Upload 2 files

src/notebooks/Creating_Dataset.ipynb

@@ -0,0 +1,492 @@
+{
+  "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": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 244
+        },
+        "id": "5KvqZbgdpv6x",
+        "outputId": "6aab18aa-aa15-4adf-c147-c4c3b32e674f"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Dataset generated and saved as synthetic_carbon_footprint.csv\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "   car_km_per_year  public_transport_km_per_year  flights_per_year  \\\n",
+              "0            15795                          9917                 6   \n",
+              "1              860                          7574                 8   \n",
+              "2             5390                          1689                 5   \n",
+              "3            11964                          3267                 9   \n",
+              "4            11284                          4406                 0   \n",
+              "\n",
+              "   electricity_kwh_per_year  natural_gas_m3_per_year  \\\n",
+              "0                      1067                     1526   \n",
+              "1                      4836                     1877   \n",
+              "2                      4993                     1699   \n",
+              "3                      3506                     1029   \n",
+              "4                      2537                      499   \n",
+              "\n",
+              "   renewable_energy_percentage       diet_type  meat_kg_per_year  \\\n",
+              "0                           18      vegetarian                49   \n",
+              "1                           76  non_vegetarian                39   \n",
+              "2                           28  non_vegetarian                94   \n",
+              "3                           60  non_vegetarian                 2   \n",
+              "4                           69           vegan                16   \n",
+              "\n",
+              "   waste_kg_per_year  recycling_rate  house_size_m2  num_people_household  \\\n",
+              "0                475              75            181                     4   \n",
+              "1                154              46            162                     2   \n",
+              "2                677               7            116                     5   \n",
+              "3                838              53             72                     3   \n",
+              "4                125               8            164                     1   \n",
+              "\n",
+              "   carbon_footprint_kgCO2_per_year  \n",
+              "0                         9519.570  \n",
+              "1                         8087.708  \n",
+              "2                        11279.228  \n",
+              "3                         8328.298  \n",
+              "4                         4161.735  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-edf8ae39-8746-4d33-bd1a-1a3df1ed68bd\" 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>car_km_per_year</th>\n",
+              "      <th>public_transport_km_per_year</th>\n",
+              "      <th>flights_per_year</th>\n",
+              "      <th>electricity_kwh_per_year</th>\n",
+              "      <th>natural_gas_m3_per_year</th>\n",
+              "      <th>renewable_energy_percentage</th>\n",
+              "      <th>diet_type</th>\n",
+              "      <th>meat_kg_per_year</th>\n",
+              "      <th>waste_kg_per_year</th>\n",
+              "      <th>recycling_rate</th>\n",
+              "      <th>house_size_m2</th>\n",
+              "      <th>num_people_household</th>\n",
+              "      <th>carbon_footprint_kgCO2_per_year</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>15795</td>\n",
+              "      <td>9917</td>\n",
+              "      <td>6</td>\n",
+              "      <td>1067</td>\n",
+              "      <td>1526</td>\n",
+              "      <td>18</td>\n",
+              "      <td>vegetarian</td>\n",
+              "      <td>49</td>\n",
+              "      <td>475</td>\n",
+              "      <td>75</td>\n",
+              "      <td>181</td>\n",
+              "      <td>4</td>\n",
+              "      <td>9519.570</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>860</td>\n",
+              "      <td>7574</td>\n",
+              "      <td>8</td>\n",
+              "      <td>4836</td>\n",
+              "      <td>1877</td>\n",
+              "      <td>76</td>\n",
+              "      <td>non_vegetarian</td>\n",
+              "      <td>39</td>\n",
+              "      <td>154</td>\n",
+              "      <td>46</td>\n",
+              "      <td>162</td>\n",
+              "      <td>2</td>\n",
+              "      <td>8087.708</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>5390</td>\n",
+              "      <td>1689</td>\n",
+              "      <td>5</td>\n",
+              "      <td>4993</td>\n",
+              "      <td>1699</td>\n",
+              "      <td>28</td>\n",
+              "      <td>non_vegetarian</td>\n",
+              "      <td>94</td>\n",
+              "      <td>677</td>\n",
+              "      <td>7</td>\n",
+              "      <td>116</td>\n",
+              "      <td>5</td>\n",
