Multiple_Linear_Regression.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Multiple Linear Regression",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CazISR8X_HUG"
      },
      "source": [
        "# Multiple Linear Regression"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pOyqYHTk_Q57"
      },
      "source": [
        "## Importing the libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "T_YHJjnD_Tja"
      },
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vgC61-ah_WIz"
      },
      "source": [
        "## Importing the dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UrxyEKGn_ez7"
      },
      "source": [
        "dataset = pd.read_csv('50_Startups.csv')\n",
        "X = dataset.iloc[:, :-1].values\n",
        "y = dataset.iloc[:, -1].values"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GOB3QhV9B5kD",
        "outputId": "eecdc574-cedd-4140-985d-60b93e6a7efe",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 857
        }
      },
      "source": [
        "print(X)"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[165349.2 136897.8 471784.1 'New York']\n",
            " [162597.7 151377.59 443898.53 'California']\n",
            " [153441.51 101145.55 407934.54 'Florida']\n",
            " [144372.41 118671.85 383199.62 'New York']\n",
            " [142107.34 91391.77 366168.42 'Florida']\n",
            " [131876.9 99814.71 362861.36 'New York']\n",
            " [134615.46 147198.87 127716.82 'California']\n",
            " [130298.13 145530.06 323876.68 'Florida']\n",
            " [120542.52 148718.95 311613.29 'New York']\n",
            " [123334.88 108679.17 304981.62 'California']\n",
            " [101913.08 110594.11 229160.95 'Florida']\n",
            " [100671.96 91790.61 249744.55 'California']\n",
            " [93863.75 127320.38 249839.44 'Florida']\n",
            " [91992.39 135495.07 252664.93 'California']\n",
            " [119943.24 156547.42 256512.92 'Florida']\n",
            " [114523.61 122616.84 261776.23 'New York']\n",
            " [78013.11 121597.55 264346.06 'California']\n",
            " [94657.16 145077.58 282574.31 'New York']\n",
            " [91749.16 114175.79 294919.57 'Florida']\n",
            " [86419.7 153514.11 0.0 'New York']\n",
            " [76253.86 113867.3 298664.47 'California']\n",
            " [78389.47 153773.43 299737.29 'New York']\n",
            " [73994.56 122782.75 303319.26 'Florida']\n",
            " [67532.53 105751.03 304768.73 'Florida']\n",
            " [77044.01 99281.34 140574.81 'New York']\n",
            " [64664.71 139553.16 137962.62 'California']\n",
            " [75328.87 144135.98 134050.07 'Florida']\n",
            " [72107.6 127864.55 353183.81 'New York']\n",
            " [66051.52 182645.56 118148.2 'Florida']\n",
            " [65605.48 153032.06 107138.38 'New York']\n",
            " [61994.48 115641.28 91131.24 'Florida']\n",
            " [61136.38 152701.92 88218.23 'New York']\n",
            " [63408.86 129219.61 46085.25 'California']\n",
            " [55493.95 103057.49 214634.81 'Florida']\n",
            " [46426.07 157693.92 210797.67 'California']\n",
            " [46014.02 85047.44 205517.64 'New York']\n",
            " [28663.76 127056.21 201126.82 'Florida']\n",
            " [44069.95 51283.14 197029.42 'California']\n",
            " [20229.59 65947.93 185265.1 'New York']\n",
            " [38558.51 82982.09 174999.3 'California']\n",
            " [28754.33 118546.05 172795.67 'California']\n",
            " [27892.92 84710.77 164470.71 'Florida']\n",
            " [23640.93 96189.63 148001.11 'California']\n",
            " [15505.73 127382.3 35534.17 'New York']\n",
            " [22177.74 154806.14 28334.72 'California']\n",
            " [1000.23 124153.04 1903.93 'New York']\n",
            " [1315.46 115816.21 297114.46 'Florida']\n",
            " [0.0 135426.92 0.0 'California']\n",
            " [542.05 51743.15 0.0 'New York']\n",
            " [0.0 116983.8 45173.06 'California']]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VadrvE7s_lS9"
      },
      "source": [
        "## Encoding categorical data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wV3fD1mbAvsh"
      },
      "source": [
        "from sklearn.compose import ColumnTransformer\n",
        "from sklearn.preprocessing import OneHotEncoder\n",
        "ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')\n",
        "X = np.array(ct.fit_transform(X))"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4ym3HdYeCGYG",
        "outputId": "75d3a14b-9bbd-4e62-a40b-63a6eeafca2a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 857
        }
      },
      "source": [
