{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fitur Ekstraksi Bag-of-Words (BOW)\n",
    "\n",
    "**Nama:** Fatah Sabila Rosyad  \n",
    "**NIM:** **202210715288** \n",
    "**Kelas:** F7B2 \n",
    "**MK:** NLP  \n",
    "\n",
    "**Tujuan praktikum:**  \n",
    "Melakukan ekstraksi fitur teks menggunakan Bag-of-Words dengan variasi parameter, yaitu:  \n",
    "- Mengubah contoh teks  \n",
    "- Mengubah jumlah fitur (`max_features`)  \n",
    "- Menggunakan rentang n-gram baru (`ngram_range = (1,3)`)  \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Masukkan jumlah dokumen yang ingin dimasukkan:  3\n"
     ]
    }
   ],
   "source": [
    "# Input jumlah dokumen\n",
    "n = int(input(\"Masukkan jumlah dokumen yang ingin dimasukkan: \"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "mo-yt5Ob1N8j",
    "outputId": "362ac3e0-d84b-4014-db96-cc3b10ecdb32"
   },
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Masukkan teks untuk dokumen ke-1:  Saya Fatah Sabila Rosyad, mahasiswa informatika yang sedang mempelajari NLP dan machine learning\n",
      "Masukkan teks untuk dokumen ke-2:  Fatah melakukan eksperimen Bag-of-Words untuk melihat bagaimana fitur teks direpresentasikan sebagai angka\n",
      "Masukkan teks untuk dokumen ke-3:  Pada tahap ini Fatah menggunakan n-gram untuk menguji kombinasi kata yang sering muncul bersama\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Dokumen yang Dimasukkan ===\n",
      "Doc 1: Saya Fatah Sabila Rosyad, mahasiswa informatika yang sedang mempelajari NLP dan machine learning\n",
      "Doc 2: Fatah melakukan eksperimen Bag-of-Words untuk melihat bagaimana fitur teks direpresentasikan sebagai angka\n",
      "Doc 3: Pada tahap ini Fatah menggunakan n-gram untuk menguji kombinasi kata yang sering muncul bersama\n"
     ]
    }
   ],
   "source": [
    "# Input teks dokumen satu per satu\n",
    "documents = []\n",
    "for i in range(n):\n",
    "    teks = input(f\"Masukkan teks untuk dokumen ke-{i+1}: \")\n",
    "    documents.append(teks)\n",
    "\n",
    "print(\"\\n=== Dokumen yang Dimasukkan ===\")\n",
    "for i, doc in enumerate(documents):\n",
    "    print(f\"Doc {i+1}: {doc}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "FkmxRAFq1oDK",
    "outputId": "62c4508e-1725-4f30-fbdb-4de8072498b2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Hasil Tokenisasi ===\n",
      "Doc 1: ['saya', 'fatah', 'sabila', 'rosyad,', 'mahasiswa', 'informatika', 'yang', 'sedang', 'mempelajari', 'nlp', 'dan', 'machine', 'learning']\n",
      "Doc 2: ['fatah', 'melakukan', 'eksperimen', 'bag-of-words', 'untuk', 'melihat', 'bagaimana', 'fitur', 'teks', 'direpresentasikan', 'sebagai', 'angka']\n",
      "Doc 3: ['pada', 'tahap', 'ini', 'fatah', 'menggunakan', 'n-gram', 'untuk', 'menguji', 'kombinasi', 'kata', 'yang', 'sering', 'muncul', 'bersama']\n"
     ]
    }
   ],
   "source": [
    "# Tahap Tokenisasi\n",
    "tokenized_docs = []\n",
    "for doc in documents:\n",
    "    tokens = doc.lower().split()\n",
    "    tokenized_docs.append(tokens)\n",
    "\n",
    "print(\"\\n=== Hasil Tokenisasi ===\")\n",
    "for i, tokens in enumerate(tokenized_docs):\n",
    "    print(f\"Doc {i+1}: {tokens}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ybC1Vo2C_c3q",
    "outputId": "fa31c57e-5364-4ded-fcd0-54d0db46c34b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Corpus Keseluruhan (Semua Kata dari Semua Dokumen) ===\n",
      "['saya', 'fatah', 'sabila', 'rosyad,', 'mahasiswa', 'informatika', 'yang', 'sedang', 'mempelajari', 'nlp', 'dan', 'machine', 'learning', 'fatah', 'melakukan', 'eksperimen', 'bag-of-words', 'untuk', 'melihat', 'bagaimana', 'fitur', 'teks', 'direpresentasikan', 'sebagai', 'angka', 'pada', 'tahap', 'ini', 'fatah', 'menggunakan', 'n-gram', 'untuk', 'menguji', 'kombinasi', 'kata', 'yang', 'sering', 'muncul', 'bersama']\n",
      "Jumlah total kata dalam seluruh dokumen: 39\n"
