{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2bPTX5vXSkW1",
        "outputId": "5a550ffb-597a-4de8-fc0f-d62c38f9babb"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (1.6.1)\n",
            "Requirement already satisfied: nltk in /usr/local/lib/python3.12/dist-packages (3.9.1)\n",
            "Requirement already satisfied: sastrawi in /usr/local/lib/python3.12/dist-packages (1.0.1)\n",
            "Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.0.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2026.2)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.16.3)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.5.3)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (3.6.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk) (8.4.2)\n",
            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk) (2025.11.3)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk) (4.67.3)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
          ]
        }
      ],
      "source": [
        "!pip install pandas scikit-learn nltk sastrawi"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "from sklearn.cluster import KMeans\n",
        "\n",
        "import nltk\n",
        "from nltk.tokenize import word_tokenize\n",
        "from nltk.corpus import stopwords\n",
        "\n",
        "from Sastrawi.Stemmer.StemmerFactory import StemmerFactory\n",
        "\n",
        "nltk.download('punkt')\n",
        "nltk.download('punkt_tab')\n",
        "nltk.download('stopwords')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LrBjyAsrSwtM",
        "outputId": "39bbaf57-15db-4f85-aebf-cf8e32a6dbe9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Package punkt is already up-to-date!\n",
            "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt_tab.zip.\n",
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import files\n",
        "\n",
        "uploaded = files.upload()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "PSCR_hzgSy_W",
        "outputId": "f89e2800-2c70-479e-bcfa-e272d07244d5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-3ac90f53-36f2-4108-8edc-ca955c9f08f8\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-3ac90f53-36f2-4108-8edc-ca955c9f08f8\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving Copy of Data Tracer Study - Jurusan TI - 2024.csv to Copy of Data Tracer Study - Jurusan TI - 2024 (1).csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(\"Copy of Data Tracer Study - Jurusan TI - 2024.csv\")\n",
        "\n",
        "print(\"Jumlah Data :\", len(df))\n",
        "print(\"Jumlah Kolom :\", len(df.columns))\n",
        "\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 880
        },
        "id": "OgEzci-sS1T8",
        "outputId": "f07c505d-9b5c-4a6d-d2ee-77bd5399cb7b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Jumlah Data : 361\n",
            "Jumlah Kolom : 81\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   1. Kode Perguruan Tinggi / kdptimsmh 2. Kode Program Studi / kdpstmsmh  \\\n",
              "0                                  5019        Teknik Informatika (55301)   \n",
              "1                                  5019        Teknik Informatika (55301)   \n",
              "2                                  5019        Teknik Informatika (55301)   \n",
              "3                                  5019        Teknik Informatika (55301)   \n",
              "4                                  5019        Teknik Informatika (55301)   \n",
              "\n",
              "  3. NIM / nimhsmsmh  (Gunakan Huruf Besar)   \\\n",
              "0                                  E41221847   \n",
              "1                                  E41191862   \n",
              "2                                  E41222296   \n",
              "3                                  E41222266   \n",
              "4                                  E41222286   \n",
              "\n",
              "  4. Nama Lengkap / nmmhsmsmh (Gunakan Huruf Besar)  \\\n",
              "0                           MUHAMMAD ADITYA MARTONO   \n",
              "1                          DEVANDRA LUKITO WIBISONO   \n",
              "2                                   YUNI INDAH SARI   \n",
              "3                                    ERINA SUDRAJAD   \n",
              "4                                     MUHAMMAD RAFI   \n",
              "\n",
              "  6. Alamat Email / emailmsmh  7. Tahun Lulus / tahun_lulus  \\\n",
              "0    madityamartono@gmail.com                          2024   \n",
              "1    ukiazulgrana89@gmail.com                          2024   \n",
              "2         yunii7599@gmail.com                          2024   \n",
              "3     sudrajaderina@gmail.com                          2024   \n",
              "4         rafi.abs2@gmail.com                          2024   \n",
              "\n",
              "  1. Jelaskan status Anda saat ini? f8  \\\n",
              "0    1 - Bekerja (full time/part time)   \n",
              "1    1 - Bekerja (full time/part time)   \n",
              "2    1 - Bekerja (full time/part time)   \n",
              "3    1 - Bekerja (full time/part time)   \n",
              "4    1 - Bekerja (full time/part time)   \n",
              "\n",
              "   2. Berapa bulan anda mendapatkan pekerjaan SEBELUM LULUS? f502  \\\n",
              "0                                                  1                \n",
              "1                                                  0                \n",
              "2                                                  4                \n",
              "3                                                  0                \n",
              "4                                                  0                \n",
              "\n",
              "  3.  Apakah Anda telah mendapatkan pekerjaan <= 6 bulan / termasuk bekerja sebelum lulus? f504  \\\n",
              "0                                             1 - Ya                                              \n",
              "1                                             1 - Ya                                              \n",
              "2                                          2 - Tidak                                              \n",
              "3                                          2 - Tidak                                              \n",
              "4                                             1 - Ya                                              \n",
              "\n",
              "  4. Berapa rata-rata pendapatan Anda per bulan ? f505  ...  \\\n",
              "0                  Rp 3.000.000,- s/d Rp 4.000.000,-    ...   \n",
              "1                  Rp 3.000.000,- s/d Rp 4.000.000,-    ...   \n",
              "2                  Rp 3.000.000,- s/d Rp 4.000.000,-    ...   \n",
              "3                  Rp 3.000.000,- s/d Rp 4.000.000,-    ...   \n",
              "4                  Rp 3.000.000,- s/d Rp 4.000.000,-    ...   \n",
              "\n",
              "   66. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1605  \\\n",
              "0  1 - Saya dipromosikan ke posisi yang kurang be...                                                        \n",
              "1  1 - Saya dipromosikan ke posisi yang kurang be...                                                        \n",
              "2  1 - Saya dipromosikan ke posisi yang kurang be...                                                        \n",
              "3  1 - Saya dipromosikan ke posisi yang kurang be...                                                        \n",