        "print(X)"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0.0 0.0 1.0 165349.2 136897.8 471784.1]\n",
            " [1.0 0.0 0.0 162597.7 151377.59 443898.53]\n",
            " [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n",
            " [0.0 0.0 1.0 144372.41 118671.85 383199.62]\n",
            " [0.0 1.0 0.0 142107.34 91391.77 366168.42]\n",
            " [0.0 0.0 1.0 131876.9 99814.71 362861.36]\n",
            " [1.0 0.0 0.0 134615.46 147198.87 127716.82]\n",
            " [0.0 1.0 0.0 130298.13 145530.06 323876.68]\n",
            " [0.0 0.0 1.0 120542.52 148718.95 311613.29]\n",
            " [1.0 0.0 0.0 123334.88 108679.17 304981.62]\n",
            " [0.0 1.0 0.0 101913.08 110594.11 229160.95]\n",
            " [1.0 0.0 0.0 100671.96 91790.61 249744.55]\n",
            " [0.0 1.0 0.0 93863.75 127320.38 249839.44]\n",
            " [1.0 0.0 0.0 91992.39 135495.07 252664.93]\n",
            " [0.0 1.0 0.0 119943.24 156547.42 256512.92]\n",
            " [0.0 0.0 1.0 114523.61 122616.84 261776.23]\n",
            " [1.0 0.0 0.0 78013.11 121597.55 264346.06]\n",
            " [0.0 0.0 1.0 94657.16 145077.58 282574.31]\n",
            " [0.0 1.0 0.0 91749.16 114175.79 294919.57]\n",
            " [0.0 0.0 1.0 86419.7 153514.11 0.0]\n",
            " [1.0 0.0 0.0 76253.86 113867.3 298664.47]\n",
            " [0.0 0.0 1.0 78389.47 153773.43 299737.29]\n",
            " [0.0 1.0 0.0 73994.56 122782.75 303319.26]\n",
            " [0.0 1.0 0.0 67532.53 105751.03 304768.73]\n",
            " [0.0 0.0 1.0 77044.01 99281.34 140574.81]\n",
            " [1.0 0.0 0.0 64664.71 139553.16 137962.62]\n",
            " [0.0 1.0 0.0 75328.87 144135.98 134050.07]\n",
            " [0.0 0.0 1.0 72107.6 127864.55 353183.81]\n",
            " [0.0 1.0 0.0 66051.52 182645.56 118148.2]\n",
            " [0.0 0.0 1.0 65605.48 153032.06 107138.38]\n",
            " [0.0 1.0 0.0 61994.48 115641.28 91131.24]\n",
            " [0.0 0.0 1.0 61136.38 152701.92 88218.23]\n",
            " [1.0 0.0 0.0 63408.86 129219.61 46085.25]\n",
            " [0.0 1.0 0.0 55493.95 103057.49 214634.81]\n",
            " [1.0 0.0 0.0 46426.07 157693.92 210797.67]\n",
            " [0.0 0.0 1.0 46014.02 85047.44 205517.64]\n",
            " [0.0 1.0 0.0 28663.76 127056.21 201126.82]\n",
            " [1.0 0.0 0.0 44069.95 51283.14 197029.42]\n",
            " [0.0 0.0 1.0 20229.59 65947.93 185265.1]\n",
            " [1.0 0.0 0.0 38558.51 82982.09 174999.3]\n",
            " [1.0 0.0 0.0 28754.33 118546.05 172795.67]\n",
            " [0.0 1.0 0.0 27892.92 84710.77 164470.71]\n",
            " [1.0 0.0 0.0 23640.93 96189.63 148001.11]\n",
            " [0.0 0.0 1.0 15505.73 127382.3 35534.17]\n",
            " [1.0 0.0 0.0 22177.74 154806.14 28334.72]\n",
            " [0.0 0.0 1.0 1000.23 124153.04 1903.93]\n",
            " [0.0 1.0 0.0 1315.46 115816.21 297114.46]\n",
            " [1.0 0.0 0.0 0.0 135426.92 0.0]\n",
            " [0.0 0.0 1.0 542.05 51743.15 0.0]\n",
            " [1.0 0.0 0.0 0.0 116983.8 45173.06]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WemVnqgeA70k"
      },
      "source": [
        "## Splitting the dataset into the Training set and Test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Kb_v_ae-A-20"
      },
      "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": 8,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "k-McZVsQBINc"
      },
      "source": [
        "## Training the Multiple Linear Regression model on the Training set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ywPjx0L1BMiD",
        "outputId": "721b8613-3990-468d-c2f0-c828fb4f3b7a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "from sklearn.linear_model import LinearRegression\n",
        "regressor = LinearRegression()\n",
        "regressor.fit(X_train, y_train)"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xNkXL1YQBiBT"
      },
      "source": [
        "## Predicting the Test set results"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TQKmwvtdBkyb",
        "outputId": "71d3e9ba-a6ef-4e16-9805-664f2a1b777e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 185
        }
      },
      "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": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[103015.2  103282.38]\n",
            " [132582.28 144259.4 ]\n",
            " [132447.74 146121.95]\n",
            " [ 71976.1   77798.83]\n",
            " [178537.48 191050.39]\n",
            " [116161.24 105008.31]\n",
            " [ 67851.69  81229.06]\n",
            " [ 98791.73  97483.56]\n",
            " [113969.44 110352.25]\n",
            " [167921.07 166187.94]]\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}