PCA.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNMI2vJ+5VmZJ+SLEgYvxm8",
      "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/github/Mathurshab2210/Ml_with_Mathur/blob/main/PCA.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "id": "oe97UfZZ0ZC1"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn.datasets import load_digits"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset=load_digits()"
      ],
      "metadata": {
        "id": "2Bgne3H70rHO"
      },
      "execution_count": 71,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "dataset.keys()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kRNOj-HZ0y12",
        "outputId": "793653ff-8fc9-4570-89e2-65a9e793c8c6"
      },
      "execution_count": 72,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['data', 'target', 'frame', 'feature_names', 'target_names', 'images', 'DESCR'])"
            ]
          },
          "metadata": {},
          "execution_count": 72
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset.data.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Fjn8Jm4l02dZ",
        "outputId": "6422254e-2dad-4aa9-e901-38b43cfc12fc"
      },
      "execution_count": 73,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1797, 64)"
            ]
          },
          "metadata": {},
          "execution_count": 73
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset.data[0]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CKqsJJ_q068t",
        "outputId": "cdfd1e82-4615-4014-8e14-35376b052f57"
      },
      "execution_count": 74,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ 0.,  0.,  5., 13.,  9.,  1.,  0.,  0.,  0.,  0., 13., 15., 10.,\n",
              "       15.,  5.,  0.,  0.,  3., 15.,  2.,  0., 11.,  8.,  0.,  0.,  4.,\n",
              "       12.,  0.,  0.,  8.,  8.,  0.,  0.,  5.,  8.,  0.,  0.,  9.,  8.,\n",
              "        0.,  0.,  4., 11.,  0.,  1., 12.,  7.,  0.,  0.,  2., 14.,  5.,\n",
              "       10., 12.,  0.,  0.,  0.,  0.,  6., 13., 10.,  0.,  0.,  0.])"
            ]
          },
          "metadata": {},
          "execution_count": 74
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "plt.gray()\n",
        "plt.matshow(dataset.data[5].reshape(8,8))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 310
        },
        "id": "HQYqjhFs1D-l",
        "outputId": "c12c2551-fdfa-4d79-fd29-11390b7ac9e0"
      },
      "execution_count": 75,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x7f4a565ef730>"
            ]
          },
          "metadata": {},
          "execution_count": 75
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 0 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 288x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "T4zgkyiR1eo9",
        "outputId": "6f147c54-093a-4205-8be7-54e4c0755e28"
      },
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'data': array([[ 0.,  0.,  5., ...,  0.,  0.,  0.],\n",
              "        [ 0.,  0.,  0., ..., 10.,  0.,  0.],\n",
              "        [ 0.,  0.,  0., ..., 16.,  9.,  0.],\n",
              "        ...,\n",
              "        [ 0.,  0.,  1., ...,  6.,  0.,  0.],\n",
              "        [ 0.,  0.,  2., ..., 12.,  0.,  0.],\n",
              "        [ 0.,  0., 10., ..., 12.,  1.,  0.]]),\n",
              " 'target': array([0, 1, 2, ..., 8, 9, 8]),\n",
              " 'frame': None,\n",
              " 'feature_names': ['pixel_0_0',\n",
              "  'pixel_0_1',\n",
              "  'pixel_0_2',\n",
              "  'pixel_0_3',\n",
              "  'pixel_0_4',\n",
              "  'pixel_0_5',\n",
              "  'pixel_0_6',\n",
              "  'pixel_0_7',\n",
              "  'pixel_1_0',\n",
              "  'pixel_1_1',\n",
              "  'pixel_1_2',\n",
              "  'pixel_1_3',\n",
              "  'pixel_1_4',\n",
              "  'pixel_1_5',\n",
              "  'pixel_1_6',\n",
              "  'pixel_1_7',\n",
              "  'pixel_2_0',\n",
              "  'pixel_2_1',\n",
              "  'pixel_2_2',\n",
              "  'pixel_2_3',\n",
              "  'pixel_2_4',\n",
              "  'pixel_2_5',\n",
              "  'pixel_2_6',\n",
              "  'pixel_2_7',\n",
              "  'pixel_3_0',\n",
              "  'pixel_3_1',\n",
              "  'pixel_3_2',\n",
              "  'pixel_3_3',\n",
              "  'pixel_3_4',\n",
              "  'pixel_3_5',\n",
              "  'pixel_3_6',\n",
              "  'pixel_3_7',\n",
              "  'pixel_4_0',\n",
              "  'pixel_4_1',\n",
              "  'pixel_4_2',\n",
              "  'pixel_4_3',\n",
