{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Hs5iKOIKnRfW"
      },
      "outputs": [],
      "source": [
        "# Notebook 1: Real Data Extraction and Synthetic Enrichment\n",
        "\n",
        "import pandas as pd\n",
        "import numpy as np"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Real Data Extraction and Synthetic Enrichment\n",
        "\n",
        "## Objective\n",
        "This notebook loads real-world data, cleans and prepares it, creates synthetic enrichment, combines both, and saves the final dataset for further analysis.\n"
      ],
      "metadata": {
        "id": "47POjvLpnpiw"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(\"datareal.csv\", sep=\";\", header=0)\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 201
        },
        "id": "vc20fW5QnqPz",
        "outputId": "6e2c1789-1b81-406b-a482-0ded1df40b48"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME AVG_JOB_SATISFACTION  \\\n",
              "0      Finland                     37,2          27389.0                  8,1   \n",
              "1      Iceland                     39,4          43769.0                  8,1   \n",
              "2       Norway                       34          42203.0                  8,1   \n",
              "3      Austria                     36,7          27804.0                    8   \n",
              "4  Switzerland                     35,3          49607.0                  7,9   \n",
              "\n",
              "   Unnamed: 4  Unnamed: 5  Unnamed: 6  Unnamed: 7  \n",
              "0         NaN         NaN         NaN         NaN  \n",
              "1         NaN         NaN         NaN         NaN  \n",
              "2         NaN         NaN         NaN         NaN  \n",
              "3         NaN         NaN         NaN         NaN  \n",
              "4         NaN         NaN         NaN         NaN  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-bb949cac-522d-41e2-84d1-a1cefaac468d\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <th>Unnamed: 4</th>\n",
              "      <th>Unnamed: 5</th>\n",
              "      <th>Unnamed: 6</th>\n",
              "      <th>Unnamed: 7</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37,2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8,1</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39,4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8,1</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8,1</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36,7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35,3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7,9</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</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-bb949cac-522d-41e2-84d1-a1cefaac468d')\"\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-bb949cac-522d-41e2-84d1-a1cefaac468d 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-bb949cac-522d-41e2-84d1-a1cefaac468d');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 34,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 27,\n        \"samples\": [\n          \"38,6\",\n          \"39\",\n          \"37,3\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 14,\n        \"samples\": [\n          \"7,2\",\n          \"7\",\n          \"8,1\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Unnamed: 4\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": null,\n        \"max\": null,\n        \"num_unique_values\": 0,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Unnamed: 5\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": null,\n        \"max\": null,\n        \"num_unique_values\": 0,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Unnamed: 6\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": null,\n        \"max\": null,\n        \"num_unique_values\": 0,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Unnamed: 7\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": null,\n        \"max\": null,\n        \"num_unique_values\": 0,\n        \"samples\": [],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.loc[:, ~df.columns.str.contains(\"^Unnamed\")]\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 201
        },
        "id": "l6ew3fwSofw4",
        "outputId": "fdda8a25-6528-470d-a992-f4cb3d1b2bac"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME AVG_JOB_SATISFACTION\n",
              "0      Finland                     37,2          27389.0                  8,1\n",
              "1      Iceland                     39,4          43769.0                  8,1\n",
              "2       Norway                       34          42203.0                  8,1\n",
              "3      Austria                     36,7          27804.0                    8\n",
              "4  Switzerland                     35,3          49607.0                  7,9"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ea672370-418e-4b6f-bd25-3a69e4c1802b\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37,2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8,1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39,4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8,1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8,1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36,7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35,3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7,9</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-ea672370-418e-4b6f-bd25-3a69e4c1802b')\"\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-ea672370-418e-4b6f-bd25-3a69e4c1802b 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-ea672370-418e-4b6f-bd25-3a69e4c1802b');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 34,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 27,\n        \"samples\": [\n          \"38,6\",\n          \"39\",\n          \"37,3\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 14,\n        \"samples\": [\n          \"7,2\",\n          \"7\",\n          \"8,1\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# convert comma to dot and to float\n",
        "df[\"AVG_WEEKLY_WORKING_HOURS\"] = (\n",
        "    df[\"AVG_WEEKLY_WORKING_HOURS\"]\n",
        "    .astype(str)\n",
        "    .str.replace(\",\", \".\", regex=False)\n",
        "    .astype(float)\n",
        ")\n",
        "\n",
        "df[\"AVG_JOB_SATISFACTION\"] = (\n",
        "    df[\"AVG_JOB_SATISFACTION\"]\n",
        "    .astype(str)\n",
