Parkinson's_Detection.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Parkinson's Detection.ipynb",
      "provenance": [],
      "toc_visible": true,
      "authorship_tag": "ABX9TyPMH3gBJ2IMUb62Bshi+ICu",
      "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/RasKemal/Data-Science-Projects/blob/main/Parkinson's_Detection.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "raFig-k1gyn2"
      },
      "outputs": [],
      "source": [
        "#Gerekli kütüphanelerin yüklenmesi\n",
        "import csv\n",
        "import math\n",
        "import random\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sn\n",
        "from sklearn.metrics import roc_curve, roc_auc_score\n",
        "from sklearn.naive_bayes import GaussianNB\n",
        "from sklearn.metrics import confusion_matrix, classification_report\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "from sklearn import tree\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Datayı csv dosyadan pandas dataframe'e yükleme\n",
        "data = pd.read_csv('/content/parkinsons.csv')"
      ],
      "metadata": {
        "id": "LG0RrHBlhN87"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "xlt8e5JY6tLg",
        "outputId": "702fa647-b669-426e-d9a8-47e637ae2e68"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-3bb2e154-d5e4-4a25-8929-bcc4d0dd8af0\">\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>name</th>\n",
              "      <th>MDVP:Fo(Hz)</th>\n",
              "      <th>MDVP:Fhi(Hz)</th>\n",
              "      <th>MDVP:Flo(Hz)</th>\n",
              "      <th>MDVP:Jitter(%)</th>\n",
              "      <th>MDVP:Jitter(Abs)</th>\n",
              "      <th>MDVP:RAP</th>\n",
              "      <th>MDVP:PPQ</th>\n",
              "      <th>Jitter:DDP</th>\n",
              "      <th>MDVP:Shimmer</th>\n",
              "      <th>MDVP:Shimmer(dB)</th>\n",
              "      <th>Shimmer:APQ3</th>\n",
              "      <th>Shimmer:APQ5</th>\n",
              "      <th>MDVP:APQ</th>\n",
              "      <th>Shimmer:DDA</th>\n",
              "      <th>NHR</th>\n",
              "      <th>HNR</th>\n",
              "      <th>status</th>\n",
              "      <th>RPDE</th>\n",
              "      <th>DFA</th>\n",
              "      <th>spread1</th>\n",
              "      <th>spread2</th>\n",
              "      <th>D2</th>\n",
              "      <th>PPE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>phon_R01_S01_1</td>\n",
              "      <td>119.992</td>\n",
              "      <td>157.302</td>\n",
              "      <td>74.997</td>\n",
              "      <td>0.00784</td>\n",
              "      <td>0.00007</td>\n",
              "      <td>0.00370</td>\n",
              "      <td>0.00554</td>\n",
              "      <td>0.01109</td>\n",
              "      <td>0.04374</td>\n",
              "      <td>0.426</td>\n",
              "      <td>0.02182</td>\n",
              "      <td>0.03130</td>\n",
              "      <td>0.02971</td>\n",
              "      <td>0.06545</td>\n",
              "      <td>0.02211</td>\n",
              "      <td>21.033</td>\n",
              "      <td>1</td>\n",
              "      <td>0.414783</td>\n",
              "      <td>0.815285</td>\n",
              "      <td>-4.813031</td>\n",
              "      <td>0.266482</td>\n",
              "      <td>2.301442</td>\n",
              "      <td>0.284654</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>phon_R01_S01_2</td>\n",
              "      <td>122.400</td>\n",
              "      <td>148.650</td>\n",
              "      <td>113.819</td>\n",
              "      <td>0.00968</td>\n",
              "      <td>0.00008</td>\n",
              "      <td>0.00465</td>\n",
              "      <td>0.00696</td>\n",
              "      <td>0.01394</td>\n",
              "      <td>0.06134</td>\n",
              "      <td>0.626</td>\n",
              "      <td>0.03134</td>\n",
              "      <td>0.04518</td>\n",
              "      <td>0.04368</td>\n",
              "      <td>0.09403</td>\n",
              "      <td>0.01929</td>\n",
              "      <td>19.085</td>\n",
              "      <td>1</td>\n",
              "      <td>0.458359</td>\n",
              "      <td>0.819521</td>\n",
              "      <td>-4.075192</td>\n",
              "      <td>0.335590</td>\n",
              "      <td>2.486855</td>\n",
              "      <td>0.368674</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>phon_R01_S01_3</td>\n",
              "      <td>116.682</td>\n",
              "      <td>131.111</td>\n",
              "      <td>111.555</td>\n",
              "      <td>0.01050</td>\n",
              "      <td>0.00009</td>\n",
              "      <td>0.00544</td>\n",
              "      <td>0.00781</td>\n",
              "      <td>0.01633</td>\n",
              "      <td>0.05233</td>\n",
              "      <td>0.482</td>\n",
              "      <td>0.02757</td>\n",
              "      <td>0.03858</td>\n",
              "      <td>0.03590</td>\n",
              "      <td>0.08270</td>\n",
              "      <td>0.01309</td>\n",
              "      <td>20.651</td>\n",
              "      <td>1</td>\n",
              "      <td>0.429895</td>\n",
              "      <td>0.825288</td>\n",
              "      <td>-4.443179</td>\n",
              "      <td>0.311173</td>\n",
              "      <td>2.342259</td>\n",
              "      <td>0.332634</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>phon_R01_S01_4</td>\n",
              "      <td>116.676</td>\n",
              "      <td>137.871</td>\n",
              "      <td>111.366</td>\n",
              "      <td>0.00997</td>\n",
              "      <td>0.00009</td>\n",
              "      <td>0.00502</td>\n",
              "      <td>0.00698</td>\n",
              "      <td>0.01505</td>\n",
              "      <td>0.05492</td>\n",
              "      <td>0.517</td>\n",
              "      <td>0.02924</td>\n",
              "      <td>0.04005</td>\n",
              "      <td>0.03772</td>\n",
              "      <td>0.08771</td>\n",