              "4  1 - Saya dipromosikan ke posisi yang kurang be...                                                        \n",
              "\n",
              "  67. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1606  \\\n",
              "0  1 - Saya dapat memeroleh pendapatan yang lebih...                                                       \n",
              "1  1 - Saya dapat memeroleh pendapatan yang lebih...                                                       \n",
              "2  1 - Saya dapat memeroleh pendapatan yang lebih...                                                       \n",
              "3  1 - Saya dapat memeroleh pendapatan yang lebih...                                                       \n",
              "4  1 - Saya dapat memeroleh pendapatan yang lebih...                                                       \n",
              "\n",
              "  68. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1607  \\\n",
              "0  1 - Pekerjaan saya saat ini lebih aman/terjami...                                                       \n",
              "1  1 - Pekerjaan saya saat ini lebih aman/terjami...                                                       \n",
              "2  1 - Pekerjaan saya saat ini lebih aman/terjami...                                                       \n",
              "3  1 - Pekerjaan saya saat ini lebih aman/terjami...                                                       \n",
              "4  1 - Pekerjaan saya saat ini lebih aman/terjami...                                                       \n",
              "\n",
              "  69. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1608  \\\n",
              "0          1 - Pekerjaan saya saat ini lebih menarik                                                       \n",
              "1          1 - Pekerjaan saya saat ini lebih menarik                                                       \n",
              "2          1 - Pekerjaan saya saat ini lebih menarik                                                       \n",
              "3          1 - Pekerjaan saya saat ini lebih menarik                                                       \n",
              "4          1 - Pekerjaan saya saat ini lebih menarik                                                       \n",
              "\n",
              "  70. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1609  \\\n",
              "0  1 - Pekerjaan saya saat ini lebih memungkinkan...                                                       \n",
              "1  1 - Pekerjaan saya saat ini lebih memungkinkan...                                                       \n",
              "2  1 - Pekerjaan saya saat ini lebih memungkinkan...                                                       \n",
              "3  1 - Pekerjaan saya saat ini lebih memungkinkan...                                                       \n",
              "4  1 - Pekerjaan saya saat ini lebih memungkinkan...                                                       \n",
              "\n",
              "  71. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1610  \\\n",
              "0  1 - Pekerjaan saya saat ini lokasinya lebih de...                                                       \n",
              "1  1 - Pekerjaan saya saat ini lokasinya lebih de...                                                       \n",
              "2  1 - Pekerjaan saya saat ini lokasinya lebih de...                                                       \n",
              "3  1 - Pekerjaan saya saat ini lokasinya lebih de...                                                       \n",
              "4  1 - Pekerjaan saya saat ini lokasinya lebih de...                                                       \n",
              "\n",
              "  72. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1611  \\\n",
              "0  1 - Pekerjaan saya saat ini dapat lebih menjam...                                                       \n",
              "1  1 - Pekerjaan saya saat ini dapat lebih menjam...                                                       \n",
              "2                    0 - Pekerjaan saya sudah sesuai                                                       \n",
              "3  1 - Pekerjaan saya saat ini dapat lebih menjam...                                                       \n",
              "4  1 - Pekerjaan saya saat ini dapat lebih menjam...                                                       \n",
              "\n",
              "  73. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1612  \\\n",
              "0  1 - Pada awal meniti karir ini, saya harus men...                                                       \n",
              "1  1 - Pada awal meniti karir ini, saya harus men...                                                       \n",
              "2  1 - Pada awal meniti karir ini, saya harus men...                                                       \n",
              "3  1 - Pada awal meniti karir ini, saya harus men...                                                       \n",
              "4  1 - Pada awal meniti karir ini, saya harus men...                                                       \n",
              "\n",
              "  74. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas (f1613)  \\\n",
              "0                    0 - Pekerjaan saya sudah sesuai                                                                                              \n",
              "1                                        1 - Lainnya                                                                                              \n",
              "2                                        1 - Lainnya                                                                                              \n",
              "3                                        1 - Lainnya                                                                                              \n",
              "4                                        1 - Lainnya                                                                                              \n",
              "\n",
              "  75. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas, Tuliskan (f1614)  \n",
              "0                                                NaN                                                                                                       \n",
              "1                              menambah uang bulanan                                                                                                       \n",
              "2                                                NaN                                                                                                       \n",
              "3                                                NaN                                                                                                       \n",
              "4                    karna terjamin jenjang karirnya                                                                                                       \n",
              "\n",
              "[5 rows x 81 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ed22d4a7-67e3-4f14-952f-8053773e0ec0\" class=\"colab-df-container\">\n",
              "    <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>1. Kode Perguruan Tinggi / kdptimsmh</th>\n",
              "      <th>2. Kode Program Studi / kdpstmsmh</th>\n",
              "      <th>3. NIM / nimhsmsmh  (Gunakan Huruf Besar)</th>\n",
              "      <th>4. Nama Lengkap / nmmhsmsmh (Gunakan Huruf Besar)</th>\n",
