ML 1.ipynb

simple linear regression.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "ML 1.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyO21KfcJ5D36hbc7lxJPqW9",
      "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/52cc3353ab8c454154c40c02d000cfab/ml-1.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wkSGsQKkufyG"
      },
      "source": [
        "<center>\n",
        "<h1>Simple Linear Regression</h1>\n",
        "</center>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "g-51WYNluqi0"
      },
      "source": [
        "### 1. Importing necessary libraries"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4ZJykaM4uc2E",
        "outputId": "a8a38797-b9bf-465f-b618-7733ff957e5e"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline\n",
        "\n",
        "## For ML and SLR\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.linear_model import LinearRegression\n",
        "print(\"All packages are included successfully!\")"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "All packages are included successfully!\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eHuf1xe4uwgM"
      },
      "source": [
        "### 2. Importing the dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 236
        },
        "id": "zuC0MsLNuuJS",
        "outputId": "19ccdcfc-7c77-4afc-e008-ba43978af93c"
      },
      "source": [
        "url = 'https://raw.githubusercontent.com/MainakRepositor/Datasets-/master/Salary_Data.csv'\n",
        "df = pd.read_csv(url,error_bad_lines=False)\n",
        "print(\"Displaying the top 5 rows of the dataset :\\n\")\n",
        "df.head() "
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Displaying the top 5 rows of the dataset :\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "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>YearsExperience</th>\n",
              "      <th>Salary</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1.1</td>\n",
              "      <td>39343.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1.3</td>\n",
              "      <td>46205.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1.5</td>\n",
              "      <td>37731.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2.0</td>\n",
              "      <td>43525.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2.2</td>\n",
              "      <td>39891.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   YearsExperience   Salary\n",
              "0              1.1  39343.0\n",
              "1              1.3  46205.0\n",
              "2              1.5  37731.0\n",
              "3              2.0  43525.0\n",
              "4              2.2  39891.0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yAxlTAU1u35h"
      },
      "source": [
        "### 3. Data exploration"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2cSNB1Hju0oC",
        "outputId": "053e1baf-abf7-4d65-8818-6c337c86a276"
      },
      "source": [
        "df.shape"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(30, 2)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M4UGg0aBu8_w"
      },
      "source": [
        "### 4.Checking for missing values"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SKfdUz2Lu50Z",
        "outputId": "e46dbe61-0af6-47cc-acb2-de9222a35761"
      },
      "source": [
        "print(\"Null values present : \",df.isnull().values.any())\n"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Null values present :  False\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "p6kI6Rn-vFyD"
      },
      "source": [
        "### 5.Building the Simple Linear Regression model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lPWf5F5DvBp6",
        "outputId": "0c7f0252-e8a2-44c5-fea6-538437655089"
      },
      "source": [
        "x = df.iloc[:,:-1].values.reshape(-1,1)\n",
        "y = df.iloc[:,-1].values\n",
        "print(\"Show x and y\")\n",
        "print(\"--------X---------\\n\")\n",
        "print(x)\n",
        "print(\"--------Y---------\\n\")\n",
        "print(y)\n",
        "print(\"\\n\\n\")\n",
        "print(\"type of data of x :\",type(x))\n",
        "print(\"type of data of y :\",type(y))"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Show x and y\n",
            "--------X---------\n",
            "\n",
            "[[ 1.1]\n",
            " [ 1.3]\n",
            " [ 1.5]\n",
            " [ 2. ]\n",
            " [ 2.2]\n",
            " [ 2.9]\n",
            " [ 3. ]\n",
            " [ 3.2]\n",
            " [ 3.2]\n",
            " [ 3.7]\n",
            " [ 3.9]\n",
            " [ 4. ]\n",
            " [ 4. ]\n",
            " [ 4.1]\n",
            " [ 4.5]\n",
            " [ 4.9]\n",
            " [ 5.1]\n",
            " [ 5.3]\n",
            " [ 5.9]\n",
            " [ 6. ]\n",
            " [ 6.8]\n",
            " [ 7.1]\n",
            " [ 7.9]\n",
            " [ 8.2]\n",
            " [ 8.7]\n",
            " [ 9. ]\n",
            " [ 9.5]\n",
            " [ 9.6]\n",
            " [10.3]\n",
            " [10.5]]\n",
            "--------Y---------\n",
            "\n",
            "[ 39343.  46205.  37731.  43525.  39891.  56642.  60150.  54445.  64445.\n",
            "  57189.  63218.  55794.  56957.  57081.  61111.  67938.  66029.  83088.\n",
            "  81363.  93940.  91738.  98273. 101302. 113812. 109431. 105582. 116969.\n",
            " 112635. 122391. 121872.]\n",
            "\n",
            "\n",
            "\n",
            "type of data of x : <class 'numpy.ndarray'>\n",
            "type of data of y : <class 'numpy.ndarray'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yBOpmZwBvU0F"
      },
      "source": [
        "### 6. Setting up the regressor and splitting the dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cLYD7VouvI10",
