{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "oqAhcFnEosUy"
      },
      "outputs": [],
      "source": [
        "import torch\n",
        "from google.colab import drive\n",
        "import pandas as pd\n",
        "import json\n",
        "import os\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "from pathlib import Path\n",
        "from transformers import AutoTokenizer"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GvUO342tisqd",
        "outputId": "c96fc6e3-3e9b-4df6-bb22-184e0681c61c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n",
            "GPU: Tesla T4\n",
            "VRAM (GiB): 14.56\n"
          ]
        }
      ],
      "source": [
        "# Mount Google Drive\n",
        "\n",
        "drive.mount(\"/content/drive\")\n",
        "assert torch.cuda.is_available(), \"Select Runtime > Change runtime type > GPU in Colab.\"\n",
        "print(\"GPU:\", torch.cuda.get_device_name(0))\n",
        "print(\"VRAM (GiB):\", round(torch.cuda.get_device_properties(0).total_memory / 2**30, 2))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ydvC6japxyHE",
        "outputId": "5ff85e76-f655-4f00-ab8f-1f29529245dc"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Easy.json: 5,333 records\n",
            "Medium.json: 26,581 records\n",
            "Hard.json: 16,514 records\n",
            "Total input: 48,428\n",
            "Skipped (missing or unknown difficulty): 0\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "import json\n",
        "\n",
        "base_path = '/content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder'\n",
        "input_path = os.path.join(\n",
        "    base_path,\n",
        "    'Final_combined_extracted_answers_new.json'\n",
        ")\n",
        "\n",
        "with open(input_path, 'r', encoding='utf-8-sig') as f:\n",
        "    records = json.load(f)\n",
        "\n",
        "if not isinstance(records, list):\n",
        "    raise ValueError(\"The input JSON must contain a list of records.\")\n",
        "\n",
        "grouped = {'easy': [], 'medium': [], 'hard': []}\n",
        "skipped = 0\n",
        "\n",
        "for record in records:\n",
        "    metadata = record.get('metadata') or {}\n",
        "    difficulty = str(metadata.get('difficulty', '')).strip().lower()\n",
        "\n",
        "    if difficulty in grouped:\n",
        "        grouped[difficulty].append(record)\n",
        "    else:\n",
        "        skipped += 1\n",
        "\n",
        "for difficulty, items in grouped.items():\n",
        "    filename = f'{difficulty.capitalize()}.json'\n",
        "    output_path = os.path.join(base_path, filename)\n",
        "\n",
        "    with open(output_path, 'w', encoding='utf-8') as f:\n",
        "        json.dump(items, f, ensure_ascii=False, indent=2)\n",
        "\n",
        "    print(f'{filename}: {len(items):,} records')\n",
        "\n",
        "print(f'Total input: {len(records):,}')\n",
        "print(f'Skipped (missing or unknown difficulty): {skipped:,}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 414
        },
        "id": "fa2af5f3",
        "outputId": "19aa92d2-6232-4608-91ff-3031f38cbdd9"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Easy path: /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Easy.json\n",
            "Medium path: /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Medium.json\n",
            "Hard path: /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Hard.json\n",
            "MMLU path: /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/sinhala_dev_mmlu.json\n",
            "Successfully loaded /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Easy.json with 5333 records.\n",
            "Successfully loaded /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Medium.json with 26581 records.\n",
            "Successfully loaded /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Hard.json with 16514 records.\n",
            "Standard JSON load failed for /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/sinhala_dev_mmlu.json: Extra data: line 22 column 1 (char 631)\n",
            "Attempting robust sequential object loading...\n",
            "Successfully loaded sequential JSON /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/sinhala_dev_mmlu.json with 1851 records.\n",
            "\n",
            "Total combined records: 50279\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "   q_no subject    category  \\\n",
              "0     6    Arts  humanities   \n",
              "1     7    Arts  humanities   \n",
              "2     8    Arts  humanities   \n",
              "3     9    Arts  humanities   \n",
              "4    10    Arts  humanities   \n",
              "\n",