              "      <th>6. Alamat Email / emailmsmh</th>\n",
              "      <th>7. Tahun Lulus / tahun_lulus</th>\n",
              "      <th>1. Jelaskan status Anda saat ini? f8</th>\n",
              "      <th>2. Berapa bulan anda mendapatkan pekerjaan SEBELUM LULUS? f502</th>\n",
              "      <th>3.  Apakah Anda telah mendapatkan pekerjaan &lt;= 6 bulan / termasuk bekerja sebelum lulus? f504</th>\n",
              "      <th>4. Berapa rata-rata pendapatan Anda per bulan ? f505</th>\n",
              "      <th>...</th>\n",
              "      <th>66. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1605</th>\n",
              "      <th>67. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1606</th>\n",
              "      <th>68. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1607</th>\n",
              "      <th>69. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1608</th>\n",
              "      <th>70. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1609</th>\n",
              "      <th>71. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1610</th>\n",
              "      <th>72. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1611</th>\n",
              "      <th>73. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1612</th>\n",
              "      <th>74. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas (f1613)</th>\n",
              "      <th>75. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas, Tuliskan (f1614)</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>5019</td>\n",
              "      <td>Teknik Informatika (55301)</td>\n",
              "      <td>E41221847</td>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>madityamartono@gmail.com</td>\n",
              "      <td>2024</td>\n",
              "      <td>1 - Bekerja (full time/part time)</td>\n",
              "      <td>1</td>\n",
              "      <td>1 - Ya</td>\n",
              "      <td>Rp 3.000.000,- s/d Rp 4.000.000,-</td>\n",
              "      <td>...</td>\n",
              "      <td>1 - Saya dipromosikan ke posisi yang kurang be...</td>\n",
              "      <td>1 - Saya dapat memeroleh pendapatan yang lebih...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih aman/terjami...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih menarik</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih memungkinkan...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lokasinya lebih de...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini dapat lebih menjam...</td>\n",
              "      <td>1 - Pada awal meniti karir ini, saya harus men...</td>\n",
              "      <td>0 - Pekerjaan saya sudah sesuai</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>5019</td>\n",
              "      <td>Teknik Informatika (55301)</td>\n",
              "      <td>E41191862</td>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>ukiazulgrana89@gmail.com</td>\n",
              "      <td>2024</td>\n",
              "      <td>1 - Bekerja (full time/part time)</td>\n",
              "      <td>0</td>\n",
              "      <td>1 - Ya</td>\n",
              "      <td>Rp 3.000.000,- s/d Rp 4.000.000,-</td>\n",
              "      <td>...</td>\n",
              "      <td>1 - Saya dipromosikan ke posisi yang kurang be...</td>\n",
              "      <td>1 - Saya dapat memeroleh pendapatan yang lebih...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih aman/terjami...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih menarik</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih memungkinkan...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lokasinya lebih de...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini dapat lebih menjam...</td>\n",
              "      <td>1 - Pada awal meniti karir ini, saya harus men...</td>\n",
              "      <td>1 - Lainnya</td>\n",
              "      <td>menambah uang bulanan</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>5019</td>\n",
              "      <td>Teknik Informatika (55301)</td>\n",
              "      <td>E41222296</td>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>yunii7599@gmail.com</td>\n",
              "      <td>2024</td>\n",
              "      <td>1 - Bekerja (full time/part time)</td>\n",
              "      <td>4</td>\n",
              "      <td>2 - Tidak</td>\n",
              "      <td>Rp 3.000.000,- s/d Rp 4.000.000,-</td>\n",
              "      <td>...</td>\n",
              "      <td>1 - Saya dipromosikan ke posisi yang kurang be...</td>\n",
              "      <td>1 - Saya dapat memeroleh pendapatan yang lebih...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih aman/terjami...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih menarik</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih memungkinkan...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lokasinya lebih de...</td>\n",
              "      <td>0 - Pekerjaan saya sudah sesuai</td>\n",
              "      <td>1 - Pada awal meniti karir ini, saya harus men...</td>\n",
              "      <td>1 - Lainnya</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>5019</td>\n",
              "      <td>Teknik Informatika (55301)</td>\n",
              "      <td>E41222266</td>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>sudrajaderina@gmail.com</td>\n",
              "      <td>2024</td>\n",
              "      <td>1 - Bekerja (full time/part time)</td>\n",
              "      <td>0</td>\n",
              "      <td>2 - Tidak</td>\n",
              "      <td>Rp 3.000.000,- s/d Rp 4.000.000,-</td>\n",
              "      <td>...</td>\n",
              "      <td>1 - Saya dipromosikan ke posisi yang kurang be...</td>\n",
              "      <td>1 - Saya dapat memeroleh pendapatan yang lebih...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih aman/terjami...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih menarik</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih memungkinkan...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lokasinya lebih de...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini dapat lebih menjam...</td>\n",
              "      <td>1 - Pada awal meniti karir ini, saya harus men...</td>\n",
              "      <td>1 - Lainnya</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5019</td>\n",
              "      <td>Teknik Informatika (55301)</td>\n",
              "      <td>E41222286</td>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>rafi.abs2@gmail.com</td>\n",
              "      <td>2024</td>\n",
              "      <td>1 - Bekerja (full time/part time)</td>\n",
              "      <td>0</td>\n",
              "      <td>1 - Ya</td>\n",
              "      <td>Rp 3.000.000,- s/d Rp 4.000.000,-</td>\n",
              "      <td>...</td>\n",
              "      <td>1 - Saya dipromosikan ke posisi yang kurang be...</td>\n",
              "      <td>1 - Saya dapat memeroleh pendapatan yang lebih...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih aman/terjami...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih menarik</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lebih memungkinkan...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini lokasinya lebih de...</td>\n",
              "      <td>1 - Pekerjaan saya saat ini dapat lebih menjam...</td>\n",
              "      <td>1 - Pada awal meniti karir ini, saya harus men...</td>\n",
              "      <td>1 - Lainnya</td>\n",
