PROSTATE_CANCER_KAGGLE_WITH_NORMALIZATION_AND_RESAMPLING.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "PROSTATE CANCER KAGGLE WITH NORMALIZATION AND RESAMPLING.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPB7PUfvuZzLtcdAJNun7/q"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "fZG5kfxRmzac",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "%matplotlib inline"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9Xq2d7Hqm-yn",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from google.colab import files"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GdvFpzlKnC5w",
        "colab_type": "code",
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "Ly8gQ29weXJpZ2h0IDIwMTcgR29vZ2xlIExMQwovLwovLyBMaWNlbnNlZCB1bmRlciB0aGUgQXBhY2hlIExpY2Vuc2UsIFZlcnNpb24gMi4wICh0aGUgIkxpY2Vuc2UiKTsKLy8geW91IG1heSBub3QgdXNlIHRoaXMgZmlsZSBleGNlcHQgaW4gY29tcGxpYW5jZSB3aXRoIHRoZSBMaWNlbnNlLgovLyBZb3UgbWF5IG9idGFpbiBhIGNvcHkgb2YgdGhlIExpY2Vuc2UgYXQKLy8KLy8gICAgICBodHRwOi8vd3d3LmFwYWNoZS5vcmcvbGljZW5zZXMvTElDRU5TRS0yLjAKLy8KLy8gVW5sZXNzIHJlcXVpcmVkIGJ5IGFwcGxpY2FibGUgbGF3IG9yIGFncmVlZCB0byBpbiB3cml0aW5nLCBzb2Z0d2FyZQovLyBkaXN0cmlidXRlZCB1bmRlciB0aGUgTGljZW5zZSBpcyBkaXN0cmlidXRlZCBvbiBhbiAiQVMgSVMiIEJBU0lTLAovLyBXSVRIT1VUIFdBUlJBTlRJRVMgT1IgQ09ORElUSU9OUyBPRiBBTlkgS0lORCwgZWl0aGVyIGV4cHJlc3Mgb3IgaW1wbGllZC4KLy8gU2VlIHRoZSBMaWNlbnNlIGZvciB0aGUgc3BlY2lmaWMgbGFuZ3VhZ2UgZ292ZXJuaW5nIHBlcm1pc3Npb25zIGFuZAovLyBsaW1pdGF0aW9ucyB1bmRlciB0aGUgTGljZW5zZS4KCi8qKgogKiBAZmlsZW92ZXJ2aWV3IEhlbHBlcnMgZm9yIGdvb2dsZS5jb2xhYiBQeXRob24gbW9kdWxlLgogKi8KKGZ1bmN0aW9uKHNjb3BlKSB7CmZ1bmN0aW9uIHNwYW4odGV4dCwgc3R5bGVBdHRyaWJ1dGVzID0ge30pIHsKICBjb25zdCBlbGVtZW50ID0gZG9jdW1lbnQuY3JlYXRlRWxlbWVudCgnc3BhbicpOwogIGVsZW1lbnQudGV4dENvbnRlbnQgPSB0ZXh0OwogIGZvciAoY29uc3Qga2V5IG9mIE9iamVjdC5rZXlzKHN0eWxlQXR0cmlidXRlcykpIHsKICAgIGVsZW1lbnQuc3R5bGVba2V5XSA9IHN0eWxlQXR0cmlidXRlc1trZXldOwogIH0KICByZXR1cm4gZWxlbWVudDsKfQoKLy8gTWF4IG51bWJlciBvZiBieXRlcyB3aGljaCB3aWxsIGJlIHVwbG9hZGVkIGF0IGEgdGltZS4KY29uc3QgTUFYX1BBWUxPQURfU0laRSA9IDEwMCAqIDEwMjQ7Ci8vIE1heCBhbW91bnQgb2YgdGltZSB0byBibG9jayB3YWl0aW5nIGZvciB0aGUgdXNlci4KY29uc3QgRklMRV9DSEFOR0VfVElNRU9VVF9NUyA9IDMwICogMTAwMDsKCmZ1bmN0aW9uIF91cGxvYWRGaWxlcyhpbnB1dElkLCBvdXRwdXRJZCkgewogIGNvbnN0IHN0ZXBzID0gdXBsb2FkRmlsZXNTdGVwKGlucHV0SWQsIG91dHB1dElkKTsKICBjb25zdCBvdXRwdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQob3V0cHV0SWQpOwogIC8vIENhY2hlIHN0ZXBzIG9uIHRoZSBvdXRwdXRFbGVtZW50IHRvIG1ha2UgaXQgYXZhaWxhYmxlIGZvciB0aGUgbmV4dCBjYWxsCiAgLy8gdG8gdXBsb2FkRmlsZXNDb250aW51ZSBmcm9tIFB5dGhvbi4KICBvdXRwdXRFbGVtZW50LnN0ZXBzID0gc3RlcHM7CgogIHJldHVybiBfdXBsb2FkRmlsZXNDb250aW51ZShvdXRwdXRJZCk7Cn0KCi8vIFRoaXMgaXMgcm91Z2hseSBhbiBhc3luYyBnZW5lcmF0b3IgKG5vdCBzdXBwb3J0ZWQgaW4gdGhlIGJyb3dzZXIgeWV0KSwKLy8gd2hlcmUgdGhlcmUgYXJlIG11bHRpcGxlIGFzeW5jaHJvbm91cyBzdGVwcyBhbmQgdGhlIFB5dGhvbiBzaWRlIGlzIGdvaW5nCi8vIHRvIHBvbGwgZm9yIGNvbXBsZXRpb24gb2YgZWFjaCBzdGVwLgovLyBUaGlzIHVzZXMgYSBQcm9taXNlIHRvIGJsb2NrIHRoZSBweXRob24gc2lkZSBvbiBjb21wbGV0aW9uIG9mIGVhY2ggc3RlcCwKLy8gdGhlbiBwYXNzZXMgdGhlIHJlc3VsdCBvZiB0aGUgcHJldmlvdXMgc3RlcCBhcyB0aGUgaW5wdXQgdG8gdGhlIG5leHQgc3RlcC4KZnVuY3Rpb24gX3VwbG9hZEZpbGVzQ29udGludWUob3V0cHV0SWQpIHsKICBjb25zdCBvdXRwdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQob3V0cHV0SWQpOwogIGNvbnN0IHN0ZXBzID0gb3V0cHV0RWxlbWVudC5zdGVwczsKCiAgY29uc3QgbmV4dCA9IHN0ZXBzLm5leHQob3V0cHV0RWxlbWVudC5sYXN0UHJvbWlzZVZhbHVlKTsKICByZXR1cm4gUHJvbWlzZS5yZXNvbHZlKG5leHQudmFsdWUucHJvbWlzZSkudGhlbigodmFsdWUpID0+IHsKICAgIC8vIENhY2hlIHRoZSBsYXN0IHByb21pc2UgdmFsdWUgdG8gbWFrZSBpdCBhdmFpbGFibGUgdG8gdGhlIG5leHQKICAgIC8vIHN0ZXAgb2YgdGhlIGdlbmVyYXRvci4KICAgIG91dHB1dEVsZW1lbnQubGFzdFByb21pc2VWYWx1ZSA9IHZhbHVlOwogICAgcmV0dXJuIG5leHQudmFsdWUucmVzcG9uc2U7CiAgfSk7Cn0KCi8qKgogKiBHZW5lcmF0b3IgZnVuY3Rpb24gd2hpY2ggaXMgY2FsbGVkIGJldHdlZW4gZWFjaCBhc3luYyBzdGVwIG9mIHRoZSB1cGxvYWQKICogcHJvY2Vzcy4KICogQHBhcmFtIHtzdHJpbmd9IGlucHV0SWQgRWxlbWVudCBJRCBvZiB0aGUgaW5wdXQgZmlsZSBwaWNrZXIgZWxlbWVudC4KICogQHBhcmFtIHtzdHJpbmd9IG91dHB1dElkIEVsZW1lbnQgSUQgb2YgdGhlIG91dHB1dCBkaXNwbGF5LgogKiBAcmV0dXJuIHshSXRlcmFibGU8IU9iamVjdD59IEl0ZXJhYmxlIG9mIG5leHQgc3RlcHMuCiAqLwpmdW5jdGlvbiogdXBsb2FkRmlsZXNTdGVwKGlucHV0SWQsIG91dHB1dElkKSB7CiAgY29uc3QgaW5wdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQoaW5wdXRJZCk7CiAgaW5wdXRFbGVtZW50LmRpc2FibGVkID0gZmFsc2U7CgogIGNvbnN0IG91dHB1dEVsZW1lbnQgPSBkb2N1bWVudC5nZXRFbGVtZW50QnlJZChvdXRwdXRJZCk7CiAgb3V0cHV0RWxlbWVudC5pbm5lckhUTUwgPSAnJzsKCiAgY29uc3QgcGlja2VkUHJvbWlzZSA9IG5ldyBQcm9taXNlKChyZXNvbHZlKSA9PiB7CiAgICBpbnB1dEVsZW1lbnQuYWRkRXZlbnRMaXN0ZW5lcignY2hhbmdlJywgKGUpID0+IHsKICAgICAgcmVzb2x2ZShlLnRhcmdldC5maWxlcyk7CiAgICB9KTsKICB9KTsKCiAgY29uc3QgY2FuY2VsID0gZG9jdW1lbnQuY3JlYXRlRWxlbWVudCgnYnV0dG9uJyk7CiAgaW5wdXRFbGVtZW50LnBhcmVudEVsZW1lbnQuYXBwZW5kQ2hpbGQoY2FuY2VsKTsKICBjYW5jZWwudGV4dENvbnRlbnQgPSAnQ2FuY2VsIHVwbG9hZCc7CiAgY29uc3QgY2FuY2VsUHJvbWlzZSA9IG5ldyBQcm9taXNlKChyZXNvbHZlKSA9PiB7CiAgICBjYW5jZWwub25jbGljayA9ICgpID0+IHsKICAgICAgcmVzb2x2ZShudWxsKTsKICAgIH07CiAgfSk7CgogIC8vIENhbmNlbCB1cGxvYWQgaWYgdXNlciBoYXNuJ3QgcGlja2VkIGFueXRoaW5nIGluIHRpbWVvdXQuCiAgY29uc3QgdGltZW91dFByb21pc2UgPSBuZXcgUHJvbWlzZSgocmVzb2x2ZSkgPT4gewogICAgc2V0VGltZW91dCgoKSA9PiB7CiAgICAgIHJlc29sdmUobnVsbCk7CiAgICB9LCBGSUxFX0NIQU5HRV9USU1FT1VUX01TKTsKICB9KTsKCiAgLy8gV2FpdCBmb3IgdGhlIHVzZXIgdG8gcGljayB0aGUgZmlsZXMuCiAgY29uc3QgZmlsZXMgPSB5aWVsZCB7CiAgICBwcm9taXNlOiBQcm9taXNlLnJhY2UoW3BpY2tlZFByb21pc2UsIHRpbWVvdXRQcm9taXNlLCBjYW5jZWxQcm9taXNlXSksCiAgICByZXNwb25zZTogewogICAgICBhY3Rpb246ICdzdGFydGluZycsCiAgICB9CiAgfTsKCiAgaWYgKCFmaWxlcykgewogICAgcmV0dXJuIHsKICAgICAgcmVzcG9uc2U6IHsKICAgICAgICBhY3Rpb246ICdjb21wbGV0ZScsCiAgICAgIH0KICAgIH07CiAgfQoKICBjYW5jZWwucmVtb3ZlKCk7CgogIC8vIERpc2FibGUgdGhlIGlucHV0IGVsZW1lbnQgc2luY2UgZnVydGhlciBwaWNrcyBhcmUgbm90IGFsbG93ZWQuCiAgaW5wdXRFbGVtZW50LmRpc2FibGVkID0gdHJ1ZTsKCiAgZm9yIChjb25zdCBmaWxlIG9mIGZpbGVzKSB7CiAgICBjb25zdCBsaSA9IGRvY3VtZW50LmNyZWF0ZUVsZW1lbnQoJ2xpJyk7CiAgICBsaS5hcHBlbmQoc3BhbihmaWxlLm5hbWUsIHtmb250V2VpZ2h0OiAnYm9sZCd9KSk7CiAgICBsaS5hcHBlbmQoc3BhbigKICAgICAgICBgKCR7ZmlsZS50eXBlIHx8ICduL2EnfSkgLSAke2ZpbGUuc2l6ZX0gYnl0ZXMsIGAgKwogICAgICAgIGBsYXN0IG1vZGlmaWVkOiAkewogICAgICAgICAgICBmaWxlLmxhc3RNb2RpZmllZERhdGUgPyBmaWxlLmxhc3RNb2RpZmllZERhdGUudG9Mb2NhbGVEYXRlU3RyaW5nKCkgOgogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAnbi9hJ30gLSBgKSk7CiAgICBjb25zdCBwZXJjZW50ID0gc3BhbignMCUgZG9uZScpOwogICAgbGkuYXBwZW5kQ2hpbGQocGVyY2VudCk7CgogICAgb3V0cHV0RWxlbWVudC5hcHBlbmRDaGlsZChsaSk7CgogICAgY29uc3QgZmlsZURhdGFQcm9taXNlID0gbmV3IFByb21pc2UoKHJlc29sdmUpID0+IHsKICAgICAgY29uc3QgcmVhZGVyID0gbmV3IEZpbGVSZWFkZXIoKTsKICAgICAgcmVhZGVyLm9ubG9hZCA9IChlKSA9PiB7CiAgICAgICAgcmVzb2x2ZShlLnRhcmdldC5yZXN1bHQpOwogICAgICB9OwogICAgICByZWFkZXIucmVhZEFzQXJyYXlCdWZmZXIoZmlsZSk7CiAgICB9KTsKICAgIC8vIFdhaXQgZm9yIHRoZSBkYXRhIHRvIGJlIHJlYWR5LgogICAgbGV0IGZpbGVEYXRhID0geWllbGQgewogICAgICBwcm9taXNlOiBmaWxlRGF0YVByb21pc2UsCiAgICAgIHJlc3BvbnNlOiB7CiAgICAgICAgYWN0aW9uOiAnY29udGludWUnLAogICAgICB9CiAgICB9OwoKICAgIC8vIFVzZSBhIGNodW5rZWQgc2VuZGluZyB0byBhdm9pZCBtZXNzYWdlIHNpemUgbGltaXRzLiBTZWUgYi82MjExNTY2MC4KICAgIGxldCBwb3NpdGlvbiA9IDA7CiAgICB3aGlsZSAocG9zaXRpb24gPCBmaWxlRGF0YS5ieXRlTGVuZ3RoKSB7CiAgICAgIGNvbnN0IGxlbmd0aCA9IE1hdGgubWluKGZpbGVEYXRhLmJ5dGVMZW5ndGggLSBwb3NpdGlvbiwgTUFYX1BBWUxPQURfU0laRSk7CiAgICAgIGNvbnN0IGNodW5rID0gbmV3IFVpbnQ4QXJyYXkoZmlsZURhdGEsIHBvc2l0aW9uLCBsZW5ndGgpOwogICAgICBwb3NpdGlvbiArPSBsZW5ndGg7CgogICAgICBjb25zdCBiYXNlNjQgPSBidG9hKFN0cmluZy5mcm9tQ2hhckNvZGUuYXBwbHkobnVsbCwgY2h1bmspKTsKICAgICAgeWllbGQgewogICAgICAgIHJlc3BvbnNlOiB7CiAgICAgICAgICBhY3Rpb246ICdhcHBlbmQnLAogICAgICAgICAgZmlsZTogZmlsZS5uYW1lLAogICAgICAgICAgZGF0YTogYmFzZTY0LAogICAgICAgIH0sCiAgICAgIH07CiAgICAgIHBlcmNlbnQudGV4dENvbnRlbnQgPQogICAgICAgICAgYCR7TWF0aC5yb3VuZCgocG9zaXRpb24gLyBmaWxlRGF0YS5ieXRlTGVuZ3RoKSAqIDEwMCl9JSBkb25lYDsKICAgIH0KICB9CgogIC8vIEFsbCBkb25lLgogIHlpZWxkIHsKICAgIHJlc3BvbnNlOiB7CiAgICAgIGFjdGlvbjogJ2NvbXBsZXRlJywKICAgIH0KICB9Owp9CgpzY29wZS5nb29nbGUgPSBzY29wZS5nb29nbGUgfHwge307CnNjb3BlLmdvb2dsZS5jb2xhYiA9IHNjb3BlLmdvb2dsZS5jb2xhYiB8fCB7fTsKc2NvcGUuZ29vZ2xlLmNvbGFiLl9maWxlcyA9IHsKICBfdXBsb2FkRmlsZXMsCiAgX3VwbG9hZEZpbGVzQ29udGludWUsCn07Cn0pKHNlbGYpOwo=",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 76