              "                                            question  \\\n",
              "0       වෙසක් උත්සවය බෞද්ධ ආගමිකයන් හට වැදගත් වන්නේ,   \n",
              "1  මූර්තියක් ඇමීම සඳහා භාවිතා කළ හැකි පහසුම මාධ්‍...   \n",
              "2  ද්විතීයික වර්ණ කාණ්ඩයට අයත් වර්ණ ලෙස දැක්විය හ...   \n",
              "3      ඉස්ලාම් පල්ලියේ විශේෂ ගෘහ නිර්මාණ අංගය වන්නේ,   \n",
              "4         කලයක හැඩය ඇසුරින් නිර්මාණය කළ දාගැබ වන්නේ,   \n",
              "\n",
              "                                             choices answer  \\\n",
              "0  [සිදුහත් බෝසතුන්ගේ ඉපදීම, බුදුවීම, පිරිනිවීම ස...    1.0   \n",
              "1                     [සිමෙන්ති, කළුගල්, ලෝකඩ, මැටි]    4.0   \n",
              "2  [නිල්, කහ, රතු ය., දම්, රතු, කළු ය., දම්, තැඹි...    3.0   \n",
              "3                  [ගෝපුරම්, කූඩා, හර්මිකාව, අට්ටාල]    2.0   \n",
              "4  [ධාන්‍යාකාර දාගැබයි, බුබුලාකාර දාගැබයි, පද්මාක...    4.0   \n",
              "\n",
              "                                            metadata difficulty  \n",
              "0  {'difficulty': 'easy', 'grade': 6, 'source': '...       Easy  \n",
              "1  {'difficulty': 'easy', 'grade': 6, 'source': '...       Easy  \n",
              "2  {'difficulty': 'easy', 'grade': 6, 'source': '...       Easy  \n",
              "3  {'difficulty': 'easy', 'grade': 6, 'source': '...       Easy  \n",
              "4  {'difficulty': 'easy', 'grade': 6, 'source': '...       Easy  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-772e2c04-6703-4844-bf93-fbdf73e2e1a0\" 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>q_no</th>\n",
              "      <th>subject</th>\n",
              "      <th>category</th>\n",
              "      <th>question</th>\n",
              "      <th>choices</th>\n",
              "      <th>answer</th>\n",
              "      <th>metadata</th>\n",
              "      <th>difficulty</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>Arts</td>\n",
              "      <td>humanities</td>\n",
              "      <td>වෙසක් උත්සවය බෞද්ධ ආගමිකයන් හට වැදගත් වන්නේ,</td>\n",
              "      <td>[සිදුහත් බෝසතුන්ගේ ඉපදීම, බුදුවීම, පිරිනිවීම ස...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>{'difficulty': 'easy', 'grade': 6, 'source': '...</td>\n",
              "      <td>Easy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>7</td>\n",
              "      <td>Arts</td>\n",
              "      <td>humanities</td>\n",
              "      <td>මූර්තියක් ඇමීම සඳහා භාවිතා කළ හැකි පහසුම මාධ්‍...</td>\n",
              "      <td>[සිමෙන්ති, කළුගල්, ලෝකඩ, මැටි]</td>\n",
              "      <td>4.0</td>\n",
              "      <td>{'difficulty': 'easy', 'grade': 6, 'source': '...</td>\n",
              "      <td>Easy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>Arts</td>\n",
              "      <td>humanities</td>\n",
              "      <td>ද්විතීයික වර්ණ කාණ්ඩයට අයත් වර්ණ ලෙස දැක්විය හ...</td>\n",
              "      <td>[නිල්, කහ, රතු ය., දම්, රතු, කළු ය., දම්, තැඹි...</td>\n",
              "      <td>3.0</td>\n",
              "      <td>{'difficulty': 'easy', 'grade': 6, 'source': '...</td>\n",
              "      <td>Easy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>9</td>\n",
              "      <td>Arts</td>\n",
              "      <td>humanities</td>\n",
              "      <td>ඉස්ලාම් පල්ලියේ විශේෂ ගෘහ නිර්මාණ අංගය වන්නේ,</td>\n",
              "      <td>[ගෝපුරම්, කූඩා, හර්මිකාව, අට්ටාල]</td>\n",
              "      <td>2.0</td>\n",
              "      <td>{'difficulty': 'easy', 'grade': 6, 'source': '...</td>\n",
              "      <td>Easy</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>10</td>\n",
              "      <td>Arts</td>\n",
              "      <td>humanities</td>\n",
              "      <td>කලයක හැඩය ඇසුරින් නිර්මාණය කළ දාගැබ වන්නේ,</td>\n",
              "      <td>[ධාන්‍යාකාර දාගැබයි, බුබුලාකාර දාගැබයි, පද්මාක...</td>\n",
              "      <td>4.0</td>\n",
              "      <td>{'difficulty': 'easy', 'grade': 6, 'source': '...</td>\n",