              "      <td>karna terjamin jenjang karirnya</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 81 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ed22d4a7-67e3-4f14-952f-8053773e0ec0')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-ed22d4a7-67e3-4f14-952f-8053773e0ec0 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-ed22d4a7-67e3-4f14-952f-8053773e0ec0');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df"
            }
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for i, col in enumerate(df.columns):\n",
        "    print(i, col)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l8GjNtGwS3F-",
        "outputId": "169ca79d-4a7c-4a5f-ab51-08f40deebfd5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0 1. Kode Perguruan Tinggi / kdptimsmh\n",
            "1 2. Kode Program Studi / kdpstmsmh\n",
            "2 3. NIM / nimhsmsmh  (Gunakan Huruf Besar) \n",
            "3 4. Nama Lengkap / nmmhsmsmh (Gunakan Huruf Besar)\n",
            "4 6. Alamat Email / emailmsmh\n",
            "5 7. Tahun Lulus / tahun_lulus\n",
            "6 1. Jelaskan status Anda saat ini? f8\n",
            "7 2. Berapa bulan anda mendapatkan pekerjaan SEBELUM LULUS? f502\n",
            "8 3.  Apakah Anda telah mendapatkan pekerjaan <= 6 bulan / termasuk bekerja sebelum lulus? f504\n",
            "9 4. Berapa rata-rata pendapatan Anda per bulan ? f505\n",
            "10 5. Berapa bulan Anda MENDAPATKAN PEKERJAAN SETELAH LULUS? f506\n",
            "11 6. Dimana lokasi provinsi tempat Anda bekerja? f5a1\n",
            "12 7. Dimana lokasi kabupaten/kota tempat Anda bekerja? f5a2\n",
            "13 8. Apa jenis perusahaan/instansi/institusi tempat anda bekerja sekarang? f1101\n",
            "14 9. Apa nama perusahaan/kantor tempat Anda bekerja? f5b\n",
            "15 10. Bila Anda berwiraswasta, apa posisi/jabatan Anda saat ini ? f5c\n",
            "16 11. Apa tingkatan tempat kerja Anda? f5d\n",
            "17 12. Sumber biaya Studi Lanjut Anda? f18a\n",
            "18 13. Nama Perguruan Tinggi Studi Lanjut Anda? f18b\n",
            "19 14. Nama Program Studi Studi Lanjut Anda? f18c\n",
            "20 15. Tanggal Masuk Awal Studi Lanjut Anda? f18d\n",
            "21 16. Sebutkan sumberdana dalam pembiayaan kuliah? (bukan ketika Studi Lanjut) f1201\n",
            "22 17. Seberapa erat hubungan bidang studi dengan pekerjaan Anda? f14\n",
            "23 18. Tingkat pendidikan apa yang paling tepat/sesuai untuk pekerjaan anda saat ini? f15\n",
            "24 19. Pada tingkat mana kompetensi ETIKA anda pada SAAT LULUS? f1761\n",
            "25 20. Pada tingkat mana kompetensi ETIKA anda pada SAAT INI? f1762\n",
            "26 21. Pada tingkat mana kompetensi KEAHLIAN BERDASARKAN BIDANG ILMU anda kuasai pada SAAT LULUS? f1763\n",
            "27 22. Pada tingkat mana kompetensi KEAHLIAN BERDASARKAN BIDANG ILMU anda kuasai pada SAAT INI? f1764\n",
            "28 23. Pada tingkat mana kompetensi BAHASA INGGRIS anda kuasai pada SAAT LULUS? f1765\n",
            "29 24. Pada tingkat mana kompetensi BAHASA INGGRIS anda kuasai pada SAAT INI? f1766\n",
            "30 25. Pada tingkat mana kompetensi TEKNOLOGI INFORMASI anda kuasai pada SAAT LULUS? f1767\n",
            "31 26. Pada tingkat mana kompetensi TEKNOLOGI INFORMASI anda kuasai pada SAAT INI? f1768\n",
            "32 27. Pada tingkat mana kompetensi KOMUNIKASI anda kuasai pada SAAT LULUS? f1769\n",
            "33 28. Pada tingkat mana kompetensi KOMUNIKASI anda kuasai pada SAAT INI? f1770\n",
            "34 29. Pada tingkat mana kompetensi KERJA SAMA TIM anda pada SAAT LULUS? f1771\n",
            "35 30. Pada tingkat mana kompetensi KERJA SAMA TIM anda pada SAAT INI? f1772\n",
            "36 31. Pada tingkat mana kompetensi PENGEMBANGAN DIRI anda pada SAAT LULUS? f1773\n",
            "37 32. Pada tingkat mana kompetensi PENGEMBANGAN DIRI anda pada SAAT INI? f1774\n",
            "38 33. Perkuliahan (f21)\n",
            "39 34. Demonstrasi (f22)\n",
            "40 35. Partisipasi dalam proyek riset (f23)\n",
            "41 36. Magang (f24)\n",
            "42 37. Praktikum (f25)\n",
            "43 38. Kerja Lapangan (f26)\n",
            "44 39. Diskusi (f27)\n",
            "45 40. Kapan anda mulai mencari pekerjaan? f301\n",
            "46 41. Saya mencari pekerjaan, Kira-kira ....... bulan SEBELUM lulus (f302)\n",
            "47 42. Saya mencari pekerjaan, Kira-kira ....... bulan SETELAH wisuda (f303)\n",
            "48 43. Melalui iklan di koran/majalah, brosur ? (f401)\n",
            "49 44. Melamar ke perusahaan tanpa mengetahui lowongan yang ada (f402)\n",
            "50 45. Pergi ke bursa/pameran kerja (f403)\n",
            "51 46. Mencari lewat internet/iklan online/milis (f404)\n",
            "52 47. Dihubungi oleh perusahaan (f405)\n",
            "53 48. Menghubungi Kemenakertrans (f406)\n",
            "54 49. Menghubungi agen tenaga kerja komersial/swasta (f407)\n",
            "55 50. Memperoleh informasi dari pusat/kantor pengembangan karir fakultas/universitas (f408)\n",
            "56 51. Menghubungi kantor kemahasiswaan/hubungan alumni (f409)\n",
            "57 52. Membangun jejaring (network) sejak masih kuliah (f410)\n",
            "58 53. Melalui relasi (misalnya dosen, orang tua, saudara, teman, Ikatan Alumni dll.) (f411)\n",
            "59 54. Membangun bisnis sendiri (f412)\n",
            "60 55. Melalui penempatan kerja atau magang (f413)\n",
            "61 56. Bekerja di tempat yang sama dengan tempat kerja semasa kuliah (f414)\n",
            "62 57. Lainnya (f415)\n",
            "63 58. Berapa perusahaan/instansi/institusi yang sudah anda lamar (lewat surat atau e-mail) sebelum anda memperoleh pekerjaan pertama? f6\n",
            "64 59. Berapa banyak perusahaan/instansi/institusi yang merespons lamaran Anda? f7\n",
            "65 60. Berapa banyak perusahaan/instansi/institusi yang mengundang anda untuk wawancara? f7a\n",
            "66 61. Apakah Anda aktif mencari pekerjaan dalam 4 minggu terakhir? Pilihlah satu jawaban (f1001)\n",
            "67 62. Apakah pekerjaan anda saat ini tidak sesuai dengan pendidikan anda ? f1601\n",
            "68 63. Apakah pekerjaan anda saat ini tidak sesuai dengan pendidikan anda ? f1602\n",
            "69 64. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1603\n",
            "70 65. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1604\n",
            "71 66. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1605\n",
            "72 67. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1606\n",
            "73 68. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1607\n",
            "74 69. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1608\n",
            "75 70. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1609\n",
            "76 71. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1610\n",
            "77 72. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1611\n",
            "78 73. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? f1612\n",
            "79 74. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas (f1613)\n",
            "80 75. Jika pekerjaan anda saat ini tidak sesuai dengan pendidikan anda, mengapa anda mengambilnya? Selain pilihan dijawaban soal diatas, Tuliskan (f1614)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = pd.DataFrame()\n",
        "\n",
        "data[\"nim\"] = df[\"3. NIM / nimhsmsmh  (Gunakan Huruf Besar) \"]\n",
        "\n",
        "data[\"nama\"] = df[\"4. Nama Lengkap / nmmhsmsmh (Gunakan Huruf Besar)\"]\n",
        "\n",
        "data[\"perusahaan\"] = df[\"9. Apa nama perusahaan/kantor tempat Anda bekerja? f5b\"]\n",
        "\n",
        "data[\"jabatan\"] = df[\"10. Bila Anda berwiraswasta, apa posisi/jabatan Anda saat ini ? f5c\"]\n",
        "\n",
