microorganism_detection.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/kenan-erol/MicrobeClassification/blob/main/microorganism_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": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JDdeOeAzNWwb",
        "outputId": "8e86eaed-f54a-41de-9f59-67a9c478d27c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import files\n",
        "import io\n",
        "from pydrive.auth import GoogleAuth\n",
        "from pydrive.drive import GoogleDrive\n",
        "from google.colab import auth\n",
        "from oauth2client.client import GoogleCredentials\n",
        "from google.colab import drive\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 317
        },
        "id": "VZGTInwTkMTm",
        "outputId": "34e1449d-c1be-4ed3-d0b8-f64ebb445643"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Unnamed: 0  Solidity  Eccentricity  EquivDiameter  Extrema  FilledArea  \\\n",
              "0           0     10.70          15.8           5.43     3.75       0.785   \n",
              "1           1      5.60          18.3           4.14     6.16       0.364   \n",
              "2           2      8.32          19.8           4.63     6.66       0.415   \n",
              "3           3     10.10          17.9           7.29    11.10       1.470   \n",
              "4           4      6.27          20.2          20.10    10.70      14.700   \n",
              "\n",
              "   Extent  Orientation  EulerNumber  BoundingBox1  ...  ConvexHull4  \\\n",
              "0    8.14         2.15         22.3          2.97  ...         2.97   \n",
              "1    3.51        18.60         22.5          5.41  ...         5.47   \n",
              "2    5.85        21.00         22.4          5.96  ...         5.96   \n",
              "3    6.30         9.94         21.9          8.81  ...         8.88   \n",
              "4    3.97         2.58         11.9         10.20  ...        10.20   \n",
              "\n",
              "   MajorAxisLength  MinorAxisLength  Perimeter  ConvexArea  Centroid1  \\\n",
              "0             1.34             1.61      0.683       0.195       3.63   \n",
              "1             1.52             1.52      1.010       0.215       6.01   \n",
              "2             1.63             1.38      1.110       0.182       6.55   \n",
              "3             2.04             2.12      0.715       0.371      10.30   \n",
              "4             7.78             6.21      6.800       4.440      14.00   \n",
              "\n",
              "   Centroid2    Area  raddi  microorganisms  \n",
              "0      12.10   1.310   7.99       Spirogyra  \n",
              "1      20.60   0.765   7.99       Spirogyra  \n",
              "2      11.50   0.953   7.99       Spirogyra  \n",
              "3      12.00   2.340   7.99       Spirogyra  \n",
              "4       9.55  17.600   7.99       Spirogyra  \n",
              "\n",
              "[5 rows x 26 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-06143719-ff28-4e8f-bcb0-7f2c587b775a\">\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>Unnamed: 0</th>\n",
              "      <th>Solidity</th>\n",
              "      <th>Eccentricity</th>\n",
              "      <th>EquivDiameter</th>\n",
              "      <th>Extrema</th>\n",
              "      <th>FilledArea</th>\n",
              "      <th>Extent</th>\n",
              "      <th>Orientation</th>\n",
              "      <th>EulerNumber</th>\n",
              "      <th>BoundingBox1</th>\n",
              "      <th>...</th>\n",
              "      <th>ConvexHull4</th>\n",
              "      <th>MajorAxisLength</th>\n",
              "      <th>MinorAxisLength</th>\n",
              "      <th>Perimeter</th>\n",
              "      <th>ConvexArea</th>\n",
              "      <th>Centroid1</th>\n",
              "      <th>Centroid2</th>\n",
              "      <th>Area</th>\n",
              "      <th>raddi</th>\n",
              "      <th>microorganisms</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>10.70</td>\n",
              "      <td>15.8</td>\n",
              "      <td>5.43</td>\n",
              "      <td>3.75</td>\n",
              "      <td>0.785</td>\n",
              "      <td>8.14</td>\n",
              "      <td>2.15</td>\n",
              "      <td>22.3</td>\n",
              "      <td>2.97</td>\n",
              "      <td>...</td>\n",
              "      <td>2.97</td>\n",
              "      <td>1.34</td>\n",
              "      <td>1.61</td>\n",
              "      <td>0.683</td>\n",
              "      <td>0.195</td>\n",
              "      <td>3.63</td>\n",
              "      <td>12.10</td>\n",
              "      <td>1.310</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>5.60</td>\n",
              "      <td>18.3</td>\n",
              "      <td>4.14</td>\n",
              "      <td>6.16</td>\n",
              "      <td>0.364</td>\n",
              "      <td>3.51</td>\n",
              "      <td>18.60</td>\n",
              "      <td>22.5</td>\n",
              "      <td>5.41</td>\n",
              "      <td>...</td>\n",
              "      <td>5.47</td>\n",
              "      <td>1.52</td>\n",
              "      <td>1.52</td>\n",
              "      <td>1.010</td>\n",
              "      <td>0.215</td>\n",
              "      <td>6.01</td>\n",
              "      <td>20.60</td>\n",
              "      <td>0.765</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>8.32</td>\n",
              "      <td>19.8</td>\n",
              "      <td>4.63</td>\n",
              "      <td>6.66</td>\n",
              "      <td>0.415</td>\n",
              "      <td>5.85</td>\n",
              "      <td>21.00</td>\n",
              "      <td>22.4</td>\n",
              "      <td>5.96</td>\n",
              "      <td>...</td>\n",
              "      <td>5.96</td>\n",
              "      <td>1.63</td>\n",
              "      <td>1.38</td>\n",
              "      <td>1.110</td>\n",
              "      <td>0.182</td>\n",
              "      <td>6.55</td>\n",
              "      <td>11.50</td>\n",
              "      <td>0.953</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>10.10</td>\n",
              "      <td>17.9</td>\n",
              "      <td>7.29</td>\n",