     ]
    }
   ],
   "source": [
    "# Pembuatan Corpus\n",
    "corpus_all = [word for doc in tokenized_docs for word in doc]\n",
    "\n",
    "print(\"\\n=== Corpus Keseluruhan (Semua Kata dari Semua Dokumen) ===\")\n",
    "print(corpus_all)\n",
    "print(f\"Jumlah total kata dalam seluruh dokumen: {len(corpus_all)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Hasil BOW Manual (Frekuensi Kata) ===\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'fatah': 3,\n",
       " 'yang': 2,\n",
       " 'untuk': 2,\n",
       " 'saya': 1,\n",
       " 'sabila': 1,\n",
       " 'rosyad,': 1,\n",
       " 'mahasiswa': 1,\n",
       " 'informatika': 1,\n",
       " 'sedang': 1,\n",
       " 'mempelajari': 1,\n",
       " 'nlp': 1,\n",
       " 'dan': 1,\n",
       " 'machine': 1,\n",
       " 'learning': 1,\n",
       " 'melakukan': 1,\n",
       " 'eksperimen': 1,\n",
       " 'bag-of-words': 1,\n",
       " 'melihat': 1,\n",
       " 'bagaimana': 1,\n",
       " 'fitur': 1,\n",
       " 'teks': 1,\n",
       " 'direpresentasikan': 1,\n",
       " 'sebagai': 1,\n",
       " 'angka': 1,\n",
       " 'pada': 1,\n",
       " 'tahap': 1,\n",
       " 'ini': 1,\n",
       " 'menggunakan': 1,\n",
       " 'n-gram': 1,\n",
       " 'menguji': 1,\n",
       " 'kombinasi': 1,\n",
       " 'kata': 1,\n",
       " 'sering': 1,\n",
       " 'muncul': 1,\n",
       " 'bersama': 1}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 4) Membuat Bag-of-Words manual (frekuensi kata)\n",
    "bow_manual = {}\n",
    "for tokens in tokenized_docs:\n",
    "    for token in tokens:\n",
    "        bow_manual[token] = bow_manual.get(token, 0) + 1\n",
    "\n",
    "print(\"\\n=== Hasil BOW Manual (Frekuensi Kata) ===\")\n",
    "# Tampilkan dictionary secara sorted by frequency (desc)\n",
    "bow_sorted = dict(sorted(bow_manual.items(), key=lambda x: x[1], reverse=True))\n",
    "bow_sorted"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "s6S-Ma4R1xuq",
    "outputId": "98c3685b-1798-4038-d17e-6e45ca419b51"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Vocabulary (Kata Unik) ===\n",
      "['angka', 'bag-of-words', 'bagaimana', 'bersama', 'dan', 'direpresentasikan', 'eksperimen', 'fatah', 'fitur', 'informatika', 'ini', 'kata', 'kombinasi', 'learning', 'machine', 'mahasiswa', 'melakukan', 'melihat', 'mempelajari', 'menggunakan', 'menguji', 'muncul', 'n-gram', 'nlp', 'pada', 'rosyad,', 'sabila', 'saya', 'sebagai', 'sedang', 'sering', 'tahap', 'teks', 'untuk', 'yang']\n",
      "Jumlah kata unik (vocabulary size): 35\n",
      "\n",
      "=== Vocabulary (Kata Unik) ===\n",
      " 1. angka\n",
      " 2. bag-of-words\n",
      " 3. bagaimana\n",
      " 4. bersama\n",
      " 5. dan\n",
      " 6. direpresentasikan\n",
      " 7. eksperimen\n",
      " 8. fatah\n",
      " 9. fitur\n",
      "10. informatika\n",
      "11. ini\n",
      "12. kata\n",
      "13. kombinasi\n",
      "14. learning\n",
      "15. machine\n",
      "16. mahasiswa\n",
      "17. melakukan\n",
      "18. melihat\n",
      "19. mempelajari\n",
      "20. menggunakan\n",
      "21. menguji\n",
      "22. muncul\n",
      "23. n-gram\n",
      "24. nlp\n",
      "25. pada\n",
      "26. rosyad,\n",
      "27. sabila\n",
      "28. saya\n",
      "29. sebagai\n",
      "30. sedang\n",
      "31. sering\n",
      "32. tahap\n",
      "33. teks\n",
      "34. untuk\n",
      "35. yang\n",
      "\n",
      "Jumlah kata unik (vocabulary size): 35\n"
     ]
    }
   ],
   "source": [
    "# Pembuatan Vocabulary\n",
    "vocabulary = sorted(set(corpus_all))\n",
    "\n",
    "print(\"\\n=== Vocabulary (Kata Unik) ===\")\n",
    "print(vocabulary)\n",
    "print(f\"Jumlah kata unik (vocabulary size): {len(vocabulary)}\")\n",
    "\n",
    "\n",
    "vocabulary = sorted(set(corpus_all))\n",
    "\n",
    "print(\"\\n=== Vocabulary (Kata Unik) ===\")\n",