              "  'pixel_4_4',\n",
              "  'pixel_4_5',\n",
              "  'pixel_4_6',\n",
              "  'pixel_4_7',\n",
              "  'pixel_5_0',\n",
              "  'pixel_5_1',\n",
              "  'pixel_5_2',\n",
              "  'pixel_5_3',\n",
              "  'pixel_5_4',\n",
              "  'pixel_5_5',\n",
              "  'pixel_5_6',\n",
              "  'pixel_5_7',\n",
              "  'pixel_6_0',\n",
              "  'pixel_6_1',\n",
              "  'pixel_6_2',\n",
              "  'pixel_6_3',\n",
              "  'pixel_6_4',\n",
              "  'pixel_6_5',\n",
              "  'pixel_6_6',\n",
              "  'pixel_6_7',\n",
              "  'pixel_7_0',\n",
              "  'pixel_7_1',\n",
              "  'pixel_7_2',\n",
              "  'pixel_7_3',\n",
              "  'pixel_7_4',\n",
              "  'pixel_7_5',\n",
              "  'pixel_7_6',\n",
              "  'pixel_7_7'],\n",
              " 'target_names': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]),\n",
              " 'images': array([[[ 0.,  0.,  5., ...,  1.,  0.,  0.],\n",
              "         [ 0.,  0., 13., ..., 15.,  5.,  0.],\n",
              "         [ 0.,  3., 15., ..., 11.,  8.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  4., 11., ..., 12.,  7.,  0.],\n",
              "         [ 0.,  2., 14., ..., 12.,  0.,  0.],\n",
              "         [ 0.,  0.,  6., ...,  0.,  0.,  0.]],\n",
              " \n",
              "        [[ 0.,  0.,  0., ...,  5.,  0.,  0.],\n",
              "         [ 0.,  0.,  0., ...,  9.,  0.,  0.],\n",
              "         [ 0.,  0.,  3., ...,  6.,  0.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  0.,  1., ...,  6.,  0.,  0.],\n",
              "         [ 0.,  0.,  1., ...,  6.,  0.,  0.],\n",
              "         [ 0.,  0.,  0., ..., 10.,  0.,  0.]],\n",
              " \n",
              "        [[ 0.,  0.,  0., ..., 12.,  0.,  0.],\n",
              "         [ 0.,  0.,  3., ..., 14.,  0.,  0.],\n",
              "         [ 0.,  0.,  8., ..., 16.,  0.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  9., 16., ...,  0.,  0.,  0.],\n",
              "         [ 0.,  3., 13., ..., 11.,  5.,  0.],\n",
              "         [ 0.,  0.,  0., ..., 16.,  9.,  0.]],\n",
              " \n",
              "        ...,\n",
              " \n",
              "        [[ 0.,  0.,  1., ...,  1.,  0.,  0.],\n",
              "         [ 0.,  0., 13., ...,  2.,  1.,  0.],\n",
              "         [ 0.,  0., 16., ..., 16.,  5.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  0., 16., ..., 15.,  0.,  0.],\n",
              "         [ 0.,  0., 15., ..., 16.,  0.,  0.],\n",
              "         [ 0.,  0.,  2., ...,  6.,  0.,  0.]],\n",
              " \n",
              "        [[ 0.,  0.,  2., ...,  0.,  0.,  0.],\n",
              "         [ 0.,  0., 14., ..., 15.,  1.,  0.],\n",
              "         [ 0.,  4., 16., ..., 16.,  7.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  0.,  0., ..., 16.,  2.,  0.],\n",
              "         [ 0.,  0.,  4., ..., 16.,  2.,  0.],\n",
              "         [ 0.,  0.,  5., ..., 12.,  0.,  0.]],\n",
              " \n",
              "        [[ 0.,  0., 10., ...,  1.,  0.,  0.],\n",
              "         [ 0.,  2., 16., ...,  1.,  0.,  0.],\n",
              "         [ 0.,  0., 15., ..., 15.,  0.,  0.],\n",
              "         ...,\n",
              "         [ 0.,  4., 16., ..., 16.,  6.,  0.],\n",
              "         [ 0.,  8., 16., ..., 16.,  8.,  0.],\n",
              "         [ 0.,  1.,  8., ..., 12.,  1.,  0.]]]),\n",
              " 'DESCR': \".. _digits_dataset:\\n\\nOptical recognition of handwritten digits dataset\\n--------------------------------------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 1797\\n    :Number of Attributes: 64\\n    :Attribute Information: 8x8 image of integer pixels in the range 0..16.\\n    :Missing Attribute Values: None\\n    :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)\\n    :Date: July; 1998\\n\\nThis is a copy of the test set of the UCI ML hand-written digits datasets\\nhttps://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits\\n\\nThe data set contains images of hand-written digits: 10 classes where\\neach class refers to a digit.\\n\\nPreprocessing programs made available by NIST were used to extract\\nnormalized bitmaps of handwritten digits from a preprinted form. From a\\ntotal of 43 people, 30 contributed to the training set and different 13\\nto the test set. 32x32 bitmaps are divided into nonoverlapping blocks of\\n4x4 and the number of on pixels are counted in each block. This generates\\nan input matrix of 8x8 where each element is an integer in the range\\n0..16. This reduces dimensionality and gives invariance to small\\ndistortions.