              "      <td>11.10</td>\n",
              "      <td>1.470</td>\n",
              "      <td>6.30</td>\n",
              "      <td>9.94</td>\n",
              "      <td>21.9</td>\n",
              "      <td>8.81</td>\n",
              "      <td>...</td>\n",
              "      <td>8.88</td>\n",
              "      <td>2.04</td>\n",
              "      <td>2.12</td>\n",
              "      <td>0.715</td>\n",
              "      <td>0.371</td>\n",
              "      <td>10.30</td>\n",
              "      <td>12.00</td>\n",
              "      <td>2.340</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>6.27</td>\n",
              "      <td>20.2</td>\n",
              "      <td>20.10</td>\n",
              "      <td>10.70</td>\n",
              "      <td>14.700</td>\n",
              "      <td>3.97</td>\n",
              "      <td>2.58</td>\n",
              "      <td>11.9</td>\n",
              "      <td>10.20</td>\n",
              "      <td>...</td>\n",
              "      <td>10.20</td>\n",
              "      <td>7.78</td>\n",
              "      <td>6.21</td>\n",
              "      <td>6.800</td>\n",
              "      <td>4.440</td>\n",
              "      <td>14.00</td>\n",
              "      <td>9.55</td>\n",
              "      <td>17.600</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 26 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-06143719-ff28-4e8f-bcb0-7f2c587b775a')\"\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-06143719-ff28-4e8f-bcb0-7f2c587b775a 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-06143719-ff28-4e8f-bcb0-7f2c587b775a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ],
      "source": [
        "df = pd.read_csv(r\"/content/drive/My Drive/microbes ai4all/microbes.csv\")\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v4JppvnEkhHO",
        "outputId": "42d9f3ea-68f5-4818-aa8d-bca52dcd6374"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "microorganisms\n",
              "Aspergillus sp    3888\n",
              "Diatom            1818\n",
              "Penicillum        1080\n",
              "Pithophora        1350\n",
              "Protozoa          3888\n",
              "Raizopus          2552\n",
              "Spirogyra          611\n",
              "Ulothrix          7420\n",
              "Volvox            4320\n",
              "Yeast             3600\n",
              "Name: Eccentricity, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ],
      "source": [
        "# Finding out how many types of microbes we are dealing with, \n",
        "  # All objects are float64, 30527 obj\n",
        "df.columns # number of characteristics: 26\n",
        "df = df.drop(['Unnamed: 0'], axis=1) # unneeded column, can affect training so best to remove\n",
        "df.groupby('microorganisms')['Eccentricity'].count()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nGLBM1DKCfwq"
      },
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vo_iPYPi6WxQ",
        "outputId": "0bab6a22-6221-4a61-ed1f-cce7c0aba563"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Solidity           0\n",
            "Eccentricity       0\n",
            "EquivDiameter      0\n",
            "Extrema            0\n",
            "FilledArea         0\n",
            "Extent             0\n",
            "Orientation        0\n",
            "EulerNumber        0\n",
            "BoundingBox1       0\n",
            "BoundingBox2       0\n",
            "BoundingBox3       0\n",
            "BoundingBox4       0\n",
            "ConvexHull1        0\n",
            "ConvexHull2        0\n",
            "ConvexHull3        0\n",
            "ConvexHull4        0\n",
            "MajorAxisLength    0\n",
            "MinorAxisLength    0\n",
            "Perimeter          0\n",
            "ConvexArea         0\n",
            "Centroid1          0\n",
            "Centroid2          0\n",
            "Area               0\n",
            "raddi              0\n",
            "microorganisms     0\n",
            "dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# Checking for and removing null values, which will disrupt training\n",
        "print(df.isnull().sum())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "a7T6BdhX9iSK",
        "outputId": "09245b4d-ddc7-4d33-e828-97731646e861"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       Solidity  Eccentricity  EquivDiameter  Extrema  FilledArea  Extent  \\\n",
              "0         10.70          15.8           5.43     3.75      0.7850    8.14   \n",
              "1          5.60          18.3           4.14     6.16      0.3640    3.51   \n",
              "2          8.32          19.8           4.63     6.66      0.4150    5.85   \n",
              "3         10.10          17.9           7.29    11.10      1.4700    6.30   \n",
              "4          6.27          20.2          20.10    10.70     14.7000    3.97   \n",
              "...         ...           ...            ...      ...         ...     ...   \n",
              "30522      3.01          22.6           4.90    20.00      0.4340    1.40   \n",
              "30523      5.19          22.6           2.07    19.40      0.0788    1.67   \n",
              "30524      9.21          22.7           2.07    21.00      0.0790    5.81   \n",
              "30525      8.21          22.6           1.87    20.50      0.0641    5.96   \n",
              "30526      6.57          21.0           2.13    21.20      0.0840    3.77   \n",
              "\n",
              "       Orientation  EulerNumber  BoundingBox1  BoundingBox2  ...  ConvexHull4  \\\n",
              "0             2.15         22.3          2.97         10.90  ...         2.97   \n",
              "1            18.60         22.5          5.41         19.20  ...         5.47   \n",
              "2            21.00         22.4          5.96         10.20  ...         5.96   \n",
              "3             9.94         21.9          8.81         10.70  ...         8.88   \n",
              "4             2.58         11.9         10.20          1.22  ...        10.20   \n",
              "...            ...          ...           ...           ...  ...          ...   \n",
              "30522        19.90         22.1         18.10          9.92  ...        18.60   \n",