        "data[\"hubungan\"] = df[\"17. Seberapa erat hubungan bidang studi dengan pekerjaan Anda? f14\"]\n",
        "\n",
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "7xmgh9brS42G",
        "outputId": "2d3ce33e-50b1-43fa-affb-9db870f2fca1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         nim                      nama                       perusahaan  \\\n",
              "0  E41221847   MUHAMMAD ADITYA MARTONO                              NaN   \n",
              "1  E41191862  DEVANDRA LUKITO WIBISONO                  Rococo Clothing   \n",
              "2  E41222296           YUNI INDAH SARI                              NaN   \n",
              "3  E41222266            ERINA SUDRAJAD                              NaN   \n",
              "4  E41222286             MUHAMMAD RAFI  PERUMDA TIRTA BALURAN SITUBONDO   \n",
              "\n",
              "                     jabatan         hubungan  \n",
              "0                  3 - Staff   3 - Cukup Erat  \n",
              "1                  3 - Staff  4 - Kurang Erat  \n",
              "2  4 - Freelance/Kerja Lepas         2 - Erat  \n",
              "3  4 - Freelance/Kerja Lepas   3 - Cukup Erat  \n",
              "4                1 - Founder  4 - Kurang Erat  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-417e7d4a-c0f7-4b27-9e6f-4299314e0488\" class=\"colab-df-container\">\n",
              "    <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>nim</th>\n",
              "      <th>nama</th>\n",
              "      <th>perusahaan</th>\n",
              "      <th>jabatan</th>\n",
              "      <th>hubungan</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>E41221847</td>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>E41191862</td>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>Rococo Clothing</td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>E41222296</td>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>NaN</td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>2 - Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>E41222266</td>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>NaN</td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>E41222286</td>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>PERUMDA TIRTA BALURAN SITUBONDO</td>\n",
              "      <td>1 - Founder</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-417e7d4a-c0f7-4b27-9e6f-4299314e0488')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-417e7d4a-c0f7-4b27-9e6f-4299314e0488 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-417e7d4a-c0f7-4b27-9e6f-4299314e0488');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 361,\n  \"fields\": [\n    {\n      \"column\": \"nim\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"E31211988\",\n          \"E41201015\",\n          \"E41201367\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"DITA DWI ANGGRAENI\",\n          \"AJENG TIAS WULANDARI\",\n          \"FAUZAN ABDILLAH\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"perusahaan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 147,\n        \"samples\": [\n          \"Po;iteknik Negeri Jember\",\n          \"POLRES BONDOWOSO\",\n          \"PT. Tanjungsari Prima Sentosa (RIMASA)\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"jabatan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"4 - Freelance/Kerja Lepas\",\n          \"2 - Co-Founder\",\n          \"3 - Staff\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"hubungan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"4 - Kurang Erat\",\n          \"5 - Tidak sama sekali\",\n          \"2 - Erat\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = data.fillna(\"\")\n",
        "\n",
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "BRFuvi1yS6jn",
        "outputId": "552ee130-d113-4e9b-e851-bf67ada54b1d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         nim                      nama                       perusahaan  \\\n",
              "0  E41221847   MUHAMMAD ADITYA MARTONO                                    \n",
              "1  E41191862  DEVANDRA LUKITO WIBISONO                  Rococo Clothing   \n",
              "2  E41222296           YUNI INDAH SARI                                    \n",
              "3  E41222266            ERINA SUDRAJAD                                    \n",
              "4  E41222286             MUHAMMAD RAFI  PERUMDA TIRTA BALURAN SITUBONDO   \n",
              "\n",
              "                     jabatan         hubungan  \n",
              "0                  3 - Staff   3 - Cukup Erat  \n",
              "1                  3 - Staff  4 - Kurang Erat  \n",
              "2  4 - Freelance/Kerja Lepas         2 - Erat  \n",
              "3  4 - Freelance/Kerja Lepas   3 - Cukup Erat  \n",
              "4                1 - Founder  4 - Kurang Erat  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-60fc2b45-5515-4f84-98c8-ff70ce7fcc3c\" class=\"colab-df-container\">\n",
              "    <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>nim</th>\n",
              "      <th>nama</th>\n",
              "      <th>perusahaan</th>\n",
              "      <th>jabatan</th>\n",
              "      <th>hubungan</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>E41221847</td>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td></td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>E41191862</td>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>Rococo Clothing</td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>E41222296</td>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td></td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>2 - Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>E41222266</td>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td></td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>E41222286</td>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>PERUMDA TIRTA BALURAN SITUBONDO</td>\n",
              "      <td>1 - Founder</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-60fc2b45-5515-4f84-98c8-ff70ce7fcc3c')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-60fc2b45-5515-4f84-98c8-ff70ce7fcc3c button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-60fc2b45-5515-4f84-98c8-ff70ce7fcc3c');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 361,\n  \"fields\": [\n    {\n      \"column\": \"nim\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"E31211988\",\n          \"E41201015\",\n          \"E41201367\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"DITA DWI ANGGRAENI\",\n          \"AJENG TIAS WULANDARI\",\n          \"FAUZAN ABDILLAH\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"perusahaan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 148,\n        \"samples\": [\n          \"PT Tirta Fresindo Jaya\",\n          \"PT. Shopee Internasional Indonesia\",\n          \"PT. Tanjungsari Prima Sentosa (RIMASA)\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"jabatan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"4 - Freelance/Kerja Lepas\",\n          \"\",\n          \"1 - Founder\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"hubungan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"4 - Kurang Erat\",\n          \"5 - Tidak sama sekali\",\n          \"2 - Erat\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[\"teks\"] = (\n",
        "    data[\"perusahaan\"] + \" \" + data[\"jabatan\"]\n",
        ")\n",
        "\n",
        "data[[\"nama\",\"teks\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "x0sUgYwaS8oz",
        "outputId": "3d788d85-d92e-4bb1-bf9a-5c610e03a3a7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                         teks\n",
