![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install shap"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "gNIsfIay6Mvj",
+ "outputId": "f960c409-c439-42e8-8d3c-2dcd6918f2e3"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Collecting shap\n",
+ " Downloading shap-0.45.1-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (540 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m540.5/540.5 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from shap) (1.25.2)\n",
+ "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from shap) (1.11.4)\n",
+ "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from shap) (1.2.2)\n",
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from shap) (2.0.3)\n",
+ "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.10/dist-packages (from shap) (4.66.4)\n",
+ "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.10/dist-packages (from shap) (24.0)\n",
+ "Collecting slicer==0.0.8 (from shap)\n",
+ " Downloading slicer-0.0.8-py3-none-any.whl (15 kB)\n",
+ "Requirement already satisfied: numba in /usr/local/lib/python3.10/dist-packages (from shap) (0.58.1)\n",
+ "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from shap) (2.2.1)\n",
+ "Requirement already satisfied: llvmlite<0.42,>=0.41.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->shap) (0.41.1)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2023.4)\n",
+ "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2024.1)\n",
+ "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (1.4.2)\n",
+ "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (3.5.0)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->shap) (1.16.0)\n",
+ "Installing collected packages: slicer, shap\n",
+ "Successfully installed shap-0.45.1 slicer-0.0.8\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Importing the necessary libraries"
+ ],
+ "metadata": {
+ "id": "TtBTWxJaCFR_"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "UBLqLmF_03nU"
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
+ "from sklearn.model_selection import train_test_split, GridSearchCV\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "from sklearn.compose import ColumnTransformer\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "from sklearn.metrics import mean_squared_error, r2_score\n",
+ "import shap\n",
+ "import joblib"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Loading the dataset"
+ ],
+ "metadata": {
+ "id": "7ScPGfvDCK44"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ " !pip install chardet\n",
+ " import chardet\n",
+ "\n",
+ " with open(\"/content/global air pollution dataset.csv\", \"rb\") as f:\n",
+ " encoding = chardet.detect(f.read())[\"encoding\"]\n",
+ "\n",
+ " df = pd.read_csv(\"/content/global air pollution dataset.csv\", encoding=encoding)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "KAMIzTh06rL9",
+ "outputId": "23a12f8a-8a71-49a7-a010-7c0c27157769"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Requirement already satisfied: chardet in /usr/local/lib/python3.10/dist-packages (5.2.0)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Mean Median calculation\n"
+ ],
+ "metadata": {
+ "id": "Al7HsKVAUC7d"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "mean_aqi = df[[\"AQI Value\", \"CO AQI Value\", \"Ozone AQI Value\", \"NO2 AQI Value\", \"PM2.5 AQI Value\"]].mean()\n",
+ "\n",
+ "print(\"Average (Mean) AQI Values:\")\n",
+ "print(mean_aqi)\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "_KNtvDgKT21E",
+ "outputId": "e30b4863-2b45-4ebf-ec08-1295b39a684d"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Average (Mean) AQI Values:\n",
+ "AQI Value 72.010868\n",
+ "CO AQI Value 1.368367\n",
+ "Ozone AQI Value 35.193709\n",
+ "NO2 AQI Value 3.063334\n",
+ "PM2.5 AQI Value 68.519755\n",
+ "dtype: float64\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Visualising the dataset"
+ ],
+ "metadata": {
+ "id": "UNslO0C8CN92"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df.head()"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 258
+ },
+ "id": "IOaYHNRk1DvP",
+ "outputId": "968d7829-601a-4aff-9e6a-92c1f64a96b0"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " Country City AQI Value AQI Category CO AQI Value \\\n",
+ "0 Russian Federation Praskoveya 51 Moderate 1 \n",
+ "1 Brazil Presidente Dutra 41 Good 1 \n",
+ "2 Italy Priolo Gargallo 66 Moderate 1 \n",
+ "3 Poland Przasnysz 34 Good 1 \n",
+ "4 France Punaauia 22 Good 0 \n",
+ "\n",
+ " CO AQI Category Ozone AQI Value Ozone AQI Category NO2 AQI Value \\\n",
+ "0 Good 36 Good 0 \n",
+ "1 Good 5 Good 1 \n",
+ "2 Good 39 Good 2 \n",
+ "3 Good 34 Good 0 \n",
+ "4 Good 22 Good 0 \n",
+ "\n",
+ " NO2 AQI Category PM2.5 AQI Value PM2.5 AQI Category \n",
+ "0 Good 51 Moderate \n",
+ "1 Good 41 Good \n",
+ "2 Good 66 Moderate \n",
+ "3 Good 20 Good \n",
+ "4 Good 6 Good "
+ ],
+ "text/html": [
+ "\n",
+ " | \n", + " | Country | \n", + "City | \n", + "AQI Value | \n", + "AQI Category | \n", + "CO AQI Value | \n", + "CO AQI Category | \n", + "Ozone AQI Value | \n", + "Ozone AQI Category | \n", + "NO2 AQI Value | \n", + "NO2 AQI Category | \n", + "PM2.5 AQI Value | \n", + "PM2.5 AQI Category | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "Russian Federation | \n", + "Praskoveya | \n", + "51 | \n", + "Moderate | \n", + "1 | \n", + "Good | \n", + "36 | \n", + "Good | \n", + "0 | \n", + "Good | \n", + "51 | \n", + "Moderate | \n", + "
| 1 | \n", + "Brazil | \n", + "Presidente Dutra | \n", + "41 | \n", + "Good | \n", + "1 | \n", + "Good | \n", + "5 | \n", + "Good | \n", + "1 | \n", + "Good | \n", + "41 | \n", + "Good | \n", + "
| 2 | \n", + "Italy | \n", + "Priolo Gargallo | \n", + "66 | \n", + "Moderate | \n", + "1 | \n", + "Good | \n", + "39 | \n", + "Good | \n", + "2 | \n", + "Good | \n", + "66 | \n", + "Moderate | \n", + "
| 3 | \n", + "Poland | \n", + "Przasnysz | \n", + "34 | \n", + "Good | \n", + "1 | \n", + "Good | \n", + "34 | \n", + "Good | \n", + "0 | \n", + "Good | \n", + "20 | \n", + "Good | \n", + "
| 4 | \n", + "France | \n", + "Punaauia | \n", + "22 | \n", + "Good | \n", + "0 | \n", + "Good | \n", + "22 | \n", + "Good | \n", + "0 | \n", + "Good | \n", + "6 | \n", + "Good | \n", + "
GridSearchCV(cv=3, error_score='raise',\n",
+ " estimator=RandomForestRegressor(random_state=42), n_jobs=-1,\n",
+ " param_grid={'max_depth': [None, 10, 20, 30],\n",
+ " 'max_features': ['sqrt', 'log2', None],\n",
+ " 'min_samples_leaf': [1, 2, 4],\n",
+ " 'min_samples_split': [2, 5, 10],\n",
+ " 'n_estimators': [50, 100, 200]},\n",
+ " scoring='neg_mean_squared_error')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. GridSearchCV(cv=3, error_score='raise',\n",
+ " estimator=RandomForestRegressor(random_state=42), n_jobs=-1,\n",
+ " param_grid={'max_depth': [None, 10, 20, 30],\n",
+ " 'max_features': ['sqrt', 'log2', None],\n",
+ " 'min_samples_leaf': [1, 2, 4],\n",
+ " 'min_samples_split': [2, 5, 10],\n",
+ " 'n_estimators': [50, 100, 200]},\n",
+ " scoring='neg_mean_squared_error')RandomForestRegressor(random_state=42)
RandomForestRegressor(random_state=42)