        },
        "outputId": "5f0690c3-2a6a-4af3-bf00-2349332a9f66"
      },
      "source": [
        "uploaded = files.upload()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-0eeda6c2-545f-4f9d-91f2-b42e41cfa567\" name=\"files[]\" multiple disabled />\n",
              "     <output id=\"result-0eeda6c2-545f-4f9d-91f2-b42e41cfa567\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving PTRAIN.csv to PTRAIN.csv\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MyjSaFN2nKsg",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "660e49e1-a53b-4e40-cf18-870d2b46fe5d"
      },
      "source": [
        "for fn in uploaded.keys():\n",
        "  print('User uploaded file \"{name}\" with length {length} bytes'.format(\n",
        "      name=fn, length=len(uploaded[fn])))"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "User uploaded file \"PTRAIN.csv\" with length 4397 bytes\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eVXv1B8FnPj1",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 55
        },
        "outputId": "e366ef14-90b3-49d9-815d-52c3be2bf2b2"
      },
      "source": [
        "uploaded"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'PTRAIN.csv': b'id,diagnosis_result,radius,texture,perimeter,area,smoothness,compactness,symmetry,fractal_dimension\\r\\n1,M,23,12,151,954,0.143,0.278,0.242,0.079\\r\\n2,B,9,13,133,1326,0.143,0.079,0.181,0.057\\r\\n3,M,21,27,130,1203,0.125,0.16,0.207,0.06\\r\\n4,M,14,16,78,386,0.07,0.284,0.26,0.097\\r\\n5,M,9,19,135,1297,0.141,0.133,0.181,0.059\\r\\n6,B,25,25,83,477,0.128,0.17,0.209,0.076\\r\\n7,M,16,26,120,1040,0.095,0.109,0.179,0.057\\r\\n8,M,15,18,90,578,0.119,0.165,0.22,0.075\\r\\n9,M,19,24,88,520,0.127,0.193,0.235,0.074\\r\\n10,M,25,11,84,476,0.119,0.24,0.203,0.082\\r\\n11,M,24,21,103,798,0.082,0.067,0.153,0.057\\r\\n12,M,17,15,104,781,0.097,0.129,0.184,0.061\\r\\n13,B,14,15,132,1123,0.097,0.246,0.24,0.078\\r\\n14,M,12,22,104,783,0.084,0.1,0.185,0.053\\r\\n15,M,12,13,94,578,0.113,0.229,0.207,0.077\\r\\n16,M,22,19,97,659,0.114,0.16,0.23,0.071\\r\\n17,M,10,16,95,685,0.099,0.072,0.159,0.059\\r\\n18,M,15,14,108,799,0.117,0.202,0.216,0.074\\r\\n19,M,20,14,130,1260,0.098,0.103,0.158,0.054\\r\\n20,B,17,11,87,566,0.098,0.081,0.189,0.058\\r\\n21,B,16,14,86,520,0.108,0.127,0.197,0.068\\r\\n22,B,17,24,60,274,0.102,0.065,0.182,0.069\\r\\n23,M,20,27,103,704,0.107,0.214,0.252,0.07\\r\\n24,M,19,12,137,1404,0.094,0.102,0.177,0.053\\r\\n25,M,9,13,110,905,0.112,0.146,0.2,0.063\\r\\n26,M,19,27,116,913,0.119,0.228,0.304,0.074\\r\\n27,M,10,24,97,645,0.105,0.187,0.225,0.069\\r\\n28,M,16,24,122,1094,0.094,0.107,0.17,0.057\\r\\n29,M,15,15,102,732,0.108,0.17,0.193,0.065\\r\\n30,M,11,16,115,955,0.098,0.116,0.174,0.061\\r\\n31,M,11,22,125,1088,0.106,0.189,0.218,0.062\\r\\n32,M,23,26,78,441,0.111,0.152,0.23,0.078\\r\\n33,M,20,18,113,899,0.12,0.15,0.225,0.064\\r\\n34,M,11,21,128,1162,0.094,0.172,0.185,0.063\\r\\n35,M,16,23,107,807,0.104,0.156,0.2,0.065\\r\\n36,M,10,13,110,870,0.096,0.134,0.19,0.057\\r\\n37,M,18,12,94,633,0.098,0.11,0.189,0.061\\r\\n38,B,21,11,83,524,0.09,0.038,0.147,0.059\\r\\n39,M,11,15,96,699,0.094,0.051,0.157,0.055\\r\\n40,M,10,14,88,559,0.102,0.126,0.172,0.064\\r\\n41,M,24,16,86,563,0.082,0.06,0.178,0.056\\r\\n42,M,19,27,72,371,0.123,0.122,0.19,0.069\\r\\n43,M,11,11,128,1104,0.091,0.219,0.231,0.063\\r\\n44,M,15,21,87,545,0.104,0.144,0.197,0.068\\r\\n45,M,10,15,85,532,0.097,0.105,0.175,0