              "30523         5.09         22.8         19.20         16.20  ...        20.00   \n",
              "30524        12.70         22.8         20.10         11.40  ...        20.10   \n",
              "30525        11.30         22.8         20.20         20.20  ...        20.20   \n",
              "30526        16.50         22.8         20.70         18.00  ...        20.80   \n",
              "\n",
              "       MajorAxisLength  MinorAxisLength  Perimeter  ConvexArea  Centroid1  \\\n",
              "0                1.340            1.610      0.683      0.1950       3.63   \n",
              "1                1.520            1.520      1.010      0.2150       6.01   \n",
              "2                1.630            1.380      1.110      0.1820       6.55   \n",
              "3                2.040            2.120      0.715      0.3710      10.30   \n",
              "4                7.780            6.210      6.800      4.4400      14.00   \n",
              "...                ...              ...        ...         ...        ...   \n",
              "30522            4.350            1.350      1.710      0.5490      19.10   \n",
              "30523            1.460            0.411      0.458      0.0597      19.80   \n",
              "30524            1.060            0.257      0.319      0.0341      20.70   \n",
              "30525            1.010            0.285      0.350      0.0314      20.80   \n",
              "30526            0.969            0.642      0.385      0.0502      21.00   \n",
              "\n",
              "       Centroid2    Area  raddi  microorganisms  \n",
              "0          12.10   1.310   7.99       Spirogyra  \n",
              "1          20.60   0.765   7.99       Spirogyra  \n",
              "2          11.50   0.953   7.99       Spirogyra  \n",
              "3          12.00   2.340   7.99       Spirogyra  \n",
              "4           9.55  17.600   7.99       Spirogyra  \n",
              "...          ...     ...    ...             ...  \n",
              "30522      13.20   1.070   7.15        Ulothrix  \n",
              "30523      17.20   0.197   7.15        Ulothrix  \n",
              "30524      11.60   0.198   7.15        Ulothrix  \n",
              "30525      20.40   0.162   7.15        Ulothrix  \n",
              "30526      18.40   0.208   7.15        Ulothrix  \n",
              "\n",
              "[30527 rows x 25 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e2298ab0-e4cb-4f80-931e-df43d50b9b82\">\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>Solidity</th>\n",
              "      <th>Eccentricity</th>\n",
              "      <th>EquivDiameter</th>\n",
              "      <th>Extrema</th>\n",
              "      <th>FilledArea</th>\n",
              "      <th>Extent</th>\n",
              "      <th>Orientation</th>\n",
              "      <th>EulerNumber</th>\n",
              "      <th>BoundingBox1</th>\n",
              "      <th>BoundingBox2</th>\n",
              "      <th>...</th>\n",
              "      <th>ConvexHull4</th>\n",
              "      <th>MajorAxisLength</th>\n",
              "      <th>MinorAxisLength</th>\n",
              "      <th>Perimeter</th>\n",
              "      <th>ConvexArea</th>\n",
              "      <th>Centroid1</th>\n",
              "      <th>Centroid2</th>\n",
              "      <th>Area</th>\n",
              "      <th>raddi</th>\n",
              "      <th>microorganisms</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>10.70</td>\n",
              "      <td>15.8</td>\n",
              "      <td>5.43</td>\n",
              "      <td>3.75</td>\n",
              "      <td>0.7850</td>\n",
              "      <td>8.14</td>\n",
              "      <td>2.15</td>\n",
              "      <td>22.3</td>\n",
              "      <td>2.97</td>\n",
              "      <td>10.90</td>\n",
              "      <td>...</td>\n",
              "      <td>2.97</td>\n",
              "      <td>1.340</td>\n",
              "      <td>1.610</td>\n",
              "      <td>0.683</td>\n",
              "      <td>0.1950</td>\n",
              "      <td>3.63</td>\n",
              "      <td>12.10</td>\n",
              "      <td>1.310</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>5.60</td>\n",
              "      <td>18.3</td>\n",
              "      <td>4.14</td>\n",
              "      <td>6.16</td>\n",
              "      <td>0.3640</td>\n",
              "      <td>3.51</td>\n",
              "      <td>18.60</td>\n",
              "      <td>22.5</td>\n",
              "      <td>5.41</td>\n",
              "      <td>19.20</td>\n",
              "      <td>...</td>\n",
              "      <td>5.47</td>\n",
              "      <td>1.520</td>\n",
              "      <td>1.520</td>\n",
              "      <td>1.010</td>\n",
              "      <td>0.2150</td>\n",
              "      <td>6.01</td>\n",
              "      <td>20.60</td>\n",
              "      <td>0.765</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8.32</td>\n",
              "      <td>19.8</td>\n",
              "      <td>4.63</td>\n",
              "      <td>6.66</td>\n",
              "      <td>0.4150</td>\n",
              "      <td>5.85</td>\n",
              "      <td>21.00</td>\n",
              "      <td>22.4</td>\n",
              "      <td>5.96</td>\n",
              "      <td>10.20</td>\n",
              "      <td>...</td>\n",
              "      <td>5.96</td>\n",
              "      <td>1.630</td>\n",
              "      <td>1.380</td>\n",
              "      <td>1.110</td>\n",
              "      <td>0.1820</td>\n",
              "      <td>6.55</td>\n",
              "      <td>11.50</td>\n",
              "      <td>0.953</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>10.10</td>\n",
              "      <td>17.9</td>\n",
              "      <td>7.29</td>\n",
              "      <td>11.10</td>\n",
              "      <td>1.4700</td>\n",
              "      <td>6.30</td>\n",
              "      <td>9.94</td>\n",
              "      <td>21.9</td>\n",
              "      <td>8.81</td>\n",
              "      <td>10.70</td>\n",
              "      <td>...</td>\n",
              "      <td>8.88</td>\n",
              "      <td>2.040</td>\n",