    "for idx, word in enumerate(vocabulary, start=1):\n",
    "    print(f\"{idx:>2}. {word}\")\n",
    "print(f\"\\nJumlah kata unik (vocabulary size): {len(vocabulary)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Jumlah dokumen: 3\n",
      "Jumlah tokenized_docs: 3\n",
      "Jumlah kata di vocabulary (unique): 35\n",
      "Contoh 10 kata pertama vocabulary: ['angka', 'bag-of-words', 'bagaimana', 'bersama', 'dan', 'direpresentasikan', 'eksperimen', 'fatah', 'fitur', 'informatika']\n"
     ]
    }
   ],
   "source": [
    "print(\"Jumlah dokumen:\", len(documents))\n",
    "print(\"Jumlah tokenized_docs:\", len(tokenized_docs))\n",
    "print(\"Jumlah kata di vocabulary (unique):\", len(vocabulary))\n",
    "print(\"Contoh 10 kata pertama vocabulary:\", vocabulary[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "=== Info CountVectorizer ===\n",
      "n-gram range: (1, 3)\n",
      "max_features: 500\n",
      "Jumlah fitur (vocabulary size): 110\n",
      "\n",
      "Contoh 20 fitur pertama:\n",
      "['angka' 'bag' 'bag of' 'bag of words' 'bagaimana' 'bagaimana fitur'\n",
      " 'bagaimana fitur teks' 'bersama' 'dan' 'dan machine'\n",
      " 'dan machine learning' 'direpresentasikan' 'direpresentasikan sebagai'\n",
      " 'direpresentasikan sebagai angka' 'eksperimen' 'eksperimen bag'\n",
      " 'eksperimen bag of' 'fatah' 'fatah melakukan'\n",
      " 'fatah melakukan eksperimen']\n"
     ]
    }
   ],
   "source": [
    "# BOW modern: CountVectorizer dengan n-gram dan max_features \n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "\n",
    "# Ubah di sini bila mau nilai lain:\n",
    "NGRAM_RANGE = (1, 3)     # ubah n-gram (contoh: (1,2) atau (1,4))\n",
    "MAX_FEATURES = 500       # ubah jumlah fitur (contoh: 200, 1000)\n",
    "\n",
    "vectorizer = CountVectorizer(ngram_range=NGRAM_RANGE, max_features=MAX_FEATURES)\n",
    "X = vectorizer.fit_transform(documents)\n",
    "\n",
    "print(\"\\n=== Info CountVectorizer ===\")\n",
    "print(\"n-gram range:\", NGRAM_RANGE)\n",
    "print(\"max_features:\", MAX_FEATURES)\n",
    "print(\"Jumlah fitur (vocabulary size):\", len(vectorizer.vocabulary_))\n",
    "print(\"\\nContoh 20 fitur pertama:\")\n",
    "print(vectorizer.get_feature_names_out()[:20])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>angka</th>\n",
       "      <th>bag</th>\n",
       "      <th>bag of</th>\n",
       "      <th>bag of words</th>\n",
       "      <th>bagaimana</th>\n",
       "      <th>bagaimana fitur</th>\n",
       "      <th>bagaimana fitur teks</th>\n",
       "      <th>bersama</th>\n",
       "      <th>dan</th>\n",
       "      <th>dan machine</th>\n",
       "      <th>...</th>\n",
       "      <th>untuk menguji</th>\n",
       "      <th>untuk menguji kombinasi</th>\n",
       "      <th>words</th>\n",
       "      <th>words untuk</th>\n",
       "      <th>words untuk melihat</th>\n",
       "      <th>yang</th>\n",
       "      <th>yang sedang</th>\n",
       "      <th>yang sedang mempelajari</th>\n",
       "      <th>yang sering</th>\n",
       "      <th>yang sering muncul</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 110 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   angka  bag  bag of  bag of words  bagaimana  bagaimana fitur  \\\n",
       "0      0    0       0             0          0                0   \n",
       "1      1    1       1             1          1                1   \n",
       "2      0    0       0             0          0                0   \n",
       "\n",
       "   bagaimana fitur teks  bersama  dan  dan machine  ...  untuk menguji  \\\n",
       "0                     0        0    1            1  ...              0   \n",
       "1                     1        0    0            0  ...              0   \n",
       "2                     0        1    0            0  ...              1   \n",
       "\n",