              "0   MUHAMMAD ADITYA MARTONO                                    3 - Staff\n",
              "1  DEVANDRA LUKITO WIBISONO                    Rococo Clothing 3 - Staff\n",
              "2           YUNI INDAH SARI                    4 - Freelance/Kerja Lepas\n",
              "3            ERINA SUDRAJAD                    4 - Freelance/Kerja Lepas\n",
              "4             MUHAMMAD RAFI  PERUMDA TIRTA BALURAN SITUBONDO 1 - Founder"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-110d502e-d9c0-47ae-ba6c-3fc9812e1920\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>teks</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>3 - Staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>Rococo Clothing 3 - Staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>PERUMDA TIRTA BALURAN SITUBONDO 1 - Founder</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-110d502e-d9c0-47ae-ba6c-3fc9812e1920')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-110d502e-d9c0-47ae-ba6c-3fc9812e1920 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-110d502e-d9c0-47ae-ba6c-3fc9812e1920');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"teks\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"teks\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"Rococo Clothing 3 - Staff\",\n          \"PERUMDA TIRTA BALURAN SITUBONDO 1 - Founder\",\n          \" 3 - Staff\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[\"teks\"] = data[\"teks\"].str.lower()\n",
        "\n",
        "data[[\"nama\",\"teks\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "U-8QHTTBS-h8",
        "outputId": "73071abf-361b-40ab-d706-05dc7bd74689"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                         teks\n",
              "0   MUHAMMAD ADITYA MARTONO                                    3 - staff\n",
              "1  DEVANDRA LUKITO WIBISONO                    rococo clothing 3 - staff\n",
              "2           YUNI INDAH SARI                    4 - freelance/kerja lepas\n",
              "3            ERINA SUDRAJAD                    4 - freelance/kerja lepas\n",
              "4             MUHAMMAD RAFI  perumda tirta baluran situbondo 1 - founder"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f412ac11-6f38-49fa-93f4-ae9a51edb501\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>teks</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>3 - staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>rococo clothing 3 - staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>4 - freelance/kerja lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>4 - freelance/kerja lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>perumda tirta baluran situbondo 1 - founder</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f412ac11-6f38-49fa-93f4-ae9a51edb501')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-f412ac11-6f38-49fa-93f4-ae9a51edb501 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-f412ac11-6f38-49fa-93f4-ae9a51edb501');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"teks\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"teks\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"rococo clothing 3 - staff\",\n          \"perumda tirta baluran situbondo 1 - founder\",\n          \" 3 - staff\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[\"token\"] = data[\"teks\"].apply(word_tokenize)\n",
        "\n",
        "data[[\"nama\",\"token\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "WIwhRLgdS_Nw",
        "outputId": "e15825d7-64c1-47bb-8a53-605aa7a4b2e8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                              token\n",
              "0   MUHAMMAD ADITYA MARTONO                                      [3, -, staff]\n",
              "1  DEVANDRA LUKITO WIBISONO                    [rococo, clothing, 3, -, staff]\n",
              "2           YUNI INDAH SARI                     [4, -, freelance/kerja, lepas]\n",
              "3            ERINA SUDRAJAD                     [4, -, freelance/kerja, lepas]\n",
              "4             MUHAMMAD RAFI  [perumda, tirta, baluran, situbondo, 1, -, fou..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-be7e45ad-8732-40fc-819e-778e8ca7b716\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>token</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>[3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>[rococo, clothing, 3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>[perumda, tirta, baluran, situbondo, 1, -, fou...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-be7e45ad-8732-40fc-819e-778e8ca7b716')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-be7e45ad-8732-40fc-819e-778e8ca7b716 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-be7e45ad-8732-40fc-819e-778e8ca7b716');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"token\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"token\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "stop_words = set(stopwords.words('indonesian'))\n",
        "\n",
        "data[\"token\"] = data[\"token\"].apply(\n",
        "    lambda x: [word for word in x if word not in stop_words]\n",
        ")\n",
        "\n",
        "data[[\"nama\",\"token\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "DaIlHFyITCfu",
        "outputId": "dd8b2e40-f3c0-4056-8566-176d7af8dcf9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                              token\n",
              "0   MUHAMMAD ADITYA MARTONO                                      [3, -, staff]\n",
              "1  DEVANDRA LUKITO WIBISONO                    [rococo, clothing, 3, -, staff]\n",
              "2           YUNI INDAH SARI                     [4, -, freelance/kerja, lepas]\n",
              "3            ERINA SUDRAJAD                     [4, -, freelance/kerja, lepas]\n",
              "4             MUHAMMAD RAFI  [perumda, tirta, baluran, situbondo, 1, -, fou..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-32a4216c-6623-4a77-b0a1-cc35cd05434d\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>token</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>[3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>[rococo, clothing, 3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>[perumda, tirta, baluran, situbondo, 1, -, fou...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-32a4216c-6623-4a77-b0a1-cc35cd05434d')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-32a4216c-6623-4a77-b0a1-cc35cd05434d button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-32a4216c-6623-4a77-b0a1-cc35cd05434d');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"token\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"token\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "factory = StemmerFactory()\n",
        "stemmer = factory.create_stemmer()\n",
        "\n",
        "data[\"stem\"] = data[\"token\"].apply(\n",
        "    lambda words: [stemmer.stem(word) for word in words]\n",
        ")\n",
        "\n",
        "data[[\"nama\",\"stem\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "yCcr4NhfTEYz",
        "outputId": "26e0f193-8388-4fdb-883a-ab6e4acaac05"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                               stem\n",
              "0   MUHAMMAD ADITYA MARTONO                                      [3, -, staff]\n",
              "1  DEVANDRA LUKITO WIBISONO                    [rococo, clothing, 3, -, staff]\n",
              "2           YUNI INDAH SARI                     [4, -, freelance kerja, lepas]\n",
              "3            ERINA SUDRAJAD                     [4, -, freelance kerja, lepas]\n",