.062\\r\\n46,M,18,11,124,1076,0.11,0.169,0.191,0.06\\r\\n47,B,22,12,52,202,0.086,0.059,0.177,0.065\\r\\n48,M,20,14,86,535,0.116,0.123,0.213,0.068\\r\\n49,B,20,21,78,449,0.103,0.091,0.168,0.06\\r\\n50,B,25,11,87,561,0.088,0.077,0.181,0.057\\r\\n51,B,19,25,75,428,0.086,0.05,0.15,0.059\\r\\n52,B,19,22,87,572,0.077,0.061,0.135,0.06\\r\\n53,B,25,15,76,438,0.083,0.048,0.187,0.061\\r\\n54,M,14,26,120,1033,0.115,0.149,0.209,0.063\\r\\n55,M,18,25,97,713,0.091,0.071,0.162,0.057\\r\\n56,B,18,13,73,409,0.095,0.055,0.192,0.059\\r\\n57,M,10,19,126,1152,0.105,0.127,0.192,0.06\\r\\n58,M,17,20,96,657,0.114,0.137,0.203,0.068\\r\\n59,B,22,15,83,527,0.081,0.038,0.182,0.055\\r\\n60,B,23,26,54,225,0.098,0.053,0.168,0.072\\r\\n61,B,15,18,65,312,0.113,0.081,0.274,0.07\\r\\n62,B,25,15,55,222,0.124,0.09,0.183,0.068\\r\\n63,M,12,22,96,646,0.105,0.201,0.195,0.073\\r\\n64,B,24,17,59,261,0.077,0.088,0.234,0.07\\r\\n65,M,16,19,83,499,0.112,0.126,0.191,0.066\\r\\n66,M,11,21,97,668,0.117,0.148,0.195,0.067\\r\\n67,B,12,13,60,269,0.104,0.078,0.172,0.069\\r\\n68,B,18,12,72,394,0.081,0.047,0.152,0.057\\r\\n69,B,16,17,59,251,0.107,0.141,0.211,0.08\\r\\n70,B,17,21,81,503,0.098,0.052,0.159,0.057\\r\\n71,M,21,18,124,1130,0.09,0.103,0.158,0.055\\r\\n72,B,9,26,59,244,0.098,0.153,0.19,0.09\\r\\n73,M,21,12,114,929,0.107,0.183,0.193,0.065\\r\\n74,M,22,25,90,584,0.101,0.128,0.166,0.066\\r\\n75,B,18,13,79,471,0.092,0.068,0.172,0.059\\r\\n76,M,21,18,104,818,0.092,0.084,0.18,0.054\\r\\n77,B,10,17,88,559,0.129,0.105,0.24,0.066\\r\\n78,M,11,21,120,1006,0.107,0.215,0.215,0.067\\r\\n79,M,16,18,144,1245,0.129,0.345,0.291,0.081\\r\\n80,B,22,16,83,506,0.099,0.095,0.172,0.06\\r\\n81,B,10,18,74,402,0.11,0.094,0.184,0.07\\r\\n82,B,17,21,86,520,0.108,0.154,0.194,0.069\\r\\n83,M,10,15,172,1878,0.106,0.267,0.183,0.068\\r\\n84,M,20,14,129,1132,0.122,0.179,0.163,0.072\\r\\n85,B,25,21,77,443,0.097,0.072,0.208,0.06\\r\\n86,M,14,13,121,1075,0.099,0.105,0.213,0.06\\r\\n87,M,19,26,94,648,0.094,0.099,0.208,0.056\\r\\n88,M,19,11,122,1076,0.09,0.121,0.195,0.056\\r\\n89,B,11,11,80,466,0.088,0.094,0.193,0.064\\r\\n90,B,12,23,96,652,0.113,0.134,0.212,0.063\\r\\n91,B,23,27,95,663,0.09,0.086,0.169,0.059\\r\\n92,M,10,12,100,728,0.092,0.104,0.172,0.061\\r\\n93,B,14,14,85,552,0.074,0.051,0.139,0.053\\r\\n94,B,10,17,87,555,0.102,0.082,0.164,0.057\\r\\n95,M,22,26,100,706,0.104,0.155,0.186,0.063\\r\\n96,M,23,16,132,1264,0.091,0.131,0.21,0.056\\r\\n97,B,22,14,78,451,0.105,0.071,0.19,0.066\\r\\n98,B,19,27,62,295,0.102,0.053,0.135,0.069\\r\\n99,B,21,24,74,413,0.09,0.075,0.162,0.066\\r\\n100,M,16,27,94,643,0.098,0.114,0.188,0.064\\r\\n'}"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7Nj9kJYznS5x",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import io"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "z1Hu81Q7nS9s",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "d549082b-f5a0-455c-9f0d-49ec68243c16"
      },
      "source": [
        "train= pd.read_csv(io.StringIO(uploaded['PTRAIN.csv'].decode('utf-8')))\n",
        "train.head()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>diagnosis_result</th>\n",
              "      <th>radius</th>\n",
              "      <th>texture</th>\n",
              "      <th>perimeter</th>\n",
              "      <th>area</th>\n",
              "      <th>smoothness</th>\n",
              "      <th>compactness</th>\n",
              "      <th>symmetry</th>\n",
              "      <th>fractal_dimension</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>M</td>\n",
              "      <td>23</td>\n",
              "      <td>12</td>\n",
              "      <td>151</td>\n",
              "      <td>954</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.278</td>\n",
              "      <td>0.242</td>\n",
              "      <td>0.079</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>B</td>\n",