\\n\\nFor info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.\\nT. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.\\nL. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,\\n1994.\\n\\n.. topic:: References\\n\\n  - C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their\\n    Applications to Handwritten Digit Recognition, MSc Thesis, Institute of\\n    Graduate Studies in Science and Engineering, Bogazici University.\\n  - E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.\\n  - Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.\\n    Linear dimensionalityreduction using relevance weighted LDA. School of\\n    Electrical and Electronic Engineering Nanyang Technological University.\\n    2005.\\n  - Claudio Gentile. A New Approximate Maximal Margin Classification\\n    Algorithm. NIPS. 2000.\\n\"}"
            ]
          },
          "metadata": {},
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset.target"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Gl4-UMza1igJ",
        "outputId": "be6e6672-0dc6-44d0-9372-2180f6baefb2"
      },
      "execution_count": 77,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 1, 2, ..., 8, 9, 8])"
            ]
          },
          "metadata": {},
          "execution_count": 77
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.unique(dataset.target)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "q4cW_F-X1usn",
        "outputId": "c92d4eac-56e4-44cf-8917-8b170caeaafc"
      },
      "execution_count": 78,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])"
            ]
          },
          "metadata": {},
          "execution_count": 78
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset.target[0]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qFqPCEFW2Cup",
        "outputId": "8ca9bd1e-ee70-4cea-cc92-4f869e858db1"
      },
      "execution_count": 79,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0"
            ]
          },
          "metadata": {},
          "execution_count": 79
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df=pd.DataFrame(dataset.data, columns=dataset.feature_names)"
      ],
      "metadata": {
        "id": "QAqlLtwq2KT5"
      },
      "execution_count": 80,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 299
        },
        "id": "cbqbP7yX2TAF",
        "outputId": "7448ad46-8108-467f-f3d7-ac36388e51c0"
      },
      "execution_count": 81,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   pixel_0_0  pixel_0_1  pixel_0_2  pixel_0_3  pixel_0_4  pixel_0_5  \\\n",
              "0        0.0        0.0        5.0       13.0        9.0        1.0   \n",
              "1        0.0        0.0        0.0       12.0       13.0        5.0   \n",
              "2        0.0        0.0        0.0        4.0       15.0       12.0   \n",
              "3        0.0        0.0        7.0       15.0       13.0        1.0   \n",
              "4        0.0        0.0        0.0        1.0       11.0        0.0   \n",
              "\n",
              "   pixel_0_6  pixel_0_7  pixel_1_0  pixel_1_1  ...  pixel_6_6  pixel_6_7  \\\n",
              "0        0.0        0.0        0.0        0.0  ...        0.0        0.0   \n",
              "1        0.0        0.0        0.0        0.0  ...        0.0        0.0   \n",
              "2        0.0        0.0        0.0        0.0  ...        5.0        0.0   \n",
              "3        0.0        0.0        0.0        8.0  ...        9.0        0.0   \n",
              "4        0.0        0.0        0.0        0.0  ...        0.0        0.0   \n",
              "\n",
              "   pixel_7_0  pixel_7_1  pixel_7_2  pixel_7_3  pixel_7_4  pixel_7_5  \\\n",
              "0        0.0        0.0        6.0       13.0       10.0        0.0   \n",
              "1        0.0        0.0        0.0       11.0       16.0       10.0   \n",
              "2        0.0        0.0        0.0        3.0       11.0       16.0   \n",
              "3        0.0        0.0        7.0       13.0       13.0        9.0   \n",
              "4        0.0        0.0        0.0        2.0       16.0        4.0   \n",
              "\n",
              "   pixel_7_6  pixel_7_7  \n",
              "0        0.0        0.0  \n",
              "1        0.0        0.0  \n",
              "2        9.0        0.0  \n",
              "3        0.0        0.0  \n",
              "4        0.0        0.0  \n",
              "\n",
