Multivariate Regression.ipynb

multivariate-regression.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Multivariate Regression.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPm5X7kDBBctbs6+UGNwR8K",
      "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/gist/MainakRepositor/be1f6cf89989d2515c7665a7fd10c9d0/multivariate-regression.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7OUUdjDIkaeY",
        "outputId": "ea753610-9463-4044-ecaa-6b5272c6fdcc"
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline\n",
        "print(\"All necessary packages have been installed successfully!\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "All necessary packages have been installed successfully!\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 362
        },
        "id": "sODN3m2aky9t",
        "outputId": "cfe5b1ba-46bc-4d3e-9202-f5d515e80437"
      },
      "source": [
        "url = 'https://raw.githubusercontent.com/MainakRepositor/Datasets-/master/House%20rent.csv'\n",
        "df = pd.read_csv(url,error_bad_lines=False)\n",
        "df.head(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Area</th>\n",
              "      <th>Bedrooms</th>\n",
              "      <th>Age</th>\n",
              "      <th>Rent</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1024</td>\n",
              "      <td>3.0</td>\n",
              "      <td>15</td>\n",
              "      <td>11200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1200</td>\n",
              "      <td>4.0</td>\n",
              "      <td>10</td>\n",
              "      <td>33650</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>800</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5</td>\n",
              "      <td>8000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>674</td>\n",
              "      <td>2.0</td>\n",
              "      <td>10</td>\n",
              "      <td>6120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>766</td>\n",
              "      <td>2.0</td>\n",
              "      <td>11</td>\n",
              "      <td>6000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>680</td>\n",
              "      <td>NaN</td>\n",
              "      <td>36</td>\n",
              "      <td>3200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>750</td>\n",
              "      <td>NaN</td>\n",
              "      <td>10</td>\n",
              "      <td>3500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>900</td>\n",
              "      <td>3.0</td>\n",
              "      <td>20</td>\n",
              "      <td>3345</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>967</td>\n",
              "      <td>3.0</td>\n",
              "      <td>23</td>\n",
              "      <td>3100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>720</td>\n",
              "      <td>3.0</td>\n",
              "      <td>7</td>\n",
              "      <td>6200</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Area  Bedrooms  Age   Rent\n",
              "0  1024       3.0   15  11200\n",
              "1  1200       4.0   10  33650\n",
              "2   800       2.0    5   8000\n",
              "3   674       2.0   10   6120\n",
              "4   766       2.0   11   6000\n",
              "5   680       NaN   36   3200\n",
              "6   750       NaN   10   3500\n",
              "7   900       3.0   20   3345\n",
              "8   967       3.0   23   3100\n",
              "9   720       3.0    7   6200"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "q2IhmEUAlTuF",
        "outputId": "8599ef93-79af-4287-ddca-5b7c0d38a774"
      },
      "source": [
        "r,c = df.shape\n",
        "print(\"Rows = \",r)\n",
        "print(\"Column = \",c)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Rows =  40\n",
            "Column =  4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xg4Q0lvflZVE",
        "outputId": "085063c9-18cf-473c-967c-1d4644e05677"
      },
      "source": [
        "print(\"Are there any null values in the dataset ?\",df.isnull().values.any())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Are there any null values in the dataset ? True\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JYwwKQbAljZ4",
        "outputId": "c9d26663-558f-4a42-cdfe-78909c72d4ad"
      },
      "source": [
        "df.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Area        0\n",
              "Bedrooms    4\n",
              "Age         0\n",
              "Rent        0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9LB83RD0ojmd",
        "outputId": "575b274f-d90a-4eb6-ca52-6da66b29df12"
      },
      "source": [
        "median = df.Bedrooms.median()\n",
        "median"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "3.0"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 362
        },
        "id": "jhi59ntDojgG",
        "outputId": "1225b276-3014-4f86-b735-011b017507d5"
      },
      "source": [
        "df.Bedrooms = df.Bedrooms.fillna(int(median))\n",
        "df.head(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Area</th>\n",
              "      <th>Bedrooms</th>\n",
              "      <th>Age</th>\n",
              "      <th>Rent</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1024</td>\n",
              "      <td>3.0</td>\n",
              "      <td>15</td>\n",
              "      <td>11200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1200</td>\n",
              "      <td>4.0</td>\n",
              "      <td>10</td>\n",
              "      <td>33650</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>800</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5</td>\n",
              "      <td>8000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>674</td>\n",
              "      <td>2.0</td>\n",
              "      <td>10</td>\n",
              "      <td>6120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>766</td>\n",
              "      <td>2.0</td>\n",
              "      <td>11</td>\n",
              "      <td>6000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>680</td>\n",
              "      <td>3.0</td>\n",
              "      <td>36</td>\n",
              "      <td>3200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>750</td>\n",
              "      <td>3.0</td>\n",
              "      <td>10</td>\n",
              "      <td>3500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>900</td>\n",
              "      <td>3.0</td>\n",
              "      <td>20</td>\n",
              "      <td>3345</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>967</td>\n",