              "      <td>9</td>\n",
              "      <td>13</td>\n",
              "      <td>133</td>\n",
              "      <td>1326</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.079</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.057</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>M</td>\n",
              "      <td>21</td>\n",
              "      <td>27</td>\n",
              "      <td>130</td>\n",
              "      <td>1203</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.160</td>\n",
              "      <td>0.207</td>\n",
              "      <td>0.060</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>M</td>\n",
              "      <td>14</td>\n",
              "      <td>16</td>\n",
              "      <td>78</td>\n",
              "      <td>386</td>\n",
              "      <td>0.070</td>\n",
              "      <td>0.284</td>\n",
              "      <td>0.260</td>\n",
              "      <td>0.097</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>M</td>\n",
              "      <td>9</td>\n",
              "      <td>19</td>\n",
              "      <td>135</td>\n",
              "      <td>1297</td>\n",
              "      <td>0.141</td>\n",
              "      <td>0.133</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.059</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   id diagnosis_result  radius  ...  compactness  symmetry  fractal_dimension\n",
              "0   1                M      23  ...        0.278     0.242              0.079\n",
              "1   2                B       9  ...        0.079     0.181              0.057\n",
              "2   3                M      21  ...        0.160     0.207              0.060\n",
              "3   4                M      14  ...        0.284     0.260              0.097\n",
              "4   5                M       9  ...        0.133     0.181              0.059\n",
              "\n",
              "[5 rows x 10 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "f8MXFhOynTGU",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 362
        },
        "outputId": "e6cd90f8-2e18-4339-b5c8-97ef9936f16b"
      },
      "source": [
        "sns.heatmap(train.isnull(),yticklabels=False,cbar=False,cmap='viridis')"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7fca982f39e8>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FvnekFqdnTJX",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "diag=pd.get_dummies(train['diagnosis_result'],drop_first=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nNo3LM3KnTMD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train = pd.concat([train,diag],axis=1)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0pXxZIoHnTRN",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "99ee3ca4-2012-4f03-bb20-3942556cefc2"
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>diagnosis_result</th>\n",
              "      <th>radius</th>\n",
              "      <th>texture</th>\n",
              "      <th>perimeter</th>\n",
              "      <th>area</th>\n",
              "      <th>smoothness</th>\n",
              "      <th>compactness</th>\n",
              "      <th>symmetry</th>\n",
              "      <th>fractal_dimension</th>\n",
              "      <th>M</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>M</td>\n",
              "      <td>23</td>\n",
              "      <td>12</td>\n",
              "      <td>151</td>\n",
              "      <td>954</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.278</td>\n",
              "      <td>0.242</td>\n",
              "      <td>0.079</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>B</td>\n",
              "      <td>9</td>\n",
              "      <td>13</td>\n",
              "      <td>133</td>\n",
              "      <td>1326</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.079</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.057</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>M</td>\n",
              "      <td>21</td>\n",
              "      <td>27</td>\n",
              "      <td>130</td>\n",
              "      <td>1203</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.160</td>\n",
              "      <td>0.207</td>\n",
              "      <td>0.060</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>M</td>\n",
              "      <td>14</td>\n",
              "      <td>16</td>\n",
              "      <td>78</td>\n",
              "      <td>386</td>\n",
              "      <td>0.070</td>\n",
              "      <td>0.284</td>\n",
              "      <td>0.260</td>\n",
              "      <td>0.097</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>M</td>\n",
              "      <td>9</td>\n",
              "      <td>19</td>\n",
              "      <td>135</td>\n",
              "      <td>1297</td>\n",
              "      <td>0.141</td>\n",
              "      <td>0.133</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.059</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   id diagnosis_result  radius  ...  symmetry  fractal_dimension  M\n",
              "0   1                M      23  ...     0.242              0.079  1\n",
              "1   2                B       9  ...     0.181              0.057  0\n",
              "2   3                M      21  ...     0.207              0.060  1\n",
              "3   4                M      14  ...     0.260              0.097  1\n",
              "4   5                M       9  ...     0.181              0.059  1\n",
              "\n",
              "[5 rows x 11 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H_wCYgPgnTWV",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train.drop('id',axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Avyb1LIrnTUZ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train.drop('diagnosis_result',axis=1,inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "v76s7iMNpbpO",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "f9f1a59c-bf16-4040-c518-598d8803f0fe"
      },
      "source": [
        "train.head()"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>radius</th>\n",
              "      <th>texture</th>\n",
              "      <th>perimeter</th>\n",
              "      <th>area</th>\n",
              "      <th>smoothness</th>\n",
              "      <th>compactness</th>\n",
              "      <th>symmetry</th>\n",
              "      <th>fractal_dimension</th>\n",
              "      <th>M</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>23</td>\n",
              "      <td>12</td>\n",
              "      <td>151</td>\n",
              "      <td>954</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.278</td>\n",
              "      <td>0.242</td>\n",
              "      <td>0.079</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>9</td>\n",
              "      <td>13</td>\n",
              "      <td>133</td>\n",
              "      <td>1326</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.079</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.057</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>21</td>\n",
              "      <td>27</td>\n",
              "      <td>130</td>\n",
              "      <td>1203</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.160</td>\n",
              "      <td>0.207</td>\n",
              "      <td>0.060</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>14</td>\n",
              "      <td>16</td>\n",
              "      <td>78</td>\n",
              "      <td>386</td>\n",