              "      <td>0.01353</td>\n",
              "      <td>20.644</td>\n",
              "      <td>1</td>\n",
              "      <td>0.434969</td>\n",
              "      <td>0.819235</td>\n",
              "      <td>-4.117501</td>\n",
              "      <td>0.334147</td>\n",
              "      <td>2.405554</td>\n",
              "      <td>0.368975</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>phon_R01_S01_5</td>\n",
              "      <td>116.014</td>\n",
              "      <td>141.781</td>\n",
              "      <td>110.655</td>\n",
              "      <td>0.01284</td>\n",
              "      <td>0.00011</td>\n",
              "      <td>0.00655</td>\n",
              "      <td>0.00908</td>\n",
              "      <td>0.01966</td>\n",
              "      <td>0.06425</td>\n",
              "      <td>0.584</td>\n",
              "      <td>0.03490</td>\n",
              "      <td>0.04825</td>\n",
              "      <td>0.04465</td>\n",
              "      <td>0.10470</td>\n",
              "      <td>0.01767</td>\n",
              "      <td>19.649</td>\n",
              "      <td>1</td>\n",
              "      <td>0.417356</td>\n",
              "      <td>0.823484</td>\n",
              "      <td>-3.747787</td>\n",
              "      <td>0.234513</td>\n",
              "      <td>2.332180</td>\n",
              "      <td>0.410335</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>190</th>\n",
              "      <td>phon_R01_S50_2</td>\n",
              "      <td>174.188</td>\n",
              "      <td>230.978</td>\n",
              "      <td>94.261</td>\n",
              "      <td>0.00459</td>\n",
              "      <td>0.00003</td>\n",
              "      <td>0.00263</td>\n",
              "      <td>0.00259</td>\n",
              "      <td>0.00790</td>\n",
              "      <td>0.04087</td>\n",
              "      <td>0.405</td>\n",
              "      <td>0.02336</td>\n",
              "      <td>0.02498</td>\n",
              "      <td>0.02745</td>\n",
              "      <td>0.07008</td>\n",
              "      <td>0.02764</td>\n",
              "      <td>19.517</td>\n",
              "      <td>0</td>\n",
              "      <td>0.448439</td>\n",
              "      <td>0.657899</td>\n",
              "      <td>-6.538586</td>\n",
              "      <td>0.121952</td>\n",
              "      <td>2.657476</td>\n",
              "      <td>0.133050</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>191</th>\n",
              "      <td>phon_R01_S50_3</td>\n",
              "      <td>209.516</td>\n",
              "      <td>253.017</td>\n",
              "      <td>89.488</td>\n",
              "      <td>0.00564</td>\n",
              "      <td>0.00003</td>\n",
              "      <td>0.00331</td>\n",
              "      <td>0.00292</td>\n",
              "      <td>0.00994</td>\n",
              "      <td>0.02751</td>\n",
              "      <td>0.263</td>\n",
              "      <td>0.01604</td>\n",
              "      <td>0.01657</td>\n",
              "      <td>0.01879</td>\n",
              "      <td>0.04812</td>\n",
              "      <td>0.01810</td>\n",
              "      <td>19.147</td>\n",
              "      <td>0</td>\n",
              "      <td>0.431674</td>\n",
              "      <td>0.683244</td>\n",
              "      <td>-6.195325</td>\n",
              "      <td>0.129303</td>\n",
              "      <td>2.784312</td>\n",
              "      <td>0.168895</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>192</th>\n",
              "      <td>phon_R01_S50_4</td>\n",
              "      <td>174.688</td>\n",
              "      <td>240.005</td>\n",
              "      <td>74.287</td>\n",
              "      <td>0.01360</td>\n",
              "      <td>0.00008</td>\n",
              "      <td>0.00624</td>\n",
              "      <td>0.00564</td>\n",
              "      <td>0.01873</td>\n",
              "      <td>0.02308</td>\n",
              "      <td>0.256</td>\n",
              "      <td>0.01268</td>\n",
              "      <td>0.01365</td>\n",
              "      <td>0.01667</td>\n",
              "      <td>0.03804</td>\n",
              "      <td>0.10715</td>\n",
              "      <td>17.883</td>\n",
              "      <td>0</td>\n",
              "      <td>0.407567</td>\n",
              "      <td>0.655683</td>\n",
              "      <td>-6.787197</td>\n",
              "      <td>0.158453</td>\n",
              "      <td>2.679772</td>\n",
              "      <td>0.131728</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>193</th>\n",
              "      <td>phon_R01_S50_5</td>\n",
              "      <td>198.764</td>\n",
              "      <td>396.961</td>\n",
              "      <td>74.904</td>\n",
              "      <td>0.00740</td>\n",
              "      <td>0.00004</td>\n",
              "      <td>0.00370</td>\n",
              "      <td>0.00390</td>\n",
              "      <td>0.01109</td>\n",
              "      <td>0.02296</td>\n",
              "      <td>0.241</td>\n",
              "      <td>0.01265</td>\n",
              "      <td>0.01321</td>\n",
              "      <td>0.01588</td>\n",
              "      <td>0.03794</td>\n",
              "      <td>0.07223</td>\n",
              "      <td>19.020</td>\n",
              "      <td>0</td>\n",
              "      <td>0.451221</td>\n",
              "      <td>0.643956</td>\n",
              "      <td>-6.744577</td>\n",
              "      <td>0.207454</td>\n",
              "      <td>2.138608</td>\n",
              "      <td>0.123306</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>194</th>\n",
              "      <td>phon_R01_S50_6</td>\n",
              "      <td>214.289</td>\n",
              "      <td>260.277</td>\n",
              "      <td>77.973</td>\n",
              "      <td>0.00567</td>\n",
              "      <td>0.00003</td>\n",
              "      <td>0.00295</td>\n",
              "      <td>0.00317</td>\n",
              "      <td>0.00885</td>\n",
              "      <td>0.01884</td>\n",