              "      <td>2.120</td>\n",
              "      <td>0.715</td>\n",
              "      <td>0.3710</td>\n",
              "      <td>10.30</td>\n",
              "      <td>12.00</td>\n",
              "      <td>2.340</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>6.27</td>\n",
              "      <td>20.2</td>\n",
              "      <td>20.10</td>\n",
              "      <td>10.70</td>\n",
              "      <td>14.7000</td>\n",
              "      <td>3.97</td>\n",
              "      <td>2.58</td>\n",
              "      <td>11.9</td>\n",
              "      <td>10.20</td>\n",
              "      <td>1.22</td>\n",
              "      <td>...</td>\n",
              "      <td>10.20</td>\n",
              "      <td>7.780</td>\n",
              "      <td>6.210</td>\n",
              "      <td>6.800</td>\n",
              "      <td>4.4400</td>\n",
              "      <td>14.00</td>\n",
              "      <td>9.55</td>\n",
              "      <td>17.600</td>\n",
              "      <td>7.99</td>\n",
              "      <td>Spirogyra</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30522</th>\n",
              "      <td>3.01</td>\n",
              "      <td>22.6</td>\n",
              "      <td>4.90</td>\n",
              "      <td>20.00</td>\n",
              "      <td>0.4340</td>\n",
              "      <td>1.40</td>\n",
              "      <td>19.90</td>\n",
              "      <td>22.1</td>\n",
              "      <td>18.10</td>\n",
              "      <td>9.92</td>\n",
              "      <td>...</td>\n",
              "      <td>18.60</td>\n",
              "      <td>4.350</td>\n",
              "      <td>1.350</td>\n",
              "      <td>1.710</td>\n",
              "      <td>0.5490</td>\n",
              "      <td>19.10</td>\n",
              "      <td>13.20</td>\n",
              "      <td>1.070</td>\n",
              "      <td>7.15</td>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30523</th>\n",
              "      <td>5.19</td>\n",
              "      <td>22.6</td>\n",
              "      <td>2.07</td>\n",
              "      <td>19.40</td>\n",
              "      <td>0.0788</td>\n",
              "      <td>1.67</td>\n",
              "      <td>5.09</td>\n",
              "      <td>22.8</td>\n",
              "      <td>19.20</td>\n",
              "      <td>16.20</td>\n",
              "      <td>...</td>\n",
              "      <td>20.00</td>\n",
              "      <td>1.460</td>\n",
              "      <td>0.411</td>\n",
              "      <td>0.458</td>\n",
              "      <td>0.0597</td>\n",
              "      <td>19.80</td>\n",
              "      <td>17.20</td>\n",
              "      <td>0.197</td>\n",
              "      <td>7.15</td>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30524</th>\n",
              "      <td>9.21</td>\n",
              "      <td>22.7</td>\n",
              "      <td>2.07</td>\n",
              "      <td>21.00</td>\n",
              "      <td>0.0790</td>\n",
              "      <td>5.81</td>\n",
              "      <td>12.70</td>\n",
              "      <td>22.8</td>\n",
              "      <td>20.10</td>\n",
              "      <td>11.40</td>\n",
              "      <td>...</td>\n",
              "      <td>20.10</td>\n",
              "      <td>1.060</td>\n",
              "      <td>0.257</td>\n",
              "      <td>0.319</td>\n",
              "      <td>0.0341</td>\n",
              "      <td>20.70</td>\n",
              "      <td>11.60</td>\n",
              "      <td>0.198</td>\n",
              "      <td>7.15</td>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30525</th>\n",
              "      <td>8.21</td>\n",
              "      <td>22.6</td>\n",
              "      <td>1.87</td>\n",
              "      <td>20.50</td>\n",
              "      <td>0.0641</td>\n",
              "      <td>5.96</td>\n",
              "      <td>11.30</td>\n",
              "      <td>22.8</td>\n",
              "      <td>20.20</td>\n",
              "      <td>20.20</td>\n",
              "      <td>...</td>\n",
              "      <td>20.20</td>\n",
              "      <td>1.010</td>\n",
              "      <td>0.285</td>\n",
              "      <td>0.350</td>\n",
              "      <td>0.0314</td>\n",
              "      <td>20.80</td>\n",
              "      <td>20.40</td>\n",
              "      <td>0.162</td>\n",
              "      <td>7.15</td>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30526</th>\n",
              "      <td>6.57</td>\n",
              "      <td>21.0</td>\n",
              "      <td>2.13</td>\n",
              "      <td>21.20</td>\n",
              "      <td>0.0840</td>\n",
              "      <td>3.77</td>\n",
              "      <td>16.50</td>\n",
              "      <td>22.8</td>\n",
              "      <td>20.70</td>\n",
              "      <td>18.00</td>\n",
              "      <td>...</td>\n",
              "      <td>20.80</td>\n",
              "      <td>0.969</td>\n",
              "      <td>0.642</td>\n",
              "      <td>0.385</td>\n",
              "      <td>0.0502</td>\n",
              "      <td>21.00</td>\n",
              "      <td>18.40</td>\n",
              "      <td>0.208</td>\n",
              "      <td>7.15</td>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>30527 rows × 25 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e2298ab0-e4cb-4f80-931e-df43d50b9b82')\"\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-e2298ab0-e4cb-4f80-931e-df43d50b9b82 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-e2298ab0-e4cb-4f80-931e-df43d50b9b82');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "df"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NQwkOgoo9zEw",
        "outputId": "0d43c0ea-f854-4094-8651-e992c314834f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Solidity', 'Eccentricity', 'EquivDiameter', 'Extrema', 'FilledArea',\n",
              "       'Extent', 'Orientation', 'EulerNumber', 'BoundingBox1', 'BoundingBox2',\n",
              "       'BoundingBox3', 'BoundingBox4', 'ConvexHull1', 'ConvexHull2',\n",
              "       'ConvexHull3', 'ConvexHull4', 'MajorAxisLength', 'MinorAxisLength',\n",
              "       'Perimeter', 'ConvexArea', 'Centroid1', 'Centroid2', 'Area', 'raddi',\n",