        "    .str.replace(\",\", \".\", regex=False)\n",
        "    .astype(float)\n",
        ")\n",
        "\n",
        "# income sollte schon numeric sein, aber sicher ist sicher\n",
        "df[\"MEAN_NET_INCOME\"] = pd.to_numeric(df[\"MEAN_NET_INCOME\"], errors=\"coerce\")\n",
        "\n",
        "df.dtypes"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 203
        },
        "id": "4Cpsqz_TqA4I",
        "outputId": "17a2119d-3cb5-4f6e-e094-c83fa3d405e5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "COUNTRY                      object\n",
              "AVG_WEEKLY_WORKING_HOURS    float64\n",
              "MEAN_NET_INCOME             float64\n",
              "AVG_JOB_SATISFACTION        float64\n",
              "dtype: object"
            ],
            "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>COUNTRY</th>\n",
              "      <td>object</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <td>float64</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <td>float64</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <td>float64</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div><br><label><b>dtype:</b> object</label>"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"Shape:\", df.shape)\n",
        "print(\"\\nColumns:\")\n",
        "print(df.columns)\n",
        "print(\"\\nData types:\")\n",
        "print(df.dtypes)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YQcfRJ_HpepE",
        "outputId": "608efc48-5c7c-41aa-d61b-df4367155220"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Shape: (34, 4)\n",
            "\n",
            "Columns:\n",
            "Index(['COUNTRY', 'AVG_WEEKLY_WORKING_HOURS', 'MEAN_NET_INCOME',\n",
            "       'AVG_JOB_SATISFACTION'],\n",
            "      dtype='object')\n",
            "\n",
            "Data types:\n",
            "COUNTRY                      object\n",
            "AVG_WEEKLY_WORKING_HOURS     object\n",
            "MEAN_NET_INCOME             float64\n",
            "AVG_JOB_SATISFACTION         object\n",
            "dtype: object\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df[\"AVG_WEEKLY_WORKING_HOURS\"] = (\n",
        "    df[\"AVG_WEEKLY_WORKING_HOURS\"]\n",
        "    .astype(str)\n",
        "    .str.replace(\",\", \".\", regex=False)\n",
        "    .astype(float)\n",
        ")\n",
        "\n",
        "df[\"AVG_JOB_SATISFACTION\"] = (\n",
        "    df[\"AVG_JOB_SATISFACTION\"]\n",
        "    .astype(str)\n",
        "    .str.replace(\",\", \".\", regex=False)\n",
        "    .astype(float)\n",
        ")\n",
        "\n",
        "df[\"MEAN_NET_INCOME\"] = pd.to_numeric(df[\"MEAN_NET_INCOME\"], errors=\"coerce\")\n",
        "\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 201
        },
        "id": "MAfzlEwEpiND",
        "outputId": "8720cfd2-0213-4b21-d376-b3996805ba62"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0      Finland                      37.2          27389.0   \n",
              "1      Iceland                      39.4          43769.0   \n",
              "2       Norway                      34.0          42203.0   \n",
              "3      Austria                      36.7          27804.0   \n",
              "4  Switzerland                      35.3          49607.0   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  \n",
              "0                   8.1  \n",
              "1                   8.1  \n",
              "2                   8.1  \n",
              "3                   8.0  \n",
              "4                   7.9  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-20a64cb7-ce7c-4c07-adf2-0b356042fb71\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37.2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39.4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34.0</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36.7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35.3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7.9</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-20a64cb7-ce7c-4c07-adf2-0b356042fb71')\"\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-20a64cb7-ce7c-4c07-adf2-0b356042fb71 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-20a64cb7-ce7c-4c07-adf2-0b356042fb71');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 34,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.826219902872729,\n        \"min\": 30.7,\n        \"max\": 45.9,\n        \"num_unique_values\": 27,\n        \"samples\": [\n          38.6,\n          39.0,\n          37.3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5123105710524828,\n        \"min\": 6.2,\n        \"max\": 8.1,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          7.2,\n          7.0,\n          8.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(df.isna().sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xBsNuIjepk2u",
        "outputId": "0a9aca9a-a11d-43ef-bb91-30b9c8144130"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "COUNTRY                     1\n",
            "AVG_WEEKLY_WORKING_HOURS    1\n",
            "MEAN_NET_INCOME             1\n",
            "AVG_JOB_SATISFACTION        1\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.drop_duplicates(subset=[\"COUNTRY\"])\n",
        "\n",
        "df = df.dropna(subset=[\n",
        "    \"COUNTRY\",\n",
        "    \"AVG_WEEKLY_WORKING_HOURS\",\n",
        "    \"MEAN_NET_INCOME\",\n",
        "    \"AVG_JOB_SATISFACTION\"\n",
        "])\n",
        "\n",
        "df = df.reset_index(drop=True)\n",
        "\n",
        "print(df.shape)\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 217
        },
        "id": "_k1uEgSipnii",
        "outputId": "c757fdae-3bc4-4c86-ad3a-c5f1fd53b717"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(33, 4)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0      Finland                      37.2          27389.0   \n",
              "1      Iceland                      39.4          43769.0   \n",
              "2       Norway                      34.0          42203.0   \n",
              "3      Austria                      36.7          27804.0   \n",
              "4  Switzerland                      35.3          49607.0   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  \n",
              "0                   8.1  \n",
              "1                   8.1  \n",
              "2                   8.1  \n",
              "3                   8.0  \n",