              "      <td>Easy</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-772e2c04-6703-4844-bf93-fbdf73e2e1a0')\"\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-772e2c04-6703-4844-bf93-fbdf73e2e1a0 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-772e2c04-6703-4844-bf93-fbdf73e2e1a0');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"display(df_all\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"q_no\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 6,\n        \"max\": 10,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          7,\n          10,\n          8\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"subject\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"Arts\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"category\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"humanities\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"question\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"\\u0db8\\u0dd6\\u0dbb\\u0dca\\u0dad\\u0dd2\\u0dba\\u0d9a\\u0dca \\u0d87\\u0db8\\u0dd3\\u0db8 \\u0dc3\\u0db3\\u0dc4\\u0dcf \\u0db7\\u0dcf\\u0dc0\\u0dd2\\u0dad\\u0dcf \\u0d9a\\u0dc5 \\u0dc4\\u0dd0\\u0d9a\\u0dd2 \\u0db4\\u0dc4\\u0dc3\\u0dd4\\u0db8 \\u0db8\\u0dcf\\u0db0\\u0dca\\u200d\\u0dba \\u0dc0\\u0db1\\u0dca\\u0db1\\u0dda,\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"choices\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"answer\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": 1.0,\n        \"max\": 4.0,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          4.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"metadata\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"difficulty\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"Easy\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "import os\n",
        "import json\n",
        "import pandas as pd\n",
        "\n",
        "# Define directory path\n",
        "base_path = '/content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder'\n",
        "\n",
        "# File paths\n",
        "easy_path = os.path.join(base_path, 'Easy.json')\n",
        "medium_path = os.path.join(base_path, 'Medium.json')\n",
        "hard_path = os.path.join(base_path, 'Hard.json')\n",
        "mmlu_dev = os.path.join(base_path, 'sinhala_dev_mmlu.json')\n",
        "\n",
        "print(f\"Easy path: {easy_path}\")\n",
        "print(f\"Medium path: {medium_path}\")\n",
        "print(f\"Hard path: {hard_path}\")\n",
        "print(f\"MMLU path: {mmlu_dev}\")\n",
        "\n",
        "# Helper function to load JSON files to DataFrame\n",
        "def load_json_to_df(file_path, difficulty_level):\n",
        "    try:\n",
        "        with open(file_path, 'r', encoding='utf-8') as f:\n",
        "            data = json.load(f)\n",
        "        df = pd.DataFrame(data)\n",
        "        df['difficulty'] = difficulty_level\n",
        "        print(f\"Successfully loaded {file_path} with {len(df)} records.\")\n",
        "        return df\n",
        "    except Exception as e:\n",
        "        print(f\"Standard JSON load failed for {file_path}: {e}\")\n",
        "        print(\"Attempting robust sequential object loading...\")\n",
        "        try:\n",
        "            with open(file_path, 'r', encoding='utf-8') as f:\n",
        "                content = f.read().strip()\n",
        "            decoder = json.JSONDecoder()\n",
        "            pos = 0\n",
        "            records = []\n",
        "            while pos < len(content):\n",
        "                content_sub = content[pos:].lstrip()\n",
        "                if not content_sub:\n",
        "                    break\n",
        "                pos += (len(content[pos:]) - len(content_sub))\n",
        "                obj, idx = decoder.raw_decode(content[pos:])\n",
        "                records.append(obj)\n",
        "                pos += idx\n",
        "            df = pd.DataFrame(records)\n",
        "            df['difficulty'] = difficulty_level\n",
        "            print(f\"Successfully loaded sequential JSON {file_path} with {len(df)} records.\")\n",
        "            return df\n",
        "        except Exception as ex:\n",
        "            print(f\"Robust loading also failed: {ex}\")\n",
        "            return pd.DataFrame()\n",
        "\n",
        "# Load each file\n",
        "df_easy = load_json_to_df(easy_path, 'Easy')\n",
        "df_medium = load_json_to_df(medium_path, 'Medium')\n",
        "df_hard = load_json_to_df(hard_path, 'Hard')\n",
        "df_mmlu = load_json_to_df(mmlu_dev, 'Easy')\n",
        "\n",
        "# Combine all dataframes\n",
        "df_all = pd.concat([df_easy, df_medium, df_hard, df_mmlu], ignore_index=True)\n",
        "\n",
        "# Display summary and preview\n",
        "print(f\"\\nTotal combined records: {len(df_all)}\")\n",
        "display(df_all.head())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 335
        },
        "id": "XaQDqPGYmXL2",
        "outputId": "01e3c8f9-155c-4793-8d47-721ad34931fd"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "q_no          50279\n",
              "subject       50279\n",
              "category      50279\n",
              "question      50279\n",
              "choices       50279\n",
              "answer        50278\n",
              "metadata      50279\n",
              "difficulty    50279\n",
              "dtype: int64"
            ],