              "      <td>0.190</td>\n",
              "      <td>0.01026</td>\n",
              "      <td>0.01161</td>\n",
              "      <td>0.01373</td>\n",
              "      <td>0.03078</td>\n",
              "      <td>0.04398</td>\n",
              "      <td>21.209</td>\n",
              "      <td>0</td>\n",
              "      <td>0.462803</td>\n",
              "      <td>0.664357</td>\n",
              "      <td>-5.724056</td>\n",
              "      <td>0.190667</td>\n",
              "      <td>2.555477</td>\n",
              "      <td>0.148569</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>195 rows × 24 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3bb2e154-d5e4-4a25-8929-bcc4d0dd8af0')\"\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-3bb2e154-d5e4-4a25-8929-bcc4d0dd8af0 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-3bb2e154-d5e4-4a25-8929-bcc4d0dd8af0');\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",
              "  "
            ],
            "text/plain": [
              "               name  MDVP:Fo(Hz)  MDVP:Fhi(Hz)  ...   spread2        D2       PPE\n",
              "0    phon_R01_S01_1      119.992       157.302  ...  0.266482  2.301442  0.284654\n",
              "1    phon_R01_S01_2      122.400       148.650  ...  0.335590  2.486855  0.368674\n",
              "2    phon_R01_S01_3      116.682       131.111  ...  0.311173  2.342259  0.332634\n",
              "3    phon_R01_S01_4      116.676       137.871  ...  0.334147  2.405554  0.368975\n",
              "4    phon_R01_S01_5      116.014       141.781  ...  0.234513  2.332180  0.410335\n",
              "..              ...          ...           ...  ...       ...       ...       ...\n",
              "190  phon_R01_S50_2      174.188       230.978  ...  0.121952  2.657476  0.133050\n",
              "191  phon_R01_S50_3      209.516       253.017  ...  0.129303  2.784312  0.168895\n",
              "192  phon_R01_S50_4      174.688       240.005  ...  0.158453  2.679772  0.131728\n",
              "193  phon_R01_S50_5      198.764       396.961  ...  0.207454  2.138608  0.123306\n",
              "194  phon_R01_S50_6      214.289       260.277  ...  0.190667  2.555477  0.148569\n",
              "\n",
              "[195 rows x 24 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Dataset hakkında daha çok bilgi\n",
        "data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9JQfHKUohdpq",
        "outputId": "8e7daa96-d2fc-4c52-8b64-5939028e6858"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 195 entries, 0 to 194\n",
            "Data columns (total 24 columns):\n",
            " #   Column            Non-Null Count  Dtype  \n",
            "---  ------            --------------  -----  \n",
            " 0   name              195 non-null    object \n",
            " 1   MDVP:Fo(Hz)       195 non-null    float64\n",
            " 2   MDVP:Fhi(Hz)      195 non-null    float64\n",
            " 3   MDVP:Flo(Hz)      195 non-null    float64\n",
            " 4   MDVP:Jitter(%)    195 non-null    float64\n",
            " 5   MDVP:Jitter(Abs)  195 non-null    float64\n",
            " 6   MDVP:RAP          195 non-null    float64\n",
            " 7   MDVP:PPQ          195 non-null    float64\n",
            " 8   Jitter:DDP        195 non-null    float64\n",
            " 9   MDVP:Shimmer      195 non-null    float64\n",
            " 10  MDVP:Shimmer(dB)  195 non-null    float64\n",
            " 11  Shimmer:APQ3      195 non-null    float64\n",
            " 12  Shimmer:APQ5      195 non-null    float64\n",
            " 13  MDVP:APQ          195 non-null    float64\n",
            " 14  Shimmer:DDA       195 non-null    float64\n",
            " 15  NHR               195 non-null    float64\n",
            " 16  HNR               195 non-null    float64\n",
            " 17  status            195 non-null    int64  \n",
            " 18  RPDE              195 non-null    float64\n",
            " 19  DFA               195 non-null    float64\n",
            " 20  spread1           195 non-null    float64\n",
            " 21  spread2           195 non-null    float64\n",
            " 22  D2                195 non-null    float64\n",
            " 23  PPE               195 non-null    float64\n",
            "dtypes: float64(22), int64(1), object(1)\n",
            "memory usage: 36.7+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Dataset hakkında istatistiksel veri alma\n",
        "data.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 364
        },
        "id": "Qmsnjkrycnla",
        "outputId": "8d119635-fb84-439b-bcf3-1c0e51200c8a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-6f81c582-b293-4311-a145-060e14bb5ffe\">\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>MDVP:Fo(Hz)</th>\n",
              "      <th>MDVP:Fhi(Hz)</th>\n",
              "      <th>MDVP:Flo(Hz)</th>\n",
              "      <th>MDVP:Jitter(%)</th>\n",
              "      <th>MDVP:Jitter(Abs)</th>\n",
              "      <th>MDVP:RAP</th>\n",
              "      <th>MDVP:PPQ</th>\n",
              "      <th>Jitter:DDP</th>\n",
              "      <th>MDVP:Shimmer</th>\n",
              "      <th>MDVP:Shimmer(dB)</th>\n",
              "      <th>Shimmer:APQ3</th>\n",
              "      <th>Shimmer:APQ5</th>\n",
              "      <th>MDVP:APQ</th>\n",
              "      <th>Shimmer:DDA</th>\n",
              "      <th>NHR</th>\n",
              "      <th>HNR</th>\n",
              "      <th>status</th>\n",
              "      <th>RPDE</th>\n",
              "      <th>DFA</th>\n",
              "      <th>spread1</th>\n",
              "      <th>spread2</th>\n",
              "      <th>D2</th>\n",
              "      <th>PPE</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "      <td>195.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>154.228641</td>\n",
              "      <td>197.104918</td>\n",
              "      <td>116.324631</td>\n",
              "      <td>0.006220</td>\n",
              "      <td>0.000044</td>\n",
              "      <td>0.003306</td>\n",
              "      <td>0.003446</td>\n",