              "4                   7.9  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e4b8dbbc-213f-4092-a8a0-024be4addc2e\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37.2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39.4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34.0</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36.7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35.3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7.9</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-e4b8dbbc-213f-4092-a8a0-024be4addc2e')\"\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-e4b8dbbc-213f-4092-a8a0-024be4addc2e 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-e4b8dbbc-213f-4092-a8a0-024be4addc2e');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 33,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.826219902872729,\n        \"min\": 30.7,\n        \"max\": 45.9,\n        \"num_unique_values\": 27,\n        \"samples\": [\n          38.6,\n          39.0,\n          37.3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5123105710524828,\n        \"min\": 6.2,\n        \"max\": 8.1,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          7.2,\n          7.0,\n          8.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.random.seed(42)\n",
        "\n",
        "df_enriched = df.copy()\n",
        "\n",
        "# Synthetic Feature 1: Savings rate (5%–30%)\n",
        "df_enriched[\"ESTIMATED_SAVINGS_RATE\"] = np.random.uniform(0.05, 0.30, size=len(df_enriched))\n",
        "\n",
        "# Synthetic Feature 2: Monthly savings\n",
        "df_enriched[\"ESTIMATED_MONTHLY_SAVINGS\"] = (\n",
        "    df_enriched[\"MEAN_NET_INCOME\"] * df_enriched[\"ESTIMATED_SAVINGS_RATE\"]\n",
        ").round(2)\n",
        "\n",
        "# Synthetic Feature 3: Work-life balance score (based on working hours)\n",
        "df_enriched[\"WORK_LIFE_BALANCE_SCORE\"] = (\n",
        "    10\n",
        "    - (df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"] - df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].min()) /\n",
        "      (df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].max() - df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].min()) * 5\n",
        "    + np.random.normal(0, 0.3, size=len(df_enriched))\n",
        ").round(2)\n",
        "\n",
        "# Synthetic Feature 4: Income category\n",
        "df_enriched[\"INCOME_CATEGORY\"] = pd.cut(\n",
        "    df_enriched[\"MEAN_NET_INCOME\"],\n",
        "    bins=[0, 25000, 40000, 100000],\n",
        "    labels=[\"Low\", \"Medium\", \"High\"]\n",
        ")\n",
        "\n",
        "df_enriched.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 221
        },
        "id": "AhcYwO7yqMfA",
        "outputId": "8086c3a9-0096-4d87-f755-97a06519256f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0      Finland                      37.2          27389.0   \n",
              "1      Iceland                      39.4          43769.0   \n",
              "2       Norway                      34.0          42203.0   \n",
              "3      Austria                      36.7          27804.0   \n",
              "4  Switzerland                      35.3          49607.0   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  ESTIMATED_SAVINGS_RATE  ESTIMATED_MONTHLY_SAVINGS  \\\n",
              "0                   8.1                0.143635                    3934.02   \n",
              "1                   8.1                0.287679                   12591.40   \n",
              "2                   8.1                0.232998                    9833.24   \n",
              "3                   8.0                0.199665                    5551.48   \n",
              "4                   7.9                0.089005                    4415.25   \n",
              "\n",
              "   WORK_LIFE_BALANCE_SCORE INCOME_CATEGORY  \n",
              "0                     7.68          Medium  \n",
              "1                     7.42            High  \n",
              "2                     9.00            High  \n",
              "3                     7.84          Medium  \n",
              "4                     8.18            High  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0de474b8-1117-43a9-a2bd-d1f2ff9e88b1\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <th>ESTIMATED_SAVINGS_RATE</th>\n",
              "      <th>ESTIMATED_MONTHLY_SAVINGS</th>\n",
              "      <th>WORK_LIFE_BALANCE_SCORE</th>\n",
              "      <th>INCOME_CATEGORY</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37.2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.143635</td>\n",
              "      <td>3934.02</td>\n",
              "      <td>7.68</td>\n",
              "      <td>Medium</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39.4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.287679</td>\n",
              "      <td>12591.40</td>\n",
              "      <td>7.42</td>\n",
              "      <td>High</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34.0</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.232998</td>\n",
              "      <td>9833.24</td>\n",
              "      <td>9.00</td>\n",
              "      <td>High</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36.7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.199665</td>\n",
              "      <td>5551.48</td>\n",
              "      <td>7.84</td>\n",
              "      <td>Medium</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35.3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7.9</td>\n",
              "      <td>0.089005</td>\n",
              "      <td>4415.25</td>\n",
              "      <td>8.18</td>\n",
              "      <td>High</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-0de474b8-1117-43a9-a2bd-d1f2ff9e88b1')\"\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-0de474b8-1117-43a9-a2bd-d1f2ff9e88b1 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-0de474b8-1117-43a9-a2bd-d1f2ff9e88b1');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df_enriched",
