TIF_E41211245/Code Python/traning_lvq_crossValditaion.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import sklearn.preprocessing as pre\n",
    "from sklearn.model_selection import train_test_split, StratifiedKFold\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.load(\"E:\\! KULIAHHH\\Ivano Kuliah\\!SEMESTER 8\\!SKRIPSI\\Data Suara\\!REVISI\\hasil_ekstrak_mfcc_v2/X_train.npy\")\n",
    "y = np.load(\"E:\\! KULIAHHH\\Ivano Kuliah\\!SEMESTER 8\\!SKRIPSI\\Data Suara\\!REVISI\\hasil_ekstrak_mfcc_v2/y_train.npy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Encode label menjadi angka\n",
    "label_encoder = pre.LabelEncoder()\n",
    "y_encoded = label_encoder.fit_transform(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Inisialisasi K-Fold Cross-Validation\n",
    "k = 5  # Jumlah fold\n",
    "kf = StratifiedKFold(n_splits=k, shuffle=True, random_state=42)\n",
    "accuracies = []  # Simpan akurasi tiap fold"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "class LVQ:\n",
    "    def __init__(self, n_classes, n_prototypes=2, learning_rate=0.01, epochs=200):\n",
    "        self.n_classes = n_classes\n",
    "        self.n_prototypes = n_prototypes\n",
    "        self.learning_rate = learning_rate\n",
    "        self.epochs = epochs\n",
    "        self.prototypes = None\n",
    "        self.prototype_labels = None\n",
    "\n",
    "    def fit(self, X, y):\n",
    "        np.random.seed(42)\n",
    "        self.prototypes = []\n",
    "        self.prototype_labels = []\n",
    "\n",
    "        for label in np.unique(y):\n",
    "            idx = np.where(y == label)[0]\n",
    "            chosen = np.random.choice(idx, self.n_prototypes, replace=False)\n",
    "            self.prototypes.extend(X[chosen])\n",
    "            self.prototype_labels.extend([label] * self.n_prototypes)\n",
    "\n",
    "        self.prototypes = np.array(self.prototypes)\n",
    "        self.prototype_labels = np.array(self.prototype_labels)\n",
    "\n",
    "        for epoch in range(self.epochs):\n",
    "            for i in range(len(X)):\n",
    "                sample = X[i]\n",
    "                label = y[i]\n",
    "                distances = np.linalg.norm(self.prototypes - sample, axis=1)\n",
    "                winner_idx = np.argmin(distances)\n",
    "\n",
    "                if self.prototype_labels[winner_idx] == label:\n",
    "                    self.prototypes[winner_idx] += self.learning_rate * (sample - self.prototypes[winner_idx])\n",
    "                else:\n",
    "                    self.prototypes[winner_idx] -= self.learning_rate * (sample - self.prototypes[winner_idx])\n",
    "\n",
    "            self.learning_rate *= 0.95\n",
    "\n",
    "    def predict(self, X):\n",
    "        y_pred = []\n",
    "        for sample in X:\n",
    "            distances = np.linalg.norm(self.prototypes - sample, axis=1)\n",
    "            winner_idx = np.argmin(distances)\n",
    "            y_pred.append(self.prototype_labels[winner_idx])\n",
    "        return np.array(y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "🔄 Fold 1/5...\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Akurasi Fold 1: 79.59%\n",
      "🔄 Fold 2/5...\n",
      "✅ Akurasi Fold 2: 87.76%\n",
      "🔄 Fold 3/5...\n",
      "✅ Akurasi Fold 3: 77.08%\n",
      "🔄 Fold 4/5...\n",
      "✅ Akurasi Fold 4: 83.33%\n",
      "🔄 Fold 5/5...\n",
      "✅ Akurasi Fold 5: 70.83%\n",
      "\n",
      "📊 Rata-rata Akurasi dari 5-Fold Cross Validation: 79.72%\n"
     ]
    }
   ],
   "source": [
    "# K-Fold Cross-Validation\n",
    "for fold, (train_idx, test_idx) in enumerate(kf.split(X, y_encoded)):\n",
    "    print(f\"🔄 Fold {fold+1}/{k}...\")\n",
    "\n",
    "    # Split data untuk fold ini\n",
    "    X_train, X_test = X[train_idx], X[test_idx]\n",
    "    y_train, y_test = y_encoded[train_idx], y_encoded[test_idx]\n",
    "\n",
    "    # Inisialisasi dan training model LVQ\n",
    "    lvq_model = LVQ(n_classes=len(set(y_encoded)), n_prototypes=2, learning_rate=0.01, epochs=200)\n",
    "    lvq_model.fit(X_train, y_train)\n",
    "\n",
    "    # Prediksi data uji\n",
    "    y_pred = lvq_model.predict(X_test)\n",
    "\n",
    "    # Evaluasi\n",
    "    accuracy = accuracy_score(y_test, y_pred)\n",
    "    accuracies.append(accuracy)\n",
    "    print(f\"✅ Akurasi Fold {fold+1}: {accuracy * 100:.2f}%\")\n",
    "\n",
    "# Hitung rata-rata akurasi dari semua fold\n",
    "mean_accuracy = np.mean(accuracies)\n",
    "print(f\"\\n📊 Rata-rata Akurasi dari {k}-Fold Cross Validation: {mean_accuracy * 100:.2f}%\")\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}