              "[5 rows x 64 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f2402a18-504d-4541-b822-307a8f129826\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>pixel_0_0</th>\n",
              "      <th>pixel_0_1</th>\n",
              "      <th>pixel_0_2</th>\n",
              "      <th>pixel_0_3</th>\n",
              "      <th>pixel_0_4</th>\n",
              "      <th>pixel_0_5</th>\n",
              "      <th>pixel_0_6</th>\n",
              "      <th>pixel_0_7</th>\n",
              "      <th>pixel_1_0</th>\n",
              "      <th>pixel_1_1</th>\n",
              "      <th>...</th>\n",
              "      <th>pixel_6_6</th>\n",
              "      <th>pixel_6_7</th>\n",
              "      <th>pixel_7_0</th>\n",
              "      <th>pixel_7_1</th>\n",
              "      <th>pixel_7_2</th>\n",
              "      <th>pixel_7_3</th>\n",
              "      <th>pixel_7_4</th>\n",
              "      <th>pixel_7_5</th>\n",
              "      <th>pixel_7_6</th>\n",
              "      <th>pixel_7_7</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>9.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>6.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>10.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>12.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>11.0</td>\n",
              "      <td>16.0</td>\n",
              "      <td>10.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>4.0</td>\n",
              "      <td>15.0</td>\n",
              "      <td>12.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>5.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>11.0</td>\n",
              "      <td>16.0</td>\n",
              "      <td>9.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>7.0</td>\n",
              "      <td>15.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>...</td>\n",
              "      <td>9.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>7.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>13.0</td>\n",
              "      <td>9.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>11.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>16.0</td>\n",
              "      <td>4.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 64 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f2402a18-504d-4541-b822-307a8f129826')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-f2402a18-504d-4541-b822-307a8f129826 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-f2402a18-504d-4541-b822-307a8f129826');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 81
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 393
        },
        "id": "3Zo12-342oJB",
        "outputId": "0c2a3bb1-def1-463d-d7d1-ca84637aef9e"
      },
      "execution_count": 82,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       pixel_0_0    pixel_0_1    pixel_0_2    pixel_0_3    pixel_0_4  \\\n",
              "count     1797.0  1797.000000  1797.000000  1797.000000  1797.000000   \n",
              "mean         0.0     0.303840     5.204786    11.835838    11.848080   \n",
              "std          0.0     0.907192     4.754826     4.248842     4.287388   \n",
              "min          0.0     0.000000     0.000000     0.000000     0.000000   \n",
              "25%          0.0     0.000000     1.000000    10.000000    10.000000   \n",
              "50%          0.0     0.000000     4.000000    13.000000    13.000000   \n",
              "75%          0.0     0.000000     9.000000    15.000000    15.000000   \n",
              "max          0.0     8.000000    16.000000    16.000000    16.000000   \n",
              "\n",
              "         pixel_0_5    pixel_0_6    pixel_0_7    pixel_1_0    pixel_1_1  ...  \\\n",
              "count  1797.000000  1797.000000  1797.000000  1797.000000  1797.000000  ...   \n",
              "mean      5.781859     1.362270     0.129661     0.005565     1.993879  ...   \n",
              "std       5.666418     3.325775     1.037383     0.094222     3.196160  ...   \n",
              "min       0.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
              "25%       0.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
              "50%       4.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
              "75%      11.000000     0.000000     0.000000     0.000000     3.000000  ...   \n",
              "max      16.000000    16.000000    15.000000     2.000000    16.000000  ...   \n",
              "\n",
              "         pixel_6_6    pixel_6_7    pixel_7_0    pixel_7_1    pixel_7_2  \\\n",