              "summary": "{\n  \"name\": \"df_enriched\",\n  \"rows\": 33,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.826219902872729,\n        \"min\": 30.7,\n        \"max\": 45.9,\n        \"num_unique_values\": 27,\n        \"samples\": [\n          38.6,\n          39.0,\n          37.3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5123105710524828,\n        \"min\": 6.2,\n        \"max\": 8.1,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          7.2,\n          7.0,\n          8.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ESTIMATED_SAVINGS_RATE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07051759984769274,\n        \"min\": 0.055146123573950614,\n        \"max\": 0.2924774630404986,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          0.09263103092182289,\n          0.09585112746335846,\n          0.09991844553958994\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ESTIMATED_MONTHLY_SAVINGS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3018.657615281089,\n        \"min\": 281.6,\n        \"max\": 12591.4,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          281.6,\n          1685.25,\n          2586.09\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_LIFE_BALANCE_SCORE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.9677050326948963,\n        \"min\": 4.95,\n        \"max\": 10.33,\n        \"num_unique_values\": 31,\n        \"samples\": [\n          6.52,\n          7.4,\n          7.12\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"INCOME_CATEGORY\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"Medium\",\n          \"High\",\n          \"Low\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.random.seed(42)\n",
        "\n",
        "df_enriched = df.copy()\n",
        "\n",
        "# 1. Work Pressure (mehr Stunden = mehr Druck)\n",
        "df_enriched[\"WORK_PRESSURE\"] = (\n",
        "    (df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"] - df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].min()) /\n",
        "    (df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].max() - df_enriched[\"AVG_WEEKLY_WORKING_HOURS\"].min())\n",
        ").round(2)\n",
        "\n",
        "\n",
        "# 2. Cost of Living (angenommen: höheres Einkommen → höhere Lebenshaltungskosten)\n",
        "df_enriched[\"COST_OF_LIVING_INDEX\"] = (\n",
        "    df_enriched[\"MEAN_NET_INCOME\"] / df_enriched[\"MEAN_NET_INCOME\"].mean()\n",
        ").round(2)\n",
        "\n",
        "\n",
        "# 3. Financial Comfort (Einkommen vs. Kosten)\n",
        "df_enriched[\"FINANCIAL_COMFORT\"] = (\n",
        "    df_enriched[\"MEAN_NET_INCOME\"] / (df_enriched[\"COST_OF_LIVING_INDEX\"] * 1000)\n",
        ").round(2)\n",
        "\n",
        "\n",
        "# 4. Work-Life Balance (weniger Stunden = besser)\n",
        "df_enriched[\"WORK_LIFE_BALANCE\"] = (\n",
        "    1 - df_enriched[\"WORK_PRESSURE\"] + np.random.normal(0, 0.05, size=len(df_enriched))\n",
        ").clip(0,1).round(2)\n",
        "\n",
        "\n",
        "# 5. Stress Level (kombiniert mehrere Faktoren)\n",
        "df_enriched[\"STRESS_LEVEL\"] = (\n",
        "    df_enriched[\"WORK_PRESSURE\"] * 0.6 +\n",
        "    (1 - df_enriched[\"WORK_LIFE_BALANCE\"]) * 0.4 +\n",
        "    np.random.normal(0, 0.05, size=len(df_enriched))\n",
        ").clip(0,1).round(2)\n",
        "\n",
        "\n",
        "# 6. Satisfaction Driver Score (synthetic erklärende Variable)\n",
        "df_enriched[\"SATISFACTION_DRIVER_SCORE\"] = (\n",
        "    df_enriched[\"WORK_LIFE_BALANCE\"] * 0.5 +\n",
        "    df_enriched[\"FINANCIAL_COMFORT\"] * 0.3 -\n",
        "    df_enriched[\"STRESS_LEVEL\"] * 0.2\n",
        ").round(2)\n",
        "\n",
        "\n",
        "df_enriched.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 221
        },
        "id": "fWUaiDEpqVh2",
        "outputId": "5f10c579-c883-424c-c0d1-a9caca968c5a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0      Finland                      37.2          27389.0   \n",
              "1      Iceland                      39.4          43769.0   \n",
              "2       Norway                      34.0          42203.0   \n",
              "3      Austria                      36.7          27804.0   \n",
              "4  Switzerland                      35.3          49607.0   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  WORK_PRESSURE  COST_OF_LIVING_INDEX  \\\n",
              "0                   8.1           0.43                  1.42   \n",
              "1                   8.1           0.57                  2.26   \n",
              "2                   8.1           0.22                  2.18   \n",
              "3                   8.0           0.39                  1.44   \n",
              "4                   7.9           0.30                  2.56   \n",
              "\n",
              "   FINANCIAL_COMFORT  WORK_LIFE_BALANCE  STRESS_LEVEL  \\\n",
              "0              19.29               0.59          0.37   \n",
              "1              19.37               0.42          0.62   \n",
              "2              19.36               0.81          0.15   \n",
              "3              19.31               0.69          0.37   \n",
              "4              19.38               0.69          0.21   \n",
              "\n",
              "   SATISFACTION_DRIVER_SCORE  \n",
              "0                       6.01  \n",
              "1                       5.90  \n",
              "2                       6.18  \n",
              "3                       6.06  \n",
              "4                       6.12  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fe31fc4b-d6b0-4e2f-9e8f-793f5ec8f2ed\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <th>WORK_PRESSURE</th>\n",
              "      <th>COST_OF_LIVING_INDEX</th>\n",
              "      <th>FINANCIAL_COMFORT</th>\n",
              "      <th>WORK_LIFE_BALANCE</th>\n",
              "      <th>STRESS_LEVEL</th>\n",
              "      <th>SATISFACTION_DRIVER_SCORE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37.2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.42</td>\n",
              "      <td>19.29</td>\n",
              "      <td>0.59</td>\n",
              "      <td>0.37</td>\n",
              "      <td>6.01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39.4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.57</td>\n",
              "      <td>2.26</td>\n",
              "      <td>19.37</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.62</td>\n",
              "      <td>5.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34.0</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.22</td>\n",
              "      <td>2.18</td>\n",
