Created using Colaboratory

Author: DeepthiTabithaBennet

Multiple_Linear_Regression.ipynb

@@ -0,0 +1,204 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "collapsed_sections": [],
+      "authorship_tag": "ABX9TyPo1/jVmtDE9X+OTsJBXsvz",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/DeepthiTabithaBennet/Python_AppliedStatistics/blob/main/Multiple_Linear_Regression.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RmGFoV8P22AE"
+      },
+      "source": [
+        "# **Multiple Linear Regression**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "75W-ukM9p6LC"
+      },
+      "source": [
+        "# Written by Deepthi Tabitha Bennet\n",
+        "\n",
+        "!pip install matplotlib\n",
+        "!pip install sklearn\n",
+        "!pip install LinearRegression\n",
+        "\n",
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "import seaborn as sns\n",
+        "%matplotlib inline "
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YWyZDKvUvt94"
+      },
+      "source": [
+        "raw_data = pd.read_csv('Housing_Data.csv')"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "_kQumzvYsv1Y"
+      },
+      "source": [
+        "raw_data.info()"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "VGmvmAJusv6J"
+      },
+      "source": [
+        "sns.pairplot(raw_data)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "e-RE0_pmsv95"
+      },
+      "source": [
+        "x = raw_data[['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms', 'Avg. Area Number of Bedrooms', 'Area Population']]\n",
+        "y = raw_data['Price']"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "dCTLqMejvtlA"
+      },
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "LtlnUPffvtt-"
+      },
+      "source": [
+        "from sklearn.linear_model import LinearRegression\n",
+        "\n",
+        "model = LinearRegression()\n",
+        "model.fit(x_train, y_train)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "bCbrRU6hvt3O"
+      },
+      "source": [
+        "print(model.coef_)\n",
+        "print(model.intercept_)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "-ngs8G_5vt6e"
+      },
+      "source": [
+        "pd.DataFrame(model.coef_, x.columns, columns = ['Coeff'])"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "eVw4lndpC45e"
+      },
+      "source": [
+        "predictions = model.predict(x_test)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "PblNR_9BC5BQ"
+      },
+      "source": [
+        "plt.scatter(y_test, predictions)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "-3fxeEceC5Tf"
+      },
+      "source": [
+        "plt.hist(y_test - predictions)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "EI_gS2JfDFHO"
+      },
+      "source": [
+        "from sklearn import metrics\n",
+        "\n",
+        "metrics.mean_absolute_error(y_test, predictions)\n",
+        "metrics.mean_squared_error(y_test, predictions)\n",
+        "np.sqrt(metrics.mean_squared_error(y_test, predictions))"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}