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>0</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>q_no</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>subject</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>category</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>question</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>choices</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>answer</th>\n",
              "      <td>50278</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>metadata</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>difficulty</th>\n",
              "      <td>50279</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div><br><label><b>dtype:</b> int64</label>"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "df_all.count()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1SKKIPkmmaoC",
        "outputId": "b7044bcb-8d53-47f7-b68f-c04f2c0ddafa"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- Difficulty Counts ---\n",
            "difficulty\n",
            "Medium    26581\n",
            "Hard      16514\n",
            "Easy       7184\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "print(\"--- Difficulty Counts ---\")\n",
        "print(df_all['difficulty'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N2XPdeQqmgnm",
        "outputId": "870b48b9-19a3-47a2-8c99-51d240f7cd8f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- Subject Counts ---\n",
            "subject\n",
            "Buddhism                           2685\n",
            "History                            2186\n",
            "Communication and Media Studies    1964\n",
            "Science                            1857\n",
            "Christianity                       1786\n",
            "                                   ... \n",
            "History of India                     10\n",
            "History of Europe                     5\n",
            "Eastern_music                         1\n",
            "Sinhala_language_and_literature       1\n",
            "drama_and_theatre                     1\n",
            "Name: count, Length: 105, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "print(\"--- Subject Counts ---\")\n",
        "print(df_all['subject'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wUYFwY2mnF0v",
        "outputId": "46754b13-16ca-4159-fb3d-43bce8416fd7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "---No of Subjects ---\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "105"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ],
      "source": [
        "print(\"---No of Subjects ---\")\n",
        "len(df_all['subject'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4DMzLYm4nBEC",
        "outputId": "91c98324-3bab-4aff-cbf4-38819f44abab"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- Category Counts ---\n",
            "category\n",
            "humanities          19501\n",
            "stem                14849\n",
            "social_science       6881\n",
            "business_studies     3465\n",
            "other                2867\n",
            "language             2716\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "print(\"--- Category Counts ---\")\n",
        "print(df_all['category'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 407
        },
        "id": "408a898f",
        "outputId": "9b3061d8-7399-4665-aaa5-f4b55b9e0760"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Get category counts\n",
        "category_counts = df_all['category'].value_counts()\n",
        "\n",
        "# Create a pie chart\n",
        "plt.figure(figsize=(6, 4))\n",
        "plt.pie(\n",
        "    category_counts,\n",
        "    labels=category_counts.index,\n",
        "    autopct='%1.1f%%',\n",
        "    startangle=140,\n",
        "    colors=['#5DADE2', '#48C9B0', '#F4D03F', '#EB984E', '#AF7AC5', '#EC7063'],\n",
        "    wedgeprops={'edgecolor': 'white', 'linewidth': 1.5}\n",
        ")\n",
        "\n",
        "#plt.title('Distribution of Question Domains', fontsize=16, fontweight='bold', pad=20)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 407
        },
        "id": "dAHaJ1F7nDgK",
        "outputId": "8b83ed4a-11a5-4153-ba8d-40d01975bb8c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Get difficulty counts\n",
        "difficulty_counts = df_all['difficulty'].value_counts()\n",
        "\n",
        "# Create a pie chart\n",
        "plt.figure(figsize=(6, 4))\n",
        "plt.pie(\n",
        "    difficulty_counts,\n",
        "    labels=difficulty_counts.index,\n",
        "    autopct='%1.1f%%',\n",
        "    startangle=140,\n",
        "    colors=['#5DADE2', '#48C9B0', '#F4D03F'],\n",
        "    wedgeprops={'edgecolor': 'white', 'linewidth': 1.5}\n",