+              "      <td>11279.228</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>11964</td>\n",
+              "      <td>3267</td>\n",
+              "      <td>9</td>\n",
+              "      <td>3506</td>\n",
+              "      <td>1029</td>\n",
+              "      <td>60</td>\n",
+              "      <td>non_vegetarian</td>\n",
+              "      <td>2</td>\n",
+              "      <td>838</td>\n",
+              "      <td>53</td>\n",
+              "      <td>72</td>\n",
+              "      <td>3</td>\n",
+              "      <td>8328.298</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>11284</td>\n",
+              "      <td>4406</td>\n",
+              "      <td>0</td>\n",
+              "      <td>2537</td>\n",
+              "      <td>499</td>\n",
+              "      <td>69</td>\n",
+              "      <td>vegan</td>\n",
+              "      <td>16</td>\n",
+              "      <td>125</td>\n",
+              "      <td>8</td>\n",
+              "      <td>164</td>\n",
+              "      <td>1</td>\n",
+              "      <td>4161.735</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-edf8ae39-8746-4d33-bd1a-1a3df1ed68bd')\"\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-edf8ae39-8746-4d33-bd1a-1a3df1ed68bd 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-edf8ae39-8746-4d33-bd1a-1a3df1ed68bd');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    <div id=\"df-d96eea76-1da5-4c18-8114-eb8c9c0821be\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-d96eea76-1da5-4c18-8114-eb8c9c0821be')\"\n",
+              "                title=\"Suggest charts\"\n",
+              "                style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "      </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "      <script>\n",
+              "        async function quickchart(key) {\n",
+              "          const quickchartButtonEl =\n",
+              "            document.querySelector('#' + key + ' button');\n",
+              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "          try {\n",
+              "            const charts = await google.colab.kernel.invokeFunction(\n",
+              "                'suggestCharts', [key], {});\n",
+              "          } catch (error) {\n",
+              "            console.error('Error during call to suggestCharts:', error);\n",
+              "          }\n",
+              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "        }\n",
+              "        (() => {\n",
+              "          let quickchartButtonEl =\n",
+              "            document.querySelector('#df-d96eea76-1da5-4c18-8114-eb8c9c0821be button');\n",
+              "          quickchartButtonEl.style.display =\n",
+              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "        })();\n",
+              "      </script>\n",
+              "    </div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df",
+              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 2000,\n  \"fields\": [\n    {\n      \"column\": \"car_km_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5778,\n        \"min\": 9,\n        \"max\": 19994,\n        \"num_unique_values\": 1890,\n        \"samples\": [\n          7832,\n          15149,\n          4431\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"public_transport_km_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2848,\n        \"min\": 2,\n        \"max\": 9984,\n        \"num_unique_values\": 1807,\n        \"samples\": [\n          5445,\n          6525,\n          9302\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"flights_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2,\n        \"min\": 0,\n        \"max\": 9,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          7,\n          8,\n          2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"electricity_kwh_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1443,\n        \"min\": 1004,\n        \"max\": 5995,\n        \"num_unique_values\": 1660,\n        \"samples\": [\n          3916,\n          3084,\n          2103\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"natural_gas_m3_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 860,\n        \"min\": 0,\n        \"max\": 2997,\n        \"num_unique_values\": 1448,\n        \"samples\": [\n          1283,\n          2806,\n          206\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"renewable_energy_percentage\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 29,\n        \"min\": 0,\n        \"max\": 99,\n        \"num_unique_values\": 100,\n        \"samples\": [\n          15,\n          85,\n          71\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"diet_type\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"vegetarian\",\n          \"non_vegetarian\",\n          \"vegan\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"meat_kg_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 29,\n        \"min\": 0,\n        \"max\": 99,\n        \"num_unique_values\": 100,\n        \"samples\": [\n          83,\n          77,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"waste_kg_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 265,\n        \"min\": 101,\n        \"max\": 998,\n        \"num_unique_values\": 805,\n        \"samples\": [\n          345,\n          