fish-classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "amateur-rendering",
   "metadata": {
    "papermill": {
     "duration": 0.019168,
     "end_time": "2021-07-02T05:42:19.692647",
     "exception": false,
     "start_time": "2021-07-02T05:42:19.673479",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Importing Libraries 📖"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "still-stability",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:19.741865Z",
     "iopub.status.busy": "2021-07-02T05:42:19.741226Z",
     "iopub.status.idle": "2021-07-02T05:42:26.936690Z",
     "shell.execute_reply": "2021-07-02T05:42:26.936038Z",
     "shell.execute_reply.started": "2021-07-02T05:08:55.334394Z"
    },
    "papermill": {
     "duration": 7.225731,
     "end_time": "2021-07-02T05:42:26.936872",
     "exception": false,
     "start_time": "2021-07-02T05:42:19.711141",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/kaggle/input/fish-market/Fish.csv\n"
     ]
    }
   ],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "import tensorflow as tf\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "metallic-jungle",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:26.979737Z",
     "iopub.status.busy": "2021-07-02T05:42:26.979086Z",
     "iopub.status.idle": "2021-07-02T05:42:26.992725Z",
     "shell.execute_reply": "2021-07-02T05:42:26.992120Z",
     "shell.execute_reply.started": "2021-07-02T04:49:43.444601Z"
    },
    "papermill": {
     "duration": 0.037,
     "end_time": "2021-07-02T05:42:26.992893",
     "exception": false,
     "start_time": "2021-07-02T05:42:26.955893",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "data = pd.read_csv('../input/fish-market/Fish.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "operational-aerospace",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:27.040894Z",
     "iopub.status.busy": "2021-07-02T05:42:27.040161Z",
     "iopub.status.idle": "2021-07-02T05:42:27.073644Z",
     "shell.execute_reply": "2021-07-02T05:42:27.074183Z",
     "shell.execute_reply.started": "2021-07-02T04:49:46.895971Z"
    },
    "papermill": {
     "duration": 0.06204,
     "end_time": "2021-07-02T05:42:27.074377",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.012337",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Species</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Length1</th>\n",
       "      <th>Length2</th>\n",
       "      <th>Length3</th>\n",
       "      <th>Height</th>\n",
       "      <th>Width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Bream</td>\n",
       "      <td>242.0</td>\n",
       "      <td>23.2</td>\n",
       "      <td>25.4</td>\n",
       "      <td>30.0</td>\n",
       "      <td>11.5200</td>\n",
       "      <td>4.0200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Bream</td>\n",
       "      <td>290.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>26.3</td>\n",
       "      <td>31.2</td>\n",
       "      <td>12.4800</td>\n",
       "      <td>4.3056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Bream</td>\n",
       "      <td>340.0</td>\n",
       "      <td>23.9</td>\n",
       "      <td>26.5</td>\n",
       "      <td>31.1</td>\n",
       "      <td>12.3778</td>\n",
       "      <td>4.6961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bream</td>\n",
       "      <td>363.0</td>\n",
       "      <td>26.3</td>\n",
       "      <td>29.0</td>\n",
       "      <td>33.5</td>\n",
       "      <td>12.7300</td>\n",
       "      <td>4.4555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Bream</td>\n",
       "      <td>430.0</td>\n",
       "      <td>26.5</td>\n",
       "      <td>29.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>12.4440</td>\n",
       "      <td>5.1340</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>154</th>\n",
       "      <td>Smelt</td>\n",
       "      <td>12.2</td>\n",
       "      <td>11.5</td>\n",
       "      <td>12.2</td>\n",
       "      <td>13.4</td>\n",
       "      <td>2.0904</td>\n",
       "      <td>1.3936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>Smelt</td>\n",
       "      <td>13.4</td>\n",
       "      <td>11.7</td>\n",
       "      <td>12.4</td>\n",
       "      <td>13.5</td>\n",
       "      <td>2.4300</td>\n",
       "      <td>1.2690</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156</th>\n",
