Initial Commit

Dataset/userHistory.csv

@@ -0,0 +1,11 @@
+userID,namaWisata
+1,Hill of Gibeon
+1,Bukit Indah Sitalmak Talmak Sihotang
+1,Bukit Senyum
+1,Bukit Beta Tuk-tuk
+2,Tao Silalahi
+2,Pantai Silalahi
+2,Objek Wisata Pantai Paris
+2,Prapat bahari
+2,Wisata Alam Fishing-Camp Siarubung
+2,Aek Batu Sipolha

Evaluasi User to Item/evaluasiKFOLDLOG.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a95ae49e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   user_id  avg_hit_rate\n",
+      "0        1          0.75\n",
+      "1        2          0.25\n",
+      "\n",
+      "Rata-rata Hit Rate Top-5 dengan 4 lipatan: 0.50\n"
+     ]
+    }
+   ],
+   "source": [
+    "# %%\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "from sklearn.model_selection import KFold\n",
+    "\n",
+    "# %%\n",
+    "# Load data\n",
+    "df_wisata = pd.read_csv(\"../Dataset/data_Processed.csv\")\n",
+    "df_history = pd.read_csv(\"../Dataset/userHistory.csv\")\n",
+    "\n",
+    "# TF-IDF untuk semua tempat wisata\n",
+    "tfidf = TfidfVectorizer()\n",
+    "tfidf_matrix = tfidf.fit_transform(df_wisata['tags_joined'])\n",
+    "\n",
+    "# %%\n",
+    "def hit_rate_fold(train_visits, test_visits, top_n=5):\n",
+    "    # Ambil indeks train dari df_wisata\n",
+    "    visited_indices = df_wisata[df_wisata['title'].isin(train_visits)].index\n",
+    "    if len(visited_indices) == 0:\n",
+    "        return None  # Profil tidak bisa dibentuk\n",
+    "\n",
+    "    # Bangun profil user\n",
+    "    user_profile_matrix = tfidf_matrix[visited_indices].mean(axis=0)\n",
+    "    user_profile = np.asarray(user_profile_matrix).reshape(1, -1)\n",
+    "\n",
+    "    # Hitung similarity\n",
+    "    similarities = cosine_similarity(user_profile, tfidf_matrix).flatten()\n",
+    "    df_wisata['similarity'] = similarities\n",
+    "\n",
+    "    # Buang wisata yang ada di train\n",
+    "    rekomendasi = df_wisata[~df_wisata['title'].isin(train_visits)]\n",
+    "    rekomendasi = rekomendasi.sort_values(by='similarity', ascending=False)\n",
+    "\n",
+    "    # Ambil Top-N rekomendasi\n",
+    "    top_rekomendasi = rekomendasi['title'].head(top_n).tolist()\n",
+    "\n",
+    "    # Hit Rate: berapa dari test_visits yang muncul di Top-N\n",
+    "    hits = len(set(top_rekomendasi) & set(test_visits))\n",
+    "    hit_rate = hits / len(test_visits)\n",
+    "    return hit_rate\n",
+    "\n",
+    "# %%\n",
+    "def evaluate_user_kfold(user_id, top_n=5, k=5):\n",
+    "    user_visits = df_history[df_history['userID'] == user_id]['namaWisata'].tolist()\n",
+    "    \n",
+    "    if len(user_visits) < k:\n",
+    "        return None  # Data terlalu sedikit untuk KFold\n",
+    "\n",
+    "    kf = KFold(n_splits=k, shuffle=True, random_state=42)\n",
+    "    fold_hit_rates = []\n",
+    "\n",
+    "    for train_index, test_index in kf.split(user_visits):\n",
+    "        train_visits = [user_visits[i] for i in train_index]\n",
+    "        test_visits = [user_visits[i] for i in test_index]\n",
+    "\n",
+    "        hr = hit_rate_fold(train_visits, test_visits, top_n=top_n)\n",
+    "        if hr is not None:\n",
+    "            fold_hit_rates.append(hr)\n",
+    "\n",
+    "    if fold_hit_rates:\n",
+    "        return {\n",
+    "            'user_id': user_id,\n",
+    "            'avg_hit_rate': np.mean(fold_hit_rates),\n",
+    "            'folds': k,\n",
+    "            'fold_hit_rates': fold_hit_rates\n",
+    "        }\n",
+    "    else:\n",
+    "        return None\n",
+    "\n",
+    "# %%\n",
+    "# Evaluasi semua user secara dinamis\n",
+    "user_ids = df_history['userID'].unique()\n",
+    "all_results = []\n",
+    "\n",
+    "for uid in user_ids:\n",
+    "    result = evaluate_user_kfold(uid, top_n=5, k=4)\n",
+    "    if result:\n",
+    "        all_results.append(result)\n",
+    "\n",
+    "# Hasil evaluasi ke DataFrame\n",
+    "df_eval = pd.DataFrame(all_results)\n",
+    "print(df_eval[['user_id', 'avg_hit_rate']])\n",
+    "\n",
+    "# Rata-rata keseluruhan\n",
+    "average_hit_rate_all = df_eval['avg_hit_rate'].mean()\n",
+    "print(f\"\\nRata-rata Hit Rate Top-5 dengan 4 lipatan: {average_hit_rate_all:.2f}\")\n",
+    "\n",
+    "# Simpan ke file jika perlu\n",
+    "# df_eval.to_csv(\"hasil_evaluasi_hit_rate_kfold.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "274fd69c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Evaluasi User to Item/evaluasiLOG.ipynb