              "       'microorganisms'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "%matplotlib inline \n",
        "\n",
        "df.columns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 394
        },
        "id": "p706u5fh9zPa",
        "outputId": "37c7bf1b-661f-4190-fd0a-90f161dfe2f3"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           Solidity  Eccentricity  EquivDiameter       Extrema    FilledArea  \\\n",
              "count  30527.000000  30527.000000   30527.000000  30527.000000  30527.000000   \n",
              "mean       9.677744     19.466921       3.633348     11.871832      0.420022   \n",
              "std        4.063437      3.479828       2.210851      6.045135      0.875091   \n",
              "min        0.000000      0.000000       0.000000      0.000000      0.000000   \n",
              "25%        6.570000     17.300000       2.180000      6.790000      0.093700   \n",
              "50%        9.350000     20.700000       3.380000     12.000000      0.229000   \n",
              "75%       12.600000     22.200000       4.580000     17.200000      0.434500   \n",
              "max       23.000000     23.000000      23.000000     23.000000     23.000000   \n",
              "\n",
              "             Extent   Orientation   EulerNumber  BoundingBox1  BoundingBox2  \\\n",
              "count  30527.000000  30527.000000  30527.000000  30527.000000  30527.000000   \n",
              "mean       5.840625     11.751004     22.380901     10.919027     10.399429   \n",
              "std        3.250999      6.575319      0.962906      6.093280      5.797144   \n",
              "min        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
              "25%        3.280000      6.005000     22.300000      5.690000      5.730000   \n",
              "50%        5.260000     12.100000     22.600000     10.900000     10.000000   \n",
              "75%        7.850000     17.200000     22.900000     15.800000     14.900000   \n",
              "max       23.000000     23.000000     23.000000     23.000000     23.000000   \n",
              "\n",
              "       ...   ConvexHull3   ConvexHull4  MajorAxisLength  MinorAxisLength  \\\n",
              "count  ...  30527.000000  30527.000000     30527.000000     30527.000000   \n",
              "mean   ...     11.046482     11.021988         1.605159         1.014179   \n",
              "std    ...      6.089508      6.089467         1.662537         1.224326   \n",
              "min    ...      0.000000      0.000000         0.000000         0.000000   \n",
              "25%    ...      5.790000      5.755000         0.635000         0.421000   \n",
              "50%    ...     11.000000     11.000000         1.160000         0.745000   \n",
              "75%    ...     15.900000     15.900000         2.070000         1.220000   \n",
              "max    ...     23.000000     23.000000        23.000000        23.000000   \n",
              "\n",
              "          Perimeter    ConvexArea     Centroid1     Centroid2         Area  \\\n",
              "count  30527.000000  30527.000000  30527.000000  30527.000000  30527.00000   \n",
              "mean       0.829416      0.254596     11.752783     11.554286      0.80278   \n",
              "std        1.152165      0.971035      6.029756      5.700637      1.17043   \n",
              "min        0.000000      0.000000      0.000000      0.000000      0.00000   \n",
              "25%        0.253000      0.034700      6.570000      7.110000      0.21800   \n",
              "50%        0.518000      0.085700     12.100000     11.200000      0.51400   \n",
              "75%        0.968000      0.200000     16.900000     16.200000      0.93400   \n",
              "max       23.000000     23.000000     23.000000     23.000000     23.00000   \n",
              "\n",
              "              raddi  \n",
              "count  30527.000000  \n",
              "mean       5.214598  \n",
              "std        2.805199  \n",
              "min        0.000000  \n",
              "25%        3.080000  \n",
              "50%        5.320000  \n",
              "75%        7.050000  \n",
              "max       23.000000  \n",
              "\n",
              "[8 rows x 24 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-34ec0620-2572-46e3-aa15-5c3c5a5e1291\">\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>Solidity</th>\n",
              "      <th>Eccentricity</th>\n",
              "      <th>EquivDiameter</th>\n",
              "      <th>Extrema</th>\n",
              "      <th>FilledArea</th>\n",
              "      <th>Extent</th>\n",
              "      <th>Orientation</th>\n",
              "      <th>EulerNumber</th>\n",
              "      <th>BoundingBox1</th>\n",
              "      <th>BoundingBox2</th>\n",
              "      <th>...</th>\n",
              "      <th>ConvexHull3</th>\n",
              "      <th>ConvexHull4</th>\n",
              "      <th>MajorAxisLength</th>\n",
              "      <th>MinorAxisLength</th>\n",
              "      <th>Perimeter</th>\n",
              "      <th>ConvexArea</th>\n",
              "      <th>Centroid1</th>\n",
              "      <th>Centroid2</th>\n",
              "      <th>Area</th>\n",
              "      <th>raddi</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.000000</td>\n",
              "      <td>30527.00000</td>\n",
              "      <td>30527.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>9.677744</td>\n",
              "      <td>19.466921</td>\n",
              "      <td>3.633348</td>\n",
              "      <td>11.871832</td>\n",
              "      <td>0.420022</td>\n",
              "      <td>5.840625</td>\n",
              "      <td>11.751004</td>\n",
              "      <td>22.380901</td>\n",
              "      <td>10.919027</td>\n",
              "      <td>10.399429</td>\n",
              "      <td>...</td>\n",
              "      <td>11.046482</td>\n",
              "      <td>11.021988</td>\n",
              "      <td>1.605159</td>\n",
              "      <td>1.014179</td>\n",
              "      <td>0.829416</td>\n",
              "      <td>0.254596</td>\n",
              "      <td>11.752783</td>\n",
              "      <td>11.554286</td>\n",
              "      <td>0.80278</td>\n",
