semantic_similarity (2).ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "INwkG9NjJi3i"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "import transformers\n",
        "from transformers import AutoTokenizer, AutoModel\n",
        "import torch\n",
        "import torch.nn.functional as F\n",
        "from transformers import AutoModelForSequenceClassification\n",
        "\n",
        "import nltk\n",
        "from nltk.corpus import stopwords\n",
        "from nltk.stem.porter import PorterStemmer\n",
        "from wordcloud import WordCloud,STOPWORDS\n",
        "from nltk.stem import WordNetLemmatizer\n",
        "from nltk.tokenize import word_tokenize,sent_tokenize\n",
        "import re,string,unicodedata\n",
        "\n",
        "from sklearn.model_selection import train_test_split\n",
        "from string import punctuation\n",
        "from nltk.corpus import wordnet\n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nBohuaRCpgOy",
        "outputId": "1c5c41b1-5362-41b6-f6da-4c99f17b93a3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting transformers\n",
            "  Downloading transformers-4.28.0-py3-none-any.whl (7.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m53.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting huggingface-hub<1.0,>=0.11.0\n",
            "  Downloading huggingface_hub-0.13.4-py3-none-any.whl (200 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m200.1/200.1 kB\u001b[0m \u001b[31m26.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from transformers) (6.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (2022.10.31)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers) (2.27.1)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (1.22.4)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (23.0)\n",
            "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\n",
            "  Downloading tokenizers-0.13.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m93.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from transformers) (3.11.0)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers) (4.65.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (3.4)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (2.0.12)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (2022.12.7)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (1.26.15)\n",
            "Installing collected packages: tokenizers, huggingface-hub, transformers\n",
            "Successfully installed huggingface-hub-0.13.4 tokenizers-0.13.3 transformers-4.28.0\n"
          ]
        }
      ],
      "source": [
        "pip install transformers"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "DD9QrU5VzMht"
      },
      "outputs": [],
      "source": [
        "from sklearn.metrics.pairwise import cosine_similarity"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "WE9IceTtK7K3"
      },
      "outputs": [],
      "source": [
        "df = pd.read_csv(\"resume.csv\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "R5A-RIR4LDV8",
        "outputId": "47fe45bb-8e01-433c-c6cf-ec418fa723da"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       Category                                             Resume\n",
              "0  Data Science  Skills * Programming Languages: Python (pandas...\n",
              "1  Data Science  Education Details \\r\\nMay 2013 to May 2017 B.E...\n",
              "2  Data Science  Areas of Interest Deep Learning, Control Syste...\n",
              "3  Data Science  Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...\n",
              "4  Data Science  Education Details \\r\\n MCA   YMCAUST,  Faridab..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e5e33652-e71c-4151-a09f-cc1aa9966d74\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>Skills * Programming Languages: Python (pandas...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>Education Details \\r\\nMay 2013 to May 2017 B.E...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>Areas of Interest Deep Learning, Control Syste...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>Education Details \\r\\n MCA   YMCAUST,  Faridab...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e5e33652-e71c-4151-a09f-cc1aa9966d74')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-e5e33652-e71c-4151-a09f-cc1aa9966d74 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-e5e33652-e71c-4151-a09f-cc1aa9966d74');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ],
      "source": [
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tbzpcddgLUmv",
        "outputId": "b5ef7fb5-076a-4066-a570-b49aebb6511d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Data Science', 'HR', 'Advocate', 'Arts', 'Web Designing',\n",
              "       'Mechanical Engineer', 'Sales', 'Health and fitness',\n",
              "       'Civil Engineer', 'Java Developer', 'Business Analyst',\n",
              "       'SAP Developer', 'Automation Testing', 'Electrical Engineering',\n",
              "       'Operations Manager', 'Python Developer', 'DevOps Engineer',\n",
              "       'Network Security Engineer', 'PMO', 'Database', 'Hadoop',\n",
              "       'ETL Developer', 'DotNet Developer', 'Blockchain', 'Testing'],\n",
              "      dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "df.Category.unique()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xkWAvdWFr_Ve",
        "outputId": "7fb4e960-a830-4e3d-a4ea-8d8220d5e8a3"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "25"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "df.Category.nunique()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "adv = df[df[\"Category\"] == 'Testing']\n",
        "adv"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "jYwQKIvAw7Se",
        "outputId": "419db7db-3294-481c-bb1f-b04b6c14ba4e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    Category                                             Resume\n",
              "892  Testing  â¢ Good logical and analytical skills â¢ Pos...\n",
              "893  Testing  COMPUTER PROFICIENCY â¢ Basic: MS-Office (Pow...\n",
              "894  Testing  Computer Skills: â¢ Proficient in MS office (...\n",
              "895  Testing  â Willingness to accept the challenges. â ...\n",
              "896  Testing  PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...\n",
              "..       ...                                                ...\n",
              "957  Testing  Computer Skills: â¢ Proficient in MS office (...\n",
              "958  Testing  â Willingness to accept the challenges. â ...\n",
              "959  Testing  PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...\n",
              "960  Testing  COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power ...\n",
              "961  Testing  Skill Set OS Windows XP/7/8/8.1/10 Database MY...\n",
              "\n",
              "[70 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e4dd4fd4-b8f6-48a4-b949-49bed8d55cd8\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>892</th>\n",
              "      <td>Testing</td>\n",
              "      <td>â¢ Good logical and analytical skills â¢ Pos...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>893</th>\n",
              "      <td>Testing</td>\n",
              "      <td>COMPUTER PROFICIENCY â¢ Basic: MS-Office (Pow...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>894</th>\n",
              "      <td>Testing</td>\n",
              "      <td>Computer Skills: â¢ Proficient in MS office (...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>895</th>\n",
              "      <td>Testing</td>\n",
              "      <td>â Willingness to accept the challenges. â ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>896</th>\n",
              "      <td>Testing</td>\n",
              "      <td>PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>957</th>\n",
              "      <td>Testing</td>\n",
              "      <td>Computer Skills: â¢ Proficient in MS office (...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>958</th>\n",
              "      <td>Testing</td>\n",
              "      <td>â Willingness to accept the challenges. â ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>959</th>\n",
              "      <td>Testing</td>\n",
              "      <td>PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>960</th>\n",
              "      <td>Testing</td>\n",
              "      <td>COMPUTER SKILLS &amp; SOFTWARE KNOWLEDGE MS-Power ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>961</th>\n",
              "      <td>Testing</td>\n",
              "      <td>Skill Set OS Windows XP/7/8/8.1/10 Database MY...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>70 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e4dd4fd4-b8f6-48a4-b949-49bed8d55cd8')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-e4dd4fd4-b8f6-48a4-b949-49bed8d55cd8 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-e4dd4fd4-b8f6-48a4-b949-49bed8d55cd8');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "adv = df.Resume[84:104]\n",
        "adv"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dW9_YuoX5F6v",
        "outputId": "a3c70ef0-4acc-4309-cf53-cef504674e40"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "84     TECHNICAL QUALIFICATIONS: â¢ Windows, Ms. Off...\n",
              "85     Education Details \\r\\n B.Com, LL.B.,   Univers...\n",
              "86     Education Details \\r\\n LLB.   Dibrugarh Univer...\n",
              "87     Education Details \\r\\nNovember 2016 to January...\n",
              "88     SKILLS â¢ Knows English as native speaker (IE...\n",
              "89     QUALIFICATION: Introduction to Computer EXTRAE...\n",
              "90     Skills: Natural Languages: Proficient in Engli...\n",
              "91     Skills Legal Writing Efficient researcher Lega...\n",
              "92     Good grasping quality and skillful work Educat...\n",
              "93     â¢ Hard working â¢ Quick learnerEducation De...\n",
              "94     TECHNICAL QUALIFICATIONS: â¢ Windows, Ms. Off...\n",
              "95     Education Details \\r\\n B.Com, LL.B.,   Univers...\n",
              "96     Education Details \\r\\n LLB.   Dibrugarh Univer...\n",
              "97     Education Details \\r\\nNovember 2016 to January...\n",
              "98     SKILLS â¢ Knows English as native speaker (IE...\n",
              "99     QUALIFICATION: Introduction to Computer EXTRAE...\n",
              "100    Skills: Natural Languages: Proficient in Engli...\n",
              "101    Skills Legal Writing Efficient researcher Lega...\n",
              "102    Good grasping quality and skillful work Educat...\n",
              "103    â¢ Hard working â¢ Quick learnerEducation De...\n",
              "Name: Resume, dtype: object"
            ]
          },
          "metadata": {},
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "rfvPvjKVwCGl"
      },
      "outputs": [],
      "source": [
        "py = df[df['Category'] == 'Python Developer']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "yvBLYOa-1ozt",
        "outputId": "da765a61-b427-4b4d-c8e0-f42441be0476"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-b416f51f-3f37-4522-9301-b9ebaf26d979\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>185</th>\n",
              "      <td>Mechanical Engineer</td>\n",
              "      <td>Education Details \\r\\nMay 1999 to September 20...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>186</th>\n",
              "      <td>Mechanical Engineer</td>\n",
              "      <td>SKILLS: â¢ Knowledge of software / computer: ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>187</th>\n",
              "      <td>Mechanical Engineer</td>\n",
              "      <td>Education Details \\r\\nJanuary 2018 Bachelor's ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>188</th>\n",
              "      <td>Mechanical Engineer</td>\n",
              "      <td>Education Details \\r\\nJune 2014 to June 2018 B...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>189</th>\n",
              "      <td>Mechanical Engineer</td>\n",
              "      <td>* I'm hard working person. * I'm self confiden...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b416f51f-3f37-4522-9301-b9ebaf26d979')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-b416f51f-3f37-4522-9301-b9ebaf26d979 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-b416f51f-3f37-4522-9301-b9ebaf26d979');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "                Category                                             Resume\n",
              "185  Mechanical Engineer  Education Details \\r\\nMay 1999 to September 20...\n",
              "186  Mechanical Engineer  SKILLS: â¢ Knowledge of software / computer: ...\n",
              "187  Mechanical Engineer  Education Details \\r\\nJanuary 2018 Bachelor's ...\n",
              "188  Mechanical Engineer  Education Details \\r\\nJune 2014 to June 2018 B...\n",
              "189  Mechanical Engineer  * I'm hard working person. * I'm self confiden..."
            ]
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "me = df[df['Category'] == 'Mechanical Engineer']\n",
        "me.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "CsjglZhazPji",
        "outputId": "fb8b34a2-cbdb-4d4b-dae5-b4a98bad3229"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-588e5370-d39c-4e0d-b761-2fc84237facd\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>403</th>\n",
              "      <td>Business Analyst</td>\n",
              "      <td>Education Details \\r\\n BE Computer Science Mum...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>404</th>\n",
              "      <td>Business Analyst</td>\n",
              "      <td>Technical Skills Application Servers: IIS 6.0,...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>405</th>\n",
              "      <td>Business Analyst</td>\n",
              "      <td>Key Skills - Requirement Gathering - Requireme...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>406</th>\n",
              "      <td>Business Analyst</td>\n",
              "      <td>IT Skills: Area Exposure Modeling Tool: Bizagi...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>407</th>\n",
              "      <td>Business Analyst</td>\n",
              "      <td>TECHNOLOGICAL SKILLS â¦ Knowledge of Computer...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-588e5370-d39c-4e0d-b761-2fc84237facd')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-588e5370-d39c-4e0d-b761-2fc84237facd 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-588e5370-d39c-4e0d-b761-2fc84237facd');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "             Category                                             Resume\n",
              "403  Business Analyst  Education Details \\r\\n BE Computer Science Mum...\n",
              "404  Business Analyst  Technical Skills Application Servers: IIS 6.0,...\n",
              "405  Business Analyst  Key Skills - Requirement Gathering - Requireme...\n",
              "406  Business Analyst  IT Skills: Area Exposure Modeling Tool: Bizagi...\n",
              "407  Business Analyst  TECHNOLOGICAL SKILLS â¦ Knowledge of Computer..."
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ba = df[df['Category'] == 'Business Analyst']\n",
        "ba.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "5iKBRhPNwY9h",
        "outputId": "282e0cc3-a7c7-47ee-e4da-9eb1c1588dc7"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-d7dcbcbd-03ee-47de-a3d3-afcc07a1ae17\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>551</th>\n",
              "      <td>Python Developer</td>\n",
              "      <td>Technical Skills / Responsibilities: â¢ Hands...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>552</th>\n",
              "      <td>Python Developer</td>\n",
              "      <td>Education Details \\r\\nJune 2013 to June 2016 D...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>553</th>\n",
              "      <td>Python Developer</td>\n",
              "      <td>TECHNICAL PROFICIENCIES Platform: Ubuntu/Fedor...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>554</th>\n",
              "      <td>Python Developer</td>\n",
              "      <td>Technical Skills: Languages Python Python Fram...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>555</th>\n",
              "      <td>Python Developer</td>\n",
              "      <td>Training attended: 1. Successfully completed E...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d7dcbcbd-03ee-47de-a3d3-afcc07a1ae17')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-d7dcbcbd-03ee-47de-a3d3-afcc07a1ae17 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-d7dcbcbd-03ee-47de-a3d3-afcc07a1ae17');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "             Category                                             Resume\n",
              "551  Python Developer  Technical Skills / Responsibilities: â¢ Hands...\n",
              "552  Python Developer  Education Details \\r\\nJune 2013 to June 2016 D...\n",
              "553  Python Developer  TECHNICAL PROFICIENCIES Platform: Ubuntu/Fedor...\n",
              "554  Python Developer  Technical Skills: Languages Python Python Fram...\n",
              "555  Python Developer  Training attended: 1. Successfully completed E..."
            ]
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "py.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gkN7cPtzLYHv",
        "outputId": "39fc7bbb-a1c4-4d79-8b7e-ba09edd26695"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(962, 2)"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "\n",
        "df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ajTlKF34Ld1i",
        "outputId": "c8818a67-919d-4dd9-9c0a-4a1da7e60ae2"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "Category    0\n",
              "Resume      0\n",
              "dtype: int64"
            ]
          },
          "execution_count": 13,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.isnull().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        },
        "id": "ZR2wGcAWLg3D",
        "outputId": "4a9e555d-6361-4219-e6d7-24bb9ae9df81"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'skills * programming languages: python (pandas, numpy, scipy, scikit-learn, matplotlib), sql, java, javascript/jquery. * machine learning: regression, svm, naã¯ve bayes, knn, random forest, decision trees, boosting techniques, cluster analysis, word embedding, sentiment analysis, natural language processing, dimensionality reduction, topic modelling (lda, nmf), pca & neural nets. * database visualizations: mysql, sqlserver, cassandra, hbase, elasticsearch d3.js, dc.js, plotly, kibana, matplotlib, ggplot, tableau. * others: regular expression, html, css, angular 6, logstash, kafka, python flask, git, docker, computer vision - open cv and understanding of deep learning.education details \\r\\n\\r\\ndata science assurance associate \\r\\n\\r\\ndata science assurance associate - ernst & young llp\\r\\nskill details \\r\\njavascript- exprience - 24 months\\r\\njquery- exprience - 24 months\\r\\npython- exprience - 24 monthscompany details \\r\\ncompany - ernst & young llp\\r\\ndescription - fraud investigations and dispute services   assurance\\r\\ntechnology assisted review\\r\\ntar (technology assisted review) assists in accelerating the review process and run analytics and generate reports.\\r\\n* core member of a team helped in developing automated review platform tool from scratch for assisting e discovery domain, this tool implements predictive coding and topic modelling by automating reviews, resulting in reduced labor costs and time spent during the lawyers review.\\r\\n* understand the end to end flow of the solution, doing research and development for classification models, predictive analysis and mining of the information present in text data. worked on analyzing the outputs and precision monitoring for the entire tool.\\r\\n* tar assists in predictive coding, topic modelling from the evidence by following ey standards. developed the classifier models in order to identify \"red flags\" and fraud-related issues.\\r\\n\\r\\ntools & technologies: python, scikit-learn, tfidf, word2vec, doc2vec, cosine similarity, naã¯ve bayes, lda, nmf for topic modelling, vader and text blob for sentiment analysis. matplot lib, tableau dashboard for reporting.\\r\\n\\r\\nmultiple data science and analytic projects (usa clients)\\r\\ntext analytics - motor vehicle customer review data * received customer feedback survey data for past one year. performed sentiment (positive, negative & neutral) and time series analysis on customer comments across all 4 categories.\\r\\n* created heat map of terms by survey category based on frequency of words * extracted positive and negative words across all the survey categories and plotted word cloud.\\r\\n* created customized tableau dashboards for effective reporting and visualizations.\\r\\nchatbot * developed a user friendly chatbot for one of our products which handle simple questions about hours of operation, reservation options and so on.\\r\\n* this chat bot serves entire product related questions. giving overview of tool via qa platform and also give recommendation responses so that user question to build chain of relevant answer.\\r\\n* this too has intelligence to build the pipeline of questions as per user requirement and asks the relevant /recommended questions.\\r\\n\\r\\ntools & technologies: python, natural language processing, nltk, spacy, topic modelling, sentiment analysis, word embedding, scikit-learn, javascript/jquery, sqlserver\\r\\n\\r\\ninformation governance\\r\\norganizations to make informed decisions about all of the information they store. the integrated information governance portfolio synthesizes intelligence across unstructured data sources and facilitates action to ensure organizations are best positioned to counter information risk.\\r\\n* scan data from multiple sources of formats and parse different file formats, extract meta data information, push results for indexing elastic search and created customized, interactive dashboards using kibana.\\r\\n* preforming rot analysis on the data which give information of data which helps identify content that is either redundant, outdated, or trivial.\\r\\n* preforming full-text search analysis on elastic search with predefined methods which can tag as (pii) personally identifiable information (social security numbers, addresses, names, etc.) which frequently targeted during cyber-attacks.\\r\\ntools & technologies: python, flask, elastic search, kibana\\r\\n\\r\\nfraud analytic platform\\r\\nfraud analytics and investigative platform to review all red flag cases.\\r\\nâ\\x80¢ fap is a fraud analytics and investigative platform with inbuilt case manager and suite of analytics for various erp systems.\\r\\n* it can be used by clients to interrogate their accounting systems for identifying the anomalies which can be indicators of fraud by running advanced analytics\\r\\ntools & technologies: html, javascript, sqlserver, jquery, css, bootstrap, node.js, d3.js, dc.js'"
            ]
          },
          "execution_count": 14,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df['Resume'] = df['Resume'].str.lower()\n",
        "df.Resume[0]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "s3tQeyL4MESr"
      },
      "outputs": [],
      "source": [
        "text = df.Resume[0]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "nmgD2cdiNaEP"
      },
      "outputs": [],
      "source": [
        "text = re.sub(r'[^a-zA-Z0-9\\s]', '', text)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        },
        "id": "Cu7ZIb5gNeEh",
        "outputId": "91fdb2ad-e464-4a8a-b651-a8488ecb8b96"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'skills  programming languages python pandas numpy scipy scikitlearn matplotlib sql java javascriptjquery  machine learning regression svm nave bayes knn random forest decision trees boosting techniques cluster analysis word embedding sentiment analysis natural language processing dimensionality reduction topic modelling lda nmf pca  neural nets  database visualizations mysql sqlserver cassandra hbase elasticsearch d3js dcjs plotly kibana matplotlib ggplot tableau  others regular expression html css angular 6 logstash kafka python flask git docker computer vision  open cv and understanding of deep learningeducation details \\r\\n\\r\\ndata science assurance associate \\r\\n\\r\\ndata science assurance associate  ernst  young llp\\r\\nskill details \\r\\njavascript exprience  24 months\\r\\njquery exprience  24 months\\r\\npython exprience  24 monthscompany details \\r\\ncompany  ernst  young llp\\r\\ndescription  fraud investigations and dispute services   assurance\\r\\ntechnology assisted review\\r\\ntar technology assisted review assists in accelerating the review process and run analytics and generate reports\\r\\n core member of a team helped in developing automated review platform tool from scratch for assisting e discovery domain this tool implements predictive coding and topic modelling by automating reviews resulting in reduced labor costs and time spent during the lawyers review\\r\\n understand the end to end flow of the solution doing research and development for classification models predictive analysis and mining of the information present in text data worked on analyzing the outputs and precision monitoring for the entire tool\\r\\n tar assists in predictive coding topic modelling from the evidence by following ey standards developed the classifier models in order to identify red flags and fraudrelated issues\\r\\n\\r\\ntools  technologies python scikitlearn tfidf word2vec doc2vec cosine similarity nave bayes lda nmf for topic modelling vader and text blob for sentiment analysis matplot lib tableau dashboard for reporting\\r\\n\\r\\nmultiple data science and analytic projects usa clients\\r\\ntext analytics  motor vehicle customer review data  received customer feedback survey data for past one year performed sentiment positive negative  neutral and time series analysis on customer comments across all 4 categories\\r\\n created heat map of terms by survey category based on frequency of words  extracted positive and negative words across all the survey categories and plotted word cloud\\r\\n created customized tableau dashboards for effective reporting and visualizations\\r\\nchatbot  developed a user friendly chatbot for one of our products which handle simple questions about hours of operation reservation options and so on\\r\\n this chat bot serves entire product related questions giving overview of tool via qa platform and also give recommendation responses so that user question to build chain of relevant answer\\r\\n this too has intelligence to build the pipeline of questions as per user requirement and asks the relevant recommended questions\\r\\n\\r\\ntools  technologies python natural language processing nltk spacy topic modelling sentiment analysis word embedding scikitlearn javascriptjquery sqlserver\\r\\n\\r\\ninformation governance\\r\\norganizations to make informed decisions about all of the information they store the integrated information governance portfolio synthesizes intelligence across unstructured data sources and facilitates action to ensure organizations are best positioned to counter information risk\\r\\n scan data from multiple sources of formats and parse different file formats extract meta data information push results for indexing elastic search and created customized interactive dashboards using kibana\\r\\n preforming rot analysis on the data which give information of data which helps identify content that is either redundant outdated or trivial\\r\\n preforming fulltext search analysis on elastic search with predefined methods which can tag as pii personally identifiable information social security numbers addresses names etc which frequently targeted during cyberattacks\\r\\ntools  technologies python flask elastic search kibana\\r\\n\\r\\nfraud analytic platform\\r\\nfraud analytics and investigative platform to review all red flag cases\\r\\n fap is a fraud analytics and investigative platform with inbuilt case manager and suite of analytics for various erp systems\\r\\n it can be used by clients to interrogate their accounting systems for identifying the anomalies which can be indicators of fraud by running advanced analytics\\r\\ntools  technologies html javascript sqlserver jquery css bootstrap nodejs d3js dcjs'"
            ]
          },
          "execution_count": 17,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "text"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Zb8VI-RKOred",
        "outputId": "8a1d3b92-3443-4e84-cc42-bf0e3da538c8"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Unzipping corpora/stopwords.zip.\n",
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt.zip.\n",
            "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",
            "[nltk_data] Downloading package omw-1.4 to /root/nltk_data...\n"
          ]
        }
      ],
      "source": [
        "from nltk.corpus import stopwords\n",
        "lemmatizer = WordNetLemmatizer()\n",
        "nltk.download('stopwords')\n",
        "nltk.download('punkt')\n",
        "nltk.download('wordnet')\n",
        "nltk.download('omw-1.4')\n",
        "stops = set(stopwords.words(\"english\"))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1IUZLFfJPn46"
      },
      "outputs": [],
      "source": [
        "def identify_tokens(row):\n",
        "    review = row\n",
        "    tokens = nltk.word_tokenize(review)\n",
        "    # taken only words (not punctuation)\n",
        "    token_words = [w for w in tokens if w.isalpha()]\n",
        "    meaningful_words = [w for w in token_words if not w in stops]\n",
        "    lemmatize_list = [lemmatizer.lemmatize(word) for word in meaningful_words]\n",
        "    joined_words = (' '.join(lemmatize_list))\n",
        "    return joined_words"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Hrs82Aqzcow6"
      },
      "outputs": [],
      "source": [
        "df['Resume'] = df['Resume'].apply(identify_tokens)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "ILRu_XZdc-J3",
        "outputId": "147bf624-d487-4c72-c72f-da9971fe9e8e"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-e8649256-153d-47a8-9093-7afb33a425c6\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill programming language python panda numpy ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>education detail may may data scientist data s...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>area interest deep learning control system des...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill r python sap hana tableau sap hana sql s...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>education detail mca ymcaust faridabad haryana...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e8649256-153d-47a8-9093-7afb33a425c6')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-e8649256-153d-47a8-9093-7afb33a425c6 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-e8649256-153d-47a8-9093-7afb33a425c6');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "       Category                                             Resume\n",
              "0  Data Science  skill programming language python panda numpy ...\n",
              "1  Data Science  education detail may may data scientist data s...\n",
              "2  Data Science  area interest deep learning control system des...\n",
              "3  Data Science  skill r python sap hana tableau sap hana sql s...\n",
              "4  Data Science  education detail mca ymcaust faridabad haryana..."
            ]
          },
          "execution_count": 21,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        },
        "id": "o08M5-swdNsI",
        "outputId": "fa6ca6a0-2bbe-46c8-ac32-0bcc789accbd"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'skill programming language python panda numpy scipy matplotlib sql java machine learning regression svm bayes knn random forest decision tree boosting technique cluster analysis word embedding sentiment analysis natural language processing dimensionality reduction topic modelling lda nmf pca neural net database visualization mysql sqlserver cassandra hbase elasticsearch plotly kibana matplotlib ggplot tableau others regular expression html cs angular logstash kafka python flask git docker computer vision open cv understanding deep detail data science assurance associate data science assurance associate ernst young llp skill detail exprience month exprience month exprience monthscompany detail company ernst young llp description fraud investigation dispute service assurance technology assisted review tar technology assisted review assist accelerating review process run analytics generate report core member team helped developing automated review platform tool scratch assisting e discovery domain tool implement predictive coding topic modelling automating review resulting reduced labor cost time spent lawyer review understand end end flow solution research development classification model predictive analysis mining information present text data worked analyzing output precision monitoring entire tool tar assist predictive coding topic modelling evidence following ey standard developed classifier model order identify red flag issue tool technology python tfidf cosine similarity bayes lda nmf topic modelling vader text blob sentiment analysis matplot lib tableau dashboard reporting multiple data science analytic project usa client text analytics motor vehicle customer review data received customer feedback survey data past one year performed sentiment positive negative neutral time series analysis customer comment across category created heat map term survey category based frequency word extracted positive negative word across survey category plotted word cloud created customized tableau dashboard effective reporting visualization chatbot developed user friendly chatbot one product handle simple question hour operation reservation option chat bot serf entire product related question giving overview tool via qa platform also give recommendation response user question build chain relevant answer intelligence build pipeline question per user requirement asks relevant question tool technology python natural language processing nltk spacy topic modelling sentiment analysis word embedding sqlserver information governance organization make informed decision information store integrated information governance portfolio synthesizes intelligence across unstructured data source facilitates action ensure organization best positioned counter information risk scan data multiple source format parse different file format extract meta data information push result indexing elastic search created customized interactive dashboard using kibana preforming rot analysis data give information data help identify content either redundant outdated trivial preforming search analysis elastic search predefined method tag pii personally identifiable information social security number address name etc frequently targeted tool technology python flask elastic search kibana fraud analytic platform fraud analytics investigative platform review red flag case fap fraud analytics investigative platform inbuilt case manager suite analytics various erp system used client interrogate accounting system identifying anomaly indicator fraud running advanced analytics tool technology html javascript sqlserver jquery cs bootstrap'"
            ]
          },
          "execution_count": 22,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.Resume[0]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "G8knGhcUqbaU"
      },
      "outputs": [],
      "source": [
        "from transformers import DistilBertTokenizer\n",
        "from transformers import TFDistilBertForSequenceClassification\n",
        "from transformers import TextClassificationPipeline\n",
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "hjLNtdVGNfuK"
      },
      "outputs": [],
      "source": [
        "model_name = 'distilbert-base-uncased'"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 145,
          "referenced_widgets": [
            "1a448703907140b9ab8c116c18717ec1",
            "c767846fd2a6457289cfd4bbb7baad6e",
            "d3ce1a4db6a24a84b9feb9e5c569ee97",
            "6a9ddbfbf0bd447089d1f1a50f48e04c",
            "aecba3cedd4c4112966b84a860bd9e27",
            "101bd70125c24bccad7d1d45d7a03a18",
            "7dad1e32be424c76be7e9fae0ca7d51b",
            "ac75c43b30db4d409f1c47d0581af7ac",
            "870cf13f0671408fae72af9ae4324d15",
            "1be4feae2452485db247750caea0aa61",
            "890c1ba146684beaa3954fd81687536c",
            "8a099680a062426590d2c5205d8b3f5a",
            "dca32bbfd7d74ebf9bf1f2bcfeeaf493",
            "cef3f34a3d47404a9978941501f8af2e",
            "5421a6aa816940b4a3f9b9890fa49546",
            "939d4c45491b4b1ab5ead4f08031fbdc",
            "b10efaaf129a43f5bd2e181d1b07963e",
            "bb8004c09f4543e7be4d68c6e8933e2b",
            "22410d67535547adbb9261c0c2f87e9f",
            "cb30c4b1682545a2b41aacac44a797fc",
            "06397b33fad748dbaada2d57117b9f58",
            "ceae4dabdcd549e1974f98a142ea87b4",
            "a793676a62d54f5cb071ff014a8d9efb",
            "3622a3387cfd4d448e4697bdf26ff25b",
            "8bbea50d29964259be833b2ad5b76f07",
            "e8fb2942238e459dba580a1e189a7591",
            "b593d12105f6430ea399abec0c665497",
            "3298b17d03134324a8d7e829692f9730",
            "0e117abf99a84cf98b9341a7ca646f55",
            "1235618619e44192a80c1e5eb03639ce",
            "2069e89d29b04d7b8e93b87588c49b13",
            "4672b4d4114947338f2e0e8937ef477b",
            "952544a69fbd4aecba7a43504cad9e7f",
            "f3ed20cac5214025baa0fe5f4d89631b",
            "3248ca46e1084228ba64600835a37f44",
            "70df78f8701a4164a605c785e0d1e46c",
            "25c6191a288b4a928838616781d21d21",
            "1bbd1e4f38b6481e91ef13055acfec81",
            "114f62b0377445c9bb933dabd6c76f7a",
            "4024585134064efe98b3459aceae8eef",
            "88090abf7ace4e278f5d217a254a04ac",
            "31a833e86cf148c9a552754a830cea44",
            "73cd6ea5b786440488287d3be5092f4d",
            "ecdbda52ec874b03bb4fb7227cdf8e55"
          ]
        },
        "id": "MQMpFfwJOZiY",
        "outputId": "3a0f7252-a992-401d-e9a9-bf801fdf2caa"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1a448703907140b9ab8c116c18717ec1",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading (…)okenizer_config.json:   0%|          | 0.00/28.0 [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "8a099680a062426590d2c5205d8b3f5a",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading (…)lve/main/config.json:   0%|          | 0.00/483 [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "a793676a62d54f5cb071ff014a8d9efb",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading (…)solve/main/vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "f3ed20cac5214025baa0fe5f4d89631b",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/466k [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "tokenizer1 = AutoTokenizer.from_pretrained(model_name)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 121,
          "referenced_widgets": [
            "dee2ec1dd96f419e8d2b01ad11879881",
            "b03a8e52fa4747149ba7e49d1041e29a",
            "7242d1b9437e484d8205276afe85e4d2",
            "20b14bab7ac74b0d81fe491c0b90b3ca",
            "fd797d31d7f44ec1899957f62dfbd0f6",
            "3263a6238a264314b762e9b79f007e90",
            "7b0a18e93a4646d6b77a2827732f3bce",
            "e2322959cbab4fb48cde9b7c05a0a795",
            "f0167dd1a32f4ee492490715c12987c4",
            "5fd8382c640540709a899e369b324f89",
            "a0db90a5bbd84748b3a4e1055617dfae"
          ]
        },
        "id": "VTWAihR_xPCR",
        "outputId": "a31ace1b-9268-4e33-b8dd-0bbeffe4a8cb"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "dee2ec1dd96f419e8d2b01ad11879881",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading pytorch_model.bin:   0%|          | 0.00/268M [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertModel: ['vocab_projector.weight', 'vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_projector.bias', 'vocab_layer_norm.bias']\n",
            "- This IS expected if you are initializing DistilBertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing DistilBertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
          ]
        }
      ],
      "source": [
        "model1 = AutoModel.from_pretrained(model_name)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "aTtSNYJot9Ey"
      },
      "outputs": [],
      "source": [
        "tokenized_resume = []\n",
        "for words in df['Resume']:\n",
        "  tokens = tokenizer1(words, padding = True, truncation = True, max_length = 512, return_tensors = \"pt\")\n",
        "  tokenized_resume.append(tokens)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "zLhvVe5lq5A1",
        "outputId": "1e7bd869-5fcb-4218-fa2e-f4a5bcfaa916"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-63ed8d93-6670-407c-a970-0abf4b9a2950\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "      <th>encoded_text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill programming language python panda numpy ...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>education detail may may data scientist data s...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>area interest deep learning control system des...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill r python sap hana tableau sap hana sql s...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>education detail mca ymcaust faridabad haryana...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill c basic iot python matlab data science m...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>skill python tableau data visualization r stud...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>education detail rayat bahra institute enginee...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>personal skill ability quickly grasp technical...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>Data Science</td>\n",
              "      <td>expertise data quantitative analysis decision ...</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-63ed8d93-6670-407c-a970-0abf4b9a2950')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-63ed8d93-6670-407c-a970-0abf4b9a2950 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-63ed8d93-6670-407c-a970-0abf4b9a2950');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "       Category                                             Resume  \\\n",
              "0  Data Science  skill programming language python panda numpy ...   \n",
              "1  Data Science  education detail may may data scientist data s...   \n",
              "2  Data Science  area interest deep learning control system des...   \n",
              "3  Data Science  skill r python sap hana tableau sap hana sql s...   \n",
              "4  Data Science  education detail mca ymcaust faridabad haryana...   \n",
              "5  Data Science  skill c basic iot python matlab data science m...   \n",
              "6  Data Science  skill python tableau data visualization r stud...   \n",
              "7  Data Science  education detail rayat bahra institute enginee...   \n",
              "8  Data Science  personal skill ability quickly grasp technical...   \n",
              "9  Data Science  expertise data quantitative analysis decision ...   \n",
              "\n",
              "   encoded_text  \n",
              "0             6  \n",
              "1             6  \n",
              "2             6  \n",
              "3             6  \n",
              "4             6  \n",
              "5             6  \n",
              "6             6  \n",
              "7             6  \n",
              "8             6  \n",
              "9             6  "
            ]
          },
          "execution_count": 28,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df['encoded_text'] = df['Category'].astype('category').cat.codes\n",
        "\n",
        "df.head(10)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "background_save": true
        },
        "id": "9vlwjClTq_Vi"
      },
      "outputs": [],
      "source": [
        "data_texts = df['Resume'].to_list()\n",
        "\n",
        "data_labels = df['encoded_text'].to_list()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "aaiJZ5MbrJhN"
      },
      "outputs": [],
      "source": [
        "train_texts, val_texts, train_labels, val_labels = train_test_split(data_texts, data_labels, test_size = 0.2, random_state = 0 )\n",
        "\n",
        "\n",
        "#train_texts, test_texts, train_labels, test_labels = train_test_split(train_texts, train_labels, test_size = 0.10, random_state = 0 )"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "IuaZtmdMrQtz"
      },
      "outputs": [],
      "source": [
        "tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')\n",
        "\n",
        "train_encodings = tokenizer(train_texts, truncation = True, padding = True  )\n",
        "\n",
        "val_encodings = tokenizer(val_texts, truncation = True, padding = True )"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "PB8kiMDHraDH"
      },
      "outputs": [],
      "source": [
        "train_dataset = tf.data.Dataset.from_tensor_slices((\n",
        "    dict(train_encodings),\n",
        "    train_labels\n",
        "))\n",
        "\n",
        "\n",
        "val_dataset = tf.data.Dataset.from_tensor_slices((\n",
        "    dict(val_encodings),\n",
        "    val_labels\n",
        "))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 156,
          "referenced_widgets": [
            "2e66dd446a8e4aba87a5d3daf7052b4d",
            "4c0ee0c3ecf5465592af20218e423e4d",
            "6b349622c1394c4f8bcac2fe562374e7",
            "6fd1a7d83f4e4ce0885e18e018479b59",
            "862d2ad43ed2414e9751d6a490dca623",
            "b92e8cf7e0cc4430b873a7b0f759958a",
            "bf138f34d0e847699d3438421969cf5b",
            "9b06d3359a1144bcb81d38df9648dab3",
            "645d4639e00640cb9c0bf63074e4ff41",
            "7231b6e7ca364d72b5f02c223482d9c2",
            "64ae958c0415447eb8d7bc0ef5ea4611"
          ]
        },
        "id": "A4iyMDvtrt--",
        "outputId": "50afcb08-7e37-406b-bf27-53603fff9ad2"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "2e66dd446a8e4aba87a5d3daf7052b4d",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading tf_model.h5:   0%|          | 0.00/363M [00:00<?, ?B/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "Some layers from the model checkpoint at distilbert-base-uncased were not used when initializing TFDistilBertForSequenceClassification: ['vocab_transform', 'vocab_projector', 'vocab_layer_norm', 'activation_13']\n",
            "- This IS expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some layers of TFDistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['pre_classifier', 'classifier', 'dropout_19']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ],
      "source": [
        "model = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased', num_labels=25)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "D5fwfdjVsSHM"
      },
      "outputs": [],
      "source": [
        "from transformers import TFDistilBertForSequenceClassification, TFTrainer, TFTrainingArguments\n",
        "\n",
        "\n",
        "training_args = TFTrainingArguments(\n",
        "    output_dir='./results',          \n",
        "    num_train_epochs=10,              \n",
        "    per_device_train_batch_size=16,  \n",
        "    per_device_eval_batch_size=64,   \n",
        "    warmup_steps=500,                \n",
        "    weight_decay=1e-5,               \n",
        "    logging_dir='./logs',            \n",
        "    eval_steps=100                   \n",
        ")\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "URR9CstBsbLz",
        "outputId": "f7022334-5756-4074-a4d3-b32a803fe0ef"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "Some layers from the model checkpoint at distilbert-base-uncased were not used when initializing TFDistilBertForSequenceClassification: ['vocab_transform', 'vocab_projector', 'vocab_layer_norm', 'activation_13']\n",
            "- This IS expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some layers of TFDistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['pre_classifier', 'classifier', 'dropout_59']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ],
      "source": [
        "with training_args.strategy.scope():\n",
        "    trainer_model = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased', num_labels = 25 )\n",
        "\n",
        "\n",
        "trainer = TFTrainer(\n",
        "    model=trainer_model,                 \n",
        "    args=training_args,                  \n",
        "    train_dataset=train_dataset,         \n",
        "    eval_dataset=val_dataset,            \n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "background_save": true
        },
        "id": "oinZm3GPsjIG"
      },
      "outputs": [],
      "source": [
        "trainer.train()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Gl4Ogw8IQ3qA",
        "outputId": "71320756-2f54-4dd3-e39d-64d137a580fc"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "{'eval_loss': 0.08707354217767715}"
            ]
          },
          "execution_count": 41,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "trainer.evaluate()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ygahuBgsq4Gm",
        "outputId": "ffec9e87-2891-4544-f9f5-6e12a95371f4"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "('/saved_models/tokenizer_config.json',\n",
              " '/saved_models/special_tokens_map.json',\n",
              " '/saved_models/vocab.txt',\n",
              " '/saved_models/added_tokens.json')"
            ]
          },
          "execution_count": 42,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "save_directory = \"/saved_models\" \n",
        "\n",
        "model.save_pretrained(save_directory)\n",
        "\n",
        "tokenizer.save_pretrained(save_directory)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1UCid_FrrFnm",
        "outputId": "49cbc497-f3c7-4b2e-9c0f-49a006ecbfcc"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "Some layers from the model checkpoint at /saved_models were not used when initializing TFDistilBertForSequenceClassification: ['dropout_19']\n",
            "- This IS expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some layers of TFDistilBertForSequenceClassification were not initialized from the model checkpoint at /saved_models and are newly initialized: ['dropout_99']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ],
      "source": [
        "tokenizer_fine_tuned = DistilBertTokenizer.from_pretrained(save_directory)\n",
        "\n",
        "model_fine_tuned = TFDistilBertForSequenceClassification.from_pretrained(save_directory)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        },
        "id": "O_nTcWJYrLZ3",
        "outputId": "f5a1075f-b6b0-461a-f947-bb2360c7229c"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'social skill ability establish trust work team determined good work ethic ability work difficult detail january january mumbai maharashtra mumbai university bachelor electronics engineering electronics engineering mumbai maharashtra atharva college engineering malad automation electrical engineer automation electrical engineer smec automation pvt ltd skill detail company detail company smec automation pvt ltd description supply installation testing commissioning water level sensor valve actuator water tank barc hospital anushaktinagar trombay barc facility kalyan implemented academy project like automatically tank filling relay float sensor level control bottle filling conveyor belt motion waste material crashing separated conveyor belt motion plc controlling role automation instrumentation engineer marine industrial automation field instrument like control valve actuator sensor transmitter pneumatic electrical research developing new automated system level flow temperature process control pid various brand nippon selec etc plc panel wiring dol star delta control wiring phase induction motor panel testing ip knowledge control panel quality check assurance eletrical single line daigram sld power wiring daigram internship experience company smec automation pvt ltd description company profile smec automation provides specialized technical consulting service custom engineered product marine energy offshore industry applying advanced method technology smec automation one india leading manufacturer automation monitoring equipment vessel especially marine boiler main engine control igg inert gas generator alarm system project company smec automation pvt ltd description completed internship instrumentation calibration smec automation pvt month duration june november technical qualification underwent post graduate diploma industrial calibration instrumentation post graduate diploma industrial automation duration month hand practical exposure industrial automation tool like plc pac scada hmi interfacing drive mcc panel vfd successful examination post graduation diploma industrial automation post graduation diploma industrial instrumentation tuv rheinland certified qualification technical skill calculation selection cable switchgear protection expertise plc hardware like ab schneider siemens omron delta abb knowledge control relay logic ladder logic good knowledge designing interfacing plc scada intouch wincc ifix factory talkview real time data acquisition opc kepware hmi interfacing handling vfd motor control altivar series calibration pressure gauge temperature gauge control valve level flow measurement control druck injector smart dp transmitter using hart communicator piping instrumentation diagram hand tool tube pipe fitting cable cable glanding basic knowledge honeywell dc programming completed day robotic workshop kuka kr atharva college engineering training week rk electricals computer skill electrical designing software basic autocad eplan plc software rockwell unity pro xl wpl software codesys versa pro designing software wonderware proficy hmi factotytalk view successfully completed spoken tutorial program c java programming individually conducted completed day basic course basic mac o atharva college engineering completed phython workshop conducted codestrike day atharva college engineering operating system window mac'"
            ]
          },
          "execution_count": 65,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "test_text = df.Resume[456]\n",
        "\n",
        "test_text"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "tCJZ7yOBPDxs"
      },
      "outputs": [],
      "source": [
        "test_text1 = df.Resume[45]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CO9FS463rabV",
        "outputId": "8e519f50-3d55-416b-e21b-3b7f87063b37"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "array([7])"
            ]
          },
          "execution_count": 68,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "predict_input = tokenizer_fine_tuned.encode(\n",
        "    test_text1,\n",
        "    truncation = True,\n",
        "    padding = True,\n",
        "    return_tensors = 'tf'    \n",
        ")\n",
        "\n",
        "output = model_fine_tuned(predict_input)[0]\n",
        "\n",
        "prediction_value = tf.argmax(output, axis = 1).numpy()#[0]\n",
        "\n",
        "prediction_value"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "Wb1QGD_2J8Lg",
        "outputId": "ad82a4c9-f375-45ac-bf87-18a7de142bd4"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-2e83a368-9c7e-45e3-9138-393ce405b007\">\n",
              "    <div 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>Category</th>\n",
              "      <th>Resume</th>\n",
              "      <th>encoded_text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>709</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise db language sql database t...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise operating system microsoft...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>711</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system m window serv...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>712</th>\n",
              "      <td>Database</td>\n",
              "      <td>skillset oracle dba mysql mariadb postgresql d...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>713</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail january bsc mumbai maharashtr...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>714</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system linux window ...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>715</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill database oracle data pump rman...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>716</th>\n",
              "      <td>Database</td>\n",
              "      <td>software skill rdbms m sql server operating sy...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>717</th>\n",
              "      <td>Database</td>\n",
              "      <td>area expertise oracle database weblogic grid i...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>718</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail may may bachelor science info...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>719</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill sql oracle r programming pytho...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>720</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise db language sql database t...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>721</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise operating system microsoft...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>722</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system m window serv...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>723</th>\n",
              "      <td>Database</td>\n",
              "      <td>skillset oracle dba mysql mariadb postgresql d...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>724</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail january bsc mumbai maharashtr...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>725</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system linux window ...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>726</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill database oracle data pump rman...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>727</th>\n",
              "      <td>Database</td>\n",
              "      <td>software skill rdbms m sql server operating sy...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>728</th>\n",
              "      <td>Database</td>\n",
              "      <td>area expertise oracle database weblogic grid i...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>729</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail may may bachelor science info...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>730</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill sql oracle r programming pytho...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>731</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise db language sql database t...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>732</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical expertise operating system microsoft...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>733</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system m window serv...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>734</th>\n",
              "      <td>Database</td>\n",
              "      <td>skillset oracle dba mysql mariadb postgresql d...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>735</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail january bsc mumbai maharashtr...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>736</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill operating system linux window ...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>737</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill database oracle data pump rman...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>738</th>\n",
              "      <td>Database</td>\n",
              "      <td>software skill rdbms m sql server operating sy...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>739</th>\n",
              "      <td>Database</td>\n",
              "      <td>area expertise oracle database weblogic grid i...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>740</th>\n",
              "      <td>Database</td>\n",
              "      <td>education detail may may bachelor science info...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>741</th>\n",
              "      <td>Database</td>\n",