        ")\n",
        "\n",
        "#plt.title('Distribution of Question difficulty', fontsize=16, fontweight='bold', pad=20)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "99e6a345",
        "outputId": "5ed9cf0d-239f-4d45-cc29-86132e20d335"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Successfully read 3732 items from Easy.json\n",
            "Successfully read 6402 items from Medium.json\n",
            "Successfully read 12077 items from Hard.json\n",
            "\n",
            "Successfully saved combined dataset with 22211 total records to: /content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/Combined_All.json\n"
          ]
        }
      ],
      "source": [
        "# import json\n",
        "# import os\n",
        "\n",
        "# base_path = '/content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder'\n",
        "# output_file_path = os.path.join(base_path, 'Combined_All.json')\n",
        "\n",
        "# # List of target files to merge\n",
        "# files_to_merge = ['Easy.json', 'Medium.json', 'Hard.json']\n",
        "# combined_data = []\n",
        "\n",
        "# for file_name in files_to_merge:\n",
        "#     file_path = os.path.join(base_path, file_name)\n",
        "#     try:\n",
        "#         with open(file_path, 'r', encoding='utf-8') as f:\n",
        "#             data = json.load(f)\n",
        "#             # If the JSON file contains a list at its root, extend our combined list\n",
        "#             if isinstance(data, list):\n",
        "#                 # Optionally add difficulty flag inside each dictionary if not already present\n",
        "#                 difficulty_label = file_name.replace('.json', '')\n",
        "#                 for item in data:\n",
        "#                     if isinstance(item, dict):\n",
        "#                         item['difficulty'] = difficulty_label\n",
        "#                 combined_data.extend(data)\n",
        "#                 print(f\"Successfully read {len(data)} items from {file_name}\")\n",
        "#             else:\n",
        "#                 print(f\"Warning: {file_name} does not contain a list at its root. Skipping.\")\n",
        "#     except Exception as e:\n",
        "#         print(f\"Error reading {file_name}: {e}\")\n",
        "\n",
        "# # Save the combined list back to a single JSON file\n",
        "# try:\n",
        "#     with open(output_file_path, 'w', encoding='utf-8') as f:\n",
        "#         json.dump(combined_data, f, ensure_ascii=False, indent=4)\n",
        "#     print(f\"\\nSuccessfully saved combined dataset with {len(combined_data)} total records to: {output_file_path}\")\n",
        "# except Exception as e:\n",
        "#     print(f\"Error saving combined file: {e}\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6bcc6f30",
        "outputId": "4e3f39f7-e043-4eac-ec0c-73c893488154"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--- Example Record from without_dups_combined_extracted_answers_new.json ---\n",
            "{\n",
            "    \"q_no\": 6,\n",
            "    \"subject\": \"Arts\",\n",
            "    \"category\": \"humanities\",\n",
            "    \"question\": \"වෙසක් උත්සවය බෞද්ධ ආගමිකයන් හට වැදගත් වන්නේ,\",\n",
            "    \"choices\": [\n",
            "        \"සිදුහත් බෝසතුන්ගේ ඉපදීම, බුදුවීම, පිරිනිවීම සිදු වූ දිනය බැවිනි.\",\n",
            "        \"බුදුන් වහන්සේගේ ලංකා ගමනය සිදු වූ දිනය නිසා\",\n",
            "        \"මිහිඳු මා හිමියන් ලක්දිවට වැඩමකල දිනය බැවිනි\",\n",
            "        \"බුදුන් වහන්සේගේ ප්‍රථම ධර්ම දේශනාන පැවැත් වූ දිනය බැවිනි.\"\n",
            "    ],\n",
            "    \"answer\": 1,\n",
            "    \"metadata\": {\n",
            "        \"difficulty\": \"easy\",\n",
            "        \"grade\": 6,\n",
            "        \"source\": \"NWP_2021_G_06_3rdTerm_ART.pdf\",\n",
            "        \"subject_original\": \"චිත්‍ර කලාව\",\n",
            "        \"type\": \"P_NWP_3\",\n",
            "        \"year\": 2021\n",
            "    }\n",
            "}\n"
          ]
        }
      ],
      "source": [
        "import json\n",
        "import os\n",
        "\n",
        "output_file_path = '/content/drive/MyDrive/ICTER/SinhalaMCQ/Combined_folder/without_dups_combined_extracted_answers_new.json'\n",
        "\n",
        "\n",
        "with open(output_file_path, 'r', encoding='utf-8') as f:\n",
        "    combined_data = json.load(f)\n",
        "\n",
        "\n",
        "print(\"--- Example Record from without_dups_combined_extracted_answers_new.json ---\")\n",
        "print(json.dumps(combined_data[0], indent=4, ensure_ascii=False))\n",
        "\n"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}