@@ -0,0 +1,117 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a19b25b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   user_id  hit_rate\n",
+      "0        1  1.000000\n",
+      "1        2  0.333333\n",
+      "\n",
+      "Average Hit Rate@5: 0.67\n"
+     ]
+    }
+   ],
+   "source": [
+    "# %%\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "# %%\n",
+    "# Load data\n",
+    "df_wisata = pd.read_csv(\"../Dataset/data_Processed.csv\")\n",
+    "df_history = pd.read_csv(\"../Dataset/userHistory.csv\")\n",
+    "\n",
+    "# TF-IDF\n",
+    "tfidf = TfidfVectorizer()\n",
+    "tfidf_matrix = tfidf.fit_transform(df_wisata['tags_joined'])\n",
+    "\n",
+    "# %%\n",
+    "def evaluate_user_hit(user_id, top_n=5):\n",
+    "    user_visits = df_history[df_history['userID'] == user_id]['namaWisata'].tolist()\n",
+    "    \n",
+    "    if len(user_visits) < 2:\n",
+    "        return None  # Skip user dengan data terlalu sedikit\n",
+    "\n",
+    "    train_visits, test_visits = train_test_split(user_visits, test_size=0.5, random_state=42)\n",
+    "\n",
+    "    visited_indices = df_wisata[df_wisata['title'].isin(train_visits)].index\n",
+    "    if visited_indices.empty:\n",
+    "        return None\n",
+    "\n",
+    "    user_profile_matrix = tfidf_matrix[visited_indices].mean(axis=0)\n",
+    "    user_profile = np.asarray(user_profile_matrix).reshape(1, -1)\n",
+    "\n",
+    "    similarities = cosine_similarity(user_profile, tfidf_matrix).flatten()\n",
+    "    df_wisata['similarity'] = similarities\n",
+    "\n",
+    "    rekomendasi = df_wisata[~df_wisata['title'].isin(train_visits)]\n",
+    "    rekomendasi = rekomendasi.sort_values(by='similarity', ascending=False)\n",
+    "\n",
+    "    top_rekomendasi = rekomendasi['title'].head(top_n).tolist()\n",
+    "    hits = len(set(top_rekomendasi) & set(test_visits))\n",
+    "    hit_rate = hits / len(test_visits)\n",
+    "\n",
+    "    return {\n",
+    "        'user_id': user_id,\n",
+    "        'hit_rate': hit_rate,\n",
+    "        'hits': hits,\n",
+    "        'test_size': len(test_visits),\n",
+    "        'top_recommendations': top_rekomendasi,\n",
+    "        'test_visits': test_visits\n",
+    "    }\n",
+    "\n",
+    "# %%\n",
+    "# Loop ke semua user\n",
+    "user_ids = df_history['userID'].unique()\n",
+    "results = []\n",
+    "\n",
+    "for uid in user_ids:\n",
+    "    result = evaluate_user_hit(uid, top_n=5)\n",
+    "    if result:\n",
+    "        results.append(result)\n",
+    "\n",
+    "# Buat DataFrame dari hasil evaluasi\n",
+    "df_eval = pd.DataFrame(results)\n",
+    "\n",
+    "# Hitung rata-rata Hit Rate semua user\n",
+    "average_hit_rate = df_eval['hit_rate'].mean()\n",
+    "print(df_eval[['user_id', 'hit_rate']])\n",
+    "print(f\"\\nAverage Hit Rate@5: {average_hit_rate:.2f}\")\n",
+    "\n",
+    "# Simpan hasil jika perlu\n",
+    "# df_eval.to_csv(\"hasil_evaluasi_hit_rate.csv\", index=False)\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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Kode Kotor/rekomendasiLOG.ipynb