       "      <td>Smelt</td>\n",
       "      <td>12.2</td>\n",
       "      <td>12.1</td>\n",
       "      <td>13.0</td>\n",
       "      <td>13.8</td>\n",
       "      <td>2.2770</td>\n",
       "      <td>1.2558</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>Smelt</td>\n",
       "      <td>19.7</td>\n",
       "      <td>13.2</td>\n",
       "      <td>14.3</td>\n",
       "      <td>15.2</td>\n",
       "      <td>2.8728</td>\n",
       "      <td>2.0672</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>Smelt</td>\n",
       "      <td>19.9</td>\n",
       "      <td>13.8</td>\n",
       "      <td>15.0</td>\n",
       "      <td>16.2</td>\n",
       "      <td>2.9322</td>\n",
       "      <td>1.8792</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>159 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Species  Weight  Length1  Length2  Length3   Height   Width\n",
       "0     Bream   242.0     23.2     25.4     30.0  11.5200  4.0200\n",
       "1     Bream   290.0     24.0     26.3     31.2  12.4800  4.3056\n",
       "2     Bream   340.0     23.9     26.5     31.1  12.3778  4.6961\n",
       "3     Bream   363.0     26.3     29.0     33.5  12.7300  4.4555\n",
       "4     Bream   430.0     26.5     29.0     34.0  12.4440  5.1340\n",
       "..      ...     ...      ...      ...      ...      ...     ...\n",
       "154   Smelt    12.2     11.5     12.2     13.4   2.0904  1.3936\n",
       "155   Smelt    13.4     11.7     12.4     13.5   2.4300  1.2690\n",
       "156   Smelt    12.2     12.1     13.0     13.8   2.2770  1.2558\n",
       "157   Smelt    19.7     13.2     14.3     15.2   2.8728  2.0672\n",
       "158   Smelt    19.9     13.8     15.0     16.2   2.9322  1.8792\n",
       "\n",
       "[159 rows x 7 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "grand-spouse",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:27.120309Z",
     "iopub.status.busy": "2021-07-02T05:42:27.119619Z",
     "iopub.status.idle": "2021-07-02T05:42:27.125189Z",
     "shell.execute_reply": "2021-07-02T05:42:27.125700Z",
     "shell.execute_reply.started": "2021-07-02T04:50:05.69547Z"
    },
    "papermill": {
     "duration": 0.032218,
     "end_time": "2021-07-02T05:42:27.125881",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.093663",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Species    False\n",
       "Weight     False\n",
       "Length1    False\n",
       "Length2    False\n",
       "Length3    False\n",
       "Height     False\n",
       "Width      False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().any()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "asian-samoa",
   "metadata": {
    "papermill": {
     "duration": 0.019106,
     "end_time": "2021-07-02T05:42:27.164469",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.145363",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Preprocessing 🛠️"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "solar-virginia",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:27.207034Z",
     "iopub.status.busy": "2021-07-02T05:42:27.206073Z",
     "iopub.status.idle": "2021-07-02T05:42:27.216451Z",
     "shell.execute_reply": "2021-07-02T05:42:27.215918Z",
     "shell.execute_reply.started": "2021-07-02T04:54:24.08364Z"
    },
    "papermill": {
     "duration": 0.032843,
     "end_time": "2021-07-02T05:42:27.216595",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.183752",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(list(data['Species'].unique()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "continental-gravity",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:27.264014Z",
     "iopub.status.busy": "2021-07-02T05:42:27.263111Z",
     "iopub.status.idle": "2021-07-02T05:42:27.267071Z",
     "shell.execute_reply": "2021-07-02T05:42:27.266535Z",
     "shell.execute_reply.started": "2021-07-02T04:56:19.20214Z"
    },
    "papermill": {
     "duration": 0.030769,
     "end_time": "2021-07-02T05:42:27.267208",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.236439",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: 'Bream',\n",
       " 1: 'Parkki',\n",
       " 2: 'Perch',\n",
       " 3: 'Pike',\n",
       " 4: 'Roach',\n",
       " 5: 'Smelt',\n",
       " 6: 'Whitefish'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "encoder = LabelEncoder()\n",