        "outputId": "40c706fa-0f16-4c6d-df43-a59fe2126309"
      },
      "source": [
        "reg = LinearRegression()\n",
        "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=1/3,random_state=0)\n",
        "reg.fit(x_train,y_train)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tF1DEnF-vhZy"
      },
      "source": [
        "### 7. Obtaining the regressor slope, coefficients and intercepts"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ljLRlR9QvXnh",
        "outputId": "e9ee4836-fcff-4cf4-fc39-7f5d12372346"
      },
      "source": [
        "y_pred = reg.predict(x_test)\n",
        "print(y_pred)"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 40835.10590871 123079.39940819  65134.55626083  63265.36777221\n",
            " 115602.64545369 108125.8914992  116537.23969801  64199.96201652\n",
            "  76349.68719258 100649.1375447 ]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IcDuoBxmvkpA",
        "outputId": "f935e6dc-00c2-4f79-f4d0-13793b6774f6"
      },
      "source": [
        "reg.coef_"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([9345.94244312])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bS_Hdgg1vsBj",
        "outputId": "35c84474-1e24-4a0d-cce1-fcaf9b4370a7"
      },
      "source": [
        "reg.intercept_"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "26816.192244031183"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yKrkxg6avxlI"
      },
      "source": [
        "### 8. Making a prediction"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "okY_E1-QvuEb",
        "outputId": "58e13970-8c9f-48de-f7cd-36842143ab18"
      },
      "source": [
        "#Predict the salary for 8 years of experience\n",
        "\n",
        "reg.predict([[8]])"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([101583.73178901])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CODnKQlkv0Bn",
        "outputId": "8686973f-4524-4770-bd10-48a09a780be4"
      },
      "source": [
        "# Mathematical Verification\n",
        "print(\"coefficient = \",reg.coef_)\n",
        "print(\"intercept   = \",reg.intercept_)\n",
        "print(\"value of x  = \",8)\n",
        "print(\"Result (y)  = \",(reg.coef_*8 + reg.intercept_))"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "coefficient =  [9345.94244312]\n",
            "intercept   =  26816.192244031183\n",
            "value of x  =  8\n",
            "Result (y)  =  [101583.73178901]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9QLYGJk7wq_D"
      },
      "source": [
        "#### The predicted results are equal to the mathematically calculated values"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CSl7fM7Bwy6I"
      },
      "source": [
        "### 9. Predicting Accuracy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jLboRNcVweOo",
        "outputId": "32a1f237-ea7d-4686-e15d-b967e32522fb"
      },
      "source": [
        "y = reg.coef_*8 + reg.intercept_\n",
        "yp = reg.predict([[8]])\n",
        "r = int(100.00 - (y - yp))\n",
        "print(\"Predicted result accuracy percentage : \",r,\"%\")"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predicted result accuracy percentage :  100 %\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0TUIUOS2w6s8"
      },
      "source": [
        "### 10. Displaying test values"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XVWOmBoLwxnN",
        "outputId": "992d88fe-1c85-44c8-d93a-362ec833e792"
      },
      "source": [
        "print(x_test)"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 1.5]\n",
            " [10.3]\n",
            " [ 4.1]\n",
            " [ 3.9]\n",
            " [ 9.5]\n",
            " [ 8.7]\n",
            " [ 9.6]\n",
            " [ 4. ]\n",
            " [ 5.3]\n",
            " [ 7.9]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pbILzGKBw9P3",
        "outputId": "d1a39081-6046-4628-b050-18126dbdfb87"
      },
      "source": [
        "print(y_test)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 37731. 122391.  57081.  63218. 116969. 109431. 112635.  55794.  83088.\n",
            " 101302.]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tY_hwLrMxDPy"
      },
      "source": [
        "### 11. Visualizing the results"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 503
        },
        "id": "_R5cBdAAw_7u",
        "outputId": "cb21107e-2ce5-49cd-ee65-c2025aaa01c9"
      },
      "source": [
        "plt.figure(figsize=(20,7))\n",
        "plt.scatter(x_train,y_train,color='red')\n",
        "plt.plot(x_train,reg.predict(x_train),color='blue')\n",
        "plt.xlabel('Years of Experience',size=18,color='indigo')\n",
        "plt.ylabel('Salary',size=18,color='indigo')\n",
        "plt.title('Salary vs Experience regression graph (Training set)\\n',size=24,color='orange',fontweight='bold')\n",
        "plt.show()"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1440x504 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 503
        },
        "id": "IzMplqERxI9Z",
        "outputId": "ea00279c-92a7-41c5-f448-6c47c37ca32d"
      },
      "source": [
        "plt.figure(figsize=(20,7))\n",
        "plt.scatter(x_test,y_test,color='green')\n",
        "plt.plot(x_train,reg.predict(x_train),color='black')\n",
        "plt.xlabel('Years of Experience',size=18,color='indigo')\n",
        "plt.ylabel('Salary',size=18,color='indigo')\n",
        "plt.title('Salary vs Experience regression graph (Training set)\\n',size=24,color='green',fontweight='bold')\n",
        "plt.show()"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1440x504 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pvXsE4VOxNEg"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}