221,\n          585\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"recycling_rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 28,\n        \"min\": 0,\n        \"max\": 99,\n        \"num_unique_values\": 100,\n        \"samples\": [\n          32,\n          38,\n          63\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"house_size_m2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 51,\n        \"min\": 20,\n        \"max\": 199,\n        \"num_unique_values\": 180,\n        \"samples\": [\n          85,\n          153,\n          146\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"num_people_household\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 1,\n        \"max\": 5,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          2,\n          1,\n          5\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"carbon_footprint_kgCO2_per_year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2425.0349473460146,\n        \"min\": 2267.62,\n        \"max\": 17301.329999999998,\n        \"num_unique_values\": 2000,\n        \"samples\": [\n          10281.315,\n          13234.246000000001,\n          11225.571\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 1
+        }
+      ],
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "\n",
+        "# Number of samples\n",
+        "n_samples = 2000\n",
+        "np.random.seed(42)\n",
+        "\n",
+        "# Generate realistic lifestyle data\n",
+        "data = {\n",
+        "    \"car_km_per_year\": np.random.randint(0, 20000, n_samples),\n",
+        "    \"public_transport_km_per_year\": np.random.randint(0, 10000, n_samples),\n",
+        "    \"flights_per_year\": np.random.randint(0, 10, n_samples),\n",
+        "    \"electricity_kwh_per_year\": np.random.randint(1000, 6000, n_samples),\n",
+        "    \"natural_gas_m3_per_year\": np.random.randint(0, 3000, n_samples),\n",
+        "    \"renewable_energy_percentage\": np.random.randint(0, 100, n_samples),\n",
+        "    \"diet_type\": np.random.choice([\"vegetarian\", \"vegan\", \"non_vegetarian\"], n_samples, p=[0.3, 0.2, 0.5]),\n",
+        "    \"meat_kg_per_year\": np.random.randint(0, 100, n_samples),\n",
+        "    \"waste_kg_per_year\": np.random.randint(100, 1000, n_samples),\n",
+        "    \"recycling_rate\": np.random.randint(0, 100, n_samples),\n",
+        "    \"house_size_m2\": np.random.randint(20, 200, n_samples),\n",
+        "    \"num_people_household\": np.random.randint(1, 6, n_samples)\n",
+        "}\n",
+        "\n",
+        "df = pd.DataFrame(data)\n",
+        "\n",
+        "# Emission factors\n",
+        "EF_CAR = 0.2             # kg CO2 per km\n",
+        "EF_PUBLIC = 0.05         # kg CO2 per km\n",
+        "EF_FLIGHT = 250          # kg CO2 per flight\n",
+        "EF_ELECTRICITY = 0.5     # kg CO2 per kWh\n",
+        "EF_NATURAL_GAS = 2       # kg CO2 per m3\n",
+        "EF_MEAT = 27             # kg CO2 per kg\n",
+        "EF_WASTE = 1.8           # kg CO2 per kg\n",
+        "\n",
+        "# Calculate emissions\n",
+        "car_emission = df[\"car_km_per_year\"] * EF_CAR\n",
+        "public_emission = df[\"public_transport_km_per_year\"] * EF_PUBLIC\n",
+        "flight_emission = df[\"flights_per_year\"] * EF_FLIGHT\n",
+        "electricity_emission = df[\"electricity_kwh_per_year\"] * EF_ELECTRICITY * (1 - df[\"renewable_energy_percentage\"]/100)\n",
+        "gas_emission = df[\"natural_gas_m3_per_year\"] * EF_NATURAL_GAS\n",
+        "\n",
+        "# Food emission (vegetarian and vegan lower)\n",
+        "meat_factor = df[\"diet_type\"].map({\n",
+        "    \"non_vegetarian\": 1.0,\n",
+        "    \"vegetarian\": 0.5,\n",
+        "    \"vegan\": 0.2\n",
+        "})\n",
+        "food_emission = df[\"meat_kg_per_year\"] * EF_MEAT * meat_factor\n",
+        "\n",
+        "# Waste emission (recycling reduces emissions)\n",
+        "waste_emission = df[\"waste_kg_per_year\"] * EF_WASTE * (1 - df[\"recycling_rate\"]/100)\n",
+        "\n",
+        "# Total carbon footprint\n",
+        "df[\"carbon_footprint_kgCO2_per_year\"] = (\n",
+        "    car_emission + public_emission + flight_emission +\n",
+        "    electricity_emission + gas_emission + food_emission +\n",
+        "    waste_emission\n",
+        ")\n",
+        "\n",
+        "# Save dataset\n",
+        "df.to_csv(\"synthetic_carbon_footprint.csv\", index=False)\n",
+        "\n",
+        "print(\"Dataset generated and saved as synthetic_carbon_footprint.csv\")\n",
+        "df.head()\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "ARRjWA_4p5VJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

src/notebooks/Running_Model.ipynb

@@ -0,0 +1,618 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.ensemble import RandomForestRegressor\n",
+        "from sklearn.metrics import mean_absolute_error, r2_score\n",
+        "import joblib"
+      ],
+      "metadata": {
+        "id": "XmGmiHQPr-WV"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 1. Load synthetic dataset\n",
+        "df = pd.read_csv(\"synthetic_carbon_footprint.csv\")"
+      ],
+      "metadata": {
+        "id": "f1oCurY6sA9N"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 2. Encode categorical column (diet_type)\n",
+        "df_encoded = pd.get_dummies(df, columns=['diet_type'], drop_first=True)"
+      ],
+      "metadata": {