              "      <td>0.070</td>\n",
              "      <td>0.284</td>\n",
              "      <td>0.260</td>\n",
              "      <td>0.097</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>9</td>\n",
              "      <td>19</td>\n",
              "      <td>135</td>\n",
              "      <td>1297</td>\n",
              "      <td>0.141</td>\n",
              "      <td>0.133</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.059</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   radius  texture  perimeter  ...  symmetry  fractal_dimension  M\n",
              "0      23       12        151  ...     0.242              0.079  1\n",
              "1       9       13        133  ...     0.181              0.057  0\n",
              "2      21       27        130  ...     0.207              0.060  1\n",
              "3      14       16         78  ...     0.260              0.097  1\n",
              "4       9       19        135  ...     0.181              0.059  1\n",
              "\n",
              "[5 rows x 9 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0OcKgWilpfyq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X= train.drop('M',axis=1)\n",
        "Y= train['M']\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dkXl9xxJpssj",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "26e9c727-a142-4a38-8b88-532e932f1eef"
      },
      "source": [
        "X.head()"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>radius</th>\n",
              "      <th>texture</th>\n",
              "      <th>perimeter</th>\n",
              "      <th>area</th>\n",
              "      <th>smoothness</th>\n",
              "      <th>compactness</th>\n",
              "      <th>symmetry</th>\n",
              "      <th>fractal_dimension</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>23</td>\n",
              "      <td>12</td>\n",
              "      <td>151</td>\n",
              "      <td>954</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.278</td>\n",
              "      <td>0.242</td>\n",
              "      <td>0.079</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>9</td>\n",
              "      <td>13</td>\n",
              "      <td>133</td>\n",
              "      <td>1326</td>\n",
              "      <td>0.143</td>\n",
              "      <td>0.079</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.057</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>21</td>\n",
              "      <td>27</td>\n",
              "      <td>130</td>\n",
              "      <td>1203</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.160</td>\n",
              "      <td>0.207</td>\n",
              "      <td>0.060</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>14</td>\n",
              "      <td>16</td>\n",
              "      <td>78</td>\n",
              "      <td>386</td>\n",
              "      <td>0.070</td>\n",
              "      <td>0.284</td>\n",
              "      <td>0.260</td>\n",
              "      <td>0.097</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>9</td>\n",
              "      <td>19</td>\n",
              "      <td>135</td>\n",
              "      <td>1297</td>\n",
              "      <td>0.141</td>\n",
              "      <td>0.133</td>\n",
              "      <td>0.181</td>\n",
              "      <td>0.059</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   radius  texture  perimeter  ...  compactness  symmetry  fractal_dimension\n",
              "0      23       12        151  ...        0.278     0.242              0.079\n",
              "1       9       13        133  ...        0.079     0.181              0.057\n",
              "2      21       27        130  ...        0.160     0.207              0.060\n",
