multiple_linear_regression.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "multiple_linear_regression.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CazISR8X_HUG",
        "colab_type": "text"
      },
      "source": [
        "# Multiple Linear Regression"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pOyqYHTk_Q57",
        "colab_type": "text"
      },
      "source": [
        "## Importing the libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "T_YHJjnD_Tja",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vgC61-ah_WIz",
        "colab_type": "text"
      },
      "source": [
        "## Importing the dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UrxyEKGn_ez7",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "dataset = pd.read_csv('ENTER_THE_NAME_OF_YOUR_DATASET_HERE.csv')\n",
        "X = dataset.iloc[:, :-1].values\n",
        "y = dataset.iloc[:, -1].values"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WemVnqgeA70k",
        "colab_type": "text"
      },
      "source": [
        "## Splitting the dataset into the Training set and Test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Kb_v_ae-A-20",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "k-McZVsQBINc",
        "colab_type": "text"
      },
      "source": [
        "## Training the Multiple Linear Regression model on the Training set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ywPjx0L1BMiD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.linear_model import LinearRegression\n",
        "regressor = LinearRegression()\n",
        "regressor.fit(X_train, y_train)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xNkXL1YQBiBT",
        "colab_type": "text"
      },
      "source": [
        "## Predicting the Test set results"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TQKmwvtdBkyb",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "y_pred = regressor.predict(X_test)\n",
        "np.set_printoptions(precision=2)\n",
        "print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "50DZZy0UyhLi",
        "colab_type": "text"
      },
      "source": [
        "## Evaluating the Model Performance"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xPagAOKDywV4",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.metrics import r2_score\n",
        "r2_score(y_test, y_pred)"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}