              "      <td>0.009920</td>\n",
              "      <td>0.029709</td>\n",
              "      <td>0.282251</td>\n",
              "      <td>0.015664</td>\n",
              "      <td>0.017878</td>\n",
              "      <td>0.024081</td>\n",
              "      <td>0.046993</td>\n",
              "      <td>0.024847</td>\n",
              "      <td>21.885974</td>\n",
              "      <td>0.753846</td>\n",
              "      <td>0.498536</td>\n",
              "      <td>0.718099</td>\n",
              "      <td>-5.684397</td>\n",
              "      <td>0.226510</td>\n",
              "      <td>2.381826</td>\n",
              "      <td>0.206552</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>41.390065</td>\n",
              "      <td>91.491548</td>\n",
              "      <td>43.521413</td>\n",
              "      <td>0.004848</td>\n",
              "      <td>0.000035</td>\n",
              "      <td>0.002968</td>\n",
              "      <td>0.002759</td>\n",
              "      <td>0.008903</td>\n",
              "      <td>0.018857</td>\n",
              "      <td>0.194877</td>\n",
              "      <td>0.010153</td>\n",
              "      <td>0.012024</td>\n",
              "      <td>0.016947</td>\n",
              "      <td>0.030459</td>\n",
              "      <td>0.040418</td>\n",
              "      <td>4.425764</td>\n",
              "      <td>0.431878</td>\n",
              "      <td>0.103942</td>\n",
              "      <td>0.055336</td>\n",
              "      <td>1.090208</td>\n",
              "      <td>0.083406</td>\n",
              "      <td>0.382799</td>\n",
              "      <td>0.090119</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>88.333000</td>\n",
              "      <td>102.145000</td>\n",
              "      <td>65.476000</td>\n",
              "      <td>0.001680</td>\n",
              "      <td>0.000007</td>\n",
              "      <td>0.000680</td>\n",
              "      <td>0.000920</td>\n",
              "      <td>0.002040</td>\n",
              "      <td>0.009540</td>\n",
              "      <td>0.085000</td>\n",
              "      <td>0.004550</td>\n",
              "      <td>0.005700</td>\n",
              "      <td>0.007190</td>\n",
              "      <td>0.013640</td>\n",
              "      <td>0.000650</td>\n",
              "      <td>8.441000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.256570</td>\n",
              "      <td>0.574282</td>\n",
              "      <td>-7.964984</td>\n",
              "      <td>0.006274</td>\n",
              "      <td>1.423287</td>\n",
              "      <td>0.044539</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>117.572000</td>\n",
              "      <td>134.862500</td>\n",
              "      <td>84.291000</td>\n",
              "      <td>0.003460</td>\n",
              "      <td>0.000020</td>\n",
              "      <td>0.001660</td>\n",
              "      <td>0.001860</td>\n",
              "      <td>0.004985</td>\n",
              "      <td>0.016505</td>\n",
              "      <td>0.148500</td>\n",
              "      <td>0.008245</td>\n",
              "      <td>0.009580</td>\n",
              "      <td>0.013080</td>\n",
              "      <td>0.024735</td>\n",
              "      <td>0.005925</td>\n",
              "      <td>19.198000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.421306</td>\n",
              "      <td>0.674758</td>\n",
              "      <td>-6.450096</td>\n",
              "      <td>0.174351</td>\n",
              "      <td>2.099125</td>\n",
              "      <td>0.137451</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>148.790000</td>\n",
              "      <td>175.829000</td>\n",
              "      <td>104.315000</td>\n",
              "      <td>0.004940</td>\n",
              "      <td>0.000030</td>\n",
              "      <td>0.002500</td>\n",
              "      <td>0.002690</td>\n",
              "      <td>0.007490</td>\n",
              "      <td>0.022970</td>\n",
              "      <td>0.221000</td>\n",
              "      <td>0.012790</td>\n",
              "      <td>0.013470</td>\n",
              "      <td>0.018260</td>\n",
              "      <td>0.038360</td>\n",
              "      <td>0.011660</td>\n",
              "      <td>22.085000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.495954</td>\n",
              "      <td>0.722254</td>\n",
              "      <td>-5.720868</td>\n",
              "      <td>0.218885</td>\n",
              "      <td>2.361532</td>\n",
              "      <td>0.194052</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>182.769000</td>\n",
              "      <td>224.205500</td>\n",
              "      <td>140.018500</td>\n",
              "      <td>0.007365</td>\n",
              "      <td>0.000060</td>\n",
              "      <td>0.003835</td>\n",
              "      <td>0.003955</td>\n",
              "      <td>0.011505</td>\n",
              "      <td>0.037885</td>\n",
              "      <td>0.350000</td>\n",
              "      <td>0.020265</td>\n",
              "      <td>0.022380</td>\n",
              "      <td>0.029400</td>\n",
              "      <td>0.060795</td>\n",
              "      <td>0.025640</td>\n",
              "      <td>25.075500</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.587562</td>\n",
              "      <td>0.761881</td>\n",
              "      <td>-5.046192</td>\n",
              "      <td>0.279234</td>\n",
              "      <td>2.636456</td>\n",
              "      <td>0.252980</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>260.105000</td>\n",
              "      <td>592.030000</td>\n",
              "      <td>239.170000</td>\n",
              "      <td>0.033160</td>\n",
              "      <td>0.000260</td>\n",
              "      <td>0.021440</td>\n",
              "      <td>0.019580</td>\n",
              "      <td>0.064330</td>\n",
              "      <td>0.119080</td>\n",
              "      <td>1.302000</td>\n",
              "      <td>0.056470</td>\n",