              "3      14       16         78  ...        0.284     0.260              0.097\n",
              "4       9       19        135  ...        0.133     0.181              0.059\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ARTRRZcIpx4_",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 125
        },
        "outputId": "0eca424a-cda9-49b7-a119-5285b6cbaee9"
      },
      "source": [
        "Y.head()"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    1\n",
              "1    0\n",
              "2    1\n",
              "3    1\n",
              "4    1\n",
              "Name: M, dtype: uint8"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zEakfkJspx_F",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.model_selection  import train_test_split"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NTs6K-rvpyGF",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 89
        },
        "outputId": "13b15f34-2c40-4cbf-b7a6-44baaf00e9f0"
      },
      "source": [
        "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state=101)\n",
        "print(X_train.shape)\n",
        "print(X_test.shape)\n",
        "print(Y_train.shape)\n",
        "print(Y_test.shape)\n"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(80, 8)\n",
            "(20, 8)\n",
            "(80,)\n",
            "(20,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U5tE0IhNpyPA",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.preprocessing import MinMaxScaler"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1FAUWrvygddL",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "scaler = MinMaxScaler(feature_range = (0,1))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4A8fDnPEggQv",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "scaler.fit(X_train)\n",
        "X_train = scaler.transform(X_train)\n",
        "X_test = scaler.transform(X_test)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Rp5dl2BrqE9W",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "logmodel = LogisticRegression()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "to6g2wF5qFA7",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 107
        },
        "outputId": "ab406ade-b203-40ab-81b5-d3b919e62e16"
      },
      "source": [
        "logmodel.fit(X_train,Y_train)"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
              "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
              "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
              "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
              "                   warm_start=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4L0CLyeIqFPl",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "predictions = logmodel.predict(X_test)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4-CTAPtKqFM8",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "outputId": "8efa4ccd-a1e1-408d-8d10-c05619420d4a"
      },
      "source": [
        "predictions"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0],\n",
              "      dtype=uint8)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pp0tHcGdqFLX",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn import metrics"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "siPCBqqyqFIS",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "accuracy=logmodel.score(X_test,Y_test)\n",
        "accuracytrain=logmodel.score(X_train,Y_train)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J5eWWz-MqFFK",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "outputId": "bb1b466c-bb62-4bf7-889c-fbdf0e74156c"
      },
      "source": [
        "print(accuracy*100)\n",
        "print(accuracytrain*100)"
      ],
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "80.0\n",
            "90.0\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}