From 8c361ef0d5d4164c6f8becbc402a6e91b5e1d5f6 Mon Sep 17 00:00:00 2001 From: 202310715112 PUTRA AL RIFKI <202310715112@mhs.ubharajaya.ac.id> Date: Tue, 2 Dec 2025 10:46:48 +0700 Subject: [PATCH] Delete File Tugas/KNN.ipynb --- File Tugas/KNN.ipynb | 163 ------------------------------------------- 1 file changed, 163 deletions(-) delete mode 100644 File Tugas/KNN.ipynb diff --git a/File Tugas/KNN.ipynb b/File Tugas/KNN.ipynb deleted file mode 100644 index 0ff9db7..0000000 --- a/File Tugas/KNN.ipynb +++ /dev/null @@ -1,163 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 3, - "id": "c0efb2f2-b8bd-43a3-bef6-b8ffbd5b8844", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Sedang memproses data...\n", - "Sedang melatih model KNN (15 Tetangga)...\n", - "\n", - "========================================\n", - "HASIL EVALUASI (KNN)\n", - "========================================\n", - "1. Single Split Test:\n", - " - R2 Score (Akurasi) : 0.2060 (20.60%)\n", - " - RMSE (Error Kuadrat): 2.1397\n", - " - MAE (Rata-rata Error): 1.5157 poin\n", - "\n", - "2. Cross Validation (5-Fold):\n", - " - Skor per tes : [0.10580954 0.07685483 0.12809619 0.14718973 0.0873096 ]\n", - " - Rata-rata R2 : 0.1091\n", - " - Kestabilan : +/- 0.0258\n", - "\n", - "========================================\n", - "Contoh Prediksi: Rating Asli 7.0 | Prediksi KNN 5.32\n" - ] - } - ], - "source": [ - "import pandas as pd\n", - "import numpy as np\n", - "from sklearn.model_selection import train_test_split, cross_val_score\n", - "from sklearn.neighbors import KNeighborsRegressor\n", - "from sklearn.preprocessing import StandardScaler, LabelEncoder\n", - "from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error\n", - "\n", - "# ==========================================\n", - "# 1. LOAD DATA & PREPROCESSING\n", - "# ==========================================\n", - "print(\"Sedang memproses data...\")\n", - "df = pd.read_csv('Latest 2025 movies Datasets.csv')\n", - "\n", - "# Membersihkan data\n", - "df = df.dropna(subset=['release_date', 'vote_average', 'popularity', 'vote_count'])\n", - "df['release_date'] = pd.to_datetime(df['release_date'], errors='coerce')\n", - "df = df.dropna(subset=['release_date'])\n", - "\n", - "# Feature Engineering\n", - "df['release_year'] = df['release_date'].dt.year\n", - "df['release_month'] = df['release_date'].dt.month\n", - "\n", - "# Encoding Bahasa\n", - "le = LabelEncoder()\n", - "df['original_language_encoded'] = le.fit_transform(df['original_language'])\n", - "\n", - "# Fitur & Target\n", - "features = ['popularity', 'vote_count', 'release_year', 'release_month', 'original_language_encoded']\n", - "X = df[features]\n", - "y = df['vote_average']\n", - "\n", - "# Split Data\n", - "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", - "\n", - "# --- SCALING (Wajib untuk KNN) ---\n", - "scaler = StandardScaler()\n", - "X_train_scaled = scaler.fit_transform(X_train)\n", - "X_test_scaled = scaler.transform(X_test)\n", - "\n", - "# Kita juga perlu scale X full untuk Cross Validation nanti\n", - "X_scaled = scaler.transform(X)\n", - "\n", - "# ==========================================\n", - "# 2. TRAINING MODEL (KNN)\n", - "# ==========================================\n", - "print(\"Sedang melatih model KNN (15 Tetangga)...\")\n", - "model = KNeighborsRegressor(n_neighbors=15)\n", - "model.fit(X_train_scaled, y_train)\n", - "\n", - "# ==========================================\n", - "# 3. EVALUASI LENGKAP\n", - "# ==========================================\n", - "print(\"\\n\" + \"=\"*40)\n", - "print(\"HASIL EVALUASI (KNN)\")\n", - "print(\"=\"*40)\n", - "\n", - "# A. Single Split Test\n", - "y_pred = model.predict(X_test_scaled)\n", - "\n", - "r2 = r2_score(y_test, y_pred)\n", - "rmse = np.sqrt(mean_squared_error(y_test, y_pred))\n", - "mae = mean_absolute_error(y_test, y_pred)\n", - "\n", - "print(f\"1. Single Split Test:\")\n", - "print(f\" - R2 Score (Akurasi) : {r2:.4f} ({r2*100:.2f}%)\")\n", - "print(f\" - RMSE (Error Kuadrat): {rmse:.4f}\")\n", - "print(f\" - MAE (Rata-rata Error): {mae:.4f} poin\")\n", - "\n", - "# B. Cross Validation (5-Fold)\n", - "print(f\"\\n2. Cross Validation (5-Fold):\")\n", - "# Kita gunakan X_scaled (data penuh yang sudah di-scale)\n", - "cv_scores = cross_val_score(model, X_scaled, y, cv=5, scoring='r2')\n", - "\n", - "print(f\" - Skor per tes : {cv_scores}\")\n", - "print(f\" - Rata-rata R2 : {cv_scores.mean():.4f}\")\n", - "print(f\" - Kestabilan : +/- {cv_scores.std():.4f}\")\n", - "\n", - "# Contoh Prediksi\n", - "print(\"\\n\" + \"=\"*40)\n", - "print(f\"Contoh Prediksi: Rating Asli {y_test.iloc[0]} | Prediksi KNN {y_pred[0]:.2f}\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "784b48b0-d367-47da-912e-b75c91541665", - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "ffe5d513-95fe-452f-ba94-2ccd24e455b9", - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "fab61e94-fe4a-425f-81c8-ea32d2738733", - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "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": "3.12.0" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -}