implementation_step2.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPfpB54ycwOKvmnLewW0vPh",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Anil951/Early-detection-of-mental-health/blob/main/implementation_step2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# STAGE 2: SUDDEN CHANGES IN SCORES, ATTENDANCE, AND TEACHER REMARKS\n",
        "\n",
        "# SIGNIFICANT DECREASES IN A STUDENT'S SCORES, ATTENDANCE,\n",
        "# AND TEACHER REMARKS FROM ONE TERM TO THE NEXT MAY INDICATE THAT THEY COULD BE EXPERIENCING MENTAL HEALTH CHALLENGES.\n",
        "\n",
        "# DISCLAIMER: This is an assumption based on observed patterns and may not necessarily reflect the actual mental health status of the student."
      ],
      "metadata": {
        "id": "16RlC3b19ZQB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# do OCR(pytesseract) and extract data from images and store in DATAFRAMES\n",
        "# and see percent of decrease in SCORE, ATTENDENCE, REMARKS SENTIMENT"
      ],
      "metadata": {
        "id": "bix0F9dS4iAR"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# for PROTOTYPE/DEMO purpose we are taking only demo score cards (found in data/demo score cards/)\n",
        "\n",
        "# DISCLAIMER: these score cards are generated ones (refer : generate_scorecards_images.ipynb)"
      ],
      "metadata": {
        "id": "1WQgDZB5-sc0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pip install pytesseract"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aGhgmVXfZNjl",
        "outputId": "3c259a44-87b8-41b4-827e-508c8ddf79f4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting pytesseract\n",
            "  Downloading pytesseract-0.3.13-py3-none-any.whl.metadata (11 kB)\n",
            "Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.10/dist-packages (from pytesseract) (24.1)\n",
            "Requirement already satisfied: Pillow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from pytesseract) (10.4.0)\n",
            "Downloading pytesseract-0.3.13-py3-none-any.whl (14 kB)\n",
            "Installing collected packages: pytesseract\n",
            "Successfully installed pytesseract-0.3.13\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!apt-get update\n",
        "!apt-get install -y tesseract-ocr"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XUdbvSSDjFCA",
        "outputId": "3fb460d0-2c70-4e48-d950-d7b306c6ea7d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\r0% [Working]\r            \rGet:1 https://cloud.r-project.org/bin/linux/ubuntu jammy-cran40/ InRelease [3,626 B]\n",
            "Hit:2 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64  InRelease\n",
            "Get:3 http://security.ubuntu.com/ubuntu jammy-security InRelease [129 kB]\n",
            "Get:4 https://r2u.stat.illinois.edu/ubuntu jammy InRelease [6,555 B]\n",
            "Hit:5 http://archive.ubuntu.com/ubuntu jammy InRelease\n",
            "Get:6 http://archive.ubuntu.com/ubuntu jammy-updates InRelease [128 kB]\n",
            "Hit:7 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu jammy InRelease\n",
            "Get:8 https://r2u.stat.illinois.edu/ubuntu jammy/main amd64 Packages [2,611 kB]\n",
            "Get:9 http://archive.ubuntu.com/ubuntu jammy-backports InRelease [127 kB]\n",
            "Hit:10 https://ppa.launchpadcontent.net/graphics-drivers/ppa/ubuntu jammy InRelease\n",
            "Hit:11 https://ppa.launchpadcontent.net/ubuntugis/ppa/ubuntu jammy InRelease\n",
            "Get:12 https://r2u.stat.illinois.edu/ubuntu jammy/main all Packages [8,456 kB]\n",
            "Get:13 http://archive.ubuntu.com/ubuntu jammy-updates/universe amd64 Packages [1,452 kB]\n",
            "Get:14 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages [2,696 kB]\n",
            "Get:15 http://archive.ubuntu.com/ubuntu jammy-updates/restricted amd64 Packages [3,353 kB]\n",
            "Get:16 http://security.ubuntu.com/ubuntu jammy-security/main amd64 Packages [2,397 kB]\n",
            "Get:17 http://security.ubuntu.com/ubuntu jammy-security/restricted amd64 Packages [3,241 kB]\n",
            "Get:18 http://security.ubuntu.com/ubuntu jammy-security/universe amd64 Packages [1,163 kB]\n",
            "Fetched 25.8 MB in 4s (7,279 kB/s)\n",
            "Reading package lists... Done\n",
            "W: Skipping acquire of configured file 'main/source/Sources' as repository 'https://r2u.stat.illinois.edu/ubuntu jammy InRelease' does not seem to provide it (sources.list entry misspelt?)\n",
            "Reading package lists... Done\n",
            "Building dependency tree... Done\n",
            "Reading state information... Done\n",
            "The following additional packages will be installed:\n",
            "  tesseract-ocr-eng tesseract-ocr-osd\n",
            "The following NEW packages will be installed:\n",
            "  tesseract-ocr tesseract-ocr-eng tesseract-ocr-osd\n",
            "0 upgraded, 3 newly installed, 0 to remove and 51 not upgraded.\n",
            "Need to get 4,816 kB of archives.\n",
            "After this operation, 15.6 MB of additional disk space will be used.\n",
            "Get:1 http://archive.ubuntu.com/ubuntu jammy/universe amd64 tesseract-ocr-eng all 1:4.00~git30-7274cfa-1.1 [1,591 kB]\n",
            "Get:2 http://archive.ubuntu.com/ubuntu jammy/universe amd64 tesseract-ocr-osd all 1:4.00~git30-7274cfa-1.1 [2,990 kB]\n",
            "Get:3 http://archive.ubuntu.com/ubuntu jammy/universe amd64 tesseract-ocr amd64 4.1.1-2.1build1 [236 kB]\n",
            "Fetched 4,816 kB in 1s (5,119 kB/s)\n",
            "Selecting previously unselected package tesseract-ocr-eng.\n",
            "(Reading database ... 123623 files and directories currently installed.)\n",
            "Preparing to unpack .../tesseract-ocr-eng_1%3a4.00~git30-7274cfa-1.1_all.deb ...\n",
            "Unpacking tesseract-ocr-eng (1:4.00~git30-7274cfa-1.1) ...\n",
            "Selecting previously unselected package tesseract-ocr-osd.\n",
            "Preparing to unpack .../tesseract-ocr-osd_1%3a4.00~git30-7274cfa-1.1_all.deb ...\n",
            "Unpacking tesseract-ocr-osd (1:4.00~git30-7274cfa-1.1) ...\n",
            "Selecting previously unselected package tesseract-ocr.\n",
            "Preparing to unpack .../tesseract-ocr_4.1.1-2.1build1_amd64.deb ...\n",
            "Unpacking tesseract-ocr (4.1.1-2.1build1) ...\n",
            "Setting up tesseract-ocr-eng (1:4.00~git30-7274cfa-1.1) ...\n",
            "Setting up tesseract-ocr-osd (1:4.00~git30-7274cfa-1.1) ...\n",
            "Setting up tesseract-ocr (4.1.1-2.1build1) ...\n",
            "Processing triggers for man-db (2.10.2-1) ...\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pytesseract\n",
        "\n",
        "pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'"
      ],
      "metadata": {
        "id": "EwnICuaZjMbg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install pytesseract"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ckqulWCjj02_",
        "outputId": "b40cfc6c-d40c-4e5d-d8fe-50842f980e09"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: pytesseract in /usr/local/lib/python3.10/dist-packages (0.3.13)\n",
            "Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.10/dist-packages (from pytesseract) (24.1)\n",
            "Requirement already satisfied: Pillow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from pytesseract) (10.4.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import re\n",
        "from PIL import Image\n",
        "import pytesseract\n",
        "\n",
        "# Open the image\n",
        "image = Image.open('/content/report_card_class10.jpg')\n",
        "\n",
        "# Extract text from the image using Tesseract OCR\n",
        "text = pytesseract.image_to_string(image).lower()\n",
        "\n",
        "\n",
        "# PREPROCESSING\n",
        "\n",
        "def clean(subject):\n",
        "    return re.sub(r\"[^0-9a-zA-Z\\s]\", \"\", subject).strip()\n",
        "\n",
        "# Split the text into lines and remove lines containing a colon\n",
        "lines = [line.strip() for line in text.split('\\n') if ':' not in line and 'total' not in line]\n",
        "for i in lines:\n",
        "  if(len(i)==0):\n",
        "      lines.remove(i)\n",
        "\n",
        "# Apply cleaning to each line and remove any empty lines\n",
        "lines = [clean(line) for line in lines if clean(line)]\n",
        "\n",
        "print(lines)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "F8R__onmi2Nz",
        "outputId": "ad95f655-7306-4acc-8ec1-c7bc1fa9f077"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['term1', 'subject', 'math', 'sclence', 'english', 'history', 'physical education', 'score', '90', '85', '88', '80', '95', 'attendance', '92', '88', '90', '93', '97', 'remarks', 'consistently performs well shows strong skils', 'active in discussions good understanding of concepts', 'strong kills participates actively in group work', 'engaged in class discussions needs improvement', 'high energy and excellent team player', 'term2', 'subject', 'math', 'sclence', 'english', 'history', 'physical education', 'score', '85', '78', '80', '72', '90', 'attendance', '89', '84', '85', '88', '92', 'remarks', 'shows occasional struggles  needs extra practice', 'lacks motivation in class needs more focus', 'reduced participation distracted in class', 'difficulties in remembering needs to engage more', 'should improve fitness level', 'term3', 'subject', 'math', 'sclence', 'english', 'history', 'physical education', 'score', '75', '70', '72', '65', '80', 'attendance', '83', '75', '78', '80', '85', 'remarks', 'struggles with advanced topics seems frustrated', 'no interest in class lab work is neglected', 'very little participation often distracted', 'limited engagement affecting performance', 'results decreased tired uninterested']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Extracting term data into dataframes\n",
        "terms = {}\n",
        "data=lines\n",
        "i = 0\n",
        "while i < len(data):\n",
        "    if 'term' in data[i]:\n",
        "        # Initialize term info\n",
        "        term_name = data[i]\n",
        "        terms[term_name] = {}\n",
        "        i += 1\n",
        "        # Continue until next term or end of list\n",
        "        while i < len(data) and 'term' not in data[i]:\n",
        "            # Column name and values\n",
        "            col_name = data[i]\n",
        "            col_values = data[i + 1:i + 6]\n",
        "            terms[term_name][col_name] = col_values\n",
        "            i += 6  # Move to next column name\n",
        "    else:\n",
        "        i += 1  # Skip any stray data\n",
        "\n",
        "# Creating dataframes for each term\n",
        "dfs = {term: pd.DataFrame(data) for term, data in terms.items()}\n",
        "dfs"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-JytzhA0wp4-",
        "outputId": "bc3fa1c8-3dc7-4dea-f592-a01462a9833c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'term1':               subject score attendance  \\\n",
              " 0                math    90         92   \n",
              " 1             sclence    85         88   \n",
              " 2             english    88         90   \n",
              " 3             history    80         93   \n",
              " 4  physical education    95         97   \n",
              " \n",
              "                                              remarks  \n",
              " 0      consistently performs well shows strong skils  \n",
              " 1  active in discussions good understanding of co...  \n",
              " 2   strong kills participates actively in group work  \n",
              " 3     engaged in class discussions needs improvement  \n",
              " 4              high energy and excellent team player  ,\n",
              " 'term2':               subject score attendance  \\\n",
              " 0                math    85         89   \n",
              " 1             sclence    78         84   \n",
              " 2             english    80         85   \n",
              " 3             history    72         88   \n",
              " 4  physical education    90         92   \n",
              " \n",
              "                                             remarks  \n",
              " 0  shows occasional struggles  needs extra practice  \n",
              " 1        lacks motivation in class needs more focus  \n",
              " 2         reduced participation distracted in class  \n",
              " 3  difficulties in remembering needs to engage more  \n",
              " 4                      should improve fitness level  ,\n",
              " 'term3':               subject score attendance  \\\n",
              " 0                math    75         83   \n",
              " 1             sclence    70         75   \n",
              " 2             english    72         78   \n",
              " 3             history    65         80   \n",
              " 4  physical education    80         85   \n",
              " \n",
              "                                            remarks  \n",
              " 0  struggles with advanced topics seems frustrated  \n",
              " 1       no interest in class lab work is neglected  \n",
              " 2       very little participation often distracted  \n",
              " 3         limited engagement affecting performance  \n",
              " 4             results decreased tired uninterested  }"
            ]
          },
          "metadata": {},
          "execution_count": 78
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dfs['term3']"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "LX488i5L0xbi",
        "outputId": "f832bfc0-e356-4c27-aee3-9d0e2e686f73"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "              subject score attendance  \\\n",
              "0                math    75         83   \n",
              "1             sclence    70         75   \n",
              "2             english    72         78   \n",
              "3             history    65         80   \n",
              "4  physical education    80         85   \n",
              "\n",
              "                                           remarks  \n",
              "0  struggles with advanced topics seems frustrated  \n",
              "1       no interest in class lab work is neglected  \n",
              "2       very little participation often distracted  \n",
              "3         limited engagement affecting performance  \n",
              "4             results decreased tired uninterested  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-30e3fddb-b7c9-47bb-af5e-b3e1b3b12ba1\" 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>subject</th>\n",
              "      <th>score</th>\n",
              "      <th>attendance</th>\n",
              "      <th>remarks</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>math</td>\n",
              "      <td>75</td>\n",
              "      <td>83</td>\n",
              "      <td>struggles with advanced topics seems frustrated</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>sclence</td>\n",
              "      <td>70</td>\n",
              "      <td>75</td>\n",