@@ -0,0 +1,463 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6dc4cd6f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "df_wisata = pd.read_csv(\"../Dataset/data_Processed.csv\")\n",
+    "df_history = pd.read_csv(\"../Dataset/userHistory.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c3d4d826",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "tfidf = TfidfVectorizer()\n",
+    "tfidf_matrix = tfidf.fit_transform(df_wisata['tags_joined'])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "787049ea",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "TfidfVectorizer()\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(tfidf)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a4a2301c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import pickle\n",
+    "# from scipy.sparse import save_npz\n",
+    "\n",
+    "# with open(\"tfidf_vectorizer.pkl\", \"wb\") as f:\n",
+    "#     pickle.dump(tfidf, f)\n",
+    "\n",
+    "# save_npz(\"tfidf_matrix.npz\", tfidf_matrix)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ef9e4114",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>userID</th>\n",
+       "      <th>namaWisata</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Hill of Gibeon</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Bukit Indah Sitalmak Talmak Sihotang</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Bukit Senyum</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Bukit Beta Tuk-tuk</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Tao Silalahi</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   userID                            namaWisata\n",
+       "0       1                        Hill of Gibeon\n",
+       "1       1  Bukit Indah Sitalmak Talmak Sihotang\n",
+       "2       1                          Bukit Senyum\n",
+       "3       1                    Bukit Beta Tuk-tuk\n",
+       "4       2                          Tao Silalahi"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "user_id = 2\n",
+    "user_history = df_history[df_history['userID'] == user_id]['namaWisata'].tolist()\n",
+    "# df_wisata.head()\n",
+    "df_history.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4f78911d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>title</th>\n",
+       "      <th>link</th>\n",
+       "      <th>image_url</th>\n",
+       "      <th>rating</th>\n",
+       "      <th>reviews</th>\n",
+       "      <th>address</th>\n",
+       "      <th>opening_hours</th>\n",
+       "      <th>latitude</th>\n",
+       "      <th>longitude</th>\n",
+       "      <th>kategori</th>\n",
+       "      <th>aktivitas</th>\n",
+       "      <th>deskripsi</th>\n",
+       "      <th>kecamatan</th>\n",
+       "      <th>biaya_masuk</th>\n",
+       "      <th>biaya_parkir_motor</th>\n",
+       "      <th>biaya_parkir_mobil</th>\n",
+       "      <th>tags_joined</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>Objek Wisata Pantai Paris</td>\n",
+       "      <td>https://www.google.com/maps/place/Objek+Wisata...</td>\n",
+       "      <td>https://drive.google.com/drive/folders/170vaB7...</td>\n",
+       "      <td>4.3</td>\n",
+       "      <td>897</td>\n",
+       "      <td>Tigaras, Kec. Dolok Pardamean, Kabupaten Simal...</td>\n",
+       "      <td>Open 24 hours</td>\n",
+       "      <td>2.80154</td>\n",
+       "      <td>98.780056</td>\n",
+       "      <td>Bahari</td>\n",
+       "      <td>Berenang, Perahu, Banana Boat, Sepeda Air, San...</td>\n",
+       "      <td>Objek Wisata Pantai Paris di Tigaras, Dolok Pa...</td>\n",
+       "      <td>Dolok Pardamean</td>\n",
+       "      <td>40000</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>berenang perahu banana boat sepeda air santai ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                        title  \\\n",
+       "25  Objek Wisata Pantai Paris   \n",
+       "\n",
+       "                                                 link  \\\n",
+       "25  https://www.google.com/maps/place/Objek+Wisata...   \n",
+       "\n",
+       "                                            image_url  rating  reviews  \\\n",
+       "25  https://drive.google.com/drive/folders/170vaB7...     4.3      897   \n",
+       "\n",
+       "                                              address  opening_hours  \\\n",
+       "25  Tigaras, Kec. Dolok Pardamean, Kabupaten Simal...  Open 24 hours   \n",
+       "\n",
+       "    latitude  longitude kategori  \\\n",
+       "25   2.80154  98.780056   Bahari   \n",
+       "\n",
+       "                                            aktivitas  \\\n",
+       "25  Berenang, Perahu, Banana Boat, Sepeda Air, San...   \n",
+       "\n",
+       "                                            deskripsi        kecamatan  \\\n",
+       "25  Objek Wisata Pantai Paris di Tigaras, Dolok Pa...  Dolok Pardamean   \n",
+       "\n",
+       "    biaya_masuk  biaya_parkir_motor  biaya_parkir_mobil  \\\n",
+       "25        40000                   0                   0   \n",
+       "\n",
+       "                                          tags_joined  \n",