              "      <td>0.079400</td>\n",
              "      <td>0.137780</td>\n",
              "      <td>0.169420</td>\n",
              "      <td>0.314820</td>\n",
              "      <td>33.047000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.685151</td>\n",
              "      <td>0.825288</td>\n",
              "      <td>-2.434031</td>\n",
              "      <td>0.450493</td>\n",
              "      <td>3.671155</td>\n",
              "      <td>0.527367</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6f81c582-b293-4311-a145-060e14bb5ffe')\"\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-6f81c582-b293-4311-a145-060e14bb5ffe 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-6f81c582-b293-4311-a145-060e14bb5ffe');\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",
              "  "
            ],
            "text/plain": [
              "       MDVP:Fo(Hz)  MDVP:Fhi(Hz)  ...          D2         PPE\n",
              "count   195.000000    195.000000  ...  195.000000  195.000000\n",
              "mean    154.228641    197.104918  ...    2.381826    0.206552\n",
              "std      41.390065     91.491548  ...    0.382799    0.090119\n",
              "min      88.333000    102.145000  ...    1.423287    0.044539\n",
              "25%     117.572000    134.862500  ...    2.099125    0.137451\n",
              "50%     148.790000    175.829000  ...    2.361532    0.194052\n",
              "75%     182.769000    224.205500  ...    2.636456    0.252980\n",
              "max     260.105000    592.030000  ...    3.671155    0.527367\n",
              "\n",
              "[8 rows x 23 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Sütunlarda null değer var mı diye kontrol\n",
        "data.isnull().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vAfltAjThwUj",
        "outputId": "ee66b4b7-0990-4533-edca-0d72fdb1ca01"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "name                0\n",
              "MDVP:Fo(Hz)         0\n",
              "MDVP:Fhi(Hz)        0\n",
              "MDVP:Flo(Hz)        0\n",
              "MDVP:Jitter(%)      0\n",
              "MDVP:Jitter(Abs)    0\n",
              "MDVP:RAP            0\n",
              "MDVP:PPQ            0\n",
              "Jitter:DDP          0\n",
              "MDVP:Shimmer        0\n",
              "MDVP:Shimmer(dB)    0\n",
              "Shimmer:APQ3        0\n",
              "Shimmer:APQ5        0\n",
              "MDVP:APQ            0\n",
              "Shimmer:DDA         0\n",
              "NHR                 0\n",
              "HNR                 0\n",
              "status              0\n",
              "RPDE                0\n",
              "DFA                 0\n",
              "spread1             0\n",
              "spread2             0\n",
              "D2                  0\n",
              "PPE                 0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Erişilmeyen değerler var mı diye kontrol\n",
        "data.isna().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fSuVmehKwtnR",
        "outputId": "bfe722d3-5d0b-4a24-d84f-3063d74b3de2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "name                0\n",
              "MDVP:Fo(Hz)         0\n",
              "MDVP:Fhi(Hz)        0\n",
              "MDVP:Flo(Hz)        0\n",
              "MDVP:Jitter(%)      0\n",
              "MDVP:Jitter(Abs)    0\n",
              "MDVP:RAP            0\n",
              "MDVP:PPQ            0\n",
              "Jitter:DDP          0\n",
              "MDVP:Shimmer        0\n",
              "MDVP:Shimmer(dB)    0\n",
              "Shimmer:APQ3        0\n",
              "Shimmer:APQ5        0\n",
              "MDVP:APQ            0\n",
              "Shimmer:DDA         0\n",
              "NHR                 0\n",
              "HNR                 0\n",
              "status              0\n",
              "RPDE                0\n",
              "DFA                 0\n",
              "spread1             0\n",
              "spread2             0\n",
              "D2                  0\n",
              "PPE                 0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Target değişkeninin(status) dağılımı\n",
        "data['status'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4xWZuWWuh2kK",
        "outputId": "9ade0a9b-8ddd-4872-9195-f9509847a7c1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    147\n",
              "0     48\n",
              "Name: status, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Datayı status feature'una göre gruplama\n",
        "data.groupby('status').mean()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 207
        },
        "id": "cemBFG1_iArJ",
        "outputId": "40e9ebb9-1ab7-4667-eeb1-0f14d86ef5d9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-b36f5569-be30-4079-8b0b-83653d3670c0\">\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>MDVP:Fo(Hz)</th>\n",
              "      <th>MDVP:Fhi(Hz)</th>\n",
              "      <th>MDVP:Flo(Hz)</th>\n",
              "      <th>MDVP:Jitter(%)</th>\n",
              "      <th>MDVP:Jitter(Abs)</th>\n",
              "      <th>MDVP:RAP</th>\n",
              "      <th>MDVP:PPQ</th>\n",
              "      <th>Jitter:DDP</th>\n",
              "      <th>MDVP:Shimmer</th>\n",
              "      <th>MDVP:Shimmer(dB)</th>\n",
              "      <th>Shimmer:APQ3</th>\n",
              "      <th>Shimmer:APQ5</th>\n",
              "      <th>MDVP:APQ</th>\n",
              "      <th>Shimmer:DDA</th>\n",
              "      <th>NHR</th>\n",
              "      <th>HNR</th>\n",
              "      <th>RPDE</th>\n",
              "      <th>DFA</th>\n",
              "      <th>spread1</th>\n",
              "      <th>spread2</th>\n",
              "      <th>D2</th>\n",
              "      <th>PPE</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>status</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>181.937771</td>\n",
              "      <td>223.636750</td>\n",
              "      <td>145.207292</td>\n",
              "      <td>0.003866</td>\n",