              "count  1797.000000  1797.000000  1797.000000  1797.000000  1797.000000   \n",
              "mean      3.725097     0.206455     0.000556     0.279354     5.557596   \n",
              "std       4.919406     0.984401     0.023590     0.934302     5.103019   \n",
              "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
              "25%       0.000000     0.000000     0.000000     0.000000     1.000000   \n",
              "50%       1.000000     0.000000     0.000000     0.000000     4.000000   \n",
              "75%       7.000000     0.000000     0.000000     0.000000    10.000000   \n",
              "max      16.000000    13.000000     1.000000     9.000000    16.000000   \n",
              "\n",
              "         pixel_7_3    pixel_7_4    pixel_7_5    pixel_7_6    pixel_7_7  \n",
              "count  1797.000000  1797.000000  1797.000000  1797.000000  1797.000000  \n",
              "mean     12.089037    11.809126     6.764051     2.067891     0.364496  \n",
              "std       4.374694     4.933947     5.900623     4.090548     1.860122  \n",
              "min       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
              "25%      11.000000    10.000000     0.000000     0.000000     0.000000  \n",
              "50%      13.000000    14.000000     6.000000     0.000000     0.000000  \n",
              "75%      16.000000    16.000000    12.000000     2.000000     0.000000  \n",
              "max      16.000000    16.000000    16.000000    16.000000    16.000000  \n",
              "\n",
              "[8 rows x 64 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-720e18d6-6cf5-4af8-ba92-4e4983c0172f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>pixel_0_0</th>\n",
              "      <th>pixel_0_1</th>\n",
              "      <th>pixel_0_2</th>\n",
              "      <th>pixel_0_3</th>\n",
              "      <th>pixel_0_4</th>\n",
              "      <th>pixel_0_5</th>\n",
              "      <th>pixel_0_6</th>\n",
              "      <th>pixel_0_7</th>\n",
              "      <th>pixel_1_0</th>\n",
              "      <th>pixel_1_1</th>\n",
              "      <th>...</th>\n",
              "      <th>pixel_6_6</th>\n",
              "      <th>pixel_6_7</th>\n",
              "      <th>pixel_7_0</th>\n",
              "      <th>pixel_7_1</th>\n",
              "      <th>pixel_7_2</th>\n",
              "      <th>pixel_7_3</th>\n",
              "      <th>pixel_7_4</th>\n",
              "      <th>pixel_7_5</th>\n",
              "      <th>pixel_7_6</th>\n",
              "      <th>pixel_7_7</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>1797.0</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "      <td>1797.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.303840</td>\n",
              "      <td>5.204786</td>\n",
              "      <td>11.835838</td>\n",
              "      <td>11.848080</td>\n",
              "      <td>5.781859</td>\n",
              "      <td>1.362270</td>\n",
              "      <td>0.129661</td>\n",
              "      <td>0.005565</td>\n",
              "      <td>1.993879</td>\n",
              "      <td>...</td>\n",
              "      <td>3.725097</td>\n",
              "      <td>0.206455</td>\n",
              "      <td>0.000556</td>\n",
              "      <td>0.279354</td>\n",
              "      <td>5.557596</td>\n",
              "      <td>12.089037</td>\n",
              "      <td>11.809126</td>\n",
              "      <td>6.764051</td>\n",
              "      <td>2.067891</td>\n",
              "      <td>0.364496</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.907192</td>\n",
              "      <td>4.754826</td>\n",
              "      <td>4.248842</td>\n",
              "      <td>4.287388</td>\n",
              "      <td>5.666418</td>\n",
              "      <td>3.325775</td>\n",
              "      <td>1.037383</td>\n",
              "      <td>0.094222</td>\n",
              "      <td>3.196160</td>\n",
              "      <td>...</td>\n",
              "      <td>4.919406</td>\n",
              "      <td>0.984401</td>\n",
              "      <td>0.023590</td>\n",
              "      <td>0.934302</td>\n",
              "      <td>5.103019</td>\n",
              "      <td>4.374694</td>\n",
              "      <td>4.933947</td>\n",
              "      <td>5.900623</td>\n",
              "      <td>4.090548</td>\n",
              "      <td>1.860122</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>11.000000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>14.000000</td>\n",
