{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f4a1399a-f23d-4060-a07e-bce5a5c7ddac",
   "metadata": {},
   "source": [
    "# Klasifikasi Teks menggunakan ANN (TF-IDF + FNN)\n",
    "\n",
    "**Nama:** Fatah Sabila Rosyad  \n",
    "**NIM:** 202210715288  \n",
    "**Kelas:** F7B2  \n",
    "**MK:** NLP  \n",
    "\n",
    "**Tujuan praktikum:**\n",
    "Menerapkan klasifikasi teks sentimen sederhana menggunakan TF-IDF dan Feedforward Neural Network (MLPClassifier), dengan:\n",
    "- Mengubah contoh teks (menggunakan kalimat yang dibuat sendiri)\n",
    "- Mengubah parameter TF-IDF (`max_features`, `ngram_range`)\n",
    "- Mengubah arsitektur dan parameter model ANN (`hidden_layer_sizes`, `max_iter`, `learning_rate_init`)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4c395092-326a-4abc-b308-067392277cfa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---------------------------------------------------------\n",
    "# Klasifikasi Teks dengan TF-IDF + Feedforward Neural Network\n",
    "# ---------------------------------------------------------\n",
    "\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.metrics import classification_report, confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4ac91b0c-e6af-4766-8933-db10ebf69140",
   "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>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Saya Fatah Sabila Rosyad merasa sangat puas de...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Sebagai pelanggan, Fatah kecewa karena pelayan...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Pengalaman belanja Fatah kali ini menyenangkan...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Fatah benci produk ini karena mudah rusak dan ...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Menurut Fatah kualitas produk ini sangat bagus...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Fatah tidak akan membeli lagi di sini karena p...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text     label\n",
       "0  Saya Fatah Sabila Rosyad merasa sangat puas de...  positive\n",
       "1  Sebagai pelanggan, Fatah kecewa karena pelayan...  negative\n",
       "2  Pengalaman belanja Fatah kali ini menyenangkan...  positive\n",
       "3  Fatah benci produk ini karena mudah rusak dan ...  negative\n",
       "4  Menurut Fatah kualitas produk ini sangat bagus...  positive\n",
       "5  Fatah tidak akan membeli lagi di sini karena p...  negative"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 1. Contoh Dataset (teks buatan Fatah)\n",
    "# -----------------------------------------\n",
    "\n",
    "data = {\n",
    "    \"text\": [\n",
    "        \"Saya Fatah Sabila Rosyad merasa sangat puas dengan kualitas produk ini.\",\n",
    "        \"Sebagai pelanggan, Fatah kecewa karena pelayanan toko sangat lambat.\",\n",
    "        \"Pengalaman belanja Fatah kali ini menyenangkan, proses cepat dan barang sesuai.\",\n",
    "        \"Fatah benci produk ini karena mudah rusak dan tidak sesuai deskripsi.\",\n",
    "        \"Menurut Fatah kualitas produk ini sangat bagus dan layak direkomendasikan.\",\n",
    "        \"Fatah tidak akan membeli lagi di sini karena pelayanan buruk dan respon yang lambat.\"\n",
    "    ],\n",
    "    \"label\": [\"positive\", \"negative\", \"positive\", \"negative\", \"positive\", \"negative\"]\n",
    "}\n",
    "\n",
    "df = pd.DataFrame(data)\n",
    "df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6dab8e80-c225-4de8-aecc-8b457153c3ee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Jumlah data latih : 3\n",
      "Jumlah data uji   : 3\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 2. Split Train & Test (PERUBAHAN: test_size & random_state)\n",
    "# -----------------------------------------\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    df[\"text\"],\n",
    "    df[\"label\"],\n",
    "    test_size=0.34,      # semula 0.3\n",
    "    random_state=7       # semula 42\n",
    ")\n",
    "\n",
    "print(\"Jumlah data latih :\", len(X_train))\n",