              "      <td>0.000023</td>\n",
              "      <td>0.001925</td>\n",
              "      <td>0.002056</td>\n",
              "      <td>0.005776</td>\n",
              "      <td>0.017615</td>\n",
              "      <td>0.162958</td>\n",
              "      <td>0.009504</td>\n",
              "      <td>0.010509</td>\n",
              "      <td>0.013305</td>\n",
              "      <td>0.028511</td>\n",
              "      <td>0.011483</td>\n",
              "      <td>24.678750</td>\n",
              "      <td>0.442552</td>\n",
              "      <td>0.695716</td>\n",
              "      <td>-6.759264</td>\n",
              "      <td>0.160292</td>\n",
              "      <td>2.154491</td>\n",
              "      <td>0.123017</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>145.180762</td>\n",
              "      <td>188.441463</td>\n",
              "      <td>106.893558</td>\n",
              "      <td>0.006989</td>\n",
              "      <td>0.000051</td>\n",
              "      <td>0.003757</td>\n",
              "      <td>0.003900</td>\n",
              "      <td>0.011273</td>\n",
              "      <td>0.033658</td>\n",
              "      <td>0.321204</td>\n",
              "      <td>0.017676</td>\n",
              "      <td>0.020285</td>\n",
              "      <td>0.027600</td>\n",
              "      <td>0.053027</td>\n",
              "      <td>0.029211</td>\n",
              "      <td>20.974048</td>\n",
              "      <td>0.516816</td>\n",
              "      <td>0.725408</td>\n",
              "      <td>-5.333420</td>\n",
              "      <td>0.248133</td>\n",
              "      <td>2.456058</td>\n",
              "      <td>0.233828</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b36f5569-be30-4079-8b0b-83653d3670c0')\"\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-b36f5569-be30-4079-8b0b-83653d3670c0 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-b36f5569-be30-4079-8b0b-83653d3670c0');\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",
              "  "
            ],
            "text/plain": [
              "        MDVP:Fo(Hz)  MDVP:Fhi(Hz)  MDVP:Flo(Hz)  ...   spread2        D2       PPE\n",
              "status                                           ...                              \n",
              "0        181.937771    223.636750    145.207292  ...  0.160292  2.154491  0.123017\n",
              "1        145.180762    188.441463    106.893558  ...  0.248133  2.456058  0.233828\n",
              "\n",
              "[2 rows x 22 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#name analizimizde gereksiz olduğundan bu feature'ı çıkarıyoruz\n",
        "data = data.drop(['name'],axis=1)"
      ],
      "metadata": {
        "id": "H87fo0vfviDQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Status ile geri kalan featureları birbirinden ayırma\n",
        "Features = data.drop(['status'],axis=1)\n",
        "Target = data['status']\n",
        "X=Features\n",
        "y=Target"
      ],
      "metadata": {
        "id": "IdGkOxnNiHYK"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Değerleri scale etme\n",
        "stdscaler = StandardScaler()\n",
        "X = np.array(stdscaler.fit_transform(X))\n",
        "X"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ArWGgXC9u9QB",
        "outputId": "a7c217b3-0f70-44a4-9638-8d57aae89623"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[-0.82929965, -0.43616456, -0.95203729, ...,  0.48047686,\n",
              "        -0.21053082,  0.86888575],\n",
              "       [-0.77097169, -0.53097409, -0.05772056, ...,  1.31118546,\n",
              "         0.27507712,  1.80360503],\n",
              "       [-0.90947638, -0.7231683 , -0.10987483, ...,  1.01768236,\n",
              "        -0.10362861,  1.40266141],\n",
              "       ...,\n",
              "       [ 0.49557839,  0.47010361, -0.96839309, ..., -0.81807931,\n",
              "         0.78033848, -0.83241014],\n",
              "       [ 1.07876114,  2.19004398, -0.95417967, ..., -0.22906571,\n",
              "        -0.63700298, -0.92610456],\n",
              "       [ 1.45481664,  0.69224632, -0.88348115, ..., -0.43085284,\n",
              "         0.45480231, -0.64505466]])"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Datayı train ve test datalarına ayırma\n",
        "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=10)"
      ],
      "metadata": {
        "id": "TEEhLr09ifXj"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Naive Bayes Modeli\n",
        "gnb = GaussianNB()\n",
        "y_pred = gnb.fit(X_train, y_train).predict(X_test)\n",
        "print(\"Toplam %d nokta içinde yanlış etiketlenen noktaların sayısı : %d\"% (X_test.shape[0], (y_test != y_pred).sum()))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OKmwDZfriqyM",
        "outputId": "677bd815-0a81-4f4e-daaa-b53e5d2501ec"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Toplam 39 nokta içinde yanlış etiketlenen noktaların sayısı : 10\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Yöntemin confusion matrisi\n",
        "cm=confusion_matrix(y_test,y_pred)\n",
        "plt.figure(figsize=(2,2))\n",
        "plt.title(\"Naive Bayes\")\n",
        "fg=sn.heatmap(cm,annot=True)\n",
        "figure = fg.get_figure()\n",
        "plt.xlabel(\"Tahmin\")\n",
        "plt.ylabel(\"Gerçek Değer\")\n",
        "figure.savefig('Naive Bayes.jpg',dpi=400)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 187
        },
        "id": "dg-fIVldcRAa",
        "outputId": "f01a51c2-b495-43c0-8668-7489b82dbce0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 144x144 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "false_positive_rate1, true_positive_rate1, threshold1 = roc_curve(y_test, y_pred)\n",
        "plt.subplots(1, figsize=(10,10))\n",
        "plt.title('ROC - Naive Bayes')\n",
        "plt.plot(false_positive_rate1, true_positive_rate1)\n",
        "plt.plot([0, 1], [0, 1],'r--')\n",
        "plt.xlim([0, 1])\n",
        "plt.ylabel('True Positive Rate')\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.show()\n",