+        "id": "e1AJOXchsjmN"
+      },
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 3. Separate features and target\n",
+        "X = df_encoded.drop(columns=['carbon_footprint_kgCO2_per_year'])\n",
+        "y = df_encoded['carbon_footprint_kgCO2_per_year']"
+      ],
+      "metadata": {
+        "id": "2Vhu1YrMsldt"
+      },
+      "execution_count": 7,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 4. Train/test split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
+      ],
+      "metadata": {
+        "id": "jw3t3wTUspd7"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 5. Train Random Forest model\n",
+        "model = RandomForestRegressor(n_estimators=200, random_state=42)\n",
+        "model.fit(X_train, y_train)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 80
+        },
+        "id": "B3Kh4z6osrNs",
+        "outputId": "10fad54e-7a5b-40ff-cd8f-3de1547b7034"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "RandomForestRegressor(n_estimators=200, random_state=42)"
+            ],
+            "text/html": [
+              "<style>#sk-container-id-1 {\n",
+              "  /* Definition of color scheme common for light and dark mode */\n",
+              "  --sklearn-color-text: #000;\n",
+              "  --sklearn-color-text-muted: #666;\n",
+              "  --sklearn-color-line: gray;\n",
+              "  /* Definition of color scheme for unfitted estimators */\n",
+              "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+              "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+              "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+              "  --sklearn-color-unfitted-level-3: chocolate;\n",
+              "  /* Definition of color scheme for fitted estimators */\n",
+              "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+              "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+              "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+              "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+              "\n",
+              "  /* Specific color for light theme */\n",
+              "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+              "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+              "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+              "  --sklearn-color-icon: #696969;\n",
+              "\n",
+              "  @media (prefers-color-scheme: dark) {\n",
+              "    /* Redefinition of color scheme for dark theme */\n",
+              "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+              "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+              "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+              "    --sklearn-color-icon: #878787;\n",
+              "  }\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 pre {\n",
+              "  padding: 0;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 input.sk-hidden--visually {\n",
+              "  border: 0;\n",
+              "  clip: rect(1px 1px 1px 1px);\n",
+              "  clip: rect(1px, 1px, 1px, 1px);\n",
+              "  height: 1px;\n",
+              "  margin: -1px;\n",
+              "  overflow: hidden;\n",
+              "  padding: 0;\n",
+              "  position: absolute;\n",
+              "  width: 1px;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+              "  border: 1px dashed var(--sklearn-color-line);\n",
+              "  margin: 0 0.4em 0.5em 0.4em;\n",
+              "  box-sizing: border-box;\n",
+              "  padding-bottom: 0.4em;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-container {\n",
+              "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+              "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+              "     so we also need the `!important` here to be able to override the\n",
+              "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+              "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+              "  display: inline-block !important;\n",
+              "  position: relative;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+              "  display: none;\n",
+              "}\n",
+              "\n",
+              "div.sk-parallel-item,\n",
+              "div.sk-serial,\n",
+              "div.sk-item {\n",
+              "  /* draw centered vertical line to link estimators */\n",
+              "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+              "  background-size: 2px 100%;\n",
+              "  background-repeat: no-repeat;\n",
+              "  background-position: center center;\n",
+              "}\n",
+              "\n",
+              "/* Parallel-specific style estimator block */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel-item::after {\n",
+              "  content: \"\";\n",
+              "  width: 100%;\n",
+              "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+              "  flex-grow: 1;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel {\n",
+              "  display: flex;\n",
+              "  align-items: stretch;\n",
+              "  justify-content: center;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  position: relative;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel-item {\n",
+              "  display: flex;\n",
