Praktikum-NLP/Information_Extraction.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "7c7601d6-3c91-453e-8c29-706528237596",
      "metadata": {
        "scrolled": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7c7601d6-3c91-453e-8c29-706528237596",
        "outputId": "df473be6-c537-431b-8bc9-66b1ca1d64b1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Teks sumber:\n",
            "\n",
            "PT Maju Jaya resmi meluncurkan produk terbaru mereka pada 12 Agustus 2023\n",
            "di Jakarta. Acara peluncuran tersebut dihadiri oleh CEO perusahaan dan\n",
            "disaksikan oleh ratusan undangan.\n",
            "\n",
            "\n",
            "HASIL INFORMATION EXTRACTION:\n",
            "EventType: Product Launch\n",
            "Organization: PT Maju Jaya\n",
            "LaunchDateOriginal: 12 Agustus 2023\n",
            "LaunchDateISO: 2023-08-12\n",
            "Location: Jakarta\n",
            "SourceText: PT Maju Jaya resmi meluncurkan produk terbaru mereka pada 12 Agustus 2023 di Jakarta. Acara peluncuran tersebut dihadiri oleh CEO perusahaan dan disaksikan oleh ratusan undangan.\n"
          ]
        }
      ],
      "source": [
        "# =========================\n",
        "# NLP – Information Extraction (MODIFIED VERSION)\n",
        "# =========================\n",
        "\n",
        "import re\n",
        "import nltk\n",
        "from datetime import datetime\n",
        "\n",
        "# =========================\n",
        "# 1. DATA TEKS (DIMODIFIKASI)\n",
        "# =========================\n",
        "text = \"\"\"\n",
        "PT Maju Jaya resmi meluncurkan produk terbaru mereka pada 12 Agustus 2023\n",
        "di Jakarta. Acara peluncuran tersebut dihadiri oleh CEO perusahaan dan\n",
        "disaksikan oleh ratusan undangan.\n",
        "\"\"\"\n",
        "\n",
        "print(\"Teks sumber:\")\n",
        "print(text)\n",
        "\n",
        "# =========================\n",
        "# 2. PREPROCESSING TAMBAHAN\n",
        "# =========================\n",
        "def clean_text(text):\n",
        "    text = text.strip()\n",
        "    text = re.sub(r\"\\s+\", \" \", text)\n",
        "    return text\n",
        "\n",
        "text = clean_text(text)\n",
        "\n",
        "# =========================\n",
        "# 3. EKSTRAKSI TANGGAL (LEBIH DARI 1 FORMAT)\n",
        "# =========================\n",
        "date_patterns = [\n",
        "    r\"\\d{1,2}\\s(?:Januari|Februari|Maret|April|Mei|Juni|Juli|Agustus|September|Oktober|November|Desember)\\s\\d{4}\",\n",
        "    r\"\\d{4}-\\d{2}-\\d{2}\"\n",
        "]\n",
        "\n",
        "dates = []\n",
        "for pattern in date_patterns:\n",
        "    dates.extend(re.findall(pattern, text))\n",
        "\n",
        "# =========================\n",
        "# 4. NORMALISASI TANGGAL\n",
        "# =========================\n",
        "bulan_map = {\n",
        "    \"Januari\": \"01\", \"Februari\": \"02\", \"Maret\": \"03\",\n",
        "    \"April\": \"04\", \"Mei\": \"05\", \"Juni\": \"06\",\n",
        "    \"Juli\": \"07\", \"Agustus\": \"08\", \"September\": \"09\",\n",
        "    \"Oktober\": \"10\", \"November\": \"11\", \"Desember\": \"12\"\n",
        "}\n",
        "\n",
        "def normalize_date(date_str):\n",
        "    try:\n",
        "        parts = date_str.split()\n",
        "        return f\"{parts[2]}-{bulan_map[parts[1]]}-{parts[0].zfill(2)}\"\n",
        "    except:\n",
        "        return None\n",
        "\n",
        "normalized_dates = [normalize_date(d) for d in dates]\n",
        "\n",
        "# =========================\n",
        "# 5. EKSTRAKSI LOKASI (RULE-BASED)\n",
        "# =========================\n",
        "location_pattern = r\"di\\s([A-Z][a-zA-Z]+)\"\n",
        "location_match = re.search(location_pattern, text)\n",
        "location = location_match.group(1) if location_match else None\n",
        "\n",
        "# =========================\n",
        "# 6. EKSTRAKSI ORGANISASI (MODIFIKASI)\n",
        "# =========================\n",
        "org_pattern = r\"PT\\s[A-Z][a-zA-Z]+\\s[A-Z][a-zA-Z]+\"\n",
        "organization = re.findall(org_pattern, text)\n",
        "\n",
        "# =========================\n",
        "# 7. EVENT TEMPLATE (LEBIH LENGKAP)\n",
        "# =========================\n",
        "event_template = {\n",
        "    \"EventType\": \"Product Launch\",\n",
        "    \"Organization\": organization[0] if organization else None,\n",
        "    \"LaunchDateOriginal\": dates[0] if dates else None,\n",
        "    \"LaunchDateISO\": normalized_dates[0] if normalized_dates else None,\n",
        "    \"Location\": location,\n",
        "    \"SourceText\": text\n",
        "}\n",
        "\n",
        "# =========================\n",
        "# 8. OUTPUT\n",
        "# =========================\n",
        "print(\"\\nHASIL INFORMATION EXTRACTION:\")\n",
        "for key, value in event_template.items():\n",
        "    print(f\"{key}: {value}\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "1e128113-af1e-45a1-8586-48c4acf578b4",
      "metadata": {
        "id": "1e128113-af1e-45a1-8586-48c4acf578b4"
      },
      "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": "3.12.2"
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}