              "      <td>6.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>9.000000</td>\n",
              "      <td>15.000000</td>\n",
              "      <td>15.000000</td>\n",
              "      <td>11.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>7.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>12.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>0.0</td>\n",
              "      <td>8.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>15.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>13.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>9.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "      <td>16.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>8 rows × 64 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-720e18d6-6cf5-4af8-ba92-4e4983c0172f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-720e18d6-6cf5-4af8-ba92-4e4983c0172f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-720e18d6-6cf5-4af8-ba92-4e4983c0172f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yVneh4hB2q1Y",
        "outputId": "a420a5c8-1d31-469c-8a1a-2d2733a7f9a8"
      },
      "execution_count": 83,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1797 entries, 0 to 1796\n",
            "Data columns (total 64 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   pixel_0_0  1797 non-null   float64\n",
            " 1   pixel_0_1  1797 non-null   float64\n",
            " 2   pixel_0_2  1797 non-null   float64\n",
            " 3   pixel_0_3  1797 non-null   float64\n",
            " 4   pixel_0_4  1797 non-null   float64\n",
            " 5   pixel_0_5  1797 non-null   float64\n",
            " 6   pixel_0_6  1797 non-null   float64\n",
            " 7   pixel_0_7  1797 non-null   float64\n",
            " 8   pixel_1_0  1797 non-null   float64\n",
            " 9   pixel_1_1  1797 non-null   float64\n",
            " 10  pixel_1_2  1797 non-null   float64\n",
            " 11  pixel_1_3  1797 non-null   float64\n",
            " 12  pixel_1_4  1797 non-null   float64\n",
            " 13  pixel_1_5  1797 non-null   float64\n",
            " 14  pixel_1_6  1797 non-null   float64\n",
            " 15  pixel_1_7  1797 non-null   float64\n",
            " 16  pixel_2_0  1797 non-null   float64\n",
            " 17  pixel_2_1  1797 non-null   float64\n",
            " 18  pixel_2_2  1797 non-null   float64\n",
            " 19  pixel_2_3  1797 non-null   float64\n",
            " 20  pixel_2_4  1797 non-null   float64\n",
            " 21  pixel_2_5  1797 non-null   float64\n",
            " 22  pixel_2_6  1797 non-null   float64\n",
            " 23  pixel_2_7  1797 non-null   float64\n",
            " 24  pixel_3_0  1797 non-null   float64\n",
            " 25  pixel_3_1  1797 non-null   float64\n",
            " 26  pixel_3_2  1797 non-null   float64\n",
            " 27  pixel_3_3  1797 non-null   float64\n",
            " 28  pixel_3_4  1797 non-null   float64\n",
            " 29  pixel_3_5  1797 non-null   float64\n",
            " 30  pixel_3_6  1797 non-null   float64\n",
            " 31  pixel_3_7  1797 non-null   float64\n",
            " 32  pixel_4_0  1797 non-null   float64\n",
            " 33  pixel_4_1  1797 non-null   float64\n",
            " 34  pixel_4_2  1797 non-null   float64\n",
            " 35  pixel_4_3  1797 non-null   float64\n",
            " 36  pixel_4_4  1797 non-null   float64\n",
            " 37  pixel_4_5  1797 non-null   float64\n",
            " 38  pixel_4_6  1797 non-null   float64\n",
            " 39  pixel_4_7  1797 non-null   float64\n",
            " 40  pixel_5_0  1797 non-null   float64\n",
            " 41  pixel_5_1  1797 non-null   float64\n",
            " 42  pixel_5_2  1797 non-null   float64\n",
            " 43  pixel_5_3  1797 non-null   float64\n",
            " 44  pixel_5_4  1797 non-null   float64\n",
            " 45  pixel_5_5  1797 non-null   float64\n",
            " 46  pixel_5_6  1797 non-null   float64\n",
            " 47  pixel_5_7  1797 non-null   float64\n",
            " 48  pixel_6_0  1797 non-null   float64\n",
            " 49  pixel_6_1  1797 non-null   float64\n",
            " 50  pixel_6_2  1797 non-null   float64\n",
            " 51  pixel_6_3  1797 non-null   float64\n",
            " 52  pixel_6_4  1797 non-null   float64\n",
            " 53  pixel_6_5  1797 non-null   float64\n",
            " 54  pixel_6_6  1797 non-null   float64\n",
            " 55  pixel_6_7  1797 non-null   float64\n",
            " 56  pixel_7_0  1797 non-null   float64\n",
            " 57  pixel_7_1  1797 non-null   float64\n",
            " 58  pixel_7_2  1797 non-null   float64\n",
