{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "53ef867e-3e0b-4683-b472-145471fe2097",
      "metadata": {
        "id": "53ef867e-3e0b-4683-b472-145471fe2097"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "# **General Instructions for the ML Coding Problems**\n",
        "\n",
        "Please follow these instructions carefully to ensure a smooth evaluation process.\n",
        "\n",
        "## **1. Notebook Submission**\n",
        "- You **must** make a copy of this notebook and append your **full name** to the filename before submitting (e.g., `[OriginalNotebookName]_[YourName].ipynb`).\n",
        "- Share  your notebook copy with inaio@acmindia.org [This is for your own safety so that you do not accidentally lose any changes while editing the notebook]\n",
        "- After solving the questions, ensure you mention the correct URL of your  modified notebook in the test form\n",
        "- Also answer questions on external resources used and link to LLM chats used for each problem in the main test form\n",
        "\n",
        "## **2. Attempting the Questions**\n",
        "- Carefully **read each problem statement** before attempting.\n",
        "- **Attempt all parts** of each question.\n",
        "- Each question is organized into the following parts\n",
        "   - **DATA**, **TASK**, **HELPER CODE [Optional]** and **ANSWER**\n",
        "- **Follow the function signatures** provided. Do not modify them.\n",
        "- You only need to edit the cells in the **ANSWER** sections\n",
        "- If required, you may also add other modules under **IMPORTS** and **INSTALLATION INSTRUCTIONS**\n",
        "- Do not edit the other cells, especially those marked with **DO NOT MODIFY** which are meant for evaluation\n",
        "- You may add new cells to the notebook with extra code as desired\n",
        "  \n",
        "\n",
        "## **3. Scoring Criteria**\n",
        "Your score will be based on the following factors with distribution varying across each problem.\n",
        "- **Soundness & Creativity** of your approach.  \n",
        "  - Include a clear description and rationale of your solution methodology in the notebook (in markdown cells)\n",
        "  - Solutions that showcase your understanding of data and ML will garner more points\n",
        "- **Code Implementation & Readability**\n",
        "  - Ensure your implementation is correct and works\n",
        "  - Incomplete non-working code will be awarded  partial marks based on problem-wise rubric\n",
        "  - In case you have a solution but are unsure about some aspect, you can define a function that solves that aspect and present the rest of the solution\n",
        "  - Use comments to explain important parts of your code.\n",
        "- **Performance of Your Model**:\n",
        "  - Each task will be assessed based on specified performance metrics both on shared datasets and secret datasets\n",
        "  - Different performance ranges will receive different scores.\n",
        "  - Secret datasets used for last section will be shared along with the final results\n",
        "\n",
        "**Points associated with cells are marked at the beginning of the cell**\n",
        "    \n",
        "## **4. Dataset Usage**\n",
        "- **Only use the datasets provided** in this test.\n",
        "- Do **not** use the provided test data set for training.\n",
        "- Do **not** use external datasets for training or testing.\n",
        "- If the submitted performance metrics cannot be reproduced with your code and original datasets, then you will lose all the points associated with model performance.\n",
        "\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "65cb0461-0656-4d25-a67b-3385821ac8d9",
      "metadata": {
        "id": "65cb0461-0656-4d25-a67b-3385821ac8d9"
      },
      "outputs": [],
      "source": []
    },
    {
      "cell_type": "markdown",
      "id": "016204c1-8ed0-4105-8a3d-ea3f7757b05b",
      "metadata": {
        "id": "016204c1-8ed0-4105-8a3d-ea3f7757b05b"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "## Problem 7:  SmogCast: Forecasting Air Pollution in Bangalore & Delhi [14 pts]\n",
        "\n",
        "Air pollution is a serious problem in India, particularly in cities like Bangalore and Delhi. The levels of particulate matter (PM 2.5) are influenced by traffic volume, temperature, and fuel prices. While traffic volume directly contributes to pollution, temperature has seasonal effects, and fuel prices can change driving behavior.\n",
        "\n",
        "In this challenge, your task is to predict the particulate pollution level (PM 2.5) in two cities using historical data.\n",
        "\n",
        "This problem has 4 questions (3 to be attempted, 4th one private INAIO evaluation)\n",
        "\n",
        "-  **Q1: Smog Signals: What Drives Air Quality?** [4 pts]\n",
        "-  **Q2: Build an Air Pollution Prediction Model** [5 pts]\n",
        "-  **Q3: Test Air Pollution Prediction Model on Public Dataset** [3 pts]\n",
        "-  **Q4: Test Air Pollution Prediction Model on Private Dataset** [2 pts] [NOT FOR STUDENTS TO ATTEMPT]\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "123c5fbd-9159-42d1-a35c-550c43f68c34",
      "metadata": {
        "id": "123c5fbd-9159-42d1-a35c-550c43f68c34"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### INSTALLATION  \n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "bbe57e50-312a-4a19-82d9-74122c890673",
      "metadata": {
        "id": "bbe57e50-312a-4a19-82d9-74122c890673",
        "outputId": "b086a7fc-4291-42d0-94de-bfdf670a316b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (2.2.2)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (1.26.4)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (1.6.1)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (1.13.1)\n",
            "Collecting pygam\n",
            "  Downloading pygam-0.9.1-py3-none-any.whl.metadata (7.1 kB)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (3.10.0)\n",
            "Requirement already satisfied: seaborn in /usr/local/lib/python3.11/dist-packages (0.13.2)\n",
            "Requirement already satisfied: xgboost in /usr/local/lib/python3.11/dist-packages (2.1.4)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas) (2025.1)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas) (2025.1)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.4.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (3.5.0)\n",
            "Requirement already satisfied: progressbar2<5.0.0,>=4.2.0 in /usr/local/lib/python3.11/dist-packages (from pygam) (4.5.0)\n",
            "Collecting scipy\n",
            "  Downloading scipy-1.11.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m720.1 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (1.3.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (4.56.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (1.4.8)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (24.2)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (11.1.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (3.2.1)\n",
            "Requirement already satisfied: nvidia-nccl-cu12 in /usr/local/lib/python3.11/dist-packages (from xgboost) (2.21.5)\n",
            "Requirement already satisfied: python-utils>=3.8.1 in /usr/local/lib/python3.11/dist-packages (from progressbar2<5.0.0,>=4.2.0->pygam) (3.9.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n",
            "Requirement already satisfied: typing_extensions>3.10.0.2 in /usr/local/lib/python3.11/dist-packages (from python-utils>=3.8.1->progressbar2<5.0.0,>=4.2.0->pygam) (4.12.2)\n",
            "Downloading pygam-0.9.1-py3-none-any.whl (522 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m522.0/522.0 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading scipy-1.11.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (36.4 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m36.4/36.4 MB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: scipy, pygam\n",
            "  Attempting uninstall: scipy\n",
            "    Found existing installation: scipy 1.13.1\n",
            "    Uninstalling scipy-1.13.1:\n",
            "      Successfully uninstalled scipy-1.13.1\n",
            "Successfully installed pygam-0.9.1 scipy-1.11.4\n"
          ]
        }
      ],
      "source": [
        "!pip install pandas numpy scikit-learn scipy pygam matplotlib seaborn xgboost"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4ac8aa6b-a58f-492a-8541-cd849da6bbae",
      "metadata": {
        "id": "4ac8aa6b-a58f-492a-8541-cd849da6bbae"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### IMPORTS\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "b2593443-65dd-4769-a76a-8628d5cffdea",
      "metadata": {
        "id": "b2593443-65dd-4769-a76a-8628d5cffdea"
      },
      "outputs": [],
      "source": [
        "# EDIT: [O pts]\n",
        "# You may add any other free python packages along with comments\n",
        "\n",
        "# Data Types\n",
        "from typing import Any\n",
        "\n",
        "# Data handling\n",
        "import pandas as pd  # Data manipulation and analysis\n",
        "import numpy as np  # Numerical computations and array handling\n",
        "\n",
        "\n",
        "# Machine Learning - Process\n",
        "from sklearn.model_selection import train_test_split  # Splitting dataset\n",
        "from sklearn.pipeline import Pipeline, make_pipeline # Combining multiple processing steps\n",
        "\n",
        "# Machine Learning - Models\n",
        "from sklearn.linear_model import LinearRegression  # Simple regression model\n",
        "from sklearn.ensemble import RandomForestRegressor  # More powerful regression model\n",
        "from xgboost import XGBRegressor\n",
        "from statsmodels.tsa.statespace.sarimax import SARIMAX\n",
        "\n",
        "# Machine Learning - Feature Transformations\n",
        "from sklearn.preprocessing import OneHotEncoder, StandardScaler # Feature transformations if needed\n",
        "from sklearn.compose import ColumnTransformer #Transforming columns\n",
        "from sklearn.preprocessing import PolynomialFeatures # Polynomial features\n",
        "\n",
        "\n",
        "# Model evaluation\n",
        "from sklearn.metrics import (\n",
        "    mean_squared_error, # Mean squared Error\n",
        "    r2_score,  # R² Score\n",
        "    mean_absolute_percentage_error,  # MAPE\n",
        ")\n",
        "\n",
        "\n",
        "# Statistical Analysis\n",
        "from scipy.stats import pearsonr  # Pearson correlation coefficient\n",
        "\n",
        "\n",
        "# Visualization\n",
        "import matplotlib.pyplot as plt  # Plotting graphs\n",
        "import seaborn as sns  # Enhanced data visualization\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**COPY DATA**"
      ],
      "metadata": {
        "id": "A0tWAuQPK-EG"
      },
      "id": "A0tWAuQPK-EG"
    },
    {
      "cell_type": "code",
      "source": [
        "# Copy data\n",
        "!mkdir /content/data\n",
        "!wget https://raw.githubusercontent.com/inaiogit/stage2test/main/test/air_pollution_test_public.csv\n",
        "!wget https://raw.githubusercontent.com/inaiogit/stage2test/main/test/air_pollution_train.csv\n",
        "!mv air_pollution_test_public.csv air_pollution_train.csv data/"
      ],
      "metadata": {
        "id": "25qknD_pCCCT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0910f63d-21df-4d22-e679-eb0bbad032dd"
      },
      "id": "25qknD_pCCCT",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "mkdir: cannot create directory ‘/content/data’: File exists\n",
            "--2025-03-02 06:32:28--  https://raw.githubusercontent.com/inaiogit/stage2test/main/test/air_pollution_test_public.csv\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.110.133, 185.199.108.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 40211 (39K) [text/plain]\n",