              "      <td>19.36</td>\n",
              "      <td>0.81</td>\n",
              "      <td>0.15</td>\n",
              "      <td>6.18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36.7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.39</td>\n",
              "      <td>1.44</td>\n",
              "      <td>19.31</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.37</td>\n",
              "      <td>6.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35.3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7.9</td>\n",
              "      <td>0.30</td>\n",
              "      <td>2.56</td>\n",
              "      <td>19.38</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.21</td>\n",
              "      <td>6.12</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-fe31fc4b-d6b0-4e2f-9e8f-793f5ec8f2ed')\"\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-fe31fc4b-d6b0-4e2f-9e8f-793f5ec8f2ed 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-fe31fc4b-d6b0-4e2f-9e8f-793f5ec8f2ed');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df_enriched",
              "summary": "{\n  \"name\": \"df_enriched\",\n  \"rows\": 33,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 33,\n        \"samples\": [\n          \"Serbia\",\n          \"Cyprus\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.826219902872729,\n        \"min\": 30.7,\n        \"max\": 45.9,\n        \"num_unique_values\": 27,\n        \"samples\": [\n          38.6,\n          39.0,\n          37.3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12859.991823068705,\n        \"min\": 3040.0,\n        \"max\": 49607.0,\n        \"num_unique_values\": 33,\n        \"samples\": [\n          3040.0,\n          17582.0,\n          25882.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5123105710524828,\n        \"min\": 6.2,\n        \"max\": 8.1,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          7.2,\n          7.0,\n          8.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_PRESSURE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1857264606398835,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 25,\n        \"samples\": [\n          0.52,\n          0.59,\n          0.43\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"COST_OF_LIVING_INDEX\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.6638123080382213,\n        \"min\": 0.16,\n        \"max\": 2.56,\n        \"num_unique_values\": 32,\n        \"samples\": [\n          0.47,\n          0.91,\n          0.57\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"FINANCIAL_COMFORT\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.12098631903624234,\n        \"min\": 19.0,\n        \"max\": 19.66,\n        \"num_unique_values\": 21,\n        \"samples\": [\n          19.29,\n          19.57,\n          19.41\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_LIFE_BALANCE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.19779657441038972,\n        \"min\": 0.0,\n        \"max\": 0.98,\n        \"num_unique_values\": 25,\n        \"samples\": [\n          0.6,\n          0.58,\n          0.59\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"STRESS_LEVEL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.19463689970628054,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 25,\n        \"samples\": [\n          0.41,\n          0.43,\n          0.37\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"SATISFACTION_DRIVER_SCORE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1423923038012174,\n        \"min\": 5.68,\n        \"max\": 6.29,\n        \"num_unique_values\": 24,\n        \"samples\": [\n          6.03,\n          6.05,\n          6.01\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "synthetic_rows = []\n",
        "\n",
        "for _, row in df.iterrows():\n",
        "    for i in range(3):  # 3 neue Versionen pro Land\n",
        "\n",
        "        new_row = row.copy()\n",
        "\n",
        "        # kleine Variationen hinzufügen\n",
        "        new_row[\"AVG_WEEKLY_WORKING_HOURS\"] = round(\n",
        "            max(20, row[\"AVG_WEEKLY_WORKING_HOURS\"] + np.random.normal(0, 1.5)), 1\n",
        "        )\n",
        "\n",
        "        new_row[\"MEAN_NET_INCOME\"] = round(\n",
        "            max(5000, row[\"MEAN_NET_INCOME\"] + np.random.normal(0, 3000)), 2\n",
        "        )\n",
        "\n",
        "        new_row[\"AVG_JOB_SATISFACTION\"] = round(\n",
        "            min(10, max(1, row[\"AVG_JOB_SATISFACTION\"] + np.random.normal(0, 0.4))), 1\n",
        "        )\n",
        "\n",
        "        # neuen Namen geben\n",
        "        new_row[\"COUNTRY\"] = f\"{row['COUNTRY']}_synthetic_{i+1}\"\n",
        "\n",
        "        synthetic_rows.append(new_row)\n",
        "\n",
        "synthetic_df = pd.DataFrame(synthetic_rows)\n",
        "\n",
        "synthetic_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 201
        },
        "id": "JWNeZH1Xq6Xi",
        "outputId": "911d9ad7-306f-4753-a8df-fb6e21cee5fc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0  Finland_synthetic_1                      37.1         30399.60   \n",
              "0  Finland_synthetic_2                      36.2         28473.19   \n",
              "0  Finland_synthetic_3                      37.1         32082.93   \n",
              "1  Iceland_synthetic_1                      40.6         44030.14   \n",
              "1  Iceland_synthetic_2                      39.5         37806.29   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  \n",
              "0                   8.2  \n",
              "0                   8.7  \n",
              "0                   7.1  \n",
              "1                   8.0  \n",
              "1                   8.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7d95226f-c793-440d-bbd9-4f16a1486151\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_1</td>\n",
              "      <td>37.1</td>\n",
              "      <td>30399.60</td>\n",
              "      <td>8.2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_2</td>\n",
              "      <td>36.2</td>\n",
              "      <td>28473.19</td>\n",
              "      <td>8.7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_3</td>\n",
              "      <td>37.1</td>\n",
              "      <td>32082.93</td>\n",
              "      <td>7.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland_synthetic_1</td>\n",