              "      <td>technical skill sql oracle r programming pytho...</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2e83a368-9c7e-45e3-9138-393ce405b007')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-2e83a368-9c7e-45e3-9138-393ce405b007 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-2e83a368-9c7e-45e3-9138-393ce405b007');\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",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "     Category                                             Resume  encoded_text\n",
              "709  Database  technical expertise db language sql database t...             7\n",
              "710  Database  technical expertise operating system microsoft...             7\n",
              "711  Database  technical skill operating system m window serv...             7\n",
              "712  Database  skillset oracle dba mysql mariadb postgresql d...             7\n",
              "713  Database  education detail january bsc mumbai maharashtr...             7\n",
              "714  Database  technical skill operating system linux window ...             7\n",
              "715  Database  technical skill database oracle data pump rman...             7\n",
              "716  Database  software skill rdbms m sql server operating sy...             7\n",
              "717  Database  area expertise oracle database weblogic grid i...             7\n",
              "718  Database  education detail may may bachelor science info...             7\n",
              "719  Database  technical skill sql oracle r programming pytho...             7\n",
              "720  Database  technical expertise db language sql database t...             7\n",
              "721  Database  technical expertise operating system microsoft...             7\n",
              "722  Database  technical skill operating system m window serv...             7\n",
              "723  Database  skillset oracle dba mysql mariadb postgresql d...             7\n",
              "724  Database  education detail january bsc mumbai maharashtr...             7\n",
              "725  Database  technical skill operating system linux window ...             7\n",
              "726  Database  technical skill database oracle data pump rman...             7\n",
              "727  Database  software skill rdbms m sql server operating sy...             7\n",
              "728  Database  area expertise oracle database weblogic grid i...             7\n",
              "729  Database  education detail may may bachelor science info...             7\n",
              "730  Database  technical skill sql oracle r programming pytho...             7\n",
              "731  Database  technical expertise db language sql database t...             7\n",
              "732  Database  technical expertise operating system microsoft...             7\n",
              "733  Database  technical skill operating system m window serv...             7\n",
              "734  Database  skillset oracle dba mysql mariadb postgresql d...             7\n",
              "735  Database  education detail january bsc mumbai maharashtr...             7\n",
              "736  Database  technical skill operating system linux window ...             7\n",
              "737  Database  technical skill database oracle data pump rman...             7\n",
              "738  Database  software skill rdbms m sql server operating sy...             7\n",
              "739  Database  area expertise oracle database weblogic grid i...             7\n",
              "740  Database  education detail may may bachelor science info...             7\n",
              "741  Database  technical skill sql oracle r programming pytho...             7"
            ]
          },
          "execution_count": 48,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df[df['encoded_text'] == 7]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NXkbDLm-txn4",
        "outputId": "efbd928f-0871-4eb4-c4a2-39ac16ab882a"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "{'input_ids': tensor([[  101,  2495,  6987,  2238,  2238,  9827,  3274,  2671, 16920, 12434,\n",
              "          9932,  4757,  5244,  2238, 11828,  3274,  2671, 16920, 12434,  9617,\n",
              "          3372, 25667, 22195,  2906,  2267,  3330,  2470,  2803, 18750,  9722,\n",
              "          8066,  6987,  2194,  6987,  2194, 22330, 16078,  2063,  4007, 26189,\n",
              "          2102,  5183,  6412,  2215,  2147,  5502, 18750,  9722, 16462,  3716,\n",
              "          5114,  3716,  5502,   102]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "         1, 1, 1, 1, 1, 1]])}"
            ]
          },
          "execution_count": 45,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "tokenized_resume[552]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ZHoLMCX0t9OU"
      },
      "outputs": [],
      "source": [
        "text1 = df.Resume[2]\n",
        "text2 = df.Resume[3]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "bUjbVHIPwiBf"
      },
      "outputs": [],
      "source": [
        "embedding1 = tokenizer_fine_tuned(text1,truncation = True, return_tensors = 'tf', padding = True )\n",
        "embedding2 = tokenizer_fine_tuned(text2 , truncation = True, return_tensors = 'tf', padding = True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 321
        },
        "id": "165X0IjewxXO",
        "outputId": "b2f8f839-5cbc-45c5-ae21-595144e30954"
      },
      "outputs": [
        {
          "ename": "AttributeError",
          "evalue": "ignored",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-48-627b61f1cbbd>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mno_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m     \u001b[0mresume1_embedding\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel_fine_tuned\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0membedding1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdim\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m     \u001b[0mresume2_embedding\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel_fine_tuned\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0membedding2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdim\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.9/dist-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    441\u001b[0m         \u001b[0mnp_config\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menable_numpy_behavior\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    442\u001b[0m       \"\"\")\n\u001b[0;32m--> 443\u001b[0;31m     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    444\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    445\u001b[0m   \u001b[0;34m@\u001b[0m\u001b[0mstaticmethod\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mAttributeError\u001b[0m: 'tensorflow.python.framework.ops.EagerTensor' object has no attribute 'mean'"
          ]
        }
      ],
      "source": [
        "with torch.no_grad():\n",
        "    resume1_embedding = model_fine_tuned(**embedding1)[0].mean(dim=1)\n",
        "    resume2_embedding = model_fine_tuned(**embedding2)[0].mean(dim=1)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5s4kLKFDvc5F"
      },
      "outputs": [],
      "source": [
        "with torch.no_grad():\n",
        "    resume1_embedding = model_fine_tuned(**embedding1)\n",
        "    resume2_embedding = model_fine_tuned(**embedding2)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "So6FBlnByg1C"
      },
      "outputs": [],
      "source": [
        "similarity = F.cosine_similarity(resume1_embedding, resume2_embedding)\n",
        "print(similarity.item())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "qfvlkdNBynLc"
      },
      "outputs": [],
      "source": [
        "similarity"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "7EzrYIYXysM8"
      },
      "outputs": [],
      "source": [
        "df.Resume[5]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "NjNax1Knzow0"
      },
      "outputs": [],
      "source": [
        "df.Resume[186]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "V89m0ARDztvQ"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "06397b33fad748dbaada2d57117b9f58": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "0e117abf99a84cf98b9341a7ca646f55": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "101bd70125c24bccad7d1d45d7a03a18": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "114f62b0377445c9bb933dabd6c76f7a": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1235618619e44192a80c1e5eb03639ce": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1a448703907140b9ab8c116c18717ec1": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_c767846fd2a6457289cfd4bbb7baad6e",
              "IPY_MODEL_d3ce1a4db6a24a84b9feb9e5c569ee97",
              "IPY_MODEL_6a9ddbfbf0bd447089d1f1a50f48e04c"
            ],
            "layout": "IPY_MODEL_aecba3cedd4c4112966b84a860bd9e27"
          }
        },
        "1bbd1e4f38b6481e91ef13055acfec81": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1be4feae2452485db247750caea0aa61": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2069e89d29b04d7b8e93b87588c49b13": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "20b14bab7ac74b0d81fe491c0b90b3ca": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5fd8382c640540709a899e369b324f89",
            "placeholder": "​",
            "style": "IPY_MODEL_a0db90a5bbd84748b3a4e1055617dfae",
            "value": " 268M/268M [00:02&lt;00:00, 172MB/s]"
          }
        },
        "22410d67535547adbb9261c0c2f87e9f": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "25c6191a288b4a928838616781d21d21": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_73cd6ea5b786440488287d3be5092f4d",
            "placeholder": "​",
            "style": "IPY_MODEL_ecdbda52ec874b03bb4fb7227cdf8e55",
            "value": " 466k/466k [00:00&lt;00:00, 13.2MB/s]"
          }
        },