              "4             MUHAMMAD RAFI  [perumda, tirta, balur, situbondo, 1, -, founder]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0e89be05-4c0a-4336-a7bd-475623f072fc\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>stem</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>[3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>[rococo, clothing, 3, -, staff]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>[4, -, freelance kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>[4, -, freelance kerja, lepas]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>[perumda, tirta, balur, situbondo, 1, -, founder]</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0e89be05-4c0a-4336-a7bd-475623f072fc')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-0e89be05-4c0a-4336-a7bd-475623f072fc button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-0e89be05-4c0a-4336-a7bd-475623f072fc');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"stem\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"stem\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[\"clean_text\"] = data[\"stem\"].apply(\n",
        "    lambda x: \" \".join(x)\n",
        ")\n",
        "\n",
        "data[[\"nama\",\"clean_text\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "tETg-bykTGb-",
        "outputId": "081ce955-7ff6-408c-ba84-0e1fe3e84448"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama                                 clean_text\n",
              "0   MUHAMMAD ADITYA MARTONO                                  3 - staff\n",
              "1  DEVANDRA LUKITO WIBISONO                  rococo clothing 3 - staff\n",
              "2           YUNI INDAH SARI                  4 - freelance kerja lepas\n",
              "3            ERINA SUDRAJAD                  4 - freelance kerja lepas\n",
              "4             MUHAMMAD RAFI  perumda tirta balur situbondo 1 - founder"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-acb48aba-3b68-43f7-8f59-15c330cb0371\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>clean_text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>3 - staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>rococo clothing 3 - staff</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>4 - freelance kerja lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>4 - freelance kerja lepas</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>perumda tirta balur situbondo 1 - founder</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-acb48aba-3b68-43f7-8f59-15c330cb0371')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-acb48aba-3b68-43f7-8f59-15c330cb0371 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-acb48aba-3b68-43f7-8f59-15c330cb0371');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"clean_text\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"clean_text\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"rococo clothing 3 - staff\",\n          \"perumda tirta balur situbondo 1 - founder\",\n          \"3 - staff\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "vectorizer = TfidfVectorizer()\n",
        "\n",
        "X = vectorizer.fit_transform(data[\"clean_text\"])\n",
        "\n",
        "print(X.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j2Z7S2OTTIQ2",
        "outputId": "3052856b-d782-41ea-f892-201fa4f27c51"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(361, 263)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.cluster import KMeans\n",
        "\n",
        "kmeans = KMeans(\n",
        "    n_clusters=3,\n",
        "    random_state=42,\n",
        "    n_init=10\n",
        ")\n",
        "\n",
        "kmeans.fit(X)\n",
        "\n",
        "data[\"cluster\"] = kmeans.labels_\n",
        "\n",
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 293
        },
        "id": "4ChkksQRTKf1",
        "outputId": "6897bfef-a091-46bf-da11-a3b3b6872b65"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         nim                      nama                       perusahaan  \\\n",
              "0  E41221847   MUHAMMAD ADITYA MARTONO                                    \n",
              "1  E41191862  DEVANDRA LUKITO WIBISONO                  Rococo Clothing   \n",
              "2  E41222296           YUNI INDAH SARI                                    \n",
              "3  E41222266            ERINA SUDRAJAD                                    \n",
              "4  E41222286             MUHAMMAD RAFI  PERUMDA TIRTA BALURAN SITUBONDO   \n",
              "\n",
              "                     jabatan         hubungan  \\\n",
              "0                  3 - Staff   3 - Cukup Erat   \n",
              "1                  3 - Staff  4 - Kurang Erat   \n",
              "2  4 - Freelance/Kerja Lepas         2 - Erat   \n",
              "3  4 - Freelance/Kerja Lepas   3 - Cukup Erat   \n",
              "4                1 - Founder  4 - Kurang Erat   \n",
              "\n",
              "                                          teks  \\\n",
              "0                                    3 - staff   \n",
              "1                    rococo clothing 3 - staff   \n",
              "2                    4 - freelance/kerja lepas   \n",
              "3                    4 - freelance/kerja lepas   \n",
              "4  perumda tirta baluran situbondo 1 - founder   \n",
              "\n",
              "                                               token  \\\n",
              "0                                      [3, -, staff]   \n",
              "1                    [rococo, clothing, 3, -, staff]   \n",
              "2                     [4, -, freelance/kerja, lepas]   \n",
              "3                     [4, -, freelance/kerja, lepas]   \n",
              "4  [perumda, tirta, baluran, situbondo, 1, -, fou...   \n",
              "\n",
              "                                                stem  \\\n",
              "0                                      [3, -, staff]   \n",
              "1                    [rococo, clothing, 3, -, staff]   \n",
              "2                     [4, -, freelance kerja, lepas]   \n",
              "3                     [4, -, freelance kerja, lepas]   \n",
              "4  [perumda, tirta, balur, situbondo, 1, -, founder]   \n",
              "\n",
              "                                  clean_text  cluster  \n",
              "0                                  3 - staff        1  \n",
              "1                  rococo clothing 3 - staff        2  \n",
              "2                  4 - freelance kerja lepas        0  \n",
              "3                  4 - freelance kerja lepas        0  \n",
              "4  perumda tirta balur situbondo 1 - founder        2  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c612e868-9ad9-4af3-9262-0a8ca747448c\" class=\"colab-df-container\">\n",
              "    <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>nim</th>\n",
              "      <th>nama</th>\n",
              "      <th>perusahaan</th>\n",
              "      <th>jabatan</th>\n",
              "      <th>hubungan</th>\n",
              "      <th>teks</th>\n",
              "      <th>token</th>\n",
              "      <th>stem</th>\n",
              "      <th>clean_text</th>\n",
              "      <th>cluster</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>E41221847</td>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td></td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "      <td>3 - staff</td>\n",
              "      <td>[3, -, staff]</td>\n",
              "      <td>[3, -, staff]</td>\n",