            " 59  pixel_7_3  1797 non-null   float64\n",
            " 60  pixel_7_4  1797 non-null   float64\n",
            " 61  pixel_7_5  1797 non-null   float64\n",
            " 62  pixel_7_6  1797 non-null   float64\n",
            " 63  pixel_7_7  1797 non-null   float64\n",
            "dtypes: float64(64)\n",
            "memory usage: 898.6 KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x=df\n",
        "y=dataset.target"
      ],
      "metadata": {
        "id": "ilc364VI2sWx"
      },
      "execution_count": 84,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "scaler=StandardScaler()\n",
        "X_scale=scaler.fit_transform(x)"
      ],
      "metadata": {
        "id": "bykf6NI02yn2"
      },
      "execution_count": 85,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_scale"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xPZpazs63TiV",
        "outputId": "c7ca8e13-ec78-4329-dc44-8df2ef039e33"
      },
      "execution_count": 86,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ 0.        , -0.33501649, -0.04308102, ..., -1.14664746,\n",
              "        -0.5056698 , -0.19600752],\n",
              "       [ 0.        , -0.33501649, -1.09493684, ...,  0.54856067,\n",
              "        -0.5056698 , -0.19600752],\n",
              "       [ 0.        , -0.33501649, -1.09493684, ...,  1.56568555,\n",
              "         1.6951369 , -0.19600752],\n",
              "       ...,\n",
              "       [ 0.        , -0.33501649, -0.88456568, ..., -0.12952258,\n",
              "        -0.5056698 , -0.19600752],\n",
              "       [ 0.        , -0.33501649, -0.67419451, ...,  0.8876023 ,\n",
              "        -0.5056698 , -0.19600752],\n",
              "       [ 0.        , -0.33501649,  1.00877481, ...,  0.8876023 ,\n",
              "        -0.26113572, -0.19600752]])"
            ]
          },
          "metadata": {},
          "execution_count": 86
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "x_train,x_test,y_train,y_test=train_test_split(X_scale,y,test_size=0.25,random_state=42)"
      ],
      "metadata": {
        "id": "f5w_717P3fKl"
      },
      "execution_count": 87,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "model = DecisionTreeClassifier(max_depth=12)"
      ],
      "metadata": {
        "id": "0kt50pg538-u"
      },
      "execution_count": 88,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.fit(x_train,y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BaJ9ywmJ4yPi",
        "outputId": "0504322f-06d4-4194-b9bd-f569e77b09cf"
      },
      "execution_count": 89,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier(max_depth=12)"
            ]
          },
          "metadata": {},
          "execution_count": 89
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.score(x_train,y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Nazpr5sr44RN",
        "outputId": "aff768fd-4adc-4d45-ce0d-039c20ba7d99"
      },
      "execution_count": 90,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.9992576095025983"
            ]
          },
          "metadata": {},
          "execution_count": 90
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred=model.predict(x_test)"
      ],
      "metadata": {
        "id": "dbOQRoiR5AfR"
      },
      "execution_count": 91,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import confusion_matrix\n",
        "cm = confusion_matrix(y_test, y_pred)\n",
        "cm"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xuxoTIKJ5LH5",
        "outputId": "a392872e-325f-4aae-dcf3-877412ae6f74"
      },
      "execution_count": 92,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[39,  0,  1,  0,  2,  1,  0,  0,  0,  0],\n",
              "       [ 0, 32,  1,  3,  0,  0,  0,  0,  1,  0],\n",
              "       [ 0,  0, 33,  3,  0,  0,  0,  0,  2,  0],\n",
              "       [ 0,  2,  0, 38,  0,  1,  0,  1,  3,  1],\n",
              "       [ 0,  0,  0,  0, 50,  1,  2,  1,  0,  1],\n",
              "       [ 0,  0,  0,  1,  1, 50,  1,  1,  1,  4],\n",
              "       [ 0,  0,  0,  0,  1,  1, 43,  0,  0,  0],\n",
              "       [ 0,  1,  0,  2,  2,  0,  0, 35,  0,  1],\n",
              "       [ 0,  4,  2,  2,  2,  0,  0,  0, 26,  2],\n",
              "       [ 0,  1,  0,  1,  0,  1,  0,  2,  0, 43]])"
            ]
          },
          "metadata": {},
          "execution_count": 92
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.score(x_test,y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9Il6gbcS5Umt",
        "outputId": "0b9ce697-ef69-45db-a67c-d99aaa7a02bf"
      },