        "2e66dd446a8e4aba87a5d3daf7052b4d": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_4c0ee0c3ecf5465592af20218e423e4d",
              "IPY_MODEL_6b349622c1394c4f8bcac2fe562374e7",
              "IPY_MODEL_6fd1a7d83f4e4ce0885e18e018479b59"
            ],
            "layout": "IPY_MODEL_862d2ad43ed2414e9751d6a490dca623"
          }
        },
        "31a833e86cf148c9a552754a830cea44": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "3248ca46e1084228ba64600835a37f44": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_114f62b0377445c9bb933dabd6c76f7a",
            "placeholder": "​",
            "style": "IPY_MODEL_4024585134064efe98b3459aceae8eef",
            "value": "Downloading (…)/main/tokenizer.json: 100%"
          }
        },
        "3263a6238a264314b762e9b79f007e90": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3298b17d03134324a8d7e829692f9730": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3622a3387cfd4d448e4697bdf26ff25b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3298b17d03134324a8d7e829692f9730",
            "placeholder": "​",
            "style": "IPY_MODEL_0e117abf99a84cf98b9341a7ca646f55",
            "value": "Downloading (…)solve/main/vocab.txt: 100%"
          }
        },
        "4024585134064efe98b3459aceae8eef": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "4672b4d4114947338f2e0e8937ef477b": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4c0ee0c3ecf5465592af20218e423e4d": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_b92e8cf7e0cc4430b873a7b0f759958a",
            "placeholder": "​",
            "style": "IPY_MODEL_bf138f34d0e847699d3438421969cf5b",
            "value": "Downloading tf_model.h5: 100%"
          }
        },
        "5421a6aa816940b4a3f9b9890fa49546": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_06397b33fad748dbaada2d57117b9f58",
            "placeholder": "​",
            "style": "IPY_MODEL_ceae4dabdcd549e1974f98a142ea87b4",
            "value": " 483/483 [00:00&lt;00:00, 12.0kB/s]"
          }
        },
        "5fd8382c640540709a899e369b324f89": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "645d4639e00640cb9c0bf63074e4ff41": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "64ae958c0415447eb8d7bc0ef5ea4611": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "6a9ddbfbf0bd447089d1f1a50f48e04c": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_1be4feae2452485db247750caea0aa61",
            "placeholder": "​",
            "style": "IPY_MODEL_890c1ba146684beaa3954fd81687536c",
            "value": " 28.0/28.0 [00:00&lt;00:00, 626B/s]"
          }
        },
        "6b349622c1394c4f8bcac2fe562374e7": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_9b06d3359a1144bcb81d38df9648dab3",
            "max": 363423424,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_645d4639e00640cb9c0bf63074e4ff41",
            "value": 363423424
          }
        },
        "6fd1a7d83f4e4ce0885e18e018479b59": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_7231b6e7ca364d72b5f02c223482d9c2",
            "placeholder": "​",
            "style": "IPY_MODEL_64ae958c0415447eb8d7bc0ef5ea4611",
            "value": " 363M/363M [00:01&lt;00:00, 293MB/s]"
          }
        },
        "70df78f8701a4164a605c785e0d1e46c": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_88090abf7ace4e278f5d217a254a04ac",
            "max": 466062,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_31a833e86cf148c9a552754a830cea44",
            "value": 466062
          }
        },
        "7231b6e7ca364d72b5f02c223482d9c2": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7242d1b9437e484d8205276afe85e4d2": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e2322959cbab4fb48cde9b7c05a0a795",
            "max": 267967963,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_f0167dd1a32f4ee492490715c12987c4",
            "value": 267967963
          }
        },
        "73cd6ea5b786440488287d3be5092f4d": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7b0a18e93a4646d6b77a2827732f3bce": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "7dad1e32be424c76be7e9fae0ca7d51b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "862d2ad43ed2414e9751d6a490dca623": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "870cf13f0671408fae72af9ae4324d15": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "88090abf7ace4e278f5d217a254a04ac": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "890c1ba146684beaa3954fd81687536c": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "8a099680a062426590d2c5205d8b3f5a": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_dca32bbfd7d74ebf9bf1f2bcfeeaf493",
              "IPY_MODEL_cef3f34a3d47404a9978941501f8af2e",
              "IPY_MODEL_5421a6aa816940b4a3f9b9890fa49546"
            ],
            "layout": "IPY_MODEL_939d4c45491b4b1ab5ead4f08031fbdc"
          }
        },
        "8bbea50d29964259be833b2ad5b76f07": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_1235618619e44192a80c1e5eb03639ce",
            "max": 231508,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_2069e89d29b04d7b8e93b87588c49b13",
            "value": 231508
          }
        },
        "939d4c45491b4b1ab5ead4f08031fbdc": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "952544a69fbd4aecba7a43504cad9e7f": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "9b06d3359a1144bcb81d38df9648dab3": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a0db90a5bbd84748b3a4e1055617dfae": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "a793676a62d54f5cb071ff014a8d9efb": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_3622a3387cfd4d448e4697bdf26ff25b",
              "IPY_MODEL_8bbea50d29964259be833b2ad5b76f07",
              "IPY_MODEL_e8fb2942238e459dba580a1e189a7591"
            ],
            "layout": "IPY_MODEL_b593d12105f6430ea399abec0c665497"
          }
        },
        "ac75c43b30db4d409f1c47d0581af7ac": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "aecba3cedd4c4112966b84a860bd9e27": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "b03a8e52fa4747149ba7e49d1041e29a": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3263a6238a264314b762e9b79f007e90",
            "placeholder": "​",
            "style": "IPY_MODEL_7b0a18e93a4646d6b77a2827732f3bce",
            "value": "Downloading pytorch_model.bin: 100%"
          }
        },
        "b10efaaf129a43f5bd2e181d1b07963e": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "b593d12105f6430ea399abec0c665497": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "b92e8cf7e0cc4430b873a7b0f759958a": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "bb8004c09f4543e7be4d68c6e8933e2b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "bf138f34d0e847699d3438421969cf5b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "c767846fd2a6457289cfd4bbb7baad6e": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_101bd70125c24bccad7d1d45d7a03a18",
            "placeholder": "​",
            "style": "IPY_MODEL_7dad1e32be424c76be7e9fae0ca7d51b",
            "value": "Downloading (…)okenizer_config.json: 100%"
          }
        },
        "cb30c4b1682545a2b41aacac44a797fc": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "ceae4dabdcd549e1974f98a142ea87b4": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "cef3f34a3d47404a9978941501f8af2e": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_22410d67535547adbb9261c0c2f87e9f",
            "max": 483,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_cb30c4b1682545a2b41aacac44a797fc",
            "value": 483
          }
        },
        "d3ce1a4db6a24a84b9feb9e5c569ee97": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "FloatProgressModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ac75c43b30db4d409f1c47d0581af7ac",
            "max": 28,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_870cf13f0671408fae72af9ae4324d15",
            "value": 28
          }
        },
        "dca32bbfd7d74ebf9bf1f2bcfeeaf493": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_b10efaaf129a43f5bd2e181d1b07963e",
            "placeholder": "​",
            "style": "IPY_MODEL_bb8004c09f4543e7be4d68c6e8933e2b",
            "value": "Downloading (…)lve/main/config.json: 100%"
          }
        },
        "dee2ec1dd96f419e8d2b01ad11879881": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_b03a8e52fa4747149ba7e49d1041e29a",
              "IPY_MODEL_7242d1b9437e484d8205276afe85e4d2",
              "IPY_MODEL_20b14bab7ac74b0d81fe491c0b90b3ca"
            ],
            "layout": "IPY_MODEL_fd797d31d7f44ec1899957f62dfbd0f6"
          }
        },
        "e2322959cbab4fb48cde9b7c05a0a795": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e8fb2942238e459dba580a1e189a7591": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HTMLModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4672b4d4114947338f2e0e8937ef477b",
            "placeholder": "​",
            "style": "IPY_MODEL_952544a69fbd4aecba7a43504cad9e7f",
            "value": " 232k/232k [00:00&lt;00:00, 1.38MB/s]"
          }
        },
        "ecdbda52ec874b03bb4fb7227cdf8e55": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "f0167dd1a32f4ee492490715c12987c4": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ProgressStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "f3ed20cac5214025baa0fe5f4d89631b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "HBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_3248ca46e1084228ba64600835a37f44",
              "IPY_MODEL_70df78f8701a4164a605c785e0d1e46c",
              "IPY_MODEL_25c6191a288b4a928838616781d21d21"
            ],
            "layout": "IPY_MODEL_1bbd1e4f38b6481e91ef13055acfec81"
          }
        },
        "fd797d31d7f44ec1899957f62dfbd0f6": {
          "model_module": "@jupyter-widgets/base",
          "model_module_version": "1.2.0",
          "model_name": "LayoutModel",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}