              "      <td>40.6</td>\n",
              "      <td>44030.14</td>\n",
              "      <td>8.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland_synthetic_2</td>\n",
              "      <td>39.5</td>\n",
              "      <td>37806.29</td>\n",
              "      <td>8.0</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-7d95226f-c793-440d-bbd9-4f16a1486151')\"\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-7d95226f-c793-440d-bbd9-4f16a1486151 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-7d95226f-c793-440d-bbd9-4f16a1486151');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "synthetic_df",
              "summary": "{\n  \"name\": \"synthetic_df\",\n  \"rows\": 99,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 99,\n        \"samples\": [\n          \"Italy_synthetic_3\",\n          \"Czechia_synthetic_2\",\n          \"Serbia_synthetic_3\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.1257427894793697,\n        \"min\": 29.5,\n        \"max\": 46.7,\n        \"num_unique_values\": 61,\n        \"samples\": [\n          37.1,\n          32.8,\n          37.9\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13060.359152584817,\n        \"min\": 5000.0,\n        \"max\": 55265.56,\n        \"num_unique_values\": 91,\n        \"samples\": [\n          9879.51,\n          35179.78,\n          40211.72\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.6525973667018435,\n        \"min\": 5.6,\n        \"max\": 8.8,\n        \"num_unique_values\": 30,\n        \"samples\": [\n          6.1,\n          7.5,\n          6.4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.random.seed(42)\n",
        "\n",
        "synthetic_enriched = synthetic_df.copy()\n",
        "\n",
        "# WORK PRESSURE\n",
        "synthetic_enriched[\"WORK_PRESSURE\"] = (\n",
        "    (synthetic_enriched[\"AVG_WEEKLY_WORKING_HOURS\"] - df[\"AVG_WEEKLY_WORKING_HOURS\"].min()) /\n",
        "    (df[\"AVG_WEEKLY_WORKING_HOURS\"].max() - df[\"AVG_WEEKLY_WORKING_HOURS\"].min())\n",
        ").round(2)\n",
        "\n",
        "# COST OF LIVING\n",
        "synthetic_enriched[\"COST_OF_LIVING_INDEX\"] = (\n",
        "    synthetic_enriched[\"MEAN_NET_INCOME\"] / df[\"MEAN_NET_INCOME\"].mean()\n",
        ").round(2)\n",
        "\n",
        "# FINANCIAL COMFORT\n",
        "synthetic_enriched[\"FINANCIAL_COMFORT\"] = (\n",
        "    synthetic_enriched[\"MEAN_NET_INCOME\"] / (synthetic_enriched[\"COST_OF_LIVING_INDEX\"] * 1000)\n",
        ").round(2)\n",
        "\n",
        "# WORK-LIFE BALANCE\n",
        "synthetic_enriched[\"WORK_LIFE_BALANCE\"] = (\n",
        "    1 - synthetic_enriched[\"WORK_PRESSURE\"] + np.random.normal(0, 0.05, size=len(synthetic_enriched))\n",
        ").clip(0,1).round(2)\n",
        "\n",
        "# STRESS\n",
        "synthetic_enriched[\"STRESS_LEVEL\"] = (\n",
        "    synthetic_enriched[\"WORK_PRESSURE\"] * 0.6 +\n",
        "    (1 - synthetic_enriched[\"WORK_LIFE_BALANCE\"]) * 0.4 +\n",
        "    np.random.normal(0, 0.05, size=len(synthetic_enriched))\n",
        ").clip(0,1).round(2)\n",
        "\n",
        "# DRIVER SCORE\n",
        "synthetic_enriched[\"SATISFACTION_DRIVER_SCORE\"] = (\n",
        "    synthetic_enriched[\"WORK_LIFE_BALANCE\"] * 0.5 +\n",
        "    synthetic_enriched[\"FINANCIAL_COMFORT\"] * 0.3 -\n",
        "    synthetic_enriched[\"STRESS_LEVEL\"] * 0.2\n",
        ").round(2)\n",
        "\n",
        "synthetic_enriched.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 221
        },
        "id": "PNoV0eg4rGGT",
        "outputId": "30c96354-c9f1-4cf8-d5d9-142304401ba9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0  Finland_synthetic_1                      37.1         30399.60   \n",
              "0  Finland_synthetic_2                      36.2         28473.19   \n",
              "0  Finland_synthetic_3                      37.1         32082.93   \n",
              "1  Iceland_synthetic_1                      40.6         44030.14   \n",
              "1  Iceland_synthetic_2                      39.5         37806.29   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  WORK_PRESSURE  COST_OF_LIVING_INDEX  \\\n",
              "0                   8.2           0.42                  1.57   \n",
              "0                   8.7           0.36                  1.47   \n",
              "0                   7.1           0.42                  1.66   \n",
              "1                   8.0           0.65                  2.27   \n",
              "1                   8.0           0.58                  1.95   \n",
              "\n",
              "   FINANCIAL_COMFORT  WORK_LIFE_BALANCE  STRESS_LEVEL  \\\n",
              "0              19.36               0.60          0.40   \n",
              "0              19.37               0.63          0.29   \n",
              "0              19.33               0.61          0.39   \n",
              "1              19.40               0.43          0.60   \n",
              "1              19.39               0.41          0.54   \n",
              "\n",
              "   SATISFACTION_DRIVER_SCORE  \n",
              "0                       6.03  \n",
              "0                       6.07  \n",
              "0                       6.03  \n",
              "1                       5.91  \n",
              "1                       5.91  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-920f0c03-0f8f-4461-a7ca-928850a7a40f\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <th>WORK_PRESSURE</th>\n",
              "      <th>COST_OF_LIVING_INDEX</th>\n",
              "      <th>FINANCIAL_COMFORT</th>\n",
              "      <th>WORK_LIFE_BALANCE</th>\n",
              "      <th>STRESS_LEVEL</th>\n",
              "      <th>SATISFACTION_DRIVER_SCORE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_1</td>\n",
              "      <td>37.1</td>\n",
              "      <td>30399.60</td>\n",
              "      <td>8.2</td>\n",
              "      <td>0.42</td>\n",
              "      <td>1.57</td>\n",
              "      <td>19.36</td>\n",
              "      <td>0.60</td>\n",
              "      <td>0.40</td>\n",
              "      <td>6.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_2</td>\n",
              "      <td>36.2</td>\n",
              "      <td>28473.19</td>\n",
              "      <td>8.7</td>\n",
              "      <td>0.36</td>\n",