    "print(\"Jumlah data uji   :\", len(X_test))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2cb05f0c-b497-4e9e-87bc-25d167f0c0ee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape X_train_tfidf: (3, 52)\n",
      "Shape X_test_tfidf : (3, 52)\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 3. TF-IDF Vectorization (PERUBAHAN PARAMETER)\n",
    "# -----------------------------------------\n",
    "\n",
    "tfidf = TfidfVectorizer(\n",
    "    max_features=1000,      # semula 5000\n",
    "    ngram_range=(1, 2)      # tambahan: gunakan unigram + bigram\n",
    ")\n",
    "\n",
    "X_train_tfidf = tfidf.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf.transform(X_test)\n",
    "\n",
    "print(\"Shape X_train_tfidf:\", X_train_tfidf.shape)\n",
    "print(\"Shape X_test_tfidf :\", X_test_tfidf.shape)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0cb99708-b1bd-43a7-84b9-4e4925bf2914",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model selesai dilatih.\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 4. Feedforward ANN (MLPClassifier) (PERUBAHAN PARAMETER)\n",
    "# -----------------------------------------\n",
    "\n",
    "model = MLPClassifier(\n",
    "    hidden_layer_sizes=(128, 32),    # semula (256, 64)\n",
    "    activation='relu',\n",
    "    solver='adam',\n",
    "    learning_rate_init=0.001,        # tambahan\n",
    "    max_iter=300,                    # semula 500\n",
    "    random_state=7\n",
    ")\n",
    "\n",
    "model.fit(X_train_tfidf, y_train)\n",
    "print(\"Model selesai dilatih.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d388afdf-0f08-48ea-92d1-e03390dee1d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=== Classification Report ===\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       1.00      0.50      0.67         2\n",
      "    positive       0.50      1.00      0.67         1\n",
      "\n",
      "    accuracy                           0.67         3\n",
      "   macro avg       0.75      0.75      0.67         3\n",
      "weighted avg       0.83      0.67      0.67         3\n",
      "\n",
      "=== Confusion Matrix ===\n",
      "[[1 1]\n",
      " [0 1]]\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 5. Evaluasi Model\n",
    "# -----------------------------------------\n",
    "\n",
    "y_pred = model.predict(X_test_tfidf)\n",
    "\n",
    "print(\"=== Classification Report ===\")\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "print(\"=== Confusion Matrix ===\")\n",
    "print(confusion_matrix(y_test, y_pred))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "64141093-c8fd-4118-aaf3-6e48454c5e76",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediksi untuk: Menurut Fatah, pengalaman belanja kali ini sangat memuaskan.\n",
      "Hasil: positive\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 6. Prediksi Teks Baru (contoh 1 - positif)\n",
    "# -----------------------------------------\n",
    "sample_text = [\"Menurut Fatah, pengalaman belanja kali ini sangat memuaskan.\"]\n",
    "sample_vec = tfidf.transform(sample_text)\n",
    "prediction = model.predict(sample_vec)\n",
    "\n",
    "print(\"Prediksi untuk:\", sample_text[0])\n",
    "print(\"Hasil:\", prediction[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d4bf8434-fe3b-4a88-a294-207fa731de7d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediksi untuk: Saya Fatah merasa kecewa karena layanan toko sangat buruk.\n",
      "Hasil: negative\n"
     ]
    }
   ],
   "source": [
    "# -----------------------------------------\n",
    "# 6. Prediksi Teks Baru (contoh 2 - negatif)\n",
    "# -----------------------------------------\n",
    "sample_text = [\"Saya Fatah merasa kecewa karena layanan toko sangat buruk.\"]\n",
    "sample_vec = tfidf.transform(sample_text)\n",
    "prediction = model.predict(sample_vec)\n",
    "\n",
    "print(\"Prediksi untuk:\", sample_text[0])\n",
    "print(\"Hasil:\", prediction[0])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "724617be-aa1d-41bd-ad39-e6517fbcf837",
   "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": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}