+       "25  berenang perahu banana boat sepeda air santai ...  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "visited_wisata = df_wisata[df_wisata['title'].isin(user_history)]\n",
+    "visited_wisata.head(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7a4002e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "visited_indices = df_wisata[df_wisata['title'].isin(user_history)].index\n",
+    "user_profile_matrix = tfidf_matrix[visited_indices].mean(axis=0)\n",
+    "user_profile = np.asarray(user_profile_matrix).reshape(1, -1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f8a7c783",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(1, 921)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(user_profile.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "563e3e22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "\n",
+    "similarities = cosine_similarity(user_profile, tfidf_matrix)\n",
+    "#print(similarities)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b62c07e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>title</th>\n",
+       "      <th>link</th>\n",
+       "      <th>image_url</th>\n",
+       "      <th>rating</th>\n",
+       "      <th>reviews</th>\n",
+       "      <th>address</th>\n",
+       "      <th>opening_hours</th>\n",
+       "      <th>latitude</th>\n",
+       "      <th>longitude</th>\n",
+       "      <th>kategori</th>\n",
+       "      <th>aktivitas</th>\n",
+       "      <th>deskripsi</th>\n",
+       "      <th>kecamatan</th>\n",
+       "      <th>biaya_masuk</th>\n",
+       "      <th>biaya_parkir_motor</th>\n",
+       "      <th>biaya_parkir_mobil</th>\n",
+       "      <th>tags_joined</th>\n",
+       "      <th>similarity</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Hill of Gibeon</td>\n",
+       "      <td>https://www.google.com/maps/place/Hill+of+Gibe...</td>\n",
+       "      <td>https://drive.google.com/drive/folders/1AVbEcO...</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>457</td>\n",
+       "      <td>Kabupaten Toba Samosir, 21174, Sionggang Utara...</td>\n",
+       "      <td>Open 24 hours</td>\n",
+       "      <td>2.590898</td>\n",
+       "      <td>98.9978849865071</td>\n",
+       "      <td>Alam</td>\n",
+       "      <td>Aktivitas Air, Berenang, Pemandangan, Santai, ...</td>\n",
+       "      <td>Terletak di Kabupaten Toba, Sumatera Utara, Bu...</td>\n",
+       "      <td>Lumban Julu</td>\n",
+       "      <td>10000</td>\n",
+       "      <td>2000</td>\n",
+       "      <td>5000</td>\n",
+       "      <td>aktivitas air berenang pemandangan santai foto...</td>\n",
+       "      <td>0.278854</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            title                                               link  \\\n",
+       "0  Hill of Gibeon  https://www.google.com/maps/place/Hill+of+Gibe...   \n",
+       "\n",
+       "                                           image_url  rating  reviews  \\\n",
+       "0  https://drive.google.com/drive/folders/1AVbEcO...     4.5      457   \n",
+       "\n",
+       "                                             address  opening_hours  latitude  \\\n",
+       "0  Kabupaten Toba Samosir, 21174, Sionggang Utara...  Open 24 hours  2.590898   \n",
+       "\n",
+       "          longitude kategori  \\\n",
+       "0  98.9978849865071     Alam   \n",
+       "\n",
+       "                                           aktivitas  \\\n",
+       "0  Aktivitas Air, Berenang, Pemandangan, Santai, ...   \n",
+       "\n",
+       "                                           deskripsi    kecamatan  \\\n",
+       "0  Terletak di Kabupaten Toba, Sumatera Utara, Bu...  Lumban Julu   \n",
+       "\n",
+       "   biaya_masuk  biaya_parkir_motor  biaya_parkir_mobil  \\\n",
+       "0        10000                2000                5000   \n",
+       "\n",
+       "                                         tags_joined  similarity  \n",
+       "0  aktivitas air berenang pemandangan santai foto...    0.278854  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "similarities = similarities.flatten()\n",
+    "#ngubah array multidimensi jadi 1 array\n",
+    "df_wisata['similarity'] = similarities\n",
+    "df_wisata.head(1)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b73020b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                           title  similarity\n",
+      "13  Pantai Indah Situngkir (PIS)    0.519932\n",
+      "15               Pantai Kenangan    0.493438\n",
+      "3     Pantai Ikan Mas Tandarabun    0.485319\n",
+      "20                  Pantai Kasih    0.482357\n",
+      "16            pantai pasir putih    0.470786\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Hapus yang sudah dikunjungi\n",
+    "rekomendasi = df_wisata[~df_wisata['title'].isin(user_history)]\n",
+    "rekomendasi = rekomendasi.sort_values(by='similarity', ascending=False)\n",
+    "\n",
+    "# Tampilkan Top-N\n",
+    "top_n = 5\n",
+    "print(rekomendasi[['title', 'similarity']].head(top_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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Rekomendasi Item to Item/rekomendasi.py