            "Saving to: ‘air_pollution_test_public.csv’\n",
            "\n",
            "air_pollution_test_ 100%[===================>]  39.27K  --.-KB/s    in 0.05s   \n",
            "\n",
            "2025-03-02 06:32:29 (857 KB/s) - ‘air_pollution_test_public.csv’ saved [40211/40211]\n",
            "\n",
            "--2025-03-02 06:32:29--  https://raw.githubusercontent.com/inaiogit/stage2test/main/test/air_pollution_train.csv\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.109.133, 185.199.110.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 26826 (26K) [text/plain]\n",
            "Saving to: ‘air_pollution_train.csv’\n",
            "\n",
            "air_pollution_train 100%[===================>]  26.20K  --.-KB/s    in 0.02s   \n",
            "\n",
            "2025-03-02 06:32:29 (1.03 MB/s) - ‘air_pollution_train.csv’ saved [26826/26826]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "id": "9a31fe8d-7d7c-4d0d-85fc-b625fcff025c",
      "metadata": {
        "id": "9a31fe8d-7d7c-4d0d-85fc-b625fcff025c"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### **Q1: Smog Signals: What Drives Air Quality?** [4 pts]\n",
        "\n",
        "Before building a predictive model, it is  crucial to explore the data to uncover patterns, relationships, and anomalies\n",
        "to build an appropriate model. This is especially important for time-series data.\n",
        "\n",
        "\n",
        "</div>\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "f738630c-e2e4-4d33-84da-37b9dd026366",
      "metadata": {
        "id": "f738630c-e2e4-4d33-84da-37b9dd026366"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "\n",
        "### DATA\n",
        "\n",
        "You are provided with a **historical dataset** containing weekly observations of **air pollution, temperature, traffic volume, and fuel prices** for two major Indian cities:\n",
        "\n",
        "- **`air_pollution_train_path`**: historical data (each row corresponds to entries of a particular week)\n",
        "\n",
        "**Columns**\n",
        "- **`Week`** - Week index starting from the first week of observation (across multiple years)\n",
        "- **`Particulate_Level_Bangalore`** – PM2.5 pollution level in Bangalore *(Target Variable)*\n",
        "- **`Temperature_Bangalore`** – Weekly average temperature in Bangalore (°C)\n",
        "- **`Avg_Vehicle_Volume_Bangalore`** – Number of vehicles on Bangalore roads per week\n",
        "- **`Particulate_Level_Delhi`** – PM2.5 pollution level in Delhi *(Target Variable)*\n",
        "- **`Temperature_Delhi`** – Weekly average temperature in Delhi (°C)\n",
        "- **`Avg_Vehicle_Volume_Delhi`** – Number of vehicles on Delhi roads per week\n",
        "- **`Petrol_Price`** – Weekly fuel price per liter (INR), common to both cities\n",
        "\n",
        "\n",
        "\n",
        "</div>\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "109bde31-5c49-4618-a648-5b8e6bb7abc0",
      "metadata": {
        "id": "109bde31-5c49-4618-a648-5b8e6bb7abc0"
      },
      "outputs": [],
      "source": [
        "# Training datasets\n",
        "air_pollution_train_path = \"data/air_pollution_train.csv\"  # historical air pollution and related factors data\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "c8a75ea1-4c6b-4959-97a2-97801615682f",
      "metadata": {
        "id": "c8a75ea1-4c6b-4959-97a2-97801615682f"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### TASK\n",
        "\n",
        "Analyze the data and record your observations below:\n",
        "   - (a) Is there a correlation between Particulate_Level_Bangalore and Particulate_Level_Delhi ? **(Answer Yes/No and explain)**\n",
        "   - (b) What is the relationship between Particulate Level, Temperate and Average Vehicle Volume in a particular city ? **Justify with observations**   \n",
        "   - (c) How does Petrol Price impact Particulate Levels? **Justify with observations**   \n",
        "\n",
        "</div>\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "e1c7a7db-40a0-4d6c-a1ae-e62a5ea95d9f",
      "metadata": {
        "id": "e1c7a7db-40a0-4d6c-a1ae-e62a5ea95d9f"
      },
      "source": [
        "<div style=\"color:red\">\n",
        "    \n",
        "### ANSWER\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "0d984777-5591-4f49-be3b-a9a987ba6116",
      "metadata": {
        "id": "0d984777-5591-4f49-be3b-a9a987ba6116",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 226
        },
        "outputId": "0c0d9696-52c6-4ec7-e543-3683b5995fc6"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Week  Particulate_Level_Bangalore  Temperature_Bangalore  \\\n",
              "0     1                   203.696673              23.884332   \n",
              "1     2                   208.125742              22.817158   \n",
              "2     3                   212.705955              21.644363   \n",
              "3     4                   199.623883              24.049248   \n",
              "4     5                   215.323311              21.493527   \n",
              "\n",
              "   Avg_Vehicle_Volume_Bangalore  Particulate_Level_Delhi  Temperature_Delhi  \\\n",
              "0                  96203.303977               226.544283          10.777520   \n",
              "1                  98880.549229               229.993222          12.048196   \n",
              "2                 105168.012767               229.692853          12.432674   \n",
              "3                 106155.758951               236.570809          12.885539   \n",
              "4                 100747.781568               246.417325          12.248691   \n",
              "\n",
              "   Avg_Vehicle_Volume_Delhi  Petrol_Price  \n",
              "0             115113.276472     82.353010  \n",
              "1             115914.966287     83.089090  \n",
              "2             115896.557377     82.694740  \n",
              "3             123828.331536     84.657543  \n",
              "4             120127.730839     83.960813  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-afd86c51-bee4-402e-b678-db89d2880036\" 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>Week</th>\n",
              "      <th>Particulate_Level_Bangalore</th>\n",
              "      <th>Temperature_Bangalore</th>\n",
              "      <th>Avg_Vehicle_Volume_Bangalore</th>\n",
              "      <th>Particulate_Level_Delhi</th>\n",
              "      <th>Temperature_Delhi</th>\n",
              "      <th>Avg_Vehicle_Volume_Delhi</th>\n",
              "      <th>Petrol_Price</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>203.696673</td>\n",
              "      <td>23.884332</td>\n",
              "      <td>96203.303977</td>\n",
              "      <td>226.544283</td>\n",
              "      <td>10.777520</td>\n",
              "      <td>115113.276472</td>\n",
              "      <td>82.353010</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>208.125742</td>\n",
              "      <td>22.817158</td>\n",
              "      <td>98880.549229</td>\n",
              "      <td>229.993222</td>\n",
              "      <td>12.048196</td>\n",
              "      <td>115914.966287</td>\n",
              "      <td>83.089090</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>212.705955</td>\n",
              "      <td>21.644363</td>\n",
              "      <td>105168.012767</td>\n",
              "      <td>229.692853</td>\n",
              "      <td>12.432674</td>\n",
              "      <td>115896.557377</td>\n",
              "      <td>82.694740</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>199.623883</td>\n",
              "      <td>24.049248</td>\n",
              "      <td>106155.758951</td>\n",
              "      <td>236.570809</td>\n",
              "      <td>12.885539</td>\n",
              "      <td>123828.331536</td>\n",
              "      <td>84.657543</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>215.323311</td>\n",
              "      <td>21.493527</td>\n",
              "      <td>100747.781568</td>\n",
              "      <td>246.417325</td>\n",
              "      <td>12.248691</td>\n",
              "      <td>120127.730839</td>\n",
              "      <td>83.960813</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-afd86c51-bee4-402e-b678-db89d2880036')\"\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-afd86c51-bee4-402e-b678-db89d2880036 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-afd86c51-bee4-402e-b678-db89d2880036');\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-4d2fe1d1-f207-4fc4-8463-41f3830e4624\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-4d2fe1d1-f207-4fc4-8463-41f3830e4624')\"\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-4d2fe1d1-f207-4fc4-8463-41f3830e4624 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": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 200,\n  \"fields\": [\n    {\n      \"column\": \"Week\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 57,\n        \"min\": 1,\n        \"max\": 200,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          96,\n          16,\n          31\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Particulate_Level_Bangalore\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 7.284182153233355,\n        \"min\": 185.47128094566665,\n        \"max\": 227.17343859293248,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          211.8846335873002,\n          201.7114669282459,\n          188.92769080831508\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Temperature_Bangalore\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.361883484765286,\n        \"min\": 20.16015246898713,\n        \"max\": 30.116772931868987,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          23.21860713178892,\n          25.49690574261345,\n          28.782660256629235\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Avg_Vehicle_Volume_Bangalore\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6561.011414149862,\n        \"min\": 92125.76749583655,\n        \"max\": 124237.3114666228,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          115230.58058648033,\n          102801.63902260084,\n          100780.17099469942\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Particulate_Level_Delhi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12.699686678010414,\n        \"min\": 192.51492532727227,\n        \"max\": 250.43702640983008,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          229.02339349867563,\n          218.5858465094802,\n          208.36225674941852\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Temperature_Delhi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5.745071683289765,\n        \"min\": 9.600097169059412,\n        \"max\": 29.41422570797806,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          17.9986952931439,\n          21.614280484522503,\n          26.048072732824973\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Avg_Vehicle_Volume_Delhi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 8051.56797107491,\n        \"min\": 106533.2002332192,\n        \"max\": 148892.4095476813,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          140309.28047017337,\n          123502.45883793251,\n          122488.5010343331\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Petrol_Price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.9704703620455513,\n        \"min\": 82.11081303732122,\n        \"max\": 91.146604676838,\n        \"num_unique_values\": 200,\n        \"samples\": [\n          85.46164029721946,\n          85.17006892355938,\n          86.32225484214632\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "# EDIT: [1 pt]\n",