              "      <td>5.214598</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>4.063437</td>\n",
              "      <td>3.479828</td>\n",
              "      <td>2.210851</td>\n",
              "      <td>6.045135</td>\n",
              "      <td>0.875091</td>\n",
              "      <td>3.250999</td>\n",
              "      <td>6.575319</td>\n",
              "      <td>0.962906</td>\n",
              "      <td>6.093280</td>\n",
              "      <td>5.797144</td>\n",
              "      <td>...</td>\n",
              "      <td>6.089508</td>\n",
              "      <td>6.089467</td>\n",
              "      <td>1.662537</td>\n",
              "      <td>1.224326</td>\n",
              "      <td>1.152165</td>\n",
              "      <td>0.971035</td>\n",
              "      <td>6.029756</td>\n",
              "      <td>5.700637</td>\n",
              "      <td>1.17043</td>\n",
              "      <td>2.805199</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.00000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>6.570000</td>\n",
              "      <td>17.300000</td>\n",
              "      <td>2.180000</td>\n",
              "      <td>6.790000</td>\n",
              "      <td>0.093700</td>\n",
              "      <td>3.280000</td>\n",
              "      <td>6.005000</td>\n",
              "      <td>22.300000</td>\n",
              "      <td>5.690000</td>\n",
              "      <td>5.730000</td>\n",
              "      <td>...</td>\n",
              "      <td>5.790000</td>\n",
              "      <td>5.755000</td>\n",
              "      <td>0.635000</td>\n",
              "      <td>0.421000</td>\n",
              "      <td>0.253000</td>\n",
              "      <td>0.034700</td>\n",
              "      <td>6.570000</td>\n",
              "      <td>7.110000</td>\n",
              "      <td>0.21800</td>\n",
              "      <td>3.080000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>9.350000</td>\n",
              "      <td>20.700000</td>\n",
              "      <td>3.380000</td>\n",
              "      <td>12.000000</td>\n",
              "      <td>0.229000</td>\n",
              "      <td>5.260000</td>\n",
              "      <td>12.100000</td>\n",
              "      <td>22.600000</td>\n",
              "      <td>10.900000</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>11.000000</td>\n",
              "      <td>11.000000</td>\n",
              "      <td>1.160000</td>\n",
              "      <td>0.745000</td>\n",
              "      <td>0.518000</td>\n",
              "      <td>0.085700</td>\n",
              "      <td>12.100000</td>\n",
              "      <td>11.200000</td>\n",
              "      <td>0.51400</td>\n",
              "      <td>5.320000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>12.600000</td>\n",
              "      <td>22.200000</td>\n",
              "      <td>4.580000</td>\n",
              "      <td>17.200000</td>\n",
              "      <td>0.434500</td>\n",
              "      <td>7.850000</td>\n",
              "      <td>17.200000</td>\n",
              "      <td>22.900000</td>\n",
              "      <td>15.800000</td>\n",
              "      <td>14.900000</td>\n",
              "      <td>...</td>\n",
              "      <td>15.900000</td>\n",
              "      <td>15.900000</td>\n",
              "      <td>2.070000</td>\n",
              "      <td>1.220000</td>\n",
              "      <td>0.968000</td>\n",
              "      <td>0.200000</td>\n",
              "      <td>16.900000</td>\n",
              "      <td>16.200000</td>\n",
              "      <td>0.93400</td>\n",
              "      <td>7.050000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.00000</td>\n",
              "      <td>23.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>8 rows × 24 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-34ec0620-2572-46e3-aa15-5c3c5a5e1291')\"\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-34ec0620-2572-46e3-aa15-5c3c5a5e1291 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-34ec0620-2572-46e3-aa15-5c3c5a5e1291');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ],
      "source": [
        "#Check Distribution for Each Column for Outliers\n",
        "df.describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "PuYixOoXCtrQ"
      },
      "outputs": [],
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "qZwOp6F8DpQX"
      },
      "outputs": [],
      "source": [
        "df2 = df.copy()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LW8TyXXaFRip"
      },
      "source": [
        "Label Encoding for Categories"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8ViDBqjTFRwb",
        "outputId": "cf412193-90b9-4baa-fe8f-82120994204e"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "microorganisms  Target\n",
              "Aspergillus sp  0         3888\n",
              "Diatom          1         1818\n",
              "Penicillum      2         1080\n",
              "Pithophora      3         1350\n",
              "Protozoa        4         3888\n",
              "Raizopus        5         2552\n",
              "Spirogyra       6          611\n",
              "Ulothrix        7         7420\n",
              "Volvox          8         4320\n",
              "Yeast           9         3600\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ],
      "source": [
        "le_df = df.copy()\n",
        "\n",
        "# Use label encoder from sklearn to change microorganism classification into numerical encoding\n",
        "\n",
        "# Note from the future: I did not end uo using LabelEncoder\n",
        "\n",
        "le = LabelEncoder()\n",
        "le_df['Target'] = le.fit_transform(le_df['microorganisms'])\n",
        "le_df[['microorganisms', 'Target']].value_counts(sort=False)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "T8Xzh418Y7wd",
        "outputId": "43a38524-0486-42e2-c77c-c36b1f747308"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "microorganisms\n",
              "Aspergillus sp    3888\n",
              "Diatom            1818\n",
              "Penicillum        1080\n",
              "Pithophora        1350\n",
              "Protozoa          3888\n",
              "Raizopus          2552\n",
              "Spirogyra          611\n",