              "      <td>3.0</td>\n",
              "      <td>23</td>\n",
              "      <td>3100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>720</td>\n",
              "      <td>3.0</td>\n",
              "      <td>7</td>\n",
              "      <td>6200</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Area  Bedrooms  Age   Rent\n",
              "0  1024       3.0   15  11200\n",
              "1  1200       4.0   10  33650\n",
              "2   800       2.0    5   8000\n",
              "3   674       2.0   10   6120\n",
              "4   766       2.0   11   6000\n",
              "5   680       3.0   36   3200\n",
              "6   750       3.0   10   3500\n",
              "7   900       3.0   20   3345\n",
              "8   967       3.0   23   3100\n",
              "9   720       3.0    7   6200"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ud50kQkPoje-",
        "outputId": "2b41fec6-1c4b-4cdd-aa36-8d9b657223b4"
      },
      "source": [
        "df.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Area        0\n",
              "Bedrooms    0\n",
              "Age         0\n",
              "Rent        0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CwOi-5bSojdD"
      },
      "source": [
        "from sklearn.linear_model import LinearRegression\n",
        "from sklearn.model_selection import train_test_split\n",
        "reg = LinearRegression()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OtojJYnLojbm",
        "outputId": "cdf05467-9211-4e3f-eeb8-56240628d069"
      },
      "source": [
        "reg.fit(df[['Area','Bedrooms','Age']],df.Rent)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sDcVtie8ojZR",
        "outputId": "b444b56a-50a6-4c80-979e-385ed11999fa"
      },
      "source": [
        "reg.coef_"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([  34.66745591, 2440.61024394, -354.75983519])"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3hF0kppC2MJC",
        "outputId": "94ac39ef-ee3c-46ed-e8ed-345b3165e238"
      },
      "source": [
        "reg.intercept_"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "-24001.729279468836"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jOsRfgwc2MFj",
        "outputId": "109e7cfa-ab2b-4da5-e9f7-6240dcdbfdf5"
      },
      "source": [
        "reg.predict([[1000,3,10]])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([14439.95901101])"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WR0d05zb2MDE",
        "outputId": "4b84affb-8220-4792-a2d6-c1e9ac87afd1"
      },
      "source": [
        "y = 34.66745591*1000 + 2440.61024394*3 + (-354.75983519)*10 + (-24001.729279468836)\n",
        "y"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "14439.95901045117"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8x37zckv2MA_",
        "outputId": "aaaf0174-fc09-4859-84fc-c18714fceba5"
      },
      "source": [
        "r = 100 - (y - reg.predict([[1000,3,10]]))\n",
        "print(\"Accuracy of the model is :\",int(r), \"%\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy of the model is : 100 %\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Lxvlvj1d2L-i"
      },
      "source": [
        "x = df.iloc[:,0].values.reshape(-1,1)\n",
        "x1 = df.iloc[:,1].values.reshape(-1,1)\n",
        "x2 = df.iloc[:,2].values.reshape(-1,1)\n",
        "y = df.iloc[:,-1].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gr4UG32Z2L7c"
      },
      "source": [
        "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=1/4,random_state = 0)\n",
        "x1_train,x1_test,y_train,y_test = train_test_split(x1,y,test_size=1/4,random_state = 0)\n",
        "x2_train,x2_test,y_train,y_test = train_test_split(x2,y,test_size=1/4,random_state = 0)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "k8cBU53w2L5Q",
        "outputId": "516ec483-0be0-4877-e393-b44ae185f9eb"
      },
      "source": [
        "reg.fit(x_train,y_train)\n",
        "reg.fit(x1_train,y_train)\n",
        "reg.fit(x2_train,y_train)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pnE5xZVF2L3S"
      },
      "source": [
        "y_pred = reg.predict(x_test)\n",
        "y_pred = reg.predict(x1_test)\n",
        "y_pred = reg.predict(x2_test)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "40ysXFGtlnXe",
        "outputId": "6d5e18b7-9c7e-471d-b2a0-bf7559b5472f"
      },
      "source": [
        "# Area of House\n",
        "plt.figure(figsize=(25,30))\n",
        "plt.subplot(3,2,1)\n",
        "plt.scatter(x_train,y_train,c='k')\n",
        "plt.plot(x_train,reg.predict(x_train),color='blue')\n",
        "plt.xlabel('Area of house',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n",
        "plt.title('House Rent Prediction (Training set)\\n',size=24)\n",
        "\n",
        "plt.subplot(3,2,2)\n",
        "plt.scatter(x_test,y_test,c='k')\n",
        "plt.plot(x_train,reg.predict(x_train),color='blue')\n",
        "plt.xlabel('Area of house',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n",
        "plt.title('House Rent Prediction (Test set)\\n',size=24)\n",
        "\n",
        "\n",
        "## Bedrooms\n",
        "plt.subplot(3,2,3)\n",
        "plt.scatter(x1_train,y_train,c='k')\n",
        "plt.plot(x1_train,reg.predict(x1_train),color='green')\n",
        "plt.xlabel('Bedrooms',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n",
        "\n",
        "plt.subplot(3,2,4)\n",
        "plt.scatter(x1_test,y_test,c='k')\n",
        "plt.plot(x1_train,reg.predict(x1_train),color='green')\n",
        "plt.xlabel('Bedrooms',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n",
        "\n",
        "## Age of House\n",
        "plt.subplot(3,2,5)\n",
        "plt.scatter(x2_train,y_train,c='k')\n",
        "plt.plot(x2_train,reg.predict(x2_train),color='red')\n",
        "plt.xlabel('Age of house',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n",
        "\n",
        "plt.subplot(3,2,6)\n",
        "plt.scatter(x2_test,y_test,c='k')\n",
        "plt.plot(x2_train,reg.predict(x2_train),color='red')\n",
        "plt.xlabel('Age of house',size=18)\n",
        "plt.ylabel('Rent of house',size=18)\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'Rent of house')"
            ]
          },
          "metadata": {},
          "execution_count": 32
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1800x2160 with 6 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vht5POej7Y33"
      },
      "source": [
        "X  ---> Y ---> Z   ---> U  "
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}