        "# Add your data exploration code here\n",
        "data = pd.read_csv(air_pollution_train_path)\n",
        "data.head()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "swpfXHWnj2Nl",
        "outputId": "77203605-fea0-4ff3-a189-d704de122818"
      },
      "id": "swpfXHWnj2Nl",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 200 entries, 0 to 199\n",
            "Data columns (total 8 columns):\n",
            " #   Column                        Non-Null Count  Dtype  \n",
            "---  ------                        --------------  -----  \n",
            " 0   Week                          200 non-null    int64  \n",
            " 1   Particulate_Level_Bangalore   200 non-null    float64\n",
            " 2   Temperature_Bangalore         200 non-null    float64\n",
            " 3   Avg_Vehicle_Volume_Bangalore  200 non-null    float64\n",
            " 4   Particulate_Level_Delhi       200 non-null    float64\n",
            " 5   Temperature_Delhi             200 non-null    float64\n",
            " 6   Avg_Vehicle_Volume_Delhi      200 non-null    float64\n",
            " 7   Petrol_Price                  200 non-null    float64\n",
            "dtypes: float64(7), int64(1)\n",
            "memory usage: 12.6 KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "plt.scatter(data.Particulate_Level_Bangalore,data.Particulate_Level_Delhi)\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "4KjnDSrbj5vK"
      },
      "id": "4KjnDSrbj5vK"
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(data.Particulate_Level_Bangalore,data.Particulate_Level_Delhi)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "anFLkihWkFnE",
        "outputId": "cdc210c6-df4a-495d-83ba-33e445536359"
      },
      "id": "anFLkihWkFnE",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(data.Avg_Vehicle_Volume_Bangalore,data.Particulate_Level_Bangalore)\n",
        "plt.show()\n",
        "\n",
        "plt.scatter(data.Avg_Vehicle_Volume_Bangalore,data.Temperature_Bangalore)\n",
        "plt.show()\n",
        "\n",
        "plt.scatter(data.Particulate_Level_Bangalore,data.Temperature_Bangalore)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "zDy81kE9kOfR",
        "outputId": "a5c3831b-97c5-436b-f35a-b01949d834b4"
      },
      "id": "zDy81kE9kOfR",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(data.Avg_Vehicle_Volume_Delhi,data.Particulate_Level_Delhi)\n",
        "plt.show()\n",
        "\n",
        "plt.scatter(data.Avg_Vehicle_Volume_Delhi,data.Temperature_Delhi)\n",
        "plt.show()\n",
        "\n",
        "plt.scatter(data.Particulate_Level_Delhi,data.Temperature_Delhi)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "WxHHMANxks9B",
        "outputId": "3e016347-4a29-4d76-897c-ac40672ed950"
      },
      "id": "WxHHMANxks9B",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAGdCAYAAADuR1K7AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAUxBJREFUeJzt3X90VOWdP/D3BJIQQjIQIEyQH6Zo0RgKShEilLU0htj4A0uPFQW1x2KliRXpUoorVeS7RmzPWreiVtaFdingukdEEdMNRqFokBWIEkAqFEElA0hgBiMkkHm+f6QzZML8uL/vc++8X+dwDsncmdy5d+Y+n/s8n+fzeIQQAkREREQukWb3DhAREREZicENERERuQqDGyIiInIVBjdERETkKgxuiIiIyFUY3BAREZGrMLghIiIiV2FwQ0RERK7S3e4d0CIUCuHw4cPIycmBx+Oxe3eIiIhIASEETp06hYEDByItzbz+FUcGN4cPH8bgwYPt3g0iIiLS4LPPPsOgQYNMe31HBjc5OTkAOg5Obm6uzXtDRERESgSDQQwePDjSjpvFkcFNeCgqNzeXwQ0REZHDmJ1SwoRiIiIichUGN0REROQqDG6IiIjIVRjcEBERkaswuCEiIiJXYXBDRERErsLghoiIiFyFwQ0RERG5iiOL+BGR+dpDAlsPNOPoqTPIz+mBqwvz0C2Na7kRkfwY3BDRBWoam7Dw9d1oCpyJ/K7A2wOP3FiE8uICG/eMiCg5DksRUZSaxibMWrE9KrABAH/gDGat2I6axiab9oyISBkGN0QU0R4SWPj6bogYj4V/t/D13WgPxdqCiEgOqoKb6upqjBkzBjk5OcjPz8eUKVOwd+/eqG2uvfZaeDyeqH/33Xdf1DaHDh1CRUUFevbsifz8fMydOxfnzp3T/26ISJetB5ov6LHpTABoCpzB1gPN1u0UEZFKqnJuNm7ciMrKSowZMwbnzp3DQw89hLKyMuzevRvZ2dmR7WbOnInHHnss8nPPnj0j/29vb0dFRQV8Ph/ee+89NDU14c4770R6ejoef/xxA94SEWl19FT8wEbLdkREdlAV3NTU1ET9vHz5cuTn52Pbtm2YOHFi5Pc9e/aEz+eL+Rr/+7//i927d2PDhg0YMGAARo0ahUWLFmHevHl49NFHkZGRoeFtEJER8nN6GLodEZEddOXcBAIBAEBeXl7U7//85z+jX79+KC4uxvz58/H1119HHquvr8eIESMwYMCAyO8mT56MYDCIXbt2xfw7ra2tCAaDUf+IyHhXF+ahwNsD8SZ8e9Axa+rqwrw4WxAR2U9zcBMKhTB79myMHz8excXFkd/ffvvtWLFiBd5++23Mnz8f//Vf/4Xp06dHHvf7/VGBDYDIz36/P+bfqq6uhtfrjfwbPHiw1t0mogS6pXnwyI1FAHBBgBP++ZEbi1jvhoikprnOTWVlJRobG7F58+ao3997772R/48YMQIFBQX43ve+h/3792PYsGGa/tb8+fMxZ86cyM/BYJABDpFJyosL8Nz0qy6oc+NjnRsicghNwU1VVRXWrVuHTZs2YdCgQQm3HTt2LABg3759GDZsGHw+H7Zu3Rq1zZEjRwAgbp5OZmYmMjMztewqEWlQXlyA64p8rFBMRI6kalhKCIGqqiqsWbMGdXV1KCwsTPqchoYGAEBBQcfdXklJCXbu3ImjR49GtqmtrUVubi6KiorU7A4Rmahbmgclw/ri5lEXoWRYXwY2ROQYqnpuKisrsXLlSqxduxY5OTmRHBmv14usrCzs378fK1euxPe//3307dsXH330ER588EFMnDgR3/rWtwAAZWVlKCoqwowZM/Dkk0/C7/fj4YcfRmVlJXtniIiISDePEEJxqVGPJ/ad27Jly3D33Xfjs88+w/Tp09HY2IiWlhYMHjwYt9xyCx5++GHk5uZGtj948CBmzZqFd955B9nZ2bjrrrvwxBNPoHt3ZbFWMBiE1+tFIBCIel0iIiKSl1Xtt6rgRhYMboiIiJzHqvaba0sRERGRqzC4ISIiIlfRXOeGiIhSV3tIsFQASYvBDRERqVLT2HRBkccCFnkkiXBYioiIFKtpbMKsFdujAhsA8AfOYNaK7ahpbLJpz4jOY3BDRESKtIcEFr6+G7Gm2IZ/t/D13WgPOW4SLrkMh6WIyDGY52GvrQeaL+ix6UwAaAqcwdYDzSgZ1jfudjyPZDYGN0TkCMzzsN/RU/EDG6Xb8TySFTgsRUTSY56HHPJzeujajueRrMLghsgg7SGB+v3HsbbhC9TvP868A4Mwz0MeVxfmocDbA/EGkDzo6IW5ujDvgsd4HslKHJYiMgC72s1jVJ4H6dctzYNHbizCrBXb4QGiApVwwPPIjUUx82d4HslK7Lkh0old7eZSm+fBHjRzlRcX4LnpV8HnjR568nl74LnpV8UN5o3I1yFSij03RDok62r3oKOr/boiH2eDaKQmz4M9aNYoLy7AdUU+VTOe9ObrEKnBnhsiHdR0tZM2SvM8TrS0sQfNQt3SPCgZ1hc3j7oIJcP6Jg3e9eTrEKnF4IZIB3a1my+c5wHggoYx/POCisux6A0mq8pMyXmMl69DpBaDGyId2NVujWR5Hn2yM9mD5gBa83WI1GLODZEO4a52f+BMzF4DDzou3Oxq1y9Rnsfahi8UvQZ70OynJV8nFbGKsz4Mboh00DM1ltQL53l0xR40Z4l3HqkDE+P147AUkU7sarcfk1XJLVhawhjsuSEyALva7cUeNHIDlpYwDntuiAyidmosGYs9aOR0LC1hHPbcEJFrsAeNnIylJYzD4IaIXIXJquRUTIw3DoeliIiIJMDEeOMwuCEikhgXAk0drOJsHA5LERFJivVOUk84Mb7reffxvKviEUI47jYgGAzC6/UiEAggNzfX7t0hIjJcuN5J1wt0+J6dM8Dcza0Viq1qv9lzQ0QkGdY7ISbG68OcGyIiybDeCZE+DG6IiCTDeidE+jC4ISKSDOudEOnD4IaISDKsd0KkD4MbIiLJsN4JkT4MboiIJMSFQIm041RwIkpJTqgjwoVAibRhcENEUrAy2HBS5V876504IQB0Gx5zYzC4ISLbWRlsxKv86w+cwawV2znk8w9WB4Bs1J0VdMuOyy8Qka3ULjOgpxFsDwlMWFwXt0CeBx05LZvnTUq5hrWzZOdkye1XoU92hmGBCBv11Flug8svEJHrqV1mQG8jqKbyr9ahIKf3QCQ7JwBQtWo7Oi9OricQYU8al9swA4MbIrKNmmAjcLpNdyOotKKvP3gG9fuPqw5QZO6BUBp0JTsnAKICG0B7IMJGvYMVQXeqYXBDRLZRE2w8WfOx7kZQaUXfRet2obnlbORnJQGKzD0QaoIuLUs6aA1E2Kh34HIbxmOdGyIyVXtIoH7/caxt+AL1+4+jvdNtv9Jgo/mrVkMWkkxW+Tfy9zoFNsD5AKWmsSnm9kqGcha+vjvqvVslHHR1PX7x3pPWJR20LObJRr0Dl9swHoMbIjJNTWMTJiyuw7SlW/DA6gZMW7oFExbXRRpUpcsM5GVnKPp7yRpBJZV/Y0kWoBi5ineiYFAtLUGX0gAwHjWBCBv1Dlxuw3gMbojIFEp6DJQuM+DzZin6m0oawXiVf5MFUIkCFKN6IJIFg2ppCboSnRMl1AQibNQ7cLkN4zG4ISLDqekxULLMgNGNYHlxATbPm4RVM8fh6dtGYdXMcXi44nJFz40VoBjRA6F2+EgJrUFXvHPiSdC2aglE2Kifx+U2jMWEYiIynNpE0WTLDIQbwVkrtsMDRAVNWhvBrpV/6/cfV/S8WAFKOPjyB87EDOjC9XPiNfxmzRrSE3SVFxcgFBJ4eG1jJAcpXlU0PYFIuFHvmvDsk2SWmZW43IZxGNwQkeFqd/sVbde5xyDZMgNmN4J6AhS9wZdZs4b0vKeaxiZUrtwR83ld6T0HbNTPs3O5DTdRNSxVXV2NMWPGICcnB/n5+ZgyZQr27t0bc1shBK6//np4PB68+uqrUY8dOnQIFRUV6NmzJ/Lz8zF37lycO3dO85sgSmVGJqAaoaaxCf/57qeKtu3cY6DkfcQaTto8b5Ihd/d6h0j0DCuYNWtI63tK1JMUlpedjqd+ZNw5CDfqN4+6CCXD+qZkYEPGUdVzs3HjRlRWVmLMmDE4d+4cHnroIZSVlWH37t3Izs6O2vZ3v/sdPDEGaNvb21FRUQGfz4f33nsPTU1NuPPOO5Geno7HH39c37shSjGyFY0LN4pKdM7PUPM+zLyz1ds7pKQHIlYxPTNnDWl5T0oK+TW3nIUvt4djehmcXjma1NG1ttSxY8eQn5+PjRs3YuLEiZHfNzQ04IYbbsAHH3yAgoICrFmzBlOmTAEAvPnmm7jhhhtw+PBhDBgwAADw/PPPY968eTh27BgyMpJP+eTaUkRyrkVTv/84pi3domjb5/+xf3a9j0SNnVkNYbwgbkHF5Vj0xp6kw0d61rxS857WNnyBB1Y3JH3Np28bhZtHXaRpf6wk201AIm4PwhyxtlQgEAAA5OWdH6/9+uuvcfvtt2PJkiXw+XwXPKe+vh4jRoyIBDYAMHnyZMyaNQu7du3ClVdeecFzWltb0draGvk5GAzq2W0ix5O1bL3SYZN7xl+M8uIC295HssbOjN6hRBWMK1fuwL0TC/HCpgOGJUx3peY9uan+jIyVo+MFME4KwmSneSp4KBTC7NmzMX78eBQXF0d+/+CDD+Kaa67BzTffHPN5fr8/KrABEPnZ74+dhFhdXQ2v1xv5N3jwYK27TeQKRhaNM5LSxq60qOPGx473YcaU62SUTI1/7cMmLLldjqnAbqk/I2Pl6Hi1jKrX77b8c+lmmntuKisr0djYiM2bN0d+99prr6Gurg47duwwZOfC5s+fjzlz5kR+DgaDDHAopclatl7t7Byr3kf4TtkfOI1Fb+yxvKdIaRDXJzsDm+dNUp2zY3TvnBlT7+0g29pViXqR/rDpQNx9TJUFRI2kKbipqqrCunXrsGnTJgwaNCjy+7q6Ouzfvx+9e/eO2n7q1Kn4zne+g3feeQc+nw9bt26NevzIkSMAEHMYCwAyMzORmZmpZVeJXEnWYQO1jaIV7yNWV388ZjV2aoK4RMNHVg5buKH+jEw3AUp6keJJlQVEjaQquBFC4P7778eaNWvwzjvvoLCwMOrxX/3qV/jJT34S9bsRI0bgqaeewo033ggAKCkpwb/+67/i6NGjyM/PBwDU1tYiNzcXRUVFet4LUcrQWzTOTGoaRbPfR7w75WSMbuyMrGBsZe6I0+vPyHQToGQGWjJuX0DUSKqCm8rKSqxcuRJr165FTk5OJEfG6/UiKysLPp8vZu/LkCFDIoFQWVkZioqKMGPGDDz55JPw+/14+OGHUVlZyd4ZIoVkHzZQ2iia+T6U1GqJJ15jp3VIKFkQBwB9szMwemifuH9XSe6IGcMWTi4qZ8dNQLzPiBGBiRMSuGWhKrh57rnnAADXXntt1O+XLVuGu+++W9FrdOvWDevWrcOsWbNQUlKC7Oxs3HXXXXjsscfU7ApRypN92EBpo2jW+9Byp5ysYq/WIaFEQVzY8ZY2/NNv3o75ekreS1PgDJ6p+wQPlH4z4XZqOH1astU3AYk+I3oCEzt7Yp1KV50bu7DODdF5Tm+Awox+H0prtYQlqquz/qPD+NnKCydKqK3Fkyz/J97rqXkvzxs0POWmaclWvJdk9ZqW3H5lwlpG8dhZt8oMVrXfDG4oJbklIKD41BQUBOI3dus/akLVqu2IN1tYbYG9tnMhjKveEFmMUsnrqXkvBTqL/QFyFojUy8zvfHtIYMLiuoRBq8/bAwsqilC5cjuA2L1I904sxGsfNrkioIzHEUX8iLSyM7hw0x0pxackzyUvOx0LbrgCvtzYn8Gaxib87B+NUTxqZ7JsO3gibmAT7/XC70XJMJveWTWyFoiMRc11xMzcITVT/ZMNwf6y/HLeeBmAwQ1Zzs7gQsZqpWQOJfkWj98yIu75VrNOFmD8tOOuK6Y/cmMR7luRONBS+zdika02TDwy3aSoOac3j7ooYbK9kxO4ZaK5QjGRFnZUhw0zo1qpbCtyUzQ9K3WrTUg2etpx1+3KiwvwoMJkYT3Jq2qDLzu+A3ZeR2JRe065Arr52HNDlrG7u9voO1KZ7hwpPq21WtT0fqhZiuDqwjz4cjPhD7bGfDzRzJiqSZdg1daDCZ87IDcTISGwtuEL5Of0wOihfbDt4AnF711NQ23Hd8Du60gsMtedSlUMbsgydnd3GzlswOEtZ9HS1a+m90PNdOLa3X6cOReK+Viy6cnd0jx49KYrMGtF7KRUAeDMuRDu+I/3I79P8yAqGTpZ8KG0oT7R0obKldZ/B+y+jsQie92pVMRhKbKM3aXQjRo2kHExPhm4bYgu2eKRQEfg8OztVypuxMNB8cmvYycUe3umJw0K4g21eXumA8AFr931NCQbugk31AAueO/hnxdUXI5Fb+j/Dmj5zNh1HUm2r3qGQMl47Lkhy9hdCt2ormMZ7xzt5sYhOiWF956ZdhW+/y1l709JxeSs9G64rij2GnuddR1q65ediV+8/CGA+LOwwpQM3SQrrOjNytD9HdD6mbHjOqJ0X52+XIWbsOeGLJPsTtgDdbkLaim5I1XSdWx3D5RWZvWsyJbcaaR4d+MF3h54frrywAZQXmV464FmRa/XOSk1Lc0Df1D5561z8BFPeXEBNs+bhFUzx+Hp20Zh1cxx2DxvEsqLC3R/B/R8Zqy+jqjdVyYLy4E9N2QZGcaljSj1b3cPlBZm9azYndxpRb0ko+7GzQyKtQbSyZ4XL1dJz3dA72fGyuuI3Z9v0o7BDVlKhvWQ9DZWTpsZYWbys51DdFYOhRlRe8TMoFhrIK31eXq+A0Z8Zqy6jnAI2rkY3JDlZBiX1tNY2d0Dpaa3wuw7T7uG6JwwW63reRo9tI/uoDjeuVdSjVnt30pEz3fAqM+MFdcRpw5BE4MbsonTq3Da1QOltrfC7DtPO4bonDBUEO883TSyAC9sOqApKE527pMlP6v5W0po/Q4Y+Zkx4jqS6GbBiUPQ1IHBDZFGVvdAaemtMPvO044hOrMCNqPydxKdpxc2HYi5OGKygEDpuY8VbHStc2NkAK7lOyDTsG6ygFGmfSV1GNwQ6WBVD5TW3gqz7zztGKIzI2AzKn9HyXl67cMmbJz7XcVVg9Wc+1jBhtoKxWqp/Q7YPawbpjRglGFfST1OBSdyADW9FZ1ZMW3W6uJlRgdsRk5lV3qeth08gasL85Cf0wNHT3Wct3hT89We+65TkTO6p0k3NdnugndqCnHava+kDXtuiBxAa29FskJ0AsBtYwbr3j8rh+iMHCowOn9H6Xmq3e3HnP9uUNRT5NakVjsnFqgd2pRhEgSpw54bIgfQ01sR784z7KkNn2DC4jrdxfasKl5mVDFGQHuPWLyCiErP03+++6niniI3J7XaVfBOS8DI4nzOwuCGyAH0Di+Fq80+WPrNmI87rZqwUUMFWhq5msYmTFhch2lLt+CB1Q2YtnRLJDhUuh5VLPHWZLK7srcbuTlgpA4MbogcwKjeitX/dyjm75244Gei5QGUUtvIJcvPqd3tT3qeEh3eWD1FRvZUUQcGjO7H4IbIIfT2VmgdgpGZ3qECNY2c0iTU64p8cc/TPeMvVrRfXXuUmNRqLAaM7seEYiIH0ZPY6ITEVCvWiupMzbTk+v3HFQeH8c7T1gPNePHdT5PuV7zcKSa1GkeGpWDIPAxuiBxGa20d2fMMrFwrqjOljZza4DDWedI708vplb1lw4DRvRjcEKUImaut2r1WlJJGzojgUJYCdnQeA0Z3Ys4NUYqQNc9ATUE1MyXL3zEqCVVN/ky8KedK6X0+kVOx54YohciYZ2D24p5GMbLXRUlPkd5hOruG+Yhk4BFCOC6UDwaD8Hq9CAQCyM3NtXt3iBzH6sTdRNY2fIEHVjck3e7p20bh5lEXmb9DSVgRNMQbpgufoWTDdHqfT2QWq9pv9twQpSCz8wzUBE+yJzp3ZXYSqt4lIYxeUoLIiRjcEJGh1PZsyJzoHI+ZwaHeYTqnDPMRmYkJxURkGC0rbMua6GwXvfWI9D6fScjkBuy5ISJD6BkOkTHR2S56h+n0PJ9JyOQWDG6IyBB6h0NYUK2D3mE6rc+3u9YQkZE4LEVEhjBieQe9a0U5RaKhH73DdFqeL0utISKjsOeGiAzhtFlPSpgxZV7J0I/eYTq1z2cSMrkNgxsiMoQTZz0lYkb+iZqhH73DdGqe74RFVYnU4LAUERnCTbOetMz6SkbL0I/eYTqlz3djrxulNgY3RGQYNesmycqs/BM1Qz9WM2rdLCJZcFiKiAzl9FlPZuWfyDz047TVymVaPsRqqfze1WBwQ0SGM3t5BzOZFYTIPvTjlFpDqVyLJ5Xfu1oMboiIOjErCHFCwrXsvW6pXIsnld+7Fsy5ISLqxKz8E6ckXMtaayhZLpQA8C9rGtF2LmTxnpmPdYjUY3BDZAGu1yOfeOfEzCDEDQnXdkmWCwUAx1vaMK56g6bZbDKTORldVhyWIjIZx8mNYWQiZbJzYmb+iexDP7JSmuPU3HLWdcM0Miejy4rBDZGJOE5uDCMDRKXnxMwgxMkJ13ZRm+MUb5FWJ5I9GV1GHJYiMgnHyY1hZEE9tedE1vyTVJQsF6oztw3TsA6RegxuiEzCcXL9jA4QeU6cq3MulFJuGaZxSjK6TBjckLScnoSb6uPkRpw/o4ORVD8nThfOhcrLzlC0fbxhGideW5iMro6qnJvq6mq88sor+Pjjj5GVlYVrrrkGixcvxvDhwyPb/PSnP8WGDRtw+PBh9OrVK7LNZZddFtnm0KFDmDVrFt5++2306tULd911F6qrq9G9O1OAqIMbknBTeZzcqPNndDCSyufECZQkjZcXF2DSZQMwrnoDmlvOxnydRDWDnHxtYTK6cqp6bjZu3IjKykps2bIFtbW1OHv2LMrKytDS0hLZZvTo0Vi2bBn27NmDv/zlLxBCoKysDO3t7QCA9vZ2VFRUoK2tDe+99x7++Mc/Yvny5fj1r39t7Dsjx6ppbMJ9Bi9aaIdUHSc3MkfG6GAkVc+JE9Q0NmHC4jpMW7oFD6xuwLSlWzBhcV3Mz0tG9zQ8fssIeKBumMaMBVGtxjwwZTxCCM39cceOHUN+fj42btyIiRMnxtzmo48+wsiRI7Fv3z4MGzYMb775Jm644QYcPnwYAwYMAAA8//zzmDdvHo4dO4aMjOTdjcFgEF6vF4FAALm5uVp3nyTUHhIY/f9qcfLrxHdkm+dNcsSXOnwxBWKv1+O27uT2kMCExXVxh5LUnr/w6yWr6qvm85Bq58QJ4s1gS3ZO1PTCGP3ZJG2sar915dwEAgEAQF5e7LuclpYWLFu2DIWFhRg8eDAAoL6+HiNGjIgENgAwefJkBINB7Nq1K+brtLa2IhgMRv0jd3qmbl/cwAZwXsJnqo2TK82RWf7uAUX5DmYkUqbaOZGdnqTx8uICbJ43CatmjsPTt43CqpnjsHnepJjnkMnkqUVzkksoFMLs2bMxfvx4FBcXRz327LPP4pe//CVaWlowfPhw1NbWRnpk/H5/VGADIPKz3++P+beqq6uxcOFCrbtKDtEeElj27gFF2zop4TOVxsk37I79He5q0Rt7Iv9Plu9gRkG9VDonsumaVxMKCV2rsCutGcRk8tSiObiprKxEY2MjNm/efMFjd9xxB6677jo0NTXht7/9LW699Va8++676NFDW5Le/PnzMWfOnMjPwWAw0hNE7rH1QDNOno7fa9OZ0xI+U6FoW01jE15891PVz1NS0NCMYES2c2JkBWZZxRpG6p2Vrui57+77UtexYTJ5atEU3FRVVWHdunXYtGkTBg0adMHjXq8XXq8Xl156KcaNG4c+ffpgzZo1mDZtGnw+H7Zu3Rq1/ZEjRwAAPp8v5t/LzMxEZmamll0lB1F6x9Q7K50Jn5IJDy1oIdAxxJSsoqxswYiRnDiDR20wFi+vRukNzTNv74v8X8uxccKq7GQcVTk3QghUVVVhzZo1qKurQ2FhoaLnCCHQ2toKACgpKcHOnTtx9OjRyDa1tbXIzc1FUZG6Ak3kLkrvmH48/mLX3dE6nZJFDROxMt9BthonTpzBo2ZmE5A4r0YLLcemW5oHCyqK4gY2AAvhuYmqnpvKykqsXLkSa9euRU5OTiRHxuv1IisrC3//+9/x0ksvoaysDP3798fnn3+OJ554AllZWfj+978PACgrK0NRURFmzJiBJ598En6/Hw8//DAqKyvZO5Pikt1ZAUCfnumomnSppfvlZkYNhRiVp2B2voNsPSTJkmmV9GhZTct6aXqD3660HJuaxiYseiN276IRC6KSXFT13Dz33HMIBAK49tprUVBQEPn30ksvAQB69OiBv/71r/j+97+PSy65BD/60Y+Qk5OD9957D/n5+QCAbt26Yd26dejWrRtKSkowffp03HnnnXjssceMf3fkKIlmxoR/V/2DEdJc5J1O7d13IkblKZiZ7yBjD4lsM3iS9WppndmkZshZKTXHJt65D1tQcTkDG5dR1XOTrCTOwIEDsX79+qSvM3ToUEXbUeqJNzNG9vwDpzF6tXIl+QweD5BoBMjM4nmy9pDININHSa+WmmCsc36U0qB1yR1XIc3jwdFTZ/DJkVN45u39SZ+T7NgkGxLzoGP23uTiAt44uQjXOyDpuGWarqyzX8xo6MO9brNWbIcHsYvjzfxOIV7YdCBuI3PTSPMaF62NstlkmcGjNNjVGowpTeYd943zFXfr9x9XFNwkOzaynnsyF4MbkpJZM2OsCjhky+3ozKyLvdJ6NH/YFLuW0QubDuDKIX1MOT4y9ZB0JsMMnvaQwKOv7VIU7GoNxpQEv12TeY06NrKeezIXgxtKGVYFHEYP+RjNzIt9ol639pDAax8mzmsxa2hIlh4S4MIAe0FFESpXKm/0jfZM3T74g61xH+8c7OoJONQWY+wcEMXbLyW9fTKde7IOgxtKCVYFHLLmdnRm9sU+Xq+bncMDMvSQAPED7HsnFuK1D5sMq8DcVbwey5rGJjy14W+KXuPoqTOaemA6UzvkXF5cgHsnFurq7ZPl3JO1GNyQ61kZcDhhfN+ui72dwwN6G2UjJAqwX9h0AEtuvxJ9sjMNHzKNF1AtqLg8ahmMZMLBrt7lMNQMORvR2yfDuSfrMbgh17My4HDC+L5dF3u7hwfMWKNKKSUB9qI39hi+InWigOpnK3cofp2uM9msSvo36rtr57knezC4IdezMuCwuwFXyo6LvQzDA3bNxLOjR09JTRqlYgW7ViyHYeR31y2zMEkZBjfkelYGHDI04EpZfbGXZXjAjjWq7OjRM6oq8IOll9rWs2H0d9fN65NRNAY3ZAsra8BYGXDI0oArZfXFXtbhAaWfR62fWzt69IwIlAq8PQxb7kTLsXPSzQLJhcENWc7qGjBWBxyyNuCykG14QOnnUc/n1o5GWk2gZPb3Quuxc9rNAsnDI5KtqSChYDAIr9eLQCCA3Nxcu3eHVIiX4Bi+NJlZA8bqoErWCsV0ntLPoxGf2/BrALEbaaM/++0hgQmL65IGVAsqirDoDfO+F0YdO1mLYpI6VrXfDG7IMuGLbbw8gPDF1ugZI133gQEHAco/jxvnfhf/9Ju3DfncWt1IKw2ozPpeGPmd53fXHaxqvzksRZaRoQYMEwopTOnn8b/qPzXsc2v1kJzSIVKzvhdGfuf53SU1GNyQZZxQA4bkZuTdu9LP2cHmrw19PTuSuO3KceJ3nuzC4IYs45QaMCQno4d0lH7Ohub1NPT11DIioLOr14PfebILgxuyDKd1klZmrA2m9PM4o+Ri/MfmA7Z8bmVMpFUTbPE7fx5zhqyVZvcOUOoIT+sEzic0hnFaJ8WjpNLuwtd3oz2kbm6E0s9jRvc0Wz634YCua85KOKCraUy85pIZahqbMGFxHaYt3YIHVjdg2tItmLC4Lu6+hI9xvDMjkBrfebXHjfRjcEOWCic4+rzR3dA+bw9Tp4GTc6lJSlVL6efR6s+tWQGdHjIGW07A42YPDkuR5WQr4kZyMzspVenn0crPrVkzC7UOjShZ+DPW6tzh58UT73luofW4kX4MbsgWnNZJSmlNSlXTkCv9PFr1uTUjoNOTv6M12JKh/IOdUv3924nBDRFJTUtSqoyJuGoYPctIb0K21mAr1aeCp/r7txNzbohIamoT0d2Q4xAO6BIpUDjLyIj8Ha3BVqpPBU/1928nBjdEJD2lCb0yJuJq0S3Ng5tGJu5humlkgaI8DSMSssPBVry/5kHsYEvr89wi1d+/nRjcEJEjlBcXYPO8SVg1cxyevm0UVs0ch41zvwtvVgbWNnyB+v3HsWX/cdNmVlmpPSTw2oeJe5he+7BJUZBmxNCI1jIOqV7+Qcn7v23MEKz76DDq9x+XPuh2EubcEJFjdE7orWlsumBBy95Z6YpeR/Ych2S9LYDyRFSjhkaUrlNl1PPcIt77790zHQLAUxv+Fvmdk/LCZMfghogcJ16C7MnTZxU9X/YcByMTUY2sEqx1Onyql3/o+v4//bIFT2345ILt9FTcpmgMbojIURLl1SQjS7n/ZNPUjUxEDQ+NzFqxHR4g6rhpGRrSOh0+1cs/hN9/e0hgwuK6mNuw9o1xGNwQkaMoGbKJRZYcDyXT1I1ekynVh4Zkwto31mBwQ0SOonTIpndWetQwlQwNudJ6M0p7WwCgfv9xRUM9qTA05ITFKVn7xhoMbsg1nHBhI/2UDtksueMqpHk80nwe1JbiT9bbAgATFtepKlTo5qGhZD1islwfWPvGGgxuyBWcXpGWlFM6ZDPuG32lCm61DEfE622p3e3XVXHYbZL1iN07sRCvfdgkxfXB6CFHio11bsjx3FCRlpRzau0UrcMR4d6Wm0ddFAl63FCo0CjJesQEgD9sOiDN9cGpn1+nYXBDjuaWirSkjtKKxTIxajjCiIrDbqI1wdzO64MTP79Ow2EpcjTOPEhdZifIGp2jYdRwBBNSo+l5n3ZeH1IhwdtODG7I0XihT21aE2STBS5m5HAZVW+GCanRjHifdl0f3JzgbTcGN+RovNCTWskCF6XTtbUwot6M0h6g0UP7KJ4m7mTJjocSWq8PsszAogt5hBCOS0YIBoPwer0IBALIzc21e3fIRuFqn8ku9JvnTeJFh+IGLuFPxpLbr8SiN/bEHeo06vOkt1EMvw8gdg+QTLODzND1+J1oaUPlytjHI1EDp+d8coamNla13wxuyPGSXeiZoEfA+UA4UeDSJzsdzS3J16daNXOc7cMJ8RrXm0YW4IVNB+IGcE7/PiR637ECuvDxAIy7PiQLkp1+jM1kVfvNYSlyPJaWdxa7uvKVJJ8rCWwAOXK4YiWkjh7aB//0m7cVFwp0mkRDhi9sOoAlt1+JPtmZF3y2rhzSx7Drg9pijGQPBjfkCpx54Ax2duUbGZDIksPVNSG1fv9x184eVBJULHpjT8whJiOvD5yh6QwMbsg1OPNAbmYm6iqhNCDJy87AiZY2R1aPdfPsQb1BhVHXBzcfYzdhET8iUq09JFC//zjWNnyB+v3HkxZBk6HYYnhWTTJTr7oIgDOrx7p59qAsQYWbj3GY2u+3jNhzQyQhmaeYahlakqErv1uaBwsqLsfPVu5IuN26j5pizppyQg6Xm9ctkiWocPMxBtwzC4zBDZFkZL64aB1akuWuu092ZtJtmgJn0Cc7E5vnTZI2wIzHqEKBMpIlqHDzMbZ76NhIHJYikojMi4DqGVqS5a5bTZDVdcFKpzRWbl23SKYFJ914jGUYOjYSe26IJCH7FFM9Q0uy3HXLEmSZza2zB2Uq++C2YyzD0LGRGNwQSUL2i4ueoSVZuvJlCbKs4NbZgzIFFW46xrIMHRtF1bBUdXU1xowZg5ycHOTn52PKlCnYu3dv5PHm5mbcf//9GD58OLKysjBkyBD8/Oc/RyAQiHqdQ4cOoaKiAj179kR+fj7mzp2Lc+fOGfOOiBxK9ouL3l4PGbryZRraUMoNM1f06noMADhyyFBmbuvVVNVzs3HjRlRWVmLMmDE4d+4cHnroIZSVlWH37t3Izs7G4cOHcfjwYfz2t79FUVERDh48iPvuuw+HDx/G//zP/wAA2tvbUVFRAZ/Ph/feew9NTU248847kZ6ejscff9yUN0nkBLJfXIzo9ZDhrtuOoQ2ts99kTi7XS+kxcfMxkInbejV1rS117Ngx5OfnY+PGjZg4cWLMbV5++WVMnz4dLS0t6N69O958803ccMMNOHz4MAYMGAAAeP755zFv3jwcO3YMGRkZSf8u15YiN3LCIqBuWsfLqun2WhtnN69fpPSYGHkMZC6vIAsrvt9Wtd+6ZkuFh5vy8uJHcuE30L17RydRfX09RowYEQlsAGDy5MkIBoPYtWtXzNdobW1FMBiM+kfkNk4YMpFhaMkoVsyG0jr7zW0zVzpTekyMPAY1jU2YsLgO05ZuwQOrGzBt6RZMWFxn6+xDGbnp+605oTgUCmH27NkYP348iouLY27z5ZdfYtGiRbj33nsjv/P7/VGBDYDIz36/P+brVFdXY+HChVp3lcgxZJoNEo+dQ0tOuvvWM/tN9uRyrdQcE6OOgZtqt1hBhqFjI2gObiorK9HY2IjNmzfHfDwYDKKiogJFRUV49NFHtf4ZAMD8+fMxZ86cqNcePHiwrtckkpUTLi5aZonoDUyclnuhp3GWPblcKzXHxIhjIHt5BVm5YRaYpuCmqqoK69atw6ZNmzBo0KALHj916hTKy8uRk5ODNWvWID09PfKYz+fD1q1bo7Y/cuRI5LFYMjMzkZmZvLIokVu44eLSmd7AxIl333oaZ9mTy7VSc0yUvrdPjnyF+v3HYwbLbu0Bo+RU5dwIIVBVVYU1a9agrq4OhYWFF2wTDAZRVlaGjIwMvPbaa+jRI/oDWlJSgp07d+Lo0aOR39XW1iI3NxdFRUUa3wYRdSXLFGK9VZedmn+iJ0AJz1yJ15fgQUdw6JSZK2FqjkmyYxD2zNv74ubQuLUHjJJTFdxUVlZixYoVWLlyJXJycuD3++H3+3H69GkA5wOblpYWvPjiiwgGg5Ft2tvbAQBlZWUoKirCjBkz8OGHH+Ivf/kLHn74YVRWVrJ3hsggsiRQGhGYqLn7lomeAMUJyeVaqDkmiY5BLLGCZbf2gFFyqoKb5557DoFAANdeey0KCgoi/1566SUAwPbt2/H+++9j586duOSSS6K2+eyzzwAA3bp1w7p169CtWzeUlJRg+vTpuPPOO/HYY48Z/+7IFLL0CFBsRqxPZdQ5NiIwcerdt94AxU0zV8LUHpN4xyCWWMGyW3vAKDlVOTfJSuJce+21SbcBgKFDh2L9+vVq/jRJwmlJnanGiARKI8+xEYGJk+++9c5+c0JyuVpqj0nnY/DuvmN45u39cV+7aw6NLMt+kPW4thQp5sSkzlSjN4FSzTlONPsp/NgnR75StN+JAhOnV07VG6C4LbkcUH9MwsdAS7DshPIKZDwGN6QIp1Q6g56eEjXnuHa3P27vDv6xXaIgK0xJYOKGu283Bih6aTkmWnvx3NgDRokxuCFFOKXSGfQM4Sg9x79/6294+q19MXt37vtH6XYl1AQmvPsmQF8vHgPM1MLghhRxalJnqtFz8Vd67mIFNgBi/i4RtYGJWXffTqp6nOrc0ItH1mBwQ4o4OanTreI1ylov/krPnd65cVXfHYbxl/TXFEQYfffNBHljWREoshePlGBwQ4o4PanTbkZf9JM1ylou/snOsVEuHZATN0CJd5zMaDSZIG8sKwNF5tBQMh6hZO62ZKxaMp2ihRsDIHaPABuD2Iy+6MdrlLueBy0BQbzXNtKqmePiztSKdZxuGlmA1z5sMrTRbA8JTFhcFzfHKBysb543iQ2mAko/k0RWtd+qivhRanNjUTGzGVFQrzM1FX/DQzg3j7ooUvMjmfA57p2VnnRbtRIVTIt3nJoCZ/CHTQcMO35hTq16LCOnLo9B7sZhKVKF3cHKmTF93opZa+XFBcjJTMcdL76v6nmdc3zU5PskOk7x6C0/wAR543AmJcmIPTekmpYegVRkRu+AVY3yuGF9ky5a2PW0+7w98Pz0q/C8yt69ZMcpHj29K0yQNw4DRZIRe26ITGLGRd+qRlnJrKtnpl2FPtkZMXvw1PTu6W30tDyfCfLGYaBIMmJwQ2QSMy76VjbKeqbcqpmyrbfR0/J81ksxDgNFkhGDGyKTmHHRt7pRtiLHSusUdL2NZqLgbUHF5fBmZWBtwxfMK0uCgSLJiFPBiUxk1vR5txWfi3ec4jFyinHXKfMnWtqw6A33HFuruO0zSeawqv1mcENkMrMu+m5bNsDKOjeJ9oH1WrRz22eSjMfgJgEGN+Q0vOgrY2WF4lh/m4X9iMxlVfvNnBsiC3BFYmXiHScrjh/rtRC5B4MbIiKwXosV2INJVmFwQ0SE1KjXYmdwwYRjshKDGyJyDDMbZ7fXazEiuNB6/LkCO1mNwQ0ROUK8xnlBRVHcSslquLleixHBRfzjfzn6ZGfGPf5mrLFGlAxnSxGR9OI1zrHoHepw2/CJEbPA9Bz/+v3HMW3plqTPWzVzHBO1UwBnSxERQf2q4XqHOqyoymwlvbPA9B5/JmqTHRjcEFnI6bNF7Nh/tauGGzHU4aap+3qDC73HPxUStUk+DG6ILOL04Q679l/LHT1r0pynN7jQe/zdnqhNckqzeweIUkE4Z6HrHXC4C7+mscmmPVPGzv3Xc0cv61BHe0igfv9xrG34AvX7j6M9ZF7qYzi4iNd/5UFHkBovuNB7/MOJ2uG/1fVvA85N1CZ5MbghMlmy2SJARxe+mQ2cHlr238jGO1njnIiMQx01jU2YsLgO05ZuwQOrGzBt6RZMWFxnWoCoN7gw4viHV2D3eaPPh8/bg9PAyRQcliIymdPL+qvdf6OHrxJN0Y5H1qEOu+q9hIOLrufFp+C8GHX83ZaoTXJjcENkMqfPFlGz/2Y13vEa51hkHeqwu96LnuDCqOMfL1Hb6Yn2JB8GN0Qmc/psEaX7dTR4Bkve3m9a4x1unJ+p24dl7x7AydNnY26npDfCDjL04OmZBRYrODrR0oZFb6jvDerM6Yn2JCcGN0Qmc/pskWT7DwBpHuBf13+c8HWMaLxrd/vxuw1/i7sfD5Z+E1WTLpHyrt/pPXhA7OBocrH2oSZZl2VgT5LzMbghMpnTy/oryblQky+stfFOVkzOA2D1/x1C1aRLNL2+2ZT2gH365dcm74mxtPYG2T1MFw97ktyBs6WILOD02SLx9l9Lm6N1+E3NsI6MlM46+t2Gv0lfGsAIMp5Pp5dsoPPYc0NkEafPFum6/1+easWiN/Yofr7e4TenD+uEe8DuW7E96bZ6eyycMKwi2/mUtSeJtGFwQ2Qhp5f177z/axu+UPw8I4bfnJ6YDXQEiA+WXoqnNnwSdxu9uUlOGVaR7XzKkPBNxuGwFBFpoqbRUTL8lqzwn95Ku7K4uF+2ou209Fg4aVhFtvMpW08S6cOeGyKKonRIQ8ksqt5Z6Vhyx1UY942+CXtslPQ2WJ2YbdbQjlk9Fk4bVpEt0f7TL1sUbSdzzyCdx+CGiCLUDGkoaZyemDoC4y/pl/RvKp0OrKfSrhpmDu2YVRrAicMqVp3PZGoamxIOFQLyl2ygaB4hhJwL2iQQDAbh9XoRCASQm5tr9+4QuUK8ICMcqMQbVtITCLSHBCYsrovbKIcblM3zJkXdwZuZMKv1OGj5G0DsoFDL31jb8AUeWN2QdLunbxuFm0ddpOq1zWZnAnSyz2CYB8ac+1RnVfvNnhsi0jWkoWcWmNbeBrMSs9tDAr96ZafpQztm9FjIlqCrhp2J9sk+g2GzS7/JwMZBGNwQScDuqbt6hzS0Nk6yJXE+U/cJTn4de1kHwNihHaNLAzi9ErZdlH62Lu7X0+Q9ISMxuCFHsLvxN5MMU3ftCjJk6m1oDwkse/dTRdsadRyM7LGQLUHXKWT6DJJxGNx04uYG1MlkaPzNIsvaOnZd4JWuW3Wipc3QvxvL1gPNcRfj7ErWhk6WBF0nYY+XOzG4+Qc3N6BOJkvjbwaZpu6GL/DJcg9OtLQa+nc79zbEExJA5crteC7N3HOttDemd890qRs6p1fCthp7vNyJRfzgrMJXqSRZ4w90NP5di705hRlr6yQrhBdPtzQPFlQUJd1u0Rt7DD/e5cUFWHL7lUnXqTL7XCvtjfnxNYXSN3Th4a6bR12EkmGJawyR89d+owulfM+NTHfPFM2JdTvUMDrPRW/vY5/sjKTbmHW8+2RnJlxZ3IpzragoYc90aVcdJ33Y4+UuKd9zI+PKtNRBtpk0RmoPCXx5StkQT7IehfaQwNMbPsF9Onsf7Tzeev+21h6rzsLDEwDiLgnwxA9GsLH7ByOOuWzY4+Ueqnpuqqur8corr+Djjz9GVlYWrrnmGixevBjDhw+PbPPCCy9g5cqV2L59O06dOoUTJ06gd+/eUa/T3NyM+++/H6+//jrS0tIwdepUPP300+jVq5chb0oNNzegTufWWQyxelhiUZLIWNPYhEdf2wV/MHagpKb30c7jredvG5kvFy8hl/l30ZijSLJT1XOzceNGVFZWYsuWLaitrcXZs2dRVlaGlpbza3J8/fXXKC8vx0MPPRT3de644w7s2rULtbW1WLduHTZt2oR7771X+7vQwa0NqBvItrCeEeLld3WlJJEx/FrxApswpb2Pdh5vrX/bjHy58uICbJ43CatmjsPTt43CqpnjsHneJDba/8AcRXICVcFNTU0N7r77blxxxRUYOXIkli9fjkOHDmHbtm2RbWbPno1f/epXGDduXMzX2LNnD2pqavAf//EfGDt2LCZMmIDf//73WL16NQ4fPqzv3WjgxgbULRINEzhxFkOi/K6ukiUyqnmtsGS9j3Yeby1/28yEcw5PxOb2JH9yD105N4FAAACQl6e84a+vr0fv3r3x7W9/O/K70tJSpKWl4f3334/5nNbWVgSDwah/RnFbA+o2bprFoLTM+4KKy5P2FCh9rc6U9D7aebzV/m3myyVndF4Mjzk5hebZUqFQCLNnz8b48eNRXFys+Hl+vx/5+fnRO9G9O/Ly8uD3+2M+p7q6GgsXLtS6q0mx8JXc3DKLQWneVr+czKTvTU0OmNoiZHYebzV/u3Z37OtFV6maL2dGXgxzFMkpNAc3lZWVaGxsxObNm43cn5jmz5+POXPmRH4OBoMYPHiwoX/DLQ2oW9m5sJ5RjMzvUpsDprb30c7jreRvt4cEXm1QNoydivlyZhW/ZI4iOYWm4KaqqiqSCDxo0CBVz/X5fDh69GjU786dO4fm5mb4fL6Yz8nMzERmZqaWXVXFDQ0oycvIMu9KarIA7p3BsvVAM5oVLMmQly13NWEzmFm7i0sVkFOoyrkRQqCqqgpr1qxBXV0dCgsLVf/BkpISnDx5MioJua6uDqFQCGPHjlX9ekROYWR+l5KaLA+WXuraWT5Khz1uGXVRyvW+mpkXwxxFcgpVwU1lZSVWrFiBlStXIicnB36/H36/H6dPn45s4/f70dDQgH379gEAdu7ciYaGBjQ3d3yRLr/8cpSXl2PmzJnYunUr3n33XVRVVeG2227DwIEDDXxrRPIxMmE33msVeHvg+elX4YHSb7q2kVE67FFaFLs32M3MzotxU5I/uZdHCKE4fd7jiX2hXLZsGe6++24AwKOPPhoz+bfzNs3Nzaiqqooq4vfv//7viov4BYNBeL1eBAIB5ObmKt19ImnoWYG+63NHD+2DbQdPpFSuWHtIYMLiuqTDI5vnTUK3NI+u4+009fuPY9rSLUm3WzVznK5h+FQ6pmQcq9pvVcGNLBjcUKpiZdjzwkmzQOyVnMO9CMmOmdsaabWBn2zcdj4oGoObBBjcJMcLhPvEmwHTtTFPJckCl2TH7N6JhXjtwybXBYtKAz/ZyBi881pqLAY3CTC4SUzGCwTpE74bj5coKvvduJniNT7Jjlk8sgcASjntOiBj8O60Y+gEDG4SYHATn4wXiFRjxp2eVXkUbqL0mMXilmDRKb0OMgbvvJaaw6r2W3MRP5KPmfUtSBmz7vRYGVY9Pcei83RpJweLTqndpWb6uhXvh9dS59O1thTJheu+2MvM1ZJZGVY9I44Fg0VryBa881rqfAxuXES2C0QqMXu1ZK5er16yY6aEk4NFoxfNNJNswTuvpc7H4MZFZLtApBKz7/RYGVY9JccsHqcHizWNTZiwuA7Tlm7BA6sbMG3pFkxYXKer99BMsgXvvJY6H4MbF5HtApFKrLjTY2VY9RIds59OLIQH7gsWzRweNYtswTuvpc7HhGIXCV8gZq3YDg9i17dw6gVbdlbd6dm5en3nmTf9emUCAviypVXqWThA4mN25ZA+FySA+xw81dfJibDhQFSG88FrqfNxKrgLsTaD9ZxeFTaZWJ+pzpz8+XLKdGkl3FAyQKbzwWup8TgVnDSz8+4+Vbn5Ti9evY/OwkMeThweM2K6tCwNshsSYWWavs5rqXMxuHEpmS4QqUKmbnWjJBrm6Ez2IQ8zyXR3z0RY4/Fa6kwMbogM5LY7vWSzwDpzS+E7NeL1atnVkxVOhE02PMpEWHI7zpYiMlj4Tu/mURehZFhfxwY2gLbhC5mHPIxkdm0jLWSbdURkFwY3RBSXluGLVBnykLWKLUsGEHFYiogSSDbM0ZneIQ9ZknKVkjl5123Do0RqMbghorgSzQLrTO+Qh0xJuUrJnrzLRFhKZRyWIqKE4g1zdKZnyMOJFXUBVrElkhl7bogcws5hm67DHEZVKHZyRV031zYicjoGN0QOIMOwjRnDHGqScmUcYikvLsCS26/Ew2sb0dxyNvJ7J9c2InIDDksRSc6pwzZKyJyUq0RNYxMWvbEnKrDJy87AggoGNkR2YnBDJDEZa6kYSfak3ETiBZ0nWtpQudLZQSeR0zG4IZKYrLVUjOLUpFy3B51ETsfghkhiTh+2ScapFXXdHnQSOR2DGyKJOXnYRiknVtR1e9BJ5HScLUUksVRZCNFpFXVTIegkcjL23BBJzKnDNlo4acFRp+YKEaUKBjdEknPisI3bpVLQSeREHiGE49L5g8EgvF4vAoEAcnNz7d4dIku0nQvhv+o/xcHmrzE0rydmlFyMjO68P7GTDMUViZzEqvabwQ2RA7ARlZfTVjMnshODmwQY3FAqCReL6/pFDTefHJoiIqewqv1mnzYZoj0kUL//ONY2fIH6/cdZvMwgLBZHRKQep4KTbhwyMY/TF5YkIrIDe25IFzcv6igDFosjIlKPwQ1pxiET87FYHBGRegxuSDOur2M+FotzJuagEdmLOTekGYdMzBcuFjdrxXZ4gKheMiuKxXGas3rMQSOyH4Mb0oxDJtYIVyju2mD6TG4w2UirF2/afjgHjdP2iazBOjekWXtIYMLiuqSLOm6eN4l3+wawsheFtXXUC38f4g3V8vtAxDo3jpOKY+xcX8daVi0syURxbZiDRiQPDksZIJW77+0aMiHzsLaONsxBI5IHgxudOMbeEeBcV+Rj4qlLsJHWhjloRPJgcKNDsu57Dzq6768r8rm+oQ8PmZDzsZHWJjxtP1kOGqftE5mPOTc6cIyd3MhttXWsyodjDhqRPNhzowO778mN7K6tYySr8+GYg0YkBwY3OrD7ntzKDY20XflwzEEjsh+DGx04xk5mkaEysJMbabvz4ZiDRmQvVTk31dXVGDNmDHJycpCfn48pU6Zg7969UducOXMGlZWV6Nu3L3r16oWpU6fiyJEjUdscOnQIFRUV6NmzJ/Lz8zF37lycO3dO/7uxGMfYyQw1jU2YsLgO05ZuwQOrGzBt6RZMWFxnywrrVtXWMRrz4YhSm6rgZuPGjaisrMSWLVtQW1uLs2fPoqysDC0tLZFtHnzwQbz++ut4+eWXsXHjRhw+fBg/+MEPIo+3t7ejoqICbW1teO+99/DHP/4Ry5cvx69//Wvj3pWFwt33Pm/00JPP2yMlpoGTscJDKV0b5vBQih0BjhMxH44otelafuHYsWPIz8/Hxo0bMXHiRAQCAfTv3x8rV67ED3/4QwDAxx9/jMsvvxz19fUYN24c3nzzTdxwww04fPgwBgwYAAB4/vnnMW/ePBw7dgwZGRlJ/66Myy/IMIxAzsby/cap338c05ZuSbrdqpnjOHxEZCFHLL8QCAQAAHl5HTkl27Ztw9mzZ1FaWhrZ5rLLLsOQIUNQX18PAKivr8eIESMigQ0ATJ48GcFgELt27Yr5d1pbWxEMBqP+ycap3fckDw6lGMdt09mJSB3NwU0oFMLs2bMxfvx4FBcXAwD8fj8yMjLQu3fvqG0HDBgAv98f2aZzYBN+PPxYLNXV1fB6vZF/gwcP1rrbRNLiUIpxmA9HlNo0BzeVlZVobGzE6tWrjdyfmObPn49AIBD599lnn5n+N4msxtICxmI+HFHq0jQVvKqqCuvWrcOmTZswaNCgyO99Ph/a2tpw8uTJqN6bI0eOwOfzRbbZunVr1OuFZ1OFt+kqMzMTmZmZWnaVyDFYWsB4Tp7OTkTaqeq5EUKgqqoKa9asQV1dHQoLC6MeHz16NNLT0/HWW29Ffrd3714cOnQIJSUlAICSkhLs3LkTR48ejWxTW1uL3NxcFBUV6XkvRI7GoRRzMB+OKPWomi31s5/9DCtXrsTatWsxfPjwyO+9Xi+ysrIAALNmzcL69euxfPly5Obm4v777wcAvPfeewA6poKPGjUKAwcOxJNPPgm/348ZM2bgJz/5CR5//HFF+yHjbCkio1i9ZAARkVWsar9VBTceT+w7nmXLluHuu+8G0FHE7xe/+AVWrVqF1tZWTJ48Gc8++2zUkNPBgwcxa9YsvPPOO8jOzsZdd92FJ554At27KxslY3BDbsfSAkTkRlIGN7JgcEPkTgzqiNzNqvaba0sRkRQ4HEdERtFVxI+IyAhcdoKIjMTghohslWwFb6BjBe/2kONG0InIJgxuiMhWXHaCiIzG4IaIbMVlJ4jIaAxuiMhWXHaCiIzG4IaIbMUVvInIaAxuiMhWXHaCiIzG4IaIbMcVvInISCziR0RS4AreRGQUBjdEJI3wCt5ERHpwWIqIiIhchcENERERuQqDGyIiInIVBjdERETkKgxuiIiIyFUY3BAREZGrMLghIiIiV2FwQ0RERK7C4IaIiIhchRWKyZHaQ4Jl+omIKCYGN+Q4NY1NWPj6bjQFzkR+V+DtgUduLOICi0RExGEpcpaaxibMWrE9KrABAH/gDGat2I6axiab9oyIiGTB4IYcoz0ksPD13RAxHgv/buHru9EeirUFERGlCgY35BhbDzRf0GPTmQDQFDiDrQeardspIiKSDoMbcoyjp+IHNlq2IyIid2JwQ46Rn9PD0O2IiMidGNyQY1xdmIcCbw/Em/DtQcesqasL86zcLSIikgyDG3KMbmkePHJjEQBcEOCEf37kxiLWuyEiSnEMbshRyosL8Nz0q+DzRg89+bw98Nz0q1jnhoiIWMSPnKe8uADXFflYoZiIiGJicEOO1C3Ng5Jhfe3eDelwWQoiIgY3RK7BZSmIiDow54bIBbgsBRHReQxuiByOy1IQEUVjcEPkcFyWgogoGoMbIofjshRERNEY3BA5HJelICKKxuCGyOG4LAURUTQGN0QOx2UpiIiiMbghcgEuS0FEdB6L+BG5BJelICLqwOCGyEW4LAUREYeliIiIyGUY3BAREZGrMLghIiIiV2FwQ0RERK6iOrjZtGkTbrzxRgwcOBAejwevvvpq1ONHjhzB3XffjYEDB6Jnz54oLy/HJ598ErXNmTNnUFlZib59+6JXr16YOnUqjhw5ouuNEBEREQEagpuWlhaMHDkSS5YsueAxIQSmTJmCv//971i7di127NiBoUOHorS0FC0tLZHtHnzwQbz++ut4+eWXsXHjRhw+fBg/+MEP9L0TIiIiIgAeIYTQ/GSPB2vWrMGUKVMAAH/7298wfPhwNDY24oorrgAAhEIh+Hw+PP744/jJT36CQCCA/v37Y+XKlfjhD38IAPj4449x+eWXo76+HuPGjUv6d4PBILxeLwKBAHJzc7XuPhEREVnIqvbb0Jyb1tZWAECPHuerpKalpSEzMxObN28GAGzbtg1nz55FaWlpZJvLLrsMQ4YMQX19fdzXDQaDUf+IiIiIYjE0uAkHKfPnz8eJEyfQ1taGxYsX4/PPP0dTUxMAwO/3IyMjA71794567oABA+D3+2O+bnV1Nbxeb+Tf4MGDjdxtIiIichFDKxSnp6fjlVdewT333IO8vDx069YNpaWluP7666Fj9Avz58/HnDlzIj8HAgEMGTKEPThEREQOEm639cQEShi+/MLo0aPR0NCAQCCAtrY29O/fH2PHjsW3v/1tAIDP50NbWxtOnjwZ1Xtz5MgR+Hy+mK+ZmZmJzMzMyM/hg8MeHCIiIuc5deoUvF6vaa9v2tpS4Z3+5JNP8MEHH2DRokUAOoKf9PR0vPXWW5g6dSoAYO/evTh06BBKSkoUvfbAgQPx2WefIScnBx6P+xcFDAaDGDx4MD777DMmUEuM58k5eK6cgefJGdScJyEETp06hYEDB5q6T6qDm6+++gr79u2L/HzgwAE0NDQgLy8PQ4YMwcsvv4z+/ftjyJAh2LlzJx544AFMmTIFZWVlADqCnnvuuQdz5sxBXl4ecnNzcf/996OkpETRTCmgI0l50KBBanfd8XJzc/kFdwCeJ+fguXIGnidnUHqezOyxCVMd3HzwwQf47ne/G/k5nAtz1113Yfny5WhqasKcOXNw5MgRFBQU4M4778SCBQuiXuOpp55CWloapk6ditbWVkyePBnPPvuszrdCREREpLPODVmDdX2cgefJOXiunIHnyRlkPE9cW8oBMjMz8cgjj0QlVZN8eJ6cg+fKGXienEHG88SeGyIiInIV9twQERGRqzC4ISIiIldhcENERESuwuCGiIiIXIXBjQE2bdqEG2+8EQMHDoTH48Grr74a9fgrr7yCsrIy9O3bFx6PBw0NDRe8xpkzZ1BZWYm+ffuiV69emDp1Ko4cORK1zaFDh1BRUYGePXsiPz8fc+fOxblz56K2eeedd3DVVVchMzMTl1xyCZYvX37B31qyZAkuvvhi9OjRA2PHjsXWrVv1HgJHSHSezp49i3nz5mHEiBHIzs7GwIEDceedd+Lw4cNRr9Hc3Iw77rgDubm56N27N+655x589dVXUdt89NFH+M53voMePXpg8ODBePLJJy/Yl5dffhmXXXYZevTogREjRmD9+vVRjwsh8Otf/xoFBQXIyspCaWkpPvnkE+MOhuSSfaceffRRXHbZZcjOzkafPn1QWlqK999/P2obnivzJTtPnd13333weDz43e9+F/V7nidrJDtXd999NzweT9S/8vLyqG0cda4E6bZ+/XrxL//yL+KVV14RAMSaNWuiHv/Tn/4kFi5cKJYuXSoAiB07dlzwGvfdd58YPHiweOutt8QHH3wgxo0bJ6655prI4+fOnRPFxcWitLRU7NixQ6xfv17069dPzJ8/P7LN3//+d9GzZ08xZ84csXv3bvH73/9edOvWTdTU1ES2Wb16tcjIyBD/+Z//KXbt2iVmzpwpevfuLY4cOWL4cZFNovN08uRJUVpaKl566SXx8ccfi/r6enH11VeL0aNHR71GeXm5GDlypNiyZYv461//Ki655BIxbdq0yOOBQEAMGDBA3HHHHaKxsVGsWrVKZGVliT/84Q+Rbd59913RrVs38eSTT4rdu3eLhx9+WKSnp4udO3dGtnniiSeE1+sVr776qvjwww/FTTfdJAoLC8Xp06fNO0ASSfad+vOf/yxqa2vF/v37RWNjo7jnnntEbm6uOHr0aGQbnivzJTtPYa+88ooYOXKkGDhwoHjqqaeiHuN5skayc3XXXXeJ8vJy0dTUFPnX3NwctY2TzhWDG4Ml+oIfOHAgZnBz8uRJkZ6eLl5++eXI7/bs2SMAiPr6eiFExwczLS1N+P3+yDbPPfecyM3NFa2trUIIIX75y1+KK664Iuq1f/SjH4nJkydHfr766qtFZWVl5Of29nYxcOBAUV1dren9OlWi8xS2detWAUAcPHhQCCHE7t27BQDxf//3f5Ft3nzzTeHxeMQXX3whhBDi2WefFX369ImcEyGEmDdvnhg+fHjk51tvvVVUVFRE/a2xY8eKn/70p0IIIUKhkPD5fOI3v/lN5PGTJ0+KzMxMsWrVKm1v2MGUnKtAICAAiA0bNggheK7sEO88ff755+Kiiy4SjY2NYujQoVHBDc+TPeIFNzfffHPc5zjtXHFYSgLbtm3D2bNnUVpaGvndZZddhiFDhqC+vh4AUF9fjxEjRmDAgAGRbSZPnoxgMIhdu3ZFtun8GuFtwq/R1taGbdu2RW2TlpaG0tLSyDZ0XiAQgMfjiaxeX19fj969e0dWuAeA0tJSpKWlRYZE6uvrMXHiRGRkZES2mTx5Mvbu3YsTJ05Etkl0ng4cOAC/3x+1jdfrxdixY3meYmhra8MLL7wAr9eLkSNHAuC5kkUoFMKMGTMwd+5cXHHFFRc8zvMkl3feeQf5+fkYPnw4Zs2ahePHj0cec9q5YnAjAb/fj4yMjEgjGjZgwAD4/f7INp0Dm/Dj4ccSbRMMBnH69Gl8+eWXaG9vj7lN+DWow5kzZzBv3jxMmzYtUk7c7/cjPz8/arvu3bsjLy/PkPPU+fHOz4u1DQHr1q1Dr1690KNHDzz11FOora1Fv379APBcyWLx4sXo3r07fv7zn8d8nOdJHuXl5fjTn/6Et956C4sXL8bGjRtx/fXXo729HYDzzpXqhTOJ3O7s2bO49dZbIYTAc889Z/fuUBzf/e530dDQgC+//BJLly7Frbfeivfff/+CCzDZY9u2bXj66aexfft2eDweu3eHkrjtttsi/x8xYgS+9a1vYdiwYXjnnXfwve99z8Y904Y9NxLw+Xxoa2vDyZMno35/5MgR+Hy+yDZdZ0+Ff062TW5uLrKystCvXz9069Yt5jbh10h14cDm4MGDqK2tjVoEzufz4ejRo1Hbnzt3Ds3NzYacp86Pd35erG0IyM7OxiWXXIJx48bhxRdfRPfu3fHiiy8C4LmSwV//+lccPXoUQ4YMQffu3dG9e3ccPHgQv/jFL3DxxRcD4HmS2Te+8Q3069cP+/btA+C8c8XgRgKjR49Geno63nrrrcjv9u7di0OHDqGkpAQAUFJSgp07d0Z9uMKNb1FRUWSbzq8R3ib8GhkZGRg9enTUNqFQCG+99VZkm1QWDmw++eQTbNiwAX379o16vKSkBCdPnsS2bdsiv6urq0MoFMLYsWMj22zatAlnz56NbFNbW4vhw4ejT58+kW0SnafCwkL4fL6obYLBIN5//32epwRCoRBaW1sB8FzJYMaMGfjoo4/Q0NAQ+Tdw4EDMnTsXf/nLXwDwPMns888/x/Hjx1FQUADAgedKceoxxXXq1CmxY8cOsWPHDgFA/Nu//ZvYsWNHZJbN8ePHxY4dO8Qbb7whAIjVq1eLHTt2iKampshr3HfffWLIkCGirq5OfPDBB6KkpESUlJREHg9PBS8rKxMNDQ2ipqZG9O/fP+ZU8Llz54o9e/aIJUuWxJwKnpmZKZYvXy52794t7r33XtG7d++oWVhuleg8tbW1iZtuukkMGjRINDQ0RE2H7Jz5X15eLq688krx/vvvi82bN4tLL700airkyZMnxYABA8SMGTNEY2OjWL16tejZs+cFUyG7d+8ufvvb34o9e/aIRx55JOZUyN69e4u1a9eKjz76SNx8880pNW010bn66quvxPz580V9fb349NNPxQcffCB+/OMfi8zMTNHY2Bh5DZ4r8yW79nXVdbaUEDxPVkl0rk6dOiX++Z//WdTX14sDBw6IDRs2iKuuukpceuml4syZM5HXcNK5YnBjgLffflsAuODfXXfdJYQQYtmyZTEff+SRRyKvcfr0afGzn/1M9OnTR/Ts2VPccsstUcGPEEJ8+umn4vrrrxdZWVmiX79+4he/+IU4e/bsBfsyatQokZGRIb7xjW+IZcuWXbC/v//978WQIUNERkaGuPrqq8WWLVuMPiRSSnSewtP0Y/17++23I69x/PhxMW3aNNGrVy+Rm5srfvzjH4tTp05F/Z0PP/xQTJgwQWRmZoqLLrpIPPHEExfsy3//93+Lb37zmyIjI0NcccUV4o033oh6PBQKiQULFogBAwaIzMxM8b3vfU/s3bvXlOMio0Tn6vTp0+KWW24RAwcOFBkZGaKgoEDcdNNNYuvWrVGvwXNlvmTXvq5iBTc8T9ZIdK6+/vprUVZWJvr37y/S09PF0KFDxcyZMy+46XXSufIIIYTyfh4iIiIiuTHnhoiIiFyFwQ0RERG5CoMbIiIichUGN0REROQqDG6IiIjIVRjcEBERkaswuCEiIiJXYXBDRERErsLghoiIiFyFwQ0RERG5CoMbIiIichUGN0REROQq/x9VZxE9JAmxzwAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(data.Particulate_Level_Delhi,data.Petrol_Price)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "C0WULu1olS85",
        "outputId": "1752a782-1889-4606-f012-b4f53f1e4c12"
      },
      "id": "C0WULu1olS85",
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "id": "df4a5187-08ba-420b-b24a-5c8290e59b8b",
      "metadata": {
        "id": "df4a5187-08ba-420b-b24a-5c8290e59b8b"
      },
      "source": [
        "####\n",
        "**EDIT: [3 pts]**\n",
        "\n",
        "#### (a) Is there a correlation between Particulate_Level_Bangalore and Particulate_Level_Delhi ? [1 pt]\n",
        "- Yes\n",
        "- Reasons: As we can see from the plot, there seems to be a linear relation between the two\n",
        "\n",
        "#### (b) Comment on the pair-wise  relationships between Particulate Level, Temperature and Average Vehicle Volume in a particular city ? [1 pt]\n",
        "- Relationship: +ve between vehicle volume and particulate level, -ve between particulate level and temperature\n",
        "- Justification: Clear from the plots shown above\n",
        "\n",
        "#### (c) How does Petrol Price impact Particulate Levels?   [1 pt]\n",
        "- Relationship: No relation\n",
        "- Justification: Clear from the plot shown above\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "90396dfb-9b1b-48e6-8a4e-bff9ad429fc3",
      "metadata": {
        "id": "90396dfb-9b1b-48e6-8a4e-bff9ad429fc3"
      },
      "source": [
        "## **Q2: Build an Air Pollution Forecasting Model** [5 pts]"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "7aa16c19-2d02-4347-9ce4-6a4ac230e0b7",
      "metadata": {
        "id": "7aa16c19-2d02-4347-9ce4-6a4ac230e0b7"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "\n",
        "### DATA\n",
        "Use the same  **historical dataset** containing weekly observations of **air pollution, temperature, traffic volume, and fuel prices** from Q1\n",
        "\n",
        "- **`air_pollution_train_path`**: historical data (each row corresponds to entries of a particular week\n",
        "\n",
        "</div>\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "acdedf10-2dd4-4aef-ab5a-eab8a681d299",
      "metadata": {
        "id": "acdedf10-2dd4-4aef-ab5a-eab8a681d299"
      },
      "outputs": [],
      "source": [
        "# Training datasets\n",
        "air_pollution_train_path = \"data/air_pollution_train.csv\"  # historical air pollution and related factors data\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "5607c19b-2e1a-4fa7-91d0-a3833dce5fc7",
      "metadata": {
        "id": "5607c19b-2e1a-4fa7-91d0-a3833dce5fc7"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### TASK\n",
        "\n",
        "Create two functions **learn_air_pollution_forecast_model** and **forecast_air_pollution** as per the signatures defined below.  \n",
        "If you scroll down, you will see cells with the skeletal code that you need to flesh out.\n",
        "\n",
        "---\n",
        "\n",
        "### **Function 1: `learn_air_pollution_forecast_model`**\n",
        "\n",
        "```python\n",
        "def learn_air_pollution_forecast_model(\n",
        "    train_file_path: str,\n",
        "    lead_time: int\n",
        ") -> dict:\n",
        "    \"\"\"\n",
        "    Loads a dataset from a CSV file, processes it to align features with future target values at the given lead time,\n",
        "    and trains a machine learning model to predict air pollution (PM2.5) levels for Bangalore and Delhi.\n",
        "\n",
        "    Parameters:\n",
        "    - train_file_path (str): Path to the CSV file containing historical weekly data with:\n",
        "        - \"Week\" - Week index starting from the first week of observation (across multiple years)\n",
        "        - \"Particulate_Level_Bangalore\" (numerical, target variable)\n",
        "        - \"Temperature_Bangalore\" (numerical, in Celsius)\n",
        "        - \"Avg_Vehicle_Volume_Bangalore\" (numerical)\n",
        "        - \"Particulate_Level_Delhi\" (numerical, target variable)\n",
        "        - \"Temperature_Delhi\" (numerical, in Celsius)\n",
        "        - \"Avg_Vehicle_Volume_Delhi\" (numerical)\n",
        "        - \"Petrol_Price\" (numerical, INR per liter, common to both cities)\n",
        "\n",