      "execution_count": 93,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.8644444444444445"
            ]
          },
          "metadata": {},
          "execution_count": 93
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.decomposition import PCA"
      ],
      "metadata": {
        "id": "Dje2wqxP5iTd"
      },
      "execution_count": 94,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pca=PCA(0.95)"
      ],
      "metadata": {
        "id": "PWkKQONu5p_F"
      },
      "execution_count": 95,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_pca=pca.fit_transform(x)"
      ],
      "metadata": {
        "id": "JUfjzNqS6D9p"
      },
      "execution_count": 96,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_pca.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eg_8yW2v6JUm",
        "outputId": "31fd15c6-6b39-4cde-9e67-16151b781887"
      },
      "execution_count": 97,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1797, 29)"
            ]
          },
          "metadata": {},
          "execution_count": 97
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_pca"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "54Opi0n-6LRh",
        "outputId": "f4fbd2ad-6d75-4271-b157-539df7a5f87a"
      },
      "execution_count": 98,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ -1.25946645,  21.27488348,  -9.46305462, ...,   3.67072108,\n",
              "         -0.9436689 ,  -1.13250195],\n",
              "       [  7.9576113 , -20.76869896,   4.43950604, ...,   2.18261819,\n",
              "         -0.51022719,   2.31354911],\n",
              "       [  6.99192297,  -9.95598641,   2.95855808, ...,   4.22882114,\n",
              "          2.1576573 ,   0.8379578 ],\n",
              "       ...,\n",
              "       [ 10.8012837 ,  -6.96025223,   5.59955453, ...,  -3.56866194,\n",
              "          1.82444444,   3.53885886],\n",
              "       [ -4.87210009,  12.42395362, -10.17086635, ...,   3.25330054,\n",
              "          0.95484174,  -0.93895602],\n",
              "       [ -0.34438963,   6.36554919,  10.77370849, ...,  -3.01636722,\n",
              "          1.29752723,   2.58810313]])"
            ]
          },
          "metadata": {},
          "execution_count": 98
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pca.explained_variance_ratio_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bkGycOYL6nIk",
        "outputId": "008c662e-52f4-4408-df40-3e09f0acb50b"
      },
      "execution_count": 99,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.14890594, 0.13618771, 0.11794594, 0.08409979, 0.05782415,\n",
              "       0.0491691 , 0.04315987, 0.03661373, 0.03353248, 0.03078806,\n",
              "       0.02372341, 0.02272697, 0.01821863, 0.01773855, 0.01467101,\n",
              "       0.01409716, 0.01318589, 0.01248138, 0.01017718, 0.00905617,\n",
              "       0.00889538, 0.00797123, 0.00767493, 0.00722904, 0.00695889,\n",
              "       0.00596081, 0.00575615, 0.00515158, 0.0048954 ])"
            ]
          },
          "metadata": {},
          "execution_count": 99
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pca.n_components_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N40OqsbK6rsE",
        "outputId": "71100b43-f489-4bc6-b1b4-aa6a7ab00e38"
      },
      "execution_count": 100,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "29"
            ]
          },
          "metadata": {},
          "execution_count": 100
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_train,x_test,y_train,y_test=train_test_split(x_pca,y,test_size=0.25,random_state=42)"
      ],
      "metadata": {
        "id": "kFuRnT3O7In6"
      },
      "execution_count": 101,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.fit(x_train,y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XDpU195N7P2i",
        "outputId": "d712c9d5-4120-4229-bb1f-deef78aa3a71"
      },
      "execution_count": 102,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier(max_depth=12)"
            ]
          },
          "metadata": {},
          "execution_count": 102
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.score(x_test,y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "doH9-iGA7X7R",
        "outputId": "51843174-fe76-40a6-e90b-dd83a543a67d"
      },
      "execution_count": 103,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.8488888888888889"
            ]
          },
          "metadata": {},
          "execution_count": 103
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "bdvl9eEA7fgm"
      },
      "execution_count": 103,
      "outputs": []
    }
  ]
}