              "      <td>no interest in class lab work is neglected</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>english</td>\n",
              "      <td>72</td>\n",
              "      <td>78</td>\n",
              "      <td>very little participation often distracted</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>history</td>\n",
              "      <td>65</td>\n",
              "      <td>80</td>\n",
              "      <td>limited engagement affecting performance</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>physical education</td>\n",
              "      <td>80</td>\n",
              "      <td>85</td>\n",
              "      <td>results decreased tired uninterested</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-30e3fddb-b7c9-47bb-af5e-b3e1b3b12ba1')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-30e3fddb-b7c9-47bb-af5e-b3e1b3b12ba1 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-30e3fddb-b7c9-47bb-af5e-b3e1b3b12ba1');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-f156aa7e-f905-4055-b18e-84ef9908b885\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f156aa7e-f905-4055-b18e-84ef9908b885')\"\n",
              "            title=\"Suggest charts\"\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",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-f156aa7e-f905-4055-b18e-84ef9908b885 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"dfs['term3']\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"subject\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"sclence\",\n          \"physical education\",\n          \"english\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"score\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"70\",\n          \"80\",\n          \"72\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"attendance\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"75\",\n          \"85\",\n          \"78\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"remarks\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"no interest in class lab work is neglected\",\n          \"results decreased tired uninterested\",\n          \"very little participation often distracted\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# calculating the decrease in percent of SCORE, ATTENDENCE, REMARKS sentiment  form term to term"
      ],
      "metadata": {
        "id": "sQEGUZNE5Ryn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n",
        "import nltk\n",
        "\n",
        "# Download the VADER lexicon for sentiment analysis\n",
        "nltk.download(\"vader_lexicon\")\n",
        "sid = SentimentIntensityAnalyzer()\n",
        "\n",
        "# Term-wise data as dictionaries of DataFrames\n",
        "term_data = dfs\n",
        "\n",
        "# Convert scores and attendance to numeric values and analyze sentiments\n",
        "for term, df in term_data.items():\n",
        "    df['score'] = pd.to_numeric(df['score'])\n",
        "    df['attendance'] = pd.to_numeric(df['attendance'])\n",
        "    df['senti'] = df['remarks'].apply(lambda x: sid.polarity_scores(x)['compound'])\n",
        "\n",
        "# Calculate the average score, attendance, and sentiment for each term\n",
        "avg_term1 = term_data['term1'][['score', 'attendance', 'senti']].mean()\n",
        "avg_term3 = term_data['term3'][['score', 'attendance', 'senti']].mean()\n",
        "\n",
        "# Calculate overall percentage decrease from term1 to term3\n",
        "score_decrease = ((avg_term1['score'] - avg_term3['score']) / avg_term1['score']) * 100\n",
        "attendance_decrease = ((avg_term1['attendance'] - avg_term3['attendance']) / avg_term1['attendance']) * 100\n",
        "senti_decrease = avg_term1['senti'] - avg_term3['senti']\n",
        "\n",
        "# Compile the results into a DataFrame\n",
        "overall_decrease = pd.DataFrame({\n",
        "    'Metric': ['Score', 'Attendance', 'Sentiment'],\n",
        "    'Decrease (%)': [score_decrease, attendance_decrease, senti_decrease * 100]\n",
        "})\n",
        "\n",
        "print(overall_decrease)\n",
        "\n",
        "# Determine overall likelihood of mental health issues\n",
        "if score_decrease > 15 or attendance_decrease > 15 or senti_decrease < -0.2:\n",
        "    print(\"There is a high likelihood of mental health issues based on the observed decreases.\")\n",
        "else:\n",
        "    print(\"There is a low likelihood of mental health issues based on the observed decreases.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GyO8HpAV3Lnk",
        "outputId": "770bfaa1-7750-4dd3-f3a4-74c7bcbf934f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "       Metric  Decrease (%)\n",
            "0       Score     17.351598\n",
            "1  Attendance     12.826087\n",
            "2   Sentiment     88.694000\n",
            "There is a high likelihood of mental health issues based on the observed decreases.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package vader_lexicon to /root/nltk_data...\n",
            "[nltk_data]   Package vader_lexicon is already up-to-date!\n"
          ]
        }
      ]
    }
  ]
}