        "    - lead_time (int): The number of weeks ahead the model should predict (e.g., 6 weeks ahead).\n",
        "\n",
        "    Returns:\n",
        "    - model (dict): A dictionary where the key is the city name and the value is the model trained for that city.\n",
        "    ({\"Bangalore\": model_1, \"Delhi\": model_2 })\n",
        "    \"\"\"\n",
        "```\n",
        "---\n",
        "\n",
        "### **Function 2: `forecast_air_pollution`**\n",
        "\n",
        "```python\n",
        "def forecast_air_pollution(\n",
        "    model: dict,\n",
        "    past_df: pd.DataFrame,\n",
        "    future_observed_df: pd.DataFrame,\n",
        "    lead_time: int\n",
        ") -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Predicts air pollution (PM2.5) levels for Bangalore and Delhi at a future date, given a specified lead time.\n",
        "\n",
        "    Parameters:\n",
        "    - model (dict): A dictionary where the key is the city name and the value is the model trained for that city.\n",
        "    - past_df (pd.DataFrame): Past weekly data with past PM2.5 levels, temperature, vehicle volume, and petrol prices.\n",
        "    - future_observed_df (pd.DataFrame): Known future values for:\n",
        "        - \"Week\" - Week index starting from the first week of observation (across multiple years)\n",
        "        - \"Petrol_Price\" (future fuel price, known in advance)\n",
        "    - lead_time (int): The number of time steps ahead to predict (e.g., 6 weeks ahead from the last available data point).\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: A DataFrame with predicted values for:\n",
        "        - \"Particulate_Level_Bangalore\"\n",
        "        - \"Particulate_Level__Delhi\"\n",
        "    \"\"\"\n",
        "\n",
        "```\n",
        "\n",
        "\n",
        "**Hints:**\n",
        "- Load and explore the data (you already did a bit of this in Q1)\n",
        "- Choose an appropriate time series model based on what you observe\n",
        "- Train a model, analyze performance, and iterate\"\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "dd8f6483-e49c-4c8e-acf4-36aafd974782",
      "metadata": {
        "id": "dd8f6483-e49c-4c8e-acf4-36aafd974782"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### HELPER CODE\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "4aecde05-cf08-4bce-ab76-d2a801331ce1",
      "metadata": {
        "id": "4aecde05-cf08-4bce-ab76-d2a801331ce1"
      },
      "outputs": [],
      "source": [
        "# HELPER CODE\n",
        "# You may choose to use or modify any of the below code in your solution, but it is NOT mandatory\n",
        "\n",
        "def create_lag_features(\n",
        "    df: pd.DataFrame,\n",
        "    target_columns: list,\n",
        "    lags: int\n",
        ") -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Creates lag features for time-series forecasting.\n",
        "\n",
        "    Parameters:\n",
        "    - df (pd.DataFrame): The input dataframe containing time-series data.\n",
        "    - target_columns (list): List of target variable column names (e.g., [\"Particulate_Level_Bangalore\"]).\n",
        "    - lags (int): Number of past time steps (lags) to include.\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: A dataframe with added lag features.\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    df = create_lag_features(df, target_columns=[\"Particulate_Level_Bangalore\"], lags=4)\n",
        "    ```\n",
        "    \"\"\"\n",
        "    df = df.copy()\n",
        "\n",
        "    for col in target_columns:\n",
        "        for lag in range(1, lags + 1):\n",
        "            df[f\"{col}_Lag{lag}\"] = df[col].shift(lag)\n",
        "\n",
        "    df.dropna(inplace=True)  # Remove rows with NaN values due to shifting\n",
        "    return df\n",
        "\n",
        "def create_rolling_average_features(\n",
        "    df: pd.DataFrame,\n",
        "    target_columns: list,\n",
        "    window_size: int\n",
        ") -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Creates rolling average features to capture trends in time-series data.\n",
        "\n",
        "    Parameters:\n",
        "    - df (pd.DataFrame): The input dataframe containing time-series data.\n",
        "    - target_columns (list): List of target variable column names (e.g., [\"Particulate_Level_Bangalore\"]).\n",
        "    - window_size (int): The number of time steps to compute the rolling average.\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: A dataframe with added rolling average features.\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    df = create_rolling_average_features(df, target_columns=[\"Particulate_Level_Bangalore\"], window_size=4)\n",
        "    ```\n",
        "    \"\"\"\n",
        "    df = df.copy()\n",
        "\n",
        "    for col in target_columns:\n",
        "        df[f\"{col}_MA{window_size}\"] = df[col].rolling(window=window_size).mean()\n",
        "\n",
        "    df.dropna(inplace=True)  # Remove rows with NaN values due to rolling window\n",
        "    return df\n",
        "\n",
        "\n",
        "def train_xgboost_regressor(\n",
        "    df: pd.DataFrame,\n",
        "    target_column: str,\n",
        "    feature_columns: list,\n",
        "    test_size: float = 0.2,\n",
        "    n_estimators: int = 100,\n",
        "    learning_rate: float = 0.1,\n",
        "    max_depth: int = 5\n",
        ") -> tuple:\n",
        "    \"\"\"\n",
        "    Trains an XGBoost regression model for time-series forecasting.\n",
        "\n",
        "    Parameters:\n",
        "    - df (pd.DataFrame): The input dataframe containing features and target variable.\n",
        "    - target_column (str): The name of the target variable (e.g., \"Particulate_Level_Bangalore\").\n",
        "    - feature_columns (list): List of feature column names (e.g., lag features, temperature, petrol price).\n",
        "    - test_size (float): Proportion of data used for testing (default = 0.2). If 0, the entire dataset is used for training.\n",
        "    - n_estimators (int): Number of trees in the XGBoost model (default = 100).\n",
        "    - learning_rate (float): Learning rate for gradient boosting (default = 0.1).\n",
        "    - max_depth (int): Maximum depth of trees (default = 5).\n",
        "\n",
        "    Returns:\n",
        "    - tuple:\n",
        "        - trained_model (XGBRegressor): The trained XGBoost model.\n",
        "        - X_test (pd.DataFrame or None): The test set features (None if test_size=0).\n",
        "        - y_test (pd.Series or None): The actual target values for the test set (None if test_size=0).\n",
        "        - predictions (np.ndarray or None): The predicted values (None if test_size=0).\n",
        "        - RMSE (float or None): Root Mean Squared Error of the model (None if test_size=0).\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    model, X_test, y_test, predictions, rmse = train_xgboost_forecaster(\n",
        "        df, target_column=\"Particulate_Level_Bangalore\", feature_columns=[\"Temperature_Bangalore\", \"Petrol_Price\"], test_size=0\n",
        "    )\n",
        "    ```\n",
        "    \"\"\"\n",
        "    df = df.copy()\n",
        "    df.dropna(inplace=True)  # Drop missing values\n",
        "\n",
        "    # If test_size is 0, use the entire dataset for training\n",
        "    if test_size == 0:\n",
        "        X_train, y_train = df[feature_columns], df[target_column]\n",
        "        X_test, y_test, predictions, rmse = None, None, None, None\n",
        "    else:\n",
        "        X_train, X_test, y_train, y_test = train_test_split(\n",
        "            df[feature_columns], df[target_column], test_size=test_size, random_state=42\n",
        "        )\n",
        "\n",
        "    # Train XGBoost model\n",
        "    model = XGBRegressor(n_estimators=n_estimators, learning_rate=learning_rate, max_depth=max_depth)\n",
        "    model.fit(X_train, y_train)\n",
        "\n",
        "    # Make predictions if test_size > 0\n",
        "    if test_size > 0:\n",
        "        predictions = model.predict(X_test)\n",
        "        rmse = np.sqrt(mean_squared_error(y_test, predictions))\n",
        "    else:\n",
        "        predictions, rmse = None, None\n",
        "\n",
        "    return model, X_test, y_test, predictions, rmse\n",
        "\n",
        "\n",
        "def generate_forecast_timeseries_xgboost(\n",
        "    model: XGBRegressor,\n",
        "    past_df: pd.DataFrame,\n",
        "    future_observed_df: pd.DataFrame,\n",
        "    target_column: str,\n",
        "    feature_past: list,\n",
        "    feature_future_observed: list,\n",
        "    feature_future_not_observed: list,\n",
        "    lead_time: int\n",
        ") -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Generates time-series forecasts using a trained XGBoost model.\n",
        "\n",
        "    Parameters:\n",
        "    - model (XGBRegressor): The trained XGBoost model.\n",
        "    - past_df (pd.DataFrame): Historical data used to generate lag features.\n",
        "    - future_observed_df (pd.DataFrame): DataFrame containing known future values for exogenous variables.\n",
        "    - target_column (str): Name of the target variable to predict (e.g., \"Sales\", \"PM2.5\").\n",
        "    - feature_past (list): List of features derived from past values (e.g., lag features, rolling averages).\n",
        "    - feature_future_observed (list): List of features with known future values (e.g., fuel price, planned events).\n",
        "    - feature_future_not_observed (list): List of features not yet observed but estimated (e.g., forecasted traffic volume).\n",
        "    - lead_time (int): Number of time steps ahead to predict.\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: A DataFrame containing forecasted values for the specified lead_time.\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    forecast_df = generate_forecast_timeseries_xgboost(\n",
        "        model, past_df, future_df, target_column=\"Sales\",\n",
        "        feature_past=[\"Sales_Lag1\", \"Sales_Lag2\"],\n",
        "        feature_future_observed=[\"Marketing_Spend\", \"Holiday\"],\n",
        "        feature_future_not_observed=[\"Predicted_Traffic\"],\n",
        "        lead_time=6\n",
        "    )\n",
        "    print(forecast_df)\n",
        "    ```\n",
        "    \"\"\"\n",
        "    # Ensure past data includes necessary lag features\n",
        "    past_df = past_df.copy()\n",
        "\n",
        "    # Select the most recent past observation\n",
        "    forecast_input = past_df.iloc[-1:].copy()\n",
        "\n",
        "    # Merge with known future observed data\n",
        "    forecast_input.update(future_observed_df)\n",
        "\n",
        "    # Ensure correct feature selection\n",
        "    all_features = feature_past + feature_future_observed + feature_future_not_observed\n",
        "    forecast_input = forecast_input[all_features]\n",
        "\n",
        "    # Generate predictions iteratively for the specified lead time\n",
        "    predictions = []\n",
        "\n",
        "    for _ in range(lead_time):\n",
        "        pred = model.predict(forecast_input)\n",
        "        predictions.append(pred[0])  # Assuming a single target variable\n",
        "\n",
        "        # Shift data forward for iterative forecasting\n",
        "        forecast_input[f\"{target_column}_Lag1\"] = pred[0]  # Use prediction as next lag\n",
        "        for lag in range(2, len(feature_past) + 1):  # Shift other lag values\n",
        "            forecast_input[f\"{target_column}_Lag{lag}\"] = forecast_input[f\"{target_column}_Lag{lag-1}\"]\n",