              "Ulothrix          7420\n",
              "Volvox            4320\n",
              "Yeast             3600\n",
              "Name: Eccentricity, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ],
      "source": [
        "df.groupby('microorganisms')['Eccentricity'].count()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "VrS3S8vKZHSM"
      },
      "outputs": [],
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "Vl0pi0hCagvQ"
      },
      "outputs": [],
      "source": [
        ""
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bbfS0AScJVId"
      },
      "source": [
        "I will be trying three algorithms to train this model. I believe that decision trees will be the most accurate because it is sensitive to small differences in values, making me believe it will capture the most minute of differences between one microorganism and the next. \n",
        "\n",
        "The other two algorithms I used are Naive Bayes and KNN."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "id": "HaEf0rHHJz1t"
      },
      "outputs": [],
      "source": [
        "# Import some of the packages/libraries you need for supervised learning\n",
        "from scipy import stats\n",
        "from sklearn.metrics import accuracy_score\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn import metrics "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CL-5ErqF5Yn-"
      },
      "source": [
        "will be training for each algorithm then deleting and leaving the results "
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "cLGRKj4lKIlh",
        "outputId": "e4bd00cf-028e-44d8-8237-55914dc98a77"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      microorganisms\n",
              "9812           Yeast\n",
              "10515       Raizopus\n",
              "10262       Raizopus\n",
              "278        Spirogyra\n",
              "19928       Protozoa\n",
              "...              ...\n",
              "9154           Yeast\n",
              "11274       Raizopus\n",
              "11719       Raizopus\n",
              "1062          Volvox\n",
              "26109       Ulothrix\n",
              "\n",
              "[18316 rows x 1 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3f060c88-9722-4b9d-8dd4-4f77b8d21167\">\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>microorganisms</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>9812</th>\n",
              "      <td>Yeast</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10515</th>\n",
              "      <td>Raizopus</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10262</th>\n",
              "      <td>Raizopus</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>278</th>\n",
              "      <td>Spirogyra</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19928</th>\n",
              "      <td>Protozoa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9154</th>\n",
              "      <td>Yeast</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11274</th>\n",
              "      <td>Raizopus</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11719</th>\n",
              "      <td>Raizopus</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1062</th>\n",
              "      <td>Volvox</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26109</th>\n",
              "      <td>Ulothrix</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>18316 rows × 1 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3f060c88-9722-4b9d-8dd4-4f77b8d21167')\"\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-3f060c88-9722-4b9d-8dd4-4f77b8d21167 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-3f060c88-9722-4b9d-8dd4-4f77b8d21167');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ],
      "source": [
        "# Define the inputs/features for the models you'll test below\n",
        "# 60-40 split for original df\n",
        "\n",
        "x = df[['Solidity', 'Eccentricity', 'EquivDiameter', 'Extrema', 'FilledArea',\n",
        "       'Extent', 'Orientation', 'EulerNumber', 'BoundingBox1', 'BoundingBox2',\n",
        "       'BoundingBox3', 'BoundingBox4', 'ConvexHull1', 'ConvexHull2',\n",
        "       'ConvexHull3', 'ConvexHull4', 'MajorAxisLength', 'MinorAxisLength',\n",
        "       'Perimeter', 'ConvexArea', 'Centroid1', 'Centroid2', 'Area', 'raddi']].copy()\n",
        "\n",
        "# Define the targets - what we are trying to predict or classify\n",
        "# Here we are trying to predict the \"rating_levels\"\n",
        "y = df[['microorganisms']].copy()\n",
        "\n",
        "# We'll save 40 percent of our data for testing and use 60 percent for training \n",
        "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.40)\n",
        "\n",
        "sc = StandardScaler()\n",
        "x_train = sc.fit_transform(x_train)\n",
        "x_test = sc.transform(x_test)\n",
        "\n",
        "y_train"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "id": "S1jzhTMCR0AP"
      },
      "outputs": [],
      "source": [
        "# # Import necessary package\n",
        "# from sklearn.tree import DecisionTreeClassifier\n",
        "\n",
        "\n",
        "# # This is where we set our machine learning algorithm type - Decision Tree\n",
        "# dectree = DecisionTreeClassifier(criterion='entropy',random_state=0) \n",
        "# dectree.fit(x_train,y_train.values.ravel())\n",
        "\n",
        "# # Use the model to make predictions using our testing input data\n",
        "# y_pred_dectree = dectree.predict(x_test)\n",
        "\n",
        "# # Calculate the accuracy of the model as a percent\n",
        "# accuracy = metrics.accuracy_score(y_test, y_pred_dectree)\n",
        "# accuracy_percentage = 100 * accuracy\n",
        "# print('Accuracy: ',accuracy_percentage)\n",
        "\n",
        "# # took very little time, 97.46 (overfitting?), 97.65"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Q3Hf9tbupPeF",
        "outputId": "4669efbd-98ba-4b51-bcb0-5834cdc36ff1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/preprocessing/_label.py:98: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/preprocessing/_label.py:133: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        }
      ],
      "source": [
        "# build the lightgbm model\n",
        "import lightgbm as lgb\n",