              "      <td>1.47</td>\n",
              "      <td>19.37</td>\n",
              "      <td>0.63</td>\n",
              "      <td>0.29</td>\n",
              "      <td>6.07</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland_synthetic_3</td>\n",
              "      <td>37.1</td>\n",
              "      <td>32082.93</td>\n",
              "      <td>7.1</td>\n",
              "      <td>0.42</td>\n",
              "      <td>1.66</td>\n",
              "      <td>19.33</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.39</td>\n",
              "      <td>6.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland_synthetic_1</td>\n",
              "      <td>40.6</td>\n",
              "      <td>44030.14</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.65</td>\n",
              "      <td>2.27</td>\n",
              "      <td>19.40</td>\n",
              "      <td>0.43</td>\n",
              "      <td>0.60</td>\n",
              "      <td>5.91</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland_synthetic_2</td>\n",
              "      <td>39.5</td>\n",
              "      <td>37806.29</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.58</td>\n",
              "      <td>1.95</td>\n",
              "      <td>19.39</td>\n",
              "      <td>0.41</td>\n",
              "      <td>0.54</td>\n",
              "      <td>5.91</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-920f0c03-0f8f-4461-a7ca-928850a7a40f')\"\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-920f0c03-0f8f-4461-a7ca-928850a7a40f 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-920f0c03-0f8f-4461-a7ca-928850a7a40f');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "synthetic_enriched",
              "summary": "{\n  \"name\": \"synthetic_enriched\",\n  \"rows\": 99,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 99,\n        \"samples\": [\n          \"Italy_synthetic_3\",\n          \"Czechia_synthetic_2\",\n          \"Serbia_synthetic_3\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.1257427894793697,\n        \"min\": 29.5,\n        \"max\": 46.7,\n        \"num_unique_values\": 61,\n        \"samples\": [\n          37.1,\n          32.8,\n          37.9\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13060.359152584817,\n        \"min\": 5000.0,\n        \"max\": 55265.56,\n        \"num_unique_values\": 91,\n        \"samples\": [\n          9879.51,\n          35179.78,\n          40211.72\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.6525973667018435,\n        \"min\": 5.6,\n        \"max\": 8.8,\n        \"num_unique_values\": 30,\n        \"samples\": [\n          6.1,\n          7.5,\n          6.4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_PRESSURE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.20582383446743815,\n        \"min\": -0.08,\n        \"max\": 1.05,\n        \"num_unique_values\": 52,\n        \"samples\": [\n          0.55,\n          0.47,\n          0.83\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"COST_OF_LIVING_INDEX\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.6746260941696909,\n        \"min\": 0.26,\n        \"max\": 2.86,\n        \"num_unique_values\": 74,\n        \"samples\": [\n          1.95,\n          0.38,\n          1.34\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"FINANCIAL_COMFORT\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.10253899007535147,\n        \"min\": 19.07,\n        \"max\": 19.66,\n        \"num_unique_values\": 35,\n        \"samples\": [\n          19.22,\n          19.29,\n          19.28\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_LIFE_BALANCE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2070930427239679,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 55,\n        \"samples\": [\n          0.52,\n          0.38,\n          0.42\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"STRESS_LEVEL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.20114212129276393,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 54,\n        \"samples\": [\n          0.04,\n          0.83,\n          0.76\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"SATISFACTION_DRIVER_SCORE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1506471985714822,\n        \"min\": 5.57,\n        \"max\": 6.31,\n        \"num_unique_values\": 47,\n        \"samples\": [\n          5.79,\n          5.84,\n          5.8\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "final_df = pd.concat([df_enriched, synthetic_enriched], ignore_index=True)\n",
        "\n",
        "final_df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "R3DA8YhwrTVt",
        "outputId": "c0c74732-bc3e-4e18-d241-b6a93f0f46cf"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(132, 10)"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "final_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 221
        },
        "id": "AaBdHgscrkqx",
        "outputId": "63fdbf91-9388-406c-d097-bffc892187ff"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       COUNTRY  AVG_WEEKLY_WORKING_HOURS  MEAN_NET_INCOME  \\\n",
              "0      Finland                      37.2          27389.0   \n",
              "1      Iceland                      39.4          43769.0   \n",
              "2       Norway                      34.0          42203.0   \n",
              "3      Austria                      36.7          27804.0   \n",
              "4  Switzerland                      35.3          49607.0   \n",
              "\n",
              "   AVG_JOB_SATISFACTION  WORK_PRESSURE  COST_OF_LIVING_INDEX  \\\n",
              "0                   8.1           0.43                  1.42   \n",
              "1                   8.1           0.57                  2.26   \n",
              "2                   8.1           0.22                  2.18   \n",
              "3                   8.0           0.39                  1.44   \n",
              "4                   7.9           0.30                  2.56   \n",
              "\n",
              "   FINANCIAL_COMFORT  WORK_LIFE_BALANCE  STRESS_LEVEL  \\\n",
              "0              19.29               0.59          0.37   \n",
              "1              19.37               0.42          0.62   \n",
              "2              19.36               0.81          0.15   \n",
              "3              19.31               0.69          0.37   \n",
              "4              19.38               0.69          0.21   \n",