        "\n",
        "    # Convert results into a DataFrame\n",
        "    forecast_df = pd.DataFrame(predictions, columns=[f\"Predicted_{target_column}\"])\n",
        "    forecast_df.index.name = \"Time Steps Ahead\"\n",
        "\n",
        "    return forecast_df\n",
        "\n",
        "def generate_forecast_timeseries_sarima(\n",
        "    past_df: pd.DataFrame,\n",
        "    future_observed_df: pd.DataFrame,\n",
        "    target_column: str,\n",
        "    feature_past: list,\n",
        "    feature_future_observed: list,\n",
        "    feature_future_not_observed: list,\n",
        "    lead_time: int,\n",
        "    sarima_order: tuple = (1, 1, 1),\n",
        "    seasonal_order: tuple = (1, 1, 1, 12)\n",
        ") -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Generates time-series forecasts using a SARIMAX model.\n",
        "\n",
        "    Parameters:\n",
        "    - past_df (pd.DataFrame): Historical data used for model fitting.\n",
        "    - future_observed_df (pd.DataFrame): DataFrame containing known future values for exogenous variables.\n",
        "    - target_column (str): The target variable to predict.\n",
        "    - feature_past (list): Features derived from past values (e.g., lag features).\n",
        "    - feature_future_observed (list): Features with known future values (e.g., fuel prices, holidays).\n",
        "    - feature_future_not_observed (list): Features not yet observed but estimated (e.g., predicted traffic volume).\n",
        "    - lead_time (int): Number of time steps ahead to forecast.\n",
        "    - sarima_order (tuple): The (p, d, q) order for SARIMA (default = (1,1,1)).\n",
        "    - seasonal_order (tuple): The (P, D, Q, s) seasonal order (default = (1,1,1,12) for monthly data).\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: A DataFrame containing forecasted values for the specified lead_time.\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    forecast_df = generate_forecast_timeseries_sarima(\n",
        "        past_df, future_df, target_column=\"Sales\",\n",
        "        feature_past=[\"Sales_Lag1\", \"Sales_Lag2\"],\n",
        "        feature_future_observed=[\"Marketing_Spend\", \"Holiday\"],\n",
        "        feature_future_not_observed=[\"Predicted_Traffic\"],\n",
        "        lead_time=6\n",
        "    )\n",
        "    print(forecast_df)\n",
        "    ```\n",
        "    \"\"\"\n",
        "    # Prepare past and future feature data\n",
        "    exog_past = past_df[feature_future_observed + feature_future_not_observed] if feature_future_observed or feature_future_not_observed else None\n",
        "    exog_future = future_observed_df[feature_future_observed + feature_future_not_observed] if feature_future_observed or feature_future_not_observed else None\n",
        "\n",
        "    # Fit SARIMAX model\n",
        "    model = SARIMAX(\n",
        "        past_df[target_column],\n",
        "        exog=exog_past,  # Use past exogenous data for training\n",
        "        order=sarima_order,\n",
        "        seasonal_order=seasonal_order,\n",
        "        enforce_stationarity=False,\n",
        "        enforce_invertibility=False\n",
        "    )\n",
        "\n",
        "    model_fit = model.fit(disp=False)  # Fit the model silently\n",
        "\n",
        "    # Forecast future values\n",
        "    forecast = model_fit.forecast(steps=lead_time, exog=exog_future)\n",
        "\n",
        "    # Convert to DataFrame\n",
        "    forecast_df = pd.DataFrame({f\"Predicted_{target_column}\": forecast})\n",
        "    forecast_df.index.name = \"Time Steps Ahead\"\n",
        "\n",
        "    return forecast_df\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "ebb0a1cf-b311-453b-b33e-b389d46dc8ea",
      "metadata": {
        "id": "ebb0a1cf-b311-453b-b33e-b389d46dc8ea"
      },
      "source": [
        "<div style=\"color:red\">\n",
        "    \n",
        "### ANSWER\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "480dcef1-34ce-4535-8eb1-81ec4eecc4d1",
      "metadata": {
        "id": "480dcef1-34ce-4535-8eb1-81ec4eecc4d1"
      },
      "source": [
        "#### **EDIT: [1.5 pts]**\n",
        "#### You can jot down initial notes here and flesh this out in more detail after the implementation.\n",
        "\n",
        "### **Describe Your Solution Approach**\n",
        "\n",
        "#### **• Data Exploration Notes** [0.5 pt]\n",
        "  -   All of the realationships are linear.\n",
        "\n",
        "#### **• Modeling Strategy & Choices** [1 pt]\n",
        "  - **Feature Alignment & Data Preparation:** I aligned the historical data by shifting the PM2.5 target variables by the specified lead time, ensuring that the features (including temperature, vehicle volume, and petrol price) at time *t* predict the air pollution levels at time *t + lead_time*. This approach effectively captures temporal dependencies in the data.\n",
        "  - **Model Selection & Forecasting Approach:** Separate linear regression models were trained for Bangalore and Delhi due to their simplicity, interpretability, and suitability for the relatively small dataset. For forecasting, the most recent observations for features (except for the future petrol price, which is known) are carried forward to predict future PM2.5 levels.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "d81dacf7-a62f-4104-aa7e-770479ca04e0",
      "metadata": {
        "id": "d81dacf7-a62f-4104-aa7e-770479ca04e0",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6a20f8ce-14c7-4275-c74b-3f4871654e64"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 200 entries, 0 to 199\n",
            "Data columns (total 8 columns):\n",
            " #   Column                        Non-Null Count  Dtype  \n",
            "---  ------                        --------------  -----  \n",
            " 0   Week                          200 non-null    int64  \n",
            " 1   Particulate_Level_Bangalore   200 non-null    float64\n",
            " 2   Temperature_Bangalore         200 non-null    float64\n",
            " 3   Avg_Vehicle_Volume_Bangalore  200 non-null    float64\n",
            " 4   Particulate_Level_Delhi       200 non-null    float64\n",
            " 5   Temperature_Delhi             200 non-null    float64\n",
            " 6   Avg_Vehicle_Volume_Delhi      200 non-null    float64\n",
            " 7   Petrol_Price                  200 non-null    float64\n",
            "dtypes: float64(7), int64(1)\n",
            "memory usage: 12.6 KB\n"
          ]
        }
      ],
      "source": [
        "# EDIT: [0.5 pt]\n",
        "# Add any additional data exploration code here\n",
        "data.info()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "727e0871-fa0e-49e6-b09d-ad8999207ad4",
      "metadata": {
        "id": "727e0871-fa0e-49e6-b09d-ad8999207ad4"
      },
      "outputs": [],
      "source": [
        "# EDIT: [O pts]\n",
        "# Add any additional code that you need for your modeling\n",
        "# Points for any code in this well will be assigned to the air pollution model training and prediction implementation cells\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "2528f9cb-2248-4849-bfa8-452578bf9129",
      "metadata": {
        "id": "2528f9cb-2248-4849-bfa8-452578bf9129"
      },
      "outputs": [],
      "source": [
        "def learn_air_pollution_forecast_model(train_file_path: str, lead_time: int) -> dict:\n",
        "    \"\"\"\n",
        "    Loads a dataset from a CSV file, aligns features with future target values (shifted by lead_time),\n",
        "    and trains a linear regression model to predict PM2.5 levels for Bangalore and Delhi.\n",
        "\n",
        "    Parameters:\n",
        "    - train_file_path (str): Path to the CSV file.\n",
        "    - lead_time (int): Number of weeks ahead for the prediction.\n",
        "\n",
        "    Returns:\n",
        "    - dict: Dictionary with keys \"Bangalore\" and \"Delhi\" containing the trained models.\n",
        "    \"\"\"\n",
        "    # Step 1: Load Data\n",
        "    df = pd.read_csv(train_file_path)\n",
        "\n",
        "    # Step 2: Ensure Data is Sorted by Week\n",
        "    df = df.sort_values(by=[\"Week\"])\n",
        "\n",
        "    # Step 3: Shift Target Variables for the given lead time\n",
        "    df[\"Particulate_Level_Bangalore_Future\"] = df[\"Particulate_Level_Bangalore\"].shift(-lead_time)\n",
        "    df[\"Particulate_Level_Delhi_Future\"] = df[\"Particulate_Level_Delhi\"].shift(-lead_time)\n",
        "\n",
        "    # Remove rows where the future target is NaN (i.e., the last lead_time rows)\n",
        "    df = df.dropna(subset=[\"Particulate_Level_Bangalore_Future\", \"Particulate_Level_Delhi_Future\"])\n",
        "\n",
        "    # Step 4: Prepare training data for Bangalore\n",
        "    X_bangalore = df[[\"Particulate_Level_Bangalore\", \"Temperature_Bangalore\", \"Avg_Vehicle_Volume_Bangalore\", \"Petrol_Price\"]]\n",
        "    y_bangalore = df[\"Particulate_Level_Bangalore_Future\"]\n",
        "\n",
        "    # Step 5: Prepare training data for Delhi\n",
        "    X_delhi = df[[\"Particulate_Level_Delhi\", \"Temperature_Delhi\", \"Avg_Vehicle_Volume_Delhi\", \"Petrol_Price\"]]\n",
        "    y_delhi = df[\"Particulate_Level_Delhi_Future\"]\n",
        "\n",
        "    # Step 6: Train models using Linear Regression\n",
        "    model_bangalore = LinearRegression().fit(X_bangalore, y_bangalore)\n",
        "    model_delhi = LinearRegression().fit(X_delhi, y_delhi)\n",
        "\n",
        "    # Return the models in a dictionary\n",
        "    return {\"Bangalore\": model_bangalore, \"Delhi\": model_delhi}\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "9e77ecdd-a562-4bf3-ab30-5158f339c906",
      "metadata": {
        "id": "9e77ecdd-a562-4bf3-ab30-5158f339c906"
      },
      "outputs": [],
      "source": [
        "# EDIT: [0.5 pts]\n",
        "# Implement the prediction of air pollution\n",
        "# You can choose to  edit the partial implementation but keep the signature same\n",
        "\n",
        "def forecast_air_pollution(model: dict, past_df: pd.DataFrame, future_observed_df: pd.DataFrame, lead_time: int) -> pd.DataFrame:\n",
        "    \"\"\"\n",
        "    Predicts PM2.5 levels for Bangalore and Delhi for future weeks.\n",
        "\n",
        "    Parameters:\n",
        "    - model (dict): Dictionary with trained models for each city.\n",
        "    - past_df (pd.DataFrame): Past weekly data with features.\n",
        "    - future_observed_df (pd.DataFrame): Future data containing \"Week\" and known future \"Petrol_Price\".\n",
        "    - lead_time (int): Number of weeks ahead to predict.\n",
        "\n",
        "    Returns:\n",
        "    - pd.DataFrame: DataFrame with columns \"Week\", \"Predicted_Particulate_Level_Bangalore\",\n",
        "      and \"Predicted_Particulate_Level_Delhi\".\n",
        "    \"\"\"\n",
        "    # Use the most recent (last) row from past_df to obtain the latest known values for the other features.\n",
        "    last_row = past_df.iloc[-1]\n",
        "    n_future = len(future_observed_df)\n",
        "\n",
        "    # Prepare feature DataFrame for Bangalore predictions:\n",
        "    features_bangalore = pd.DataFrame({\n",
        "        \"Particulate_Level_Bangalore\": [last_row[\"Particulate_Level_Bangalore\"]] * n_future,\n",
        "        \"Temperature_Bangalore\": [last_row[\"Temperature_Bangalore\"]] * n_future,\n",
        "        \"Avg_Vehicle_Volume_Bangalore\": [last_row[\"Avg_Vehicle_Volume_Bangalore\"]] * n_future,\n",
        "        \"Petrol_Price\": future_observed_df[\"Petrol_Price\"].values\n",