+              "  flex-direction: column;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+              "  align-self: flex-end;\n",
+              "  width: 50%;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+              "  align-self: flex-start;\n",
+              "  width: 50%;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+              "  width: 0;\n",
+              "}\n",
+              "\n",
+              "/* Serial-specific style estimator block */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-serial {\n",
+              "  display: flex;\n",
+              "  flex-direction: column;\n",
+              "  align-items: center;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  padding-right: 1em;\n",
+              "  padding-left: 1em;\n",
+              "}\n",
+              "\n",
+              "\n",
+              "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+              "clickable and can be expanded/collapsed.\n",
+              "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+              "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+              "*/\n",
+              "\n",
+              "/* Pipeline and ColumnTransformer style (default) */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-toggleable {\n",
+              "  /* Default theme specific background. It is overwritten whether we have a\n",
+              "  specific estimator or a Pipeline/ColumnTransformer */\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "}\n",
+              "\n",
+              "/* Toggleable label */\n",
+              "#sk-container-id-1 label.sk-toggleable__label {\n",
+              "  cursor: pointer;\n",
+              "  display: flex;\n",
+              "  width: 100%;\n",
+              "  margin-bottom: 0;\n",
+              "  padding: 0.5em;\n",
+              "  box-sizing: border-box;\n",
+              "  text-align: center;\n",
+              "  align-items: start;\n",
+              "  justify-content: space-between;\n",
+              "  gap: 0.5em;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
+              "  font-size: 0.6rem;\n",
+              "  font-weight: lighter;\n",
+              "  color: var(--sklearn-color-text-muted);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+              "  /* Arrow on the left of the label */\n",
+              "  content: \"▸\";\n",
+              "  float: left;\n",
+              "  margin-right: 0.25em;\n",
+              "  color: var(--sklearn-color-icon);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "}\n",
+              "\n",
+              "/* Toggleable content - dropdown */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-toggleable__content {\n",
+              "  max-height: 0;\n",
+              "  max-width: 0;\n",
+              "  overflow: hidden;\n",
+              "  text-align: left;\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+              "  margin: 0.2em;\n",
+              "  border-radius: 0.25em;\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+              "  /* Expand drop-down */\n",
+              "  max-height: 200px;\n",
+              "  max-width: 100%;\n",
+              "  overflow: auto;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+              "  content: \"▾\";\n",
+              "}\n",
+              "\n",
+              "/* Pipeline/ColumnTransformer-specific style */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Estimator-specific style */\n",
+              "\n",
+              "/* Colorize estimator box */\n",
+              "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+              "#sk-container-id-1 div.sk-label label {\n",
+              "  /* The background is the default theme color */\n",
+              "  color: var(--sklearn-color-text-on-default-background);\n",
+              "}\n",
+              "\n",
+              "/* On hover, darken the color of the background */\n",
+              "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Label box, darken color on hover, fitted */\n",
+              "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Estimator label */\n",
+              "\n",
+              "#sk-container-id-1 div.sk-label label {\n",
+              "  font-family: monospace;\n",
+              "  font-weight: bold;\n",
+              "  display: inline-block;\n",
+              "  line-height: 1.2em;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-label-container {\n",
+              "  text-align: center;\n",
+              "}\n",
+              "\n",
+              "/* Estimator-specific */\n",
+              "#sk-container-id-1 div.sk-estimator {\n",
+              "  font-family: monospace;\n",
+              "  border: 1px dotted var(--sklearn-color-border-box);\n",
+              "  border-radius: 0.25em;\n",
+              "  box-sizing: border-box;\n",
+              "  margin-bottom: 0.5em;\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-estimator.fitted {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "/* on hover */\n",
+              "#sk-container-id-1 div.sk-estimator:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+              "\n",
+              "/* Common style for \"i\" and \"?\" */\n",
+              "\n",
+              ".sk-estimator-doc-link,\n",
+              "a:link.sk-estimator-doc-link,\n",