              "\n",
              "   SATISFACTION_DRIVER_SCORE  \n",
              "0                       6.01  \n",
              "1                       5.90  \n",
              "2                       6.18  \n",
              "3                       6.06  \n",
              "4                       6.12  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-94b3753b-2838-40fa-97bf-8d142fdfdf9f\" 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>COUNTRY</th>\n",
              "      <th>AVG_WEEKLY_WORKING_HOURS</th>\n",
              "      <th>MEAN_NET_INCOME</th>\n",
              "      <th>AVG_JOB_SATISFACTION</th>\n",
              "      <th>WORK_PRESSURE</th>\n",
              "      <th>COST_OF_LIVING_INDEX</th>\n",
              "      <th>FINANCIAL_COMFORT</th>\n",
              "      <th>WORK_LIFE_BALANCE</th>\n",
              "      <th>STRESS_LEVEL</th>\n",
              "      <th>SATISFACTION_DRIVER_SCORE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Finland</td>\n",
              "      <td>37.2</td>\n",
              "      <td>27389.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.43</td>\n",
              "      <td>1.42</td>\n",
              "      <td>19.29</td>\n",
              "      <td>0.59</td>\n",
              "      <td>0.37</td>\n",
              "      <td>6.01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Iceland</td>\n",
              "      <td>39.4</td>\n",
              "      <td>43769.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.57</td>\n",
              "      <td>2.26</td>\n",
              "      <td>19.37</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.62</td>\n",
              "      <td>5.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Norway</td>\n",
              "      <td>34.0</td>\n",
              "      <td>42203.0</td>\n",
              "      <td>8.1</td>\n",
              "      <td>0.22</td>\n",
              "      <td>2.18</td>\n",
              "      <td>19.36</td>\n",
              "      <td>0.81</td>\n",
              "      <td>0.15</td>\n",
              "      <td>6.18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Austria</td>\n",
              "      <td>36.7</td>\n",
              "      <td>27804.0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.39</td>\n",
              "      <td>1.44</td>\n",
              "      <td>19.31</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.37</td>\n",
              "      <td>6.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Switzerland</td>\n",
              "      <td>35.3</td>\n",
              "      <td>49607.0</td>\n",
              "      <td>7.9</td>\n",
              "      <td>0.30</td>\n",
              "      <td>2.56</td>\n",
              "      <td>19.38</td>\n",
              "      <td>0.69</td>\n",
              "      <td>0.21</td>\n",
              "      <td>6.12</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-94b3753b-2838-40fa-97bf-8d142fdfdf9f')\"\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-94b3753b-2838-40fa-97bf-8d142fdfdf9f 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-94b3753b-2838-40fa-97bf-8d142fdfdf9f');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "final_df",
              "summary": "{\n  \"name\": \"final_df\",\n  \"rows\": 132,\n  \"fields\": [\n    {\n      \"column\": \"COUNTRY\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 132,\n        \"samples\": [\n          \"Denmark_synthetic_3\",\n          \"Spain_synthetic_3\",\n          \"Poland\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_WEEKLY_WORKING_HOURS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.0439629980154277,\n        \"min\": 29.5,\n        \"max\": 46.7,\n        \"num_unique_values\": 70,\n        \"samples\": [\n          38.9,\n          37.2,\n          41.6\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MEAN_NET_INCOME\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12961.860338117047,\n        \"min\": 3040.0,\n        \"max\": 55265.56,\n        \"num_unique_values\": 124,\n        \"samples\": [\n          40075.0,\n          26627.68,\n          44030.14\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"AVG_JOB_SATISFACTION\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.6194006639584302,\n        \"min\": 5.6,\n        \"max\": 8.8,\n        \"num_unique_values\": 30,\n        \"samples\": [\n          5.6,\n          8.7,\n          6.8\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_PRESSURE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2003536515873169,\n        \"min\": -0.08,\n        \"max\": 1.05,\n        \"num_unique_values\": 57,\n        \"samples\": [\n          0.43,\n          0.38,\n          0.37\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"COST_OF_LIVING_INDEX\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.66942505912527,\n        \"min\": 0.16,\n        \"max\": 2.86,\n        \"num_unique_values\": 96,\n        \"samples\": [\n          0.8,\n          2.17,\n          0.84\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"FINANCIAL_COMFORT\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1069680783668568,\n        \"min\": 19.0,\n        \"max\": 19.66,\n        \"num_unique_values\": 41,\n        \"samples\": [\n          19.17,\n          19.43,\n          19.25\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"WORK_LIFE_BALANCE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.20410584264902806,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 61,\n        \"samples\": [\n          0.59,\n          0.67,\n          0.53\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"STRESS_LEVEL\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1990030088918233,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 62,\n        \"samples\": [\n          0.47,\n          0.3,\n          0.37\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"SATISFACTION_DRIVER_SCORE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14815050318443265,\n        \"min\": 5.57,\n        \"max\": 6.31,\n        \"num_unique_values\": 52,\n        \"samples\": [\n          5.98,\n          5.73,\n          5.67\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "final_df.to_csv(\"final_dataset.csv\", index=False)"
      ],
      "metadata": {
        "id": "f4Yymv0yrVyb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "ieiGGvL_rvir"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}