        "    })\n",
        "\n",
        "    # Prepare feature DataFrame for Delhi predictions:\n",
        "    features_delhi = pd.DataFrame({\n",
        "        \"Particulate_Level_Delhi\": [last_row[\"Particulate_Level_Delhi\"]] * n_future,\n",
        "        \"Temperature_Delhi\": [last_row[\"Temperature_Delhi\"]] * n_future,\n",
        "        \"Avg_Vehicle_Volume_Delhi\": [last_row[\"Avg_Vehicle_Volume_Delhi\"]] * n_future,\n",
        "        \"Petrol_Price\": future_observed_df[\"Petrol_Price\"].values\n",
        "    })\n",
        "\n",
        "    # Generate predictions using the trained models\n",
        "    pred_bangalore = model[\"Bangalore\"].predict(features_bangalore)\n",
        "    pred_delhi = model[\"Delhi\"].predict(features_delhi)\n",
        "\n",
        "    # Combine predictions with the week information from future_observed_df,\n",
        "    # using column names that the evaluation function expects.\n",
        "    pred_df = pd.DataFrame({\n",
        "        \"Week\": future_observed_df[\"Week\"],\n",
        "        \"Predicted_Particulate_Level_Bangalore\": pred_bangalore,\n",
        "        \"Predicted_Particulate_Level_Delhi\": pred_delhi\n",
        "    })\n",
        "\n",
        "    return pred_df\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "b2b32973-f713-4c29-9f7e-8af081fab10a",
      "metadata": {
        "id": "b2b32973-f713-4c29-9f7e-8af081fab10a"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "## **Q3: Test Air Pollution Forecast  on Public Dataset** [3 pts]\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "174ad98c-1104-4638-af34-13cff87cfe7c",
      "metadata": {
        "id": "174ad98c-1104-4638-af34-13cff87cfe7c"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "\n",
        "### DATA\n",
        "You are now invited to demonstrate the accuracy of your air pollution model on a test dataset from a different time period.\n",
        "\n",
        "**Use this only as your test set. Do not use this for training! No peeking into the air pollution columns column**\n",
        "\n",
        "- air_pollution_test_public_path: # historical air pollution and related factors data - same format as train set in Q1-Q2\n",
        "\n",
        "**Columns**\n",
        "- **`Week`** - Week index starting from the first week of observation (across multiple years)\n",
        "- **`Particulate_Level_Bangalore`** – PM2.5 pollution level in Bangalore *(Target Variable)*\n",
        "- **`Temperature_Bangalore`** – Weekly average temperature in Bangalore (°C)\n",
        "- **`Avg_Vehicle_Volume_Bangalore`** – Number of vehicles on Bangalore roads per week\n",
        "- **`Particulate_Level_Delhi`** – PM2.5 pollution level in Delhi *(Target Variable)*\n",
        "- **`Temperature_Delhi`** – Weekly average temperature in Delhi (°C)\n",
        "- **`Avg_Vehicle_Volume_Delhi`** – Number of vehicles on Delhi roads per week\n",
        "- **`Petrol_Price`** – Weekly fuel price per liter (INR), common to both cities\n",
        "                                            \n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "6545d03d-d186-4e35-a68a-6982dade2017",
      "metadata": {
        "id": "6545d03d-d186-4e35-a68a-6982dade2017"
      },
      "outputs": [],
      "source": [
        "# Public Test Dataset\n",
        "air_pollution_test_public_path = \"data/air_pollution_test_public.csv\"  #"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "b5ebae74-5747-43be-bb08-4b751447baa9",
      "metadata": {
        "id": "b5ebae74-5747-43be-bb08-4b751447baa9"
      },
      "source": [
        "<div style=\"color:blue\">  \n",
        "\n",
        "### TASK\n",
        "\n",
        "Execute the code below as is with your implementation of **learn_air_pollution_forecast_model** and **forecast_air_pollution** to test your model\n",
        "\n",
        "- Evaluate your model on this test set.\n",
        "- Compute **MAPE (mean absolute percentage error) and MSE (mean squared error)**\n",
        "  \n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "712424fb-20f3-4e94-ab42-d16b8c8273d2",
      "metadata": {
        "id": "712424fb-20f3-4e94-ab42-d16b8c8273d2"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "    \n",
        "### HELPER CODE\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "2b861f33-3a7d-480c-8478-7c16b5294cc3",
      "metadata": {
        "id": "2b861f33-3a7d-480c-8478-7c16b5294cc3"
      },
      "outputs": [],
      "source": [
        "# DO NOT MODIFY\n",
        "\n",
        "# HELPER CODE\n",
        "# Use these functions directly since these are meant for evaluation\n",
        "\n",
        "def evaluate_forecast(\n",
        "    model: Any,\n",
        "    test_file_path: str,\n",
        "    lead_time: int,\n",
        "    test_horizon: int\n",
        ") -> dict:\n",
        "    \"\"\"\n",
        "    Evaluates the trained forecasting model using MAPE and MSE on a test dataset.\n",
        "\n",
        "    Parameters:\n",
        "    - model (Any): A trained forecasting model from `learn_air_pollution_forecast_model`.\n",
        "    - test_file_path (str): Path to the CSV file containing both historical and test data.\n",
        "    - lead_time (int): Number of time steps ahead to forecast.\n",
        "    - test_horizon (int): Number of last weeks to use for accuracy evaluation (default = 12 weeks).\n",
        "\n",
        "    Returns:\n",
        "    - dict: A dictionary containing MAPE and MSE scores for Bangalore and Delhi.\n",
        "\n",
        "    Example Usage:\n",
        "    ```python\n",
        "    metrics = evaluate_forecast(model, \"test_data.csv\", lead_time=6, test_horizon=12)\n",
        "    print(metrics)\n",
        "    ```\n",
        "    \"\"\"\n",
        "    # Step 1: Load the Test Dataset\n",
        "    test_df = pd.read_csv(test_file_path)\n",
        "\n",
        "    # Step 2: Ensure Test Data is Sorted by Week\n",
        "    test_df = test_df.sort_values(by=\"Week\")\n",
        "\n",
        "    # Step 3: Define Past Data & Extract Last `test_horizon` Weeks for Evaluation\n",
        "    past_df = test_df.iloc[:-test_horizon].reset_index(drop=True)  # Use all rows except the last `test_horizon`\n",
        "    test_df = test_df.iloc[-test_horizon:].reset_index(drop=True)  # Use only the last `test_horizon` weeks\n",
        "\n",
        "    # Step 4: Extract Future Observed Features Required for Forecasting\n",
        "    future_observed_df = test_df[[\"Week\", \"Petrol_Price\"]].head(lead_time)  # Assuming only petrol price is known\n",
        "\n",
        "    # Step 5: Generate Forecasts Using the Model\n",
        "    forecast_df = forecast_air_pollution(model, past_df, future_observed_df, lead_time)\n",
        "\n",
        "    # Step 6: Merge Forecasts with Actual Test Values\n",
        "    merged_df = forecast_df.merge(test_df, on=\"Week\", how=\"left\")\n",
        "\n",
        "    # Step 7: Compute MAPE (Mean Absolute Percentage Error) using sklearn\n",
        "    mape_bangalore = mean_absolute_percentage_error(\n",
        "        merged_df[\"Particulate_Level_Bangalore\"], merged_df[\"Predicted_Particulate_Level_Bangalore\"]\n",
        "    )\n",
        "    mape_delhi = mean_absolute_percentage_error(\n",
        "        merged_df[\"Particulate_Level_Delhi\"], merged_df[\"Predicted_Particulate_Level_Delhi\"]\n",
        "    )\n",
        "\n",
        "    # Step 8: Compute MSE (Mean Squared Error)\n",
        "    mse_bangalore = mean_squared_error(\n",
        "        merged_df[\"Particulate_Level_Bangalore\"], merged_df[\"Predicted_Particulate_Level_Bangalore\"]\n",
        "    )\n",
        "    mse_delhi = mean_squared_error(\n",
        "        merged_df[\"Particulate_Level_Delhi\"], merged_df[\"Predicted_Particulate_Level_Delhi\"]\n",
        "    )\n",
        "\n",
        "    # Step 9: Store and Return Results\n",
        "    results = {\n",
        "        \"MAPE_Bangalore\": mape_bangalore * 100,  # Convert to percentage\n",
        "        \"MAPE_Delhi\": mape_delhi * 100,  # Convert to percentage\n",
        "        \"MSE_Bangalore\": mse_bangalore,\n",
        "        \"MSE_Delhi\": mse_delhi\n",
        "    }\n",
        "\n",
        "    return results\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "a114f9f5-f1b3-4a1a-ba55-7ce0c573ef08",
      "metadata": {
        "id": "a114f9f5-f1b3-4a1a-ba55-7ce0c573ef08",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "a155cf76-6da2-4bed-b1fd-21028d0feeb9"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{'MAPE_Bangalore': 2.3420671061017027, 'MAPE_Delhi': 2.3216532885246517, 'MSE_Bangalore': 37.10163535586846, 'MSE_Delhi': 35.111938556330465}\n",
            "{'MAPE_Bangalore': 2.1099703137419175, 'MAPE_Delhi': 3.175302326203667, 'MSE_Bangalore': 27.448565170806845, 'MSE_Delhi': 58.07529112621429}\n"
          ]
        }
      ],
      "source": [
        "# DO NOT MODIFY\n",
        "# Run this code and observe the MSE and  MAPE values for train & test sets for 3 wks of lead time on 12 wks of test horizon\n",
        "# [pts depend on performance range]\n",
        "model = learn_air_pollution_forecast_model(air_pollution_train_path, lead_time=3)\n",
        "print(evaluate_forecast(model,air_pollution_train_path, lead_time=6, test_horizon=12))\n",
        "print(evaluate_forecast(model,air_pollution_test_public_path, lead_time=6, test_horizon=12))\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "06100e12-6da5-42f1-b437-0b17fd92280f",
      "metadata": {
        "id": "06100e12-6da5-42f1-b437-0b17fd92280f"
      },
      "source": [
        "<div style=\"color:red\">\n",
        "    \n",
        "### ANSWER\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "40a1cb92-1a56-4277-b6ad-51dda9dcbd9d",
      "metadata": {
        "id": "40a1cb92-1a56-4277-b6ad-51dda9dcbd9d"
      },
      "source": [
        "#### **EDIT: [3 pts]**\n",
        "#### You can jot down the train and test metrics below\n",
        "\n",
        "### **Train Set Performance**\n",
        "  - MAPE for Particulate_Matter_Bangalore: 2.3420671061017027\n",
        "  - MSE for Particulate_Matter_Bangalore: 37.10163535586846\n",
        "  - MAPE for Particulate_Matter_Delhi: 2.3216532885246517\n",
        "  - MSE for Particulate_Matter_Delhi: 35.111938556330465\n",
        "\n",
        "### **Public Test Set Performance** [varying points for different range]\n",
        "  - MAPE for Particulate_Matter_Bangalore: 2.1099703137419175\n",
        "  - MSE for Particulate_Matter_Bangalore: 27.448565170806845\n",
        "  - MAPE for Particulate_Matter_Delhi: 3.175302326203667\n",
        "  - MSE for Particulate_Matter_Delhi: 58.07529112621429\n",
        "\n",
        "### **Any Additional Observations**\n",
        "  -   None\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "15e0f606-9220-4647-9165-2077c2c9edc5",
      "metadata": {
        "id": "15e0f606-9220-4647-9165-2077c2c9edc5"
      },
      "source": [
        "<div style=\"color:red\">\n",
        "\n",
        "## YOU CAN STOP THE TEST HERE -- BELOW EVALUATION TO BE PERFORMED BY INAIO\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "55913a7f-d68b-4825-9394-26746d8c9c8b",
      "metadata": {
        "id": "55913a7f-d68b-4825-9394-26746d8c9c8b"
      },
      "source": [
        "<div style=\"color:blue\">\n",
        "\n",
        "## **Q4: Test Air Pollution Forecast on Private Dataset** [2 pts]\n",
        "\n",
        "- Same metrics and lead time as Public Dataset\n",
        "\n",
        "</div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "ea8e6016-4b27-4adb-9f6e-e4481b0c126c",
      "metadata": {
        "id": "ea8e6016-4b27-4adb-9f6e-e4481b0c126c"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.18"
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}