\n",
      "File \u001b[0;32mcupy/_core/core.pyx:137\u001b[0m, in \u001b[0;36mcupy._core.core.ndarray.__new__\u001b[0;34m()\u001b[0m\n",
      "File \u001b[0;32mcupy/_core/core.pyx:202\u001b[0m, in \u001b[0;36mcupy._core.core._ndarray_base._init\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mTypeError\u001b[0m: 'ndarray' object cannot be interpreted as an integer"
     ]
    }
   ],
   "source": [
    "# Perform grid search\n",
    "print(\"Performing grid search...\")\n",
    "best_configs = grid_search(X_train, Y_train, X_val, Y_val, layer_configs, alpha=0.01, iterations=4000)\n",
    "\n",
    "print(\"\\nTop 5 Architectures:\")\n",
    "for config, accuracy, _, _ in best_configs[:5]:\n",
    "    print(f\"Hidden Layers: {config}, Validation Accuracy: {accuracy:.4f}\")\n",
    "\n",
    "# Select the best configuration\n",
    "best_config, best_accuracy, best_params, best_acc_store = best_configs[0]\n",
    "best_layer_dims = [input_size] + list(best_config) + [output_size]\n",
    "\n",
    "print(f\"\\nBest architecture: {best_layer_dims}\")\n",
    "print(f\"Best validation accuracy: {best_accuracy:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the accuracy data for the best model\n",
    "df = pd.DataFrame(best_acc_store, columns=['Train Accuracy', 'Validation Accuracy'])\n",
    "df.to_csv('results/bel_acc.csv', index=False)\n",
    "\n",
    "# Save the weights of the best model\n",
    "np.savez(\"weights/bel_weights\", **best_params)\n",
    "\n",
    "# Evaluate on test set\n",
    "test_AL, _ = forward_prop(X_test, best_params)\n",
    "test_predictions = get_predictions(test_AL)\n",
    "test_accuracy = get_accuracy(test_predictions, Y_test)\n",
    "print(f\"Test Accuracy: {test_accuracy:.4f}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "semantics",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}