              "      <td>3 - staff</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>E41191862</td>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>Rococo Clothing</td>\n",
              "      <td>3 - Staff</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "      <td>rococo clothing 3 - staff</td>\n",
              "      <td>[rococo, clothing, 3, -, staff]</td>\n",
              "      <td>[rococo, clothing, 3, -, staff]</td>\n",
              "      <td>rococo clothing 3 - staff</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>E41222296</td>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td></td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>2 - Erat</td>\n",
              "      <td>4 - freelance/kerja lepas</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "      <td>[4, -, freelance kerja, lepas]</td>\n",
              "      <td>4 - freelance kerja lepas</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>E41222266</td>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td></td>\n",
              "      <td>4 - Freelance/Kerja Lepas</td>\n",
              "      <td>3 - Cukup Erat</td>\n",
              "      <td>4 - freelance/kerja lepas</td>\n",
              "      <td>[4, -, freelance/kerja, lepas]</td>\n",
              "      <td>[4, -, freelance kerja, lepas]</td>\n",
              "      <td>4 - freelance kerja lepas</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>E41222286</td>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>PERUMDA TIRTA BALURAN SITUBONDO</td>\n",
              "      <td>1 - Founder</td>\n",
              "      <td>4 - Kurang Erat</td>\n",
              "      <td>perumda tirta baluran situbondo 1 - founder</td>\n",
              "      <td>[perumda, tirta, baluran, situbondo, 1, -, fou...</td>\n",
              "      <td>[perumda, tirta, balur, situbondo, 1, -, founder]</td>\n",
              "      <td>perumda tirta balur situbondo 1 - founder</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c612e868-9ad9-4af3-9262-0a8ca747448c')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-c612e868-9ad9-4af3-9262-0a8ca747448c button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-c612e868-9ad9-4af3-9262-0a8ca747448c');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 361,\n  \"fields\": [\n    {\n      \"column\": \"nim\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"E31211988\",\n          \"E41201015\",\n          \"E41201367\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 361,\n        \"samples\": [\n          \"DITA DWI ANGGRAENI\",\n          \"AJENG TIAS WULANDARI\",\n          \"FAUZAN ABDILLAH\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"perusahaan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 148,\n        \"samples\": [\n          \"PT Tirta Fresindo Jaya\",\n          \"PT. Shopee Internasional Indonesia\",\n          \"PT. Tanjungsari Prima Sentosa (RIMASA)\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"jabatan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"4 - Freelance/Kerja Lepas\",\n          \"\",\n          \"1 - Founder\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"hubungan\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"4 - Kurang Erat\",\n          \"5 - Tidak sama sekali\",\n          \"2 - Erat\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"teks\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 157,\n        \"samples\": [\n          \" \",\n          \"cv. mark desain 3 - staff\",\n          \"pt tirta fresindo jaya \"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"token\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"stem\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"clean_text\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 156,\n        \"samples\": [\n          \"softwarehouse 3 - staff\",\n          \"pt  musik proaktif 4 - freelance kerja lepas\",\n          \"eiger indonesia 3 - staff\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"cluster\",\n      \"properties\": {\n        \"dtype\": \"int32\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          1,\n          2,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cluster_map = {\n",
        "    0:\"Cluster 0\",\n",
        "    1:\"Cluster 1\",\n",
        "    2:\"Cluster 2\"\n",
        "}\n",
        "\n",
        "data[\"hasil\"] = data[\"cluster\"].map(cluster_map)\n",
        "\n",
        "data[[\"nama\",\"hasil\"]].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "rH_Og9-iTNvN",
        "outputId": "fd5825cb-11f0-457d-e429-0a6a71ca0497"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                       nama      hasil\n",
              "0   MUHAMMAD ADITYA MARTONO  Cluster 1\n",
              "1  DEVANDRA LUKITO WIBISONO  Cluster 2\n",
              "2           YUNI INDAH SARI  Cluster 0\n",
              "3            ERINA SUDRAJAD  Cluster 0\n",
              "4             MUHAMMAD RAFI  Cluster 2"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-28be794f-f7fd-4e83-97ef-9fdd83862e62\" class=\"colab-df-container\">\n",
              "    <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>nama</th>\n",
              "      <th>hasil</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>MUHAMMAD ADITYA MARTONO</td>\n",
              "      <td>Cluster 1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DEVANDRA LUKITO WIBISONO</td>\n",
              "      <td>Cluster 2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>YUNI INDAH SARI</td>\n",
              "      <td>Cluster 0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ERINA SUDRAJAD</td>\n",
              "      <td>Cluster 0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>MUHAMMAD RAFI</td>\n",
              "      <td>Cluster 2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-28be794f-f7fd-4e83-97ef-9fdd83862e62')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-28be794f-f7fd-4e83-97ef-9fdd83862e62 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-28be794f-f7fd-4e83-97ef-9fdd83862e62');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data[[\\\"nama\\\",\\\"hasil\\\"]]\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"nama\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"DEVANDRA LUKITO WIBISONO\",\n          \"MUHAMMAD RAFI\",\n          \"YUNI INDAH SARI\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"hasil\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"Cluster 1\",\n          \"Cluster 2\",\n          \"Cluster 0\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[\"hasil\"].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 210
        },
        "id": "90wcmuMzTPYr",
        "outputId": "d7f01740-ee6d-4ca1-e388-fbd901075f4f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "hasil\n",
              "Cluster 2    191\n",
              "Cluster 0    118\n",
              "Cluster 1     52\n",
              "Name: count, dtype: int64"
            ],
            "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>count</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hasil</th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Cluster 2</th>\n",
              "      <td>191</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Cluster 0</th>\n",
              "      <td>118</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Cluster 1</th>\n",
              "      <td>52</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div><br><label><b>dtype:</b> int64</label>"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.to_csv(\"hasil_cluster.csv\", index=False)\n",
        "\n",
        "print(\"Selesai\")"
      ],
      "metadata": {
        "id": "YyT8Hn3aTQ9e"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}