@@ -0,0 +1,57 @@
+# rekomendasi_app_api.py
+from flask import Flask, request, jsonify
+import pandas as pd
+import pickle
+import os
+
+app = Flask(__name__)
+
+# === Load data dan model ===
+base_dir = os.path.dirname(os.path.abspath(__file__))
+
+df = pd.read_csv(os.path.join(base_dir, "..", "Dataset", "data_Processed.csv"))
+
+with open(os.path.join(base_dir, "similarity_matrix.pkl"), "rb") as f:
+    similarity_matrix = pickle.load(f)
+
+# === Fungsi rekomendasi ===
+def rekomendasi_tempat(tempat_id, top_n=5):
+    if tempat_id < 0 or tempat_id >= len(df):
+        return None
+
+    sim_scores = list(enumerate(similarity_matrix[tempat_id]))
+    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)[1:top_n+1]
+    input_title = df.iloc[tempat_id]['title']
+    rekomendasi = []
+    for i, score in sim_scores:
+        rekomendasi.append({
+            'title': df.iloc[i]['title'],
+            'index': i,
+            'kategori': df.iloc[i]['kategori'],
+            'similarity': round(score, 3)
+        })
+    
+    return {
+        "tempat_id": tempat_id,
+        "rekomendasi": rekomendasi,
+        "input_title": input_title
+        }
+
+# === Endpoint Flask ===
+@app.route("/recommenditi", methods=["GET"])
+def rekomendasi_api():
+    tempat_id = request.args.get("tempat_id", type=int)
+
+    if tempat_id is None:
+        return jsonify({"error": "Parameter 'tempat_id' diperlukan."}), 400
+
+    hasil = rekomendasi_tempat(tempat_id)
+
+    if hasil is None:
+        return jsonify({"message": f"Tempat '{tempat_id}' tidak ditemukan."}), 404
+
+    return jsonify(hasil)
+
+# === Run ===
+if __name__ == "__main__":
+    app.run(debug=True)