        "clf = lgb.LGBMClassifier()\n",
        "clf.fit(x_train, y_train)\n",
        "\n",
        "# predict the results\n",
        "y_pred=clf.predict(x_test)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-htLTWwtm-it",
        "outputId": "f50201d7-2417-4610-8c9d-fc62584f139d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "LightGBM Model accuracy score: 0.9734\n"
          ]
        }
      ],
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "accuracy=accuracy_score(y_pred, y_test)\n",
        "print('LightGBM Model accuracy score: {0:0.4f}'.format(accuracy))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VEw1SJzxmzIp",
        "outputId": "85801700-60e9-40b9-9e45-c67af14df848"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training-set accuracy score: 0.9938\n"
          ]
        }
      ],
      "source": [
        "y_pred_train = clf.predict(x_train)\n",
        "print('Training-set accuracy score: {0:0.4f}'.format(accuracy_score(y_train, y_pred_train)))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FXWmyaEjxYFk",
        "outputId": "d6c2bbc6-43dc-4f56-a21c-46feb530040a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.9733846531815576\n"
          ]
        }
      ],
      "source": [
        "# precision\n",
        "from sklearn.metrics import precision_score\n",
        "precision = precision_score(y_test, y_pred, average = 'micro')\n",
        "print(precision)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "CyCCHQ5tS3Md",
        "outputId": "fa778add-56db-410e-e0a9-1330d2c754d8"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Empty DataFrame\n",
              "Columns: []\n",
              "Index: [Aspergillus sp, Diatom, Penicillum, Pithophora, Protozoa, Raizopus, Spirogyra, Ulothrix, Volvox, Yeast]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-8b03028e-5608-4855-b208-e9220798512a\">\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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>microorganisms</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Aspergillus sp</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Diatom</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Penicillum</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pithophora</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Protozoa</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Raizopus</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Spirogyra</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Ulothrix</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Volvox</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Yeast</th>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8b03028e-5608-4855-b208-e9220798512a')\"\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-8b03028e-5608-4855-b208-e9220798512a 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-8b03028e-5608-4855-b208-e9220798512a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ],
      "source": [
        "y_test.groupby('microorganisms').count()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kwwjiNlHuRRC"
      },
      "source": [
        "Training set accuracy is 99.38 while the test accuracy is 97.01"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nBFEKI7suXLZ",
        "outputId": "b85e615b-677c-4451-ff2e-a4ac03a77fed"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Confusion matrix\n",
            "\n",
            " [[1516    7    0    2    3    0    2   65   11    8]\n",
            " [   0  691    0    5    0    0    0    0    0    0]\n",
            " [   0    0  440    0    0    0    0    0    0    0]\n",
            " [  15    8    0  458    4    0    0   40    4    0]\n",
            " [   0    0    0    0 1569    0    0    0    0    0]\n",
            " [   0    0    0    0    0  997    0    0    0    0]\n",
            " [   8    5    0    3    1    0  190   35    3    6]\n",
            " [  12    8    0    8   11    0    0 2883   17    9]\n",
            " [   0    0    0    0    0    0    0    4 1679    0]\n",
            " [   0    0    0    4    0    0    0   11    6 1463]]\n"
          ]
        }
      ],
      "source": [
        "# confusion matrix for evaluation\n",
        "\n",
        "from sklearn.metrics import confusion_matrix\n",
        "cm = confusion_matrix(y_test, y_pred)\n",
        "print('Confusion matrix\\n\\n', cm)\n",
        "\n",
        "# microorganisms\n",
        "# Aspergillus sp    3888\n",
        "# Diatom            1818\n",
        "# Penicillum        1080\n",
        "# Pithophora        1350\n",
        "# Protozoa          3888\n",
        "# Raizopus          2552\n",
        "# Spirogyra          611\n",
        "# Ulothrix          7420\n",
        "# Volvox            4320\n",
        "# Yeast             3600\n",
        "\n",
        "microorganisms_arr = ['Aspergillus sp','Diatom','Penicillum','Pithophora','Protozoa','Raizopus','Spirogyra','Ulothrix','Volvox','Yeast']\n",
        "\n",
        "sns_col_name, sns_ind, short = [], [], []\n",
        "for i in range(len(microorganisms_arr)):\n",
        "  word = microorganisms_arr[i]\n",
        "  short.append(word[:3])\n",
        "  col_name_str, ind_name_str = \"Actual \" + short[i] + '.', \"Predicted \" + word\n",
        "  sns_col_name.append(col_name_str)\n",
        "  sns_ind.append(ind_name_str)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 329
        },
        "id": "oQqHrOshwxhn",
        "outputId": "ce804509-e5d4-4d36-d906-1e3422d3afca"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7ff14d1af510>"
            ]
          },
          "metadata": {},
          "execution_count": 20
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ],
      "source": [
        "cm_matrix = pd.DataFrame(data=cm, columns=sns_col_name, \n",
        "                                 index=sns_ind)\n",
        "\n",
        "sns.heatmap(cm_matrix, annot=True, fmt='d', cmap='YlGnBu')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gC2pbCxeCyJ6"
      },
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "id": "6VpnUwXET1Kj"
      },
      "outputs": [],
      "source": [
        ""
      ]
    }
  ],
  "metadata": {
    "colab": {
      "name": "microorganism_detection.ipynb",
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.7"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}