        "print('roc_auc_score for Naive Bayes: ', roc_auc_score(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 638
        },
        "id": "dcx6pl3J22Nf",
        "outputId": "89fcd218-35bf-44b3-f412-5139a95ad87d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "roc_auc_score for Naive Bayes:  0.8214285714285714\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Logistic Regression yöntemi ile modelleme\n",
        "log_reg = LogisticRegression()\n",
        "log_reg.fit(X_train,y_train)\n",
        "Y_predmod1=log_reg.predict(X_test)\n",
        "for i,j in enumerate(Y_predmod1):\n",
        "    if(j<0.5):\n",
        "        Y_predmod1[i]=0\n",
        "    else:\n",
        "        Y_predmod1[i]=1\n",
        "print(Y_predmod1)\n",
        "Y_test=np.array(y_test)\n",
        "print(\"Logistic Regression Doğruluk :\", log_reg.score(X_test,Y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "G2pV10kNjh2b",
        "outputId": "5131f688-4678-451a-d7a6-1b7b8b239852"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1 1 1 1 0 1 0 1 1 1 1 1 1 1 1 0 1 1 0 1 1 0 0 1 1 1 1 1 0 0 1 1 1 0 0 1 0\n",
            " 1 0]\n",
            "Logistic Regression Doğruluk : 0.9743589743589743\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fpr, tpr, thresholds = roc_curve()"
      ],
      "metadata": {
        "id": "w9wKUe5evAgz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Yöntemin confusion matrisi\n",
        "cm=confusion_matrix(Y_test,Y_predmod1)\n",
        "plt.figure(figsize=(2,2))\n",
        "plt.title(\"Logistic Regression\")\n",
        "fg=sn.heatmap(cm,annot=True)\n",
        "figure = fg.get_figure()\n",
        "plt.xlabel(\"Tahmin\")\n",
        "plt.ylabel(\"Gerçek Değer\")\n",
        "figure.savefig('Logistic Regression.jpg',dpi=400)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 187
        },
        "id": "LGZ-YOndYwGD",
        "outputId": "b2840d93-3d8a-4bb3-baaf-203bff766e9a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 144x144 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "false_positive_rate1, true_positive_rate1, threshold1 = roc_curve(Y_test, Y_predmod1)\n",
        "plt.subplots(1, figsize=(10,10))\n",
        "plt.title('ROC - Logistic Regression')\n",
        "plt.plot(false_positive_rate1, true_positive_rate1)\n",
        "plt.plot([0, 1], [0, 1],'r--')\n",
        "plt.xlim([0, 1])\n",
        "plt.ylabel('True Positive Rate')\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.show()\n",
        "print('roc_auc_score for Logistic Regression: ', roc_auc_score(Y_test, Y_predmod1))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 638
        },
        "id": "OnJz500u9GV9",
        "outputId": "3af13084-e5df-4562-e172-d8b855458848"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "roc_auc_score for Logistic Regression:  0.9821428571428572\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Decision Tree yöntemi ile modelleme\n",
        "dtree = tree.DecisionTreeClassifier()\n",
        "dtree.fit(X_train,y_train)\n",
        "Y_predmod3=dtree.predict(X_test)\n",
        "print(\"\\nDecision Tree Doğruluk:\",dtree.score(X_test,y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LWAe_-T6kIer",
        "outputId": "246fdc9e-aac9-428a-ce0e-7be65db4be87"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Decision Tree Doğruluk: 0.9230769230769231\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Yöntemin confusion matrisi\n",
        "cm=confusion_matrix(Y_test,Y_predmod3)\n",
        "plt.figure(figsize=(2,2))\n",
        "plt.title(\"Desicion Tree\")\n",
        "fg=sn.heatmap(cm,annot=True,cmap='BrBG')\n",
        "figure = fg.get_figure()\n",
        "plt.xlabel(\"Tahmin\")\n",
        "plt.ylabel(\"Gerçek Değer\")\n",
        "figure.savefig('Desicion Tree.jpg',dpi=400)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 187
        },
        "id": "b3iPv6GoaEGC",
        "outputId": "04ea9f7a-e0e2-49ac-b81d-1d1d52de474c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAKUAAACqCAYAAADMfY8PAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAASGUlEQVR4nO2deZhU5ZWH319v0CwuBFECCAou4xK3qNlkHEMiZDTOJNHRGGNiFE2iT5xoRkQT18kwGYY8miFBImqMC6K44C7iikZQxEgQoigoGIiICrRIr2f++G5r0V3Vdbuh6t7qOu/z3Kfv8t37ner+9fm2W+fIzHCcNFGRtAGO0xYXpZM6XJRO6nBROqnDRemkDhelkzpclBlIWizpyBjl6iTtXgSTyhKV2jylpBXAzkAT0Ay8AtwITDWzlgRN2yok1WUc9gLqCZ8P4Ewzu7n4ViVDVdIGdJFjzexRSdsD/whcBRwOfD9Zs7qOmfVp3Y/+8U43s0fblpNUZWZNxbSt2JR0821m681sFvBvwKmS9gOQ1EPSRElvSfq7pCmSaqNr/SXdJ+kDSe9JelpSRXRthaRR0X6lpPGSXpe0UdICSUOiayZpRLS/vaQbJa2V9KakizOe9z1JcyNb3pe0XNKYznxGSUdKWiXpAklrgOslVUgaF9m2TtIMSf0y7vmcpGejz/jnOF2SNFHSomzFzOYDq4AjolMTgD2BA4ERwCDgF9G186KyOxG6AeOBbH2YnwInAV8DtgNOAzZlKfcbYHtgd4LX/i5beuzDgb8C/YFfAdMkqZMfcRegHzAUGAucA/xLVN+ngfeByQCSBgH3A1dG95wPzJS0UyfrTA4zK6kNWAGMynL+OeAiQMCHwPCMa58Hlkf7lwP3ACM6ejZBSMflsMEIYq8EGoB9Mq6dCTwR7X8PWJZxrVd07y5xPyNwZFRHz4zrS4AvZxwPBBoJ3bELgD+2ed7DwKlJ/+3ibqXap8zGIOA9ggfsBSzIcEgiCAjgf4BLgUei61PNbEKW5w0BXs9TZ3+gGngz49ybkS2trGndMbNNUZ196BxrzWxzxvFQ4C5JmQO7ZoLnHwocL+nYjGvVwOOdrDMxuoUoJR1KEMJc4F3gI2BfM3u7bVkz20hows+L+qCPSXrezOa0KboSGA78pYOq3yV4qKGEWQCAXYF29W4lbbsXK4HTzOyZtgUlrSR4yjO2sQ1Fo6T7lJK2k3QMMB24ycwWWZgW+j3wa0kDonKDJB0d7R8jaUTUr1tP8DDZppKuBa6QtIcCn5H0qcwCZtYMzAD+U1JfSUMJfdGbCvSRW5kS1TkUQNJOko6Lrt0EHCvp6Giw1jMaLA0usE3bjFIV5b2SNhI8xkXAJLYcXFwALAOek7QBeBTYK7q2R3RcB/wJ+K2ZZWvaJhEE9wiwAZgG1GYpdw6hD/sGwVPfAly3NR8uBlcBswhdkI2E/vThAGa2EjiOMIBbS/gd/YwS+luX3OS50/0pmf8ep3xwUTqpw0XppA4XpZM6XJRO6kj15Pmbz1xeUlMDE8b9MmkTOs3vnt6cdR1eRxzU7ndvTy/s7Jp9l0i1KJ0EqUxOGi5KJztVlfnLFKrqxGp20o17Sid1VFcnVrWL0smOe0onbajS+5RO2qiuSaxqF6WTHR99O6nDPaWTOrxP6aQOH307aaO6xptvJ2VUVbmndFJGlfcpnbRR4823kza8+XZSR7WL0kkb3nw7qcObbyd1JDn6zvttxihI0sRiGOOkh5qamnZbscjrKc2sWdKXimFMoblr9lIeeGoZGIwZOYJvfHXvpE3qkB0HDObUi6axXb8BmBlzZ03j8TsmF6XuUmi+F0qaBdxOiDAGgJndWRCrCsDyVR/wwFPL+M3Fo6muqmD8pMc5/IBBDNq5b9Km5aS5uYmZky9g5asv0aO2DxdO+xNLXpjDmhVLC153TQmIsiewDjgq45wBJSPKlavXs/du/enZI3zk/fcawDMvvsUJY/ZN2LLcbFi3hg3rQiDg+o/qWLNiKTv0H1QUUdb2SPno28xKNhVIK8MG7cD1d/6ZDXX11FRX8vyiv7HnsH75b0wJ/XYZypA9D2TFK/OLUl9XPGWUPeNGQphrI4TuvirKXHEbMIwQz/0EM3s/13Ni1SxpT+B3wM5mtp+kzwBfN7MrO7hnb0Lwztb4328Ds8xsSZw6tzW7fnp7ThizD+P+9zF69qhk+JAdqeh0koZk6FHbmzOvvJXbrz6fzZs