Rekomendasi Item to Item/similarity_matrix.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc5a936cae12829abf36556df1e2b72e0f649a1dfd99eab7cd1f84023dc27bb
+size 148130

Rekomendasi User to Item (CBF)/rekomendasi_deploy.py

@@ -0,0 +1,58 @@
+from flask import Flask, request, jsonify
+import pandas as pd
+import numpy as np
+import pickle
+from scipy.sparse import load_npz
+from sklearn.metrics.pairwise import cosine_similarity
+import os
+
+# === Inisialisasi Flask ===
+app = Flask(__name__)
+
+# === Load Model & Data Sekali Saja Saat Aplikasi Mulai ===
+base_dir = os.path.dirname(os.path.abspath(__file__))
+
+with open(os.path.join(base_dir, "tfidf_vectorizer.pkl"), "rb") as f:
+    tfidf = pickle.load(f)
+
+tfidf_matrix = load_npz(os.path.join(base_dir, "tfidf_matrix.npz"))
+df_wisata = pd.read_csv(os.path.join(base_dir,"..", "Dataset", "data_Processed.csv"))
+df_history = pd.read_csv(os.path.join(base_dir,"..", "Dataset", "userHistory.csv"))
+
+# === Fungsi Rekomendasi ===
+def recommend_for_user(user_id, top_n=5):
+    user_history = df_history[df_history['userID'] == user_id]['namaWisata'].tolist()
+    visited_indices = df_wisata[df_wisata['title'].isin(user_history)].index
+
+    if len(visited_indices) == 0:
+        return []
+
+    user_profile_matrix = tfidf_matrix[visited_indices].mean(axis=0)
+    user_profile = np.asarray(user_profile_matrix).reshape(1, -1)
+    similarities = cosine_similarity(user_profile, tfidf_matrix).flatten()
+
+    df_temp = df_wisata.copy()
+    df_temp['similarity'] = similarities
+    rekomendasi = df_temp[~df_temp['title'].isin(user_history)]
+    rekomendasi = rekomendasi.sort_values(by='similarity', ascending=False)
+
+    return rekomendasi[['title', 'similarity']].head(top_n).to_dict(orient="records")
+
+# === Endpoint API ===
+@app.route("/recommenduti", methods=["GET"])
+def recommend():
+    user_id = request.args.get("user_id", type=int)
+
+    if user_id is None:
+        return jsonify({"error": "Parameter user_id diperlukan."}), 400
+
+    hasil = recommend_for_user(user_id)
+
+    if not hasil:
+        return jsonify({"message": f"Tidak ada data history untuk user ID {user_id}."}), 404
+
+    return jsonify({"user_id": user_id, "rekomendasi": hasil})
+
+# === Run Server ===
+if __name__ == "__main__":
+    app.run(debug=True)

Rekomendasi User to Item (CBF)/tfidf_matrix.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faedb0b4226402f3a7ca92b0a889fd056870b9749bfd38104e5a48f387aa9a66
+size 37767

Rekomendasi User to Item (CBF)/tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff55d00fd0f9f1db48e35f1b7f09d677f5c9174bbdb06da49440f4fee87ae947
+size 18864