+              "a:visited.sk-estimator-doc-link {\n",
+              "  float: right;\n",
+              "  font-size: smaller;\n",
+              "  line-height: 1em;\n",
+              "  font-family: monospace;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  border-radius: 1em;\n",
+              "  height: 1em;\n",
+              "  width: 1em;\n",
+              "  text-decoration: none !important;\n",
+              "  margin-left: 0.5em;\n",
+              "  text-align: center;\n",
+              "  /* unfitted */\n",
+              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-unfitted-level-1);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link.fitted,\n",
+              "a:link.sk-estimator-doc-link.fitted,\n",
+              "a:visited.sk-estimator-doc-link.fitted {\n",
+              "  /* fitted */\n",
+              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-fitted-level-1);\n",
+              "}\n",
+              "\n",
+              "/* On hover */\n",
+              "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+              ".sk-estimator-doc-link:hover,\n",
+              "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+              ".sk-estimator-doc-link:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+              ".sk-estimator-doc-link.fitted:hover,\n",
+              "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+              ".sk-estimator-doc-link.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "/* Span, style for the box shown on hovering the info icon */\n",
+              ".sk-estimator-doc-link span {\n",
+              "  display: none;\n",
+              "  z-index: 9999;\n",
+              "  position: relative;\n",
+              "  font-weight: normal;\n",
+              "  right: .2ex;\n",
+              "  padding: .5ex;\n",
+              "  margin: .5ex;\n",
+              "  width: min-content;\n",
+              "  min-width: 20ex;\n",
+              "  max-width: 50ex;\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  box-shadow: 2pt 2pt 4pt #999;\n",
+              "  /* unfitted */\n",
+              "  background: var(--sklearn-color-unfitted-level-0);\n",
+              "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link.fitted span {\n",
+              "  /* fitted */\n",
+              "  background: var(--sklearn-color-fitted-level-0);\n",
+              "  border: var(--sklearn-color-fitted-level-3);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link:hover span {\n",
+              "  display: block;\n",
+              "}\n",
+              "\n",
+              "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+              "\n",
+              "#sk-container-id-1 a.estimator_doc_link {\n",
+              "  float: right;\n",
+              "  font-size: 1rem;\n",
+              "  line-height: 1em;\n",
+              "  font-family: monospace;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  border-radius: 1rem;\n",
+              "  height: 1rem;\n",
+              "  width: 1rem;\n",
+              "  text-decoration: none;\n",
+              "  /* unfitted */\n",
+              "  color: var(--sklearn-color-unfitted-level-1);\n",
+              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+              "  /* fitted */\n",
+              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-fitted-level-1);\n",
+              "}\n",
+              "\n",
+              "/* On hover */\n",
+              "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-3);\n",
+              "}\n",
+              "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(n_estimators=200, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(n_estimators=200, random_state=42)</pre></div> </div></div></div></div>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 9
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 6. Evaluate\n",
+        "y_pred = model.predict(X_test)\n",
+        "print(\"MAE:\", mean_absolute_error(y_test, y_pred))\n",
+        "print(\"R2 Score:\", r2_score(y_test, y_pred))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "W4te3CYess68",
+        "outputId": "5f64c684-7c0e-4919-bdc6-1b2cb9449db1"
+      },
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "MAE: 649.0838915624994\n",
+            "R2 Score: 0.8898286296616447\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 7. Save model to .pkl file\n",
+        "joblib.dump(model, \"carbon_model.pkl\")\n",
+        "print(\"Model saved as carbon_model.pkl\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wWhBeYS0sv7F",
+        "outputId": "ce8ee282-f8c7-4fb0-cc64-7345a4a142b1"
+      },
+      "execution_count": 11,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Model saved as carbon_model.pkl\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# 8. (Optional) Save column names for later use in Streamlit app\n",
+        "joblib.dump(X_train.columns.tolist(), \"model_columns.pkl\")\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "fQDQLIeZqiFm",
+        "outputId": "a82094cf-1f09-4c04-b5df-c13a0644b5ac"
+      },
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['model_columns.pkl']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 12
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "Weh3-Ujbr9T2"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}