2FqXOnl0b2DQB55nZi5L6EuLOzyYkJJhjZhMkjQPGEQLbZiVuLKHfAxcS4ntjZi8DJ+YqLOkCQshnAfOjTcCtkVE5kTRW0guSXrjlnhdimhePMSNH8NtLxjBp3Ffp07uGQbtst02fXwgqKqsYe+V05s+ezktP3VO0emuqqtpt+TCz1Wb2YrS/kZDFYhDBOf0hKvYHQrqVnMT10b3MbH6b9C8dZb36ASEQfmPmSUmTgMWEPDdZMbOpwFTY9rGE3t+wmR2368k76z5k7oKVXH3x0dvy8QXhlHHXsGbFUubcdnVR662p3rp5SknDgIOAeYQWdnV0aQ2hec9JXFG+K2k4UZYCSd8CVndQvoWQdOjNNucHkj3ofVG4YvJTbKirp6qygnO+cyh9eiXXmY/D8P2/wOdGn8yq1xcx/rp5ANwz9Rcsfu7hgtddm6X5ljSWkFyqlamRE2lbrg8wEzjXzDZkOjMzM0kdOpu4ovwxwXvtLeltYDnwnQ7KnwvMkfQaIRA8hFQeI4CzY9a5zZl04VeTqrpLvL7oWX54RM9E6s7WXGe2YrmQVE0Q5M0ZU4Z/lzTQzFZLGgi809Ez4o6+3wBGSeoNVET9hY7KPxQNjg5jy4HO81GaDyfldHH0LUIWjSVmNinj0izgVEK37VRCxrecxB19/7TNMYQcNAvM7KVs90T5bJ6L83wnfXRxnvKLwCnAIkmtuhhPEOMMST8gdOlO6OghOUUpaTQh/doC4LPRdm90+RjgZeAsSbeb2a+68gmc9NKV9ynNbC5hliUbX477nI5qXgjcSljFGQwcbGZ1AJIuIWRKHQksIGRndboRNRXp/I7OUOCDaH8AUJ9xrZEwzP9IUn27O52Sp2dKv/e9ETg92r8ZmCeptYN6LHBLNPB5JdvNTmlTk8ZvM2YuB5rZFZIeJHRkAc4ys9bllpMLaJ+TENUVySUO6YyP7glsMLPro6ypu5nZ8kIZ5iRLbWXKI/lGA5vPEjLBXk9Ian4Tn3hOp5tRCp7yXwnrmK2L7X+L3gJxuim1VSn3lEBD5pplNMBxujHVKZ0SymSGpGuAHSSdAZxGeJ3N6abUpL35NrOJkr4CbCD0K39hZrMLapmTKD3T3nxL2oEwkT4DeNXM1hfUKidxqpVSTympB3AN4U3hNwhvqg+VdBdhrrKh8CY6SVCZ4FdF8v07XESY/hliZgeb2YGE9yKrgJ8X2jgnOWoqKtptxSJfTd8Azsh8fzLa/xFhmsjpplSidluxyNenbDGzTW1PmlldvlfandKmKsHmO58oTdKOZH9HLrHv2jiFJ80rOtsT3pfMJkr3lN2YqiI21+3r7gAzG1YkO5yUUZXWKSGnfElz8+2UKUk23zJLb9fw+INq0mtcFu7ok94IbrmwpxdmVd/GDz9s97vv27t3UZQay0dHX41sey5n6BWn9Kmkpd1WLOI239+UtNnMbgaQNJnwJrrTXbGOQkUVltiiBGZJagFGAx+YWTvv6XQjEnytId8LGZlRRU8H7gaeAS6T1M/M3iukcU6CpNhTLiBMkivj5z9HmwG7F9Q6JznSKkoz261YhjjpQi2N+QsViLij716SLpY0NTreQ9IxhTXNSRRrar8VibjT9tcDDcAXouO3gZzxzp1uQAmIcngUWa015vkmckfXcroD1tB+KxKxv2IrqZZPwksPZ8uAV053I60DnQwuAR4Chki6mRAZ43uFMspJAWkXpZnNlvQi8DlCs/0TM3u3oJY5idLSlFxDGHf0fTrQbGb3m9l9QHO29XCn+9DS3NBuy4ek6yS9I+kvGef6SZot6bXo5475nhN3oHO2mbUGUCVKYTZO0tVR5Aynm2HNje22GNxAWIbOZBwh29gewJzouEPiinKLwDKSKqJ7fwZ8PuYznBKiuemjdls+zOwpoO3Sc6eyjUH8gc4jkqbzSQ6VscDdZlYv6Zsxn+GUEC3xPGMcOpVtDOKL8nzgTML3vQFmA9cCmNlrnTTSKQGy9SHjZhzLRZxsYxBDlJIqgcVmtjcwJa4BTmnT0ri53bk4Gcey0KlsYxCjTxllCPurpF07aYxTwrQ0N7bbukhrtjGIkW0M4jffOwKLJc0HPmw9aWZf76yFTmkQZ2DTFkm3AkcC/SWtIiy6dCrbGMQXpQezKjO64hnN7KQcl2JnG4P4KzpPShoK7GFmj0rqRZtpIqd7EWeyvFDEDZp6BmHU1Q8YTshMO4VO/gckzQ8vmcohI7/G+vfWct7xByVtTlYGD9iZGy+6gp37fQozY+qsmVx9x61Mv3QCe+06DIAd+vTlg7qNHHTaiQWzo7m+8833tqIz+b4PI2S5x8xekzSgYFYViCfuvZGHbvstZ19xfdKm5KSpuZnzJk9i4atL6VPbiwXTbmH2C/M48dJPFkIm/vinrP+wrqB2NDcm5ynjrujUZ0btlVRFCQa4WvLiXOrWv5+0GR2yZt27LHx1KQB1H21iyYrlDOq/0xZlTvinr3Drow8V1I6WhoZ2W7GI6ymflDQeqI0C8v+IT9IsOwVi6C4DOWjPvZj3ysfvN3DEAQfz9/ffY9mqtwpad1N9u7CkRSOupxwHrAUWEVZ2HgAu7mqlkr7f1XvLhd61tcy8ciLnXj2RjZs+noXjpFGjC+4lAVoaG9ptxSLu6LuFkDdnW+XOuYzwvZ92ZC5lHTy4kt37Jxf9KymqKquYeeVEbp79IHc99djH5ysrK/nGyKM45PRvF9yGJPuU+YIRHAcMNrPJ0fE8oLWDc4GZ3d7BvS/nukQHi/KZS1mlFuBqWzFt3CUsWbGcX9920xbnRx1yOEvfWsHba/Ou1G01TZuTa77zecr/ADLnHXoAhwK9CZ4upygJwjsaaDuyEPBs58zcNvzkv/7IvoeMpO8O/Zny0BvMmHI5j919QxKm5OSL+x/Id0cfw8uvv8rC66YDMH7q//Hgc3M5cdTRRWm6gaI2123JJ8oaM1uZcTzXzNYB62LkZ7wP6GNmL7W9IOmJzpm5bbjqwlOSqLZTPLPoJXRE9jnU7//ykqLZkdrmm7Dm/TFmdnbG4U50QEcBsMys8J0iZ6toTrD5zjeKmBet5myBpDOB+YUxyUkDzY0N7bZikc9T/jtwt6RvE+X6Bg4h9C3zvtbulC4NDSn9iq2ZvQN8QdJRQGvs5PvN7LEObnO6AU3NzYnVHXee8jHAhVhGNDWlXJRO+ZHa5tspX5qaksty6KJ0spL6PqVTfnjz7aQOH+g4qcNF6aSOhkZvvp2U4aNvJ3UkqEkXpZOd+qbk3q92UTpZSXCc46J0stPY4p7SSRkJzp27KJ3sNDa7p3RShntKJ3V4n9JJHT76dlJHkvOUMiu/IBSSxnYmq0EaKEWbu0r5BeoJjM1fJHWUos1dolxF6aQYF6WTOspVlKXYNytFm7tEWQ50nHRTrp7SSTFlJ0pJoyX9VdIySXlzTydNtsTu3Z2yEmWU/HQyMAbYBzhJ0j7JWpWXG2if2L1bU1aiJOQCWmZmb0QpWKYTkqSnlhyJ3bs15SbKQUBmZOJV0TknRZSbKJ0SoNxE+TYwJON4cHTOSRHlJsrngT0k7SaphpD5YlbCNjltKCtRmlkTcDbwMLAEmGFmi5O1qmOixO5/AvaStCpK5t6t8RUdJ3WUlad0SgMXpZM6XJRO6nBROqnDRemkDv82IyDpU8Cc6HAXoBlYGx0fFq2Tt5a9AbjPzO7oYl1nAZvM7MauW9y9cVECUWbeAwEkXQrUmdnEAtU1pRDP7U54850DSWdIel7SnyXNlNQr4/JISc9KekPSt6LyR0p6UtI90fkJkk6WNF/SIknDo3KXSjo/2n9C0n9HZV6VdEQCHzV1uChzc6eZHWpmBxBWfzJXUgYCXwKOASZknD8AOAv4B+AUYE8zOwy4FjgnRz1VUZlzgeIl9E4xLsrc7CfpaUmLgJP5JGEqwN1m1mJmrwA7Z5x/3sxWm1k98DrwSHR+ETAsRz13Rj8XdFCmrHBR5uYG4Gwz2x+4DOiZca0+Y185zrdkHLeQu//eWqa5gzJlhYsyN32B1ZKqCZ7SKRL+n5mbnwPzCFND8wgidYqAvyXkpA5vvp3U4aJ0UoeL0kkdLkondbgondThonRSh4vSSR0uSid1/D9Dz2zn7JkRZAAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 144x144 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "false_positive_rate1, true_positive_rate1, threshold1 = roc_curve(Y_test, Y_predmod3)\n",
        "plt.subplots(1, figsize=(10,10))\n",
        "plt.title('ROC - DecisionTree')\n",
        "plt.plot(false_positive_rate1, true_positive_rate1)\n",
        "plt.plot([0, 1], [0, 1],'r--')\n",
        "plt.xlim([0, 1])\n",
        "plt.ylabel('True Positive Rate')\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.show()\n",
        "print('roc_auc_score for Decision Tree: ', roc_auc_score(Y_test, Y_predmod3))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 638
        },
        "id": "XV-XQYv32fAj",
        "outputId": "60321c84-7933-4f35-c5e4-d8e2c98b9b3e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "roc_auc_score for Decision Tree:  0.8912337662337663\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# K-Nearest Neighbor yöntemi ile modelleme\n",
        "neigh = KNeighborsClassifier()\n",
        "neigh.fit(X, y)\n",
        "Y_predmod4 = neigh.predict(X_test)\n",
        "print(\"\\nK-neighbor Doğruluk:\",neigh.score(X_test,y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ils-JRlekV29",
        "outputId": "04f94cad-58a5-4b07-9703-f36e12b780b1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "K-neighbor Doğruluk: 0.9743589743589743\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cm=confusion_matrix(Y_test,Y_predmod4)\n",
        "plt.figure(figsize=(2,2))\n",
        "plt.title(\"K-Neighbor\")\n",
        "fg=sn.heatmap(cm,annot=True,cmap='BrBG')\n",
        "figure = fg.get_figure()\n",
        "plt.xlabel(\"Tahmin\")\n",
        "plt.ylabel(\"Gerçek Değer\")\n",
        "figure.savefig('K-Neighbor.jpg',dpi=400)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 187
        },
        "id": "L7P2bZpRbKwp",
        "outputId": "0bab41f9-d656-41b6-d22c-77bcd424ce27"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 144x144 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}