Reekraj_Roy.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Reekraj_Roy.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyNizJXJnk9hvk1gi1FxXI0K",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/REEKRAJROY/Python-and-Machine-Learning/blob/main/Reekraj_Roy.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w_EDKejyYZ33"
      },
      "source": [
        "#importing libraries to be used in the model\r\n",
        "import pandas as pd\r\n",
        "import numpy as np"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "STPAyalLYnaq"
      },
      "source": [
        "from sklearn.datasets import load_iris\r\n",
        "iris_dataset = load_iris()    #load_iris() returns the dictionary"
      ],
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GQXdoQA4bwL8",
        "outputId": "5dac177d-c61e-40e1-dd4a-23700a4672b1"
      },
      "source": [
        "#calling out keys of iris_dataset\r\n",
        "print(\"Keys of iris_dataset: \\n{}\".format(iris_dataset.keys()))"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Keys of iris_dataset: \n",
            "dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename'])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HNNl1WpGccTq",
        "outputId": "ff32a9c0-c9e4-44d0-d11b-394715c92652"
      },
      "source": [
        "#DECSCR has a String attached that conatins description of the dataset\r\n",
        "#This is used with the Slicing operator to display upto a particular key\r\n",
        "print(iris_dataset['DESCR'][:193]+ \"\\n..\")"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            ".. _iris_dataset:\n",
            "\n",
            "Iris plants dataset\n",
            "--------------------\n",
            "\n",
            "**Data Set Characteristics:**\n",
            "\n",
            "    :Number of Instances: 150 (50 in each of three classes)\n",
            "    :Number of Attributes: 4 numeric, pre\n",
            "..\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yVD52PFRddW3",
        "outputId": "6df8e15b-d7c9-46f6-9439-f3b8cd143bd1"
      },
      "source": [
        "#species of flowers which we need to categorize\r\n",
        "print(\"Target names: {}\".format(iris_dataset['target_names']))"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Target names: ['setosa' 'versicolor' 'virginica']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AQBIfjzkc3w-",
        "outputId": "9c7cb414-4588-4a1d-c394-dc7e1233811f"
      },
      "source": [
        "#description of each of the columns \r\n",
        "print(\"Feature names: \\n{}\".format(iris_dataset['feature_names']))"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Feature names: \n",
            "['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NSVg36cGeeTH",
        "outputId": "8e7f9835-f83b-4ccc-957a-41cf33e0ff36"
      },
      "source": [
        "#data type is diplayed\r\n",
        "print(\"Type of data: {}\".format(type(iris_dataset['data'])))"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Type of data: <class 'numpy.ndarray'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gA55wRkWezoU",
        "outputId": "57c8ef76-07e2-41d9-9493-987bc3583ed8"
      },
      "source": [
        "#shape of the dataset is displayed\r\n",
        "print(\"Shape of data: {}\".format(iris_dataset['data'].shape))"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shape of data: (150, 4)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rVh6AmAmfILO",
        "outputId": "75a79338-e105-40c0-91fa-c435d9df540a"
      },
      "source": [
        "#data points and attributes are displayed for the first five elements\r\n",
        "print(\"First five columns of data:\\n{}\".format(iris_dataset['data'][:5]))"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "First five columns of data:\n",
            "[[5.1 3.5 1.4 0.2]\n",
            " [4.9 3.  1.4 0.2]\n",
            " [4.7 3.2 1.3 0.2]\n",
            " [4.6 3.1 1.5 0.2]\n",
            " [5.  3.6 1.4 0.2]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CWjbfm9mgZXQ",
        "outputId": "f92b3ada-2705-4719-a15e-59a261e1f4d7"
      },
      "source": [
        "#which category a particular flower belongs to\r\n",
        "print(\"Type of target: {}\".format(type(iris_dataset['target'])))"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Type of target: <class 'numpy.ndarray'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PUhuwWJfgixE",
        "outputId": "869b48ce-e751-4b0e-d087-363f60b37228"
      },
      "source": [
        "#dumping entire values of our target\r\n",
        "#0->sentosa\r\n",
        "#1->versicolor\r\n",
        "#2->virginica \r\n",
        "print(\"Target:\\n{}\".format(iris_dataset['target']))"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Target:\n",
            "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
            " 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
            " 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2\n",
            " 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n",
            " 2 2]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w4PHnODUgwJU"
      },
      "source": [
        "from sklearn.model_selection import train_test_split\r\n",
        "X_train, X_test, y_train, y_test = train_test_split(\r\n",
        "    iris_dataset['data'], iris_dataset['target'], random_state=0)"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P-C-yqK4hUn2",
        "outputId": "1d564c60-dd34-4e64-abc6-38fd65c9a524"
      },
      "source": [
        "print(\"X_train shape: {}\".format(X_train.shape))\r\n",
        "print(\"y_train shape: {}\".format(y_train.shape))\r\n",
        "print(\"X_test shape: {}\".format(X_test.shape))\r\n",
        "print(\"y_test shape: {}\".format(y_test.shape))"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "X_train shape: (112, 4)\n",
            "y_train shape: (112,)\n",
            "X_test shape: (38, 4)\n",
            "y_test shape: (38,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "52_kkiAjjCuA"
      },
      "source": [
        "#using sklearn for k nearest neighbor\r\n",
        "#making the machine learning model\r\n",
        "from sklearn.neighbors import KNeighborsClassifier\r\n",
        "knn = KNeighborsClassifier(n_neighbors=1)"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LQtZef45j7lL",
        "outputId": "6229ffb5-e4af-4d15-f0c8-a763c130a7d7"
      },
      "source": [
        "#training the model\r\n",
        "#This function of KNeighbor Classifier is used for training\r\n",
        "knn.fit(X_train, y_train)"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
              "                     metric_params=None, n_jobs=None, n_neighbors=1, p=2,\n",
              "                     weights='uniform')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VJK3bPsakU5c",
        "outputId": "08115b5a-a57a-494b-be57-62223400b7c4"
      },
      "source": [
        "#checking with a single data point\r\n",
        "X_new = np.array([[5, 2.9, 1, 0]])\r\n",
        "print(\"X_new.shape: {}\".format(X_new.shape))"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "X_new.shape: (1, 4)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j1vxNx8Mk_bE",
        "outputId": "4d8106a7-0238-4b46-a525-535b413c6d37"
      },
      "source": [
        "#calling predict methd of knn object\r\n",
        "prediction = knn.predict(X_new)\r\n",
        "\r\n",
        "print(\"Prediction: {}\".format(prediction))\r\n",
        "print(\"Predicted target name: {}\".format(\r\n",
        "  iris_dataset['target_names'][prediction]))"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Prediction: [0]\n",
            "Predicted target name: ['setosa']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6wIhVsWml9Kp",
        "outputId": "4bdeb224-de42-42a6-a727-8522e32bf006"
      },
      "source": [
        "#testing the model for data points for X_test\r\n",
        "y_pred = knn.predict(X_test)\r\n",
        "print(\"Test set predictions:\\n {}\".format(y_pred))"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Test set predictions:\n",
            " [2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0\n",
            " 2]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pvqmUFTumOSo",
        "outputId": "84c151e5-1003-47cc-b887-3a939225a44f"
      },
      "source": [
        "#checking accuracy of the model\r\n",
        "print(\"Test set score: {}\".format(np.mean(y_pred == y_test)))"
      ],
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Test set score: 0.9736842105263158\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EnOUBqVZmlFR"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}