       "   untuk menguji kombinasi  words  words untuk  words untuk melihat  yang  \\\n",
       "0                        0      0            0                    0     1   \n",
       "1                        0      1            1                    1     0   \n",
       "2                        1      0            0                    0     1   \n",
       "\n",
       "   yang sedang  yang sedang mempelajari  yang sering  yang sering muncul  \n",
       "0            1                        1            0                   0  \n",
       "1            0                        0            0                   0  \n",
       "2            0                        0            1                   1  \n",
       "\n",
       "[3 rows x 110 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 6) Konversi hasil ke DataFrame\n",
    "import pandas as pd\n",
    "\n",
    "df_features = pd.DataFrame(X.toarray(), columns=vectorizer.get_feature_names_out())\n",
    "display(df_features)   # di Jupyter ini akan tampil tabel\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "ShevCTva2Fg9"
   },
   "outputs": [],
   "source": [
    "# Representasi Numerik (Matriks BoW)\n",
    "bow_matrix = []\n",
    "for doc in tokenized_docs:\n",
    "    vector = [doc.count(word) for word in vocabulary]\n",
    "    bow_matrix.append(vector)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>angka</th>\n",
       "      <th>bag-of-words</th>\n",
       "      <th>bagaimana</th>\n",
       "      <th>bersama</th>\n",
       "      <th>dan</th>\n",
       "      <th>direpresentasikan</th>\n",
       "      <th>eksperimen</th>\n",
       "      <th>fatah</th>\n",
       "      <th>fitur</th>\n",
       "      <th>informatika</th>\n",
       "      <th>...</th>\n",
       "      <th>rosyad,</th>\n",
       "      <th>sabila</th>\n",
       "      <th>saya</th>\n",
       "      <th>sebagai</th>\n",
       "      <th>sedang</th>\n",
       "      <th>sering</th>\n",
       "      <th>tahap</th>\n",
       "      <th>teks</th>\n",
       "      <th>untuk</th>\n",
       "      <th>yang</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   angka  bag-of-words  bagaimana  bersama  dan  direpresentasikan  \\\n",
       "0      0             0          0        0    1                  0   \n",
       "1      1             1          1        0    0                  1   \n",
       "2      0             0          0        1    0                  0   \n",
       "\n",
       "   eksperimen  fatah  fitur  informatika  ...  rosyad,  sabila  saya  sebagai  \\\n",
       "0           0      1      0            1  ...        1       1     1        0   \n",
       "1           1      1      1            0  ...        0       0     0        1   \n",
       "2           0      1      0            0  ...        0       0     0        0   \n",
       "\n",
       "   sedang  sering  tahap  teks  untuk  yang  \n",
       "0       1       0      0     0      0     1  \n",
       "1       0       0      0     1      1     0  \n",
       "2       0       1      1     0      1     1  \n",
       "\n",
       "[3 rows x 35 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Shape (dokumen x fitur): (3, 35)\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Buat matrix manual berdasarkan vocabulary yang sudah kamu buat\n",
    "bow_matrix = []\n",
    "for tokens in tokenized_docs:\n",
    "    # hitung frekuensi tiap kata pada vocabulary pada dokumen ini\n",
    "    vector = [tokens.count(word) for word in vocabulary]   # tokens adalah list kata\n",
    "    bow_matrix.append(vector)\n",
    "\n",
    "# Konversi ke DataFrame agar rapi saat ditampilkan\n",
    "df_bow_manual = pd.DataFrame(bow_matrix, columns=vocabulary)\n",
    "display(df_bow_manual)   # di Jupyter ini akan tampil tabel\n",
    "print(\"\\nShape (dokumen x fitur):\", df_bow_manual.shape)\n"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": 4
}