    "data['Species'] = encoder.fit_transform(data['Species'])\n",
    "\n",
    "fish_type = {index: type for index, type in enumerate(encoder.classes_)}\n",
    "fish_type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "arbitrary-devices",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:27.311163Z",
     "iopub.status.busy": "2021-07-02T05:42:27.310228Z",
     "iopub.status.idle": "2021-07-02T05:42:28.038911Z",
     "shell.execute_reply": "2021-07-02T05:42:28.039431Z",
     "shell.execute_reply.started": "2021-07-02T04:56:28.982978Z"
    },
    "papermill": {
     "duration": 0.752123,
     "end_time": "2021-07-02T05:42:28.039608",
     "exception": false,
     "start_time": "2021-07-02T05:42:27.287485",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x720 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (12, 10))\n",
    "sns.heatmap(data.corr(), annot = True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "played-structure",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.090088Z",
     "iopub.status.busy": "2021-07-02T05:42:28.089375Z",
     "iopub.status.idle": "2021-07-02T05:42:28.092314Z",
     "shell.execute_reply": "2021-07-02T05:42:28.091777Z",
     "shell.execute_reply.started": "2021-07-02T05:03:04.820689Z"
    },
    "papermill": {
     "duration": 0.030154,
     "end_time": "2021-07-02T05:42:28.092448",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.062294",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "X = data.drop('Species', axis = 1)\n",
    "y = data['Species']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "beautiful-accessory",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.154556Z",
     "iopub.status.busy": "2021-07-02T05:42:28.153412Z",
     "iopub.status.idle": "2021-07-02T05:42:28.157719Z",
     "shell.execute_reply": "2021-07-02T05:42:28.158284Z",
     "shell.execute_reply.started": "2021-07-02T05:03:07.497451Z"
    },
    "papermill": {
     "duration": 0.044212,
     "end_time": "2021-07-02T05:42:28.158452",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.114240",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Weight</th>\n",
       "      <th>Length1</th>\n",
       "      <th>Length2</th>\n",
       "      <th>Length3</th>\n",
       "      <th>Height</th>\n",
       "      <th>Width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>242.0</td>\n",
       "      <td>23.2</td>\n",
       "      <td>25.4</td>\n",
       "      <td>30.0</td>\n",
       "      <td>11.5200</td>\n",
       "      <td>4.0200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>290.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>26.3</td>\n",
       "      <td>31.2</td>\n",
       "      <td>12.4800</td>\n",
       "      <td>4.3056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>340.0</td>\n",
       "      <td>23.9</td>\n",
       "      <td>26.5</td>\n",
       "      <td>31.1</td>\n",
       "      <td>12.3778</td>\n",
       "      <td>4.6961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>363.0</td>\n",
       "      <td>26.3</td>\n",
       "      <td>29.0</td>\n",
       "      <td>33.5</td>\n",
       "      <td>12.7300</td>\n",
       "      <td>4.4555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>430.0</td>\n",
       "      <td>26.5</td>\n",
       "      <td>29.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>12.4440</td>\n",
       "      <td>5.1340</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>154</th>\n",
       "      <td>12.2</td>\n",
       "      <td>11.5</td>\n",
       "      <td>12.2</td>\n",
       "      <td>13.4</td>\n",
       "      <td>2.0904</td>\n",
       "      <td>1.3936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>13.4</td>\n",
       "      <td>11.7</td>\n",
       "      <td>12.4</td>\n",
       "      <td>13.5</td>\n",
       "      <td>2.4300</td>\n",
       "      <td>1.2690</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156</th>\n",
       "      <td>12.2</td>\n",
       "      <td>12.1</td>\n",
       "      <td>13.0</td>\n",
       "      <td>13.8</td>\n",
       "      <td>2.2770</td>\n",
       "      <td>1.2558</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>19.7</td>\n",
       "      <td>13.2</td>\n",
       "      <td>14.3</td>\n",
       "      <td>15.2</td>\n",
       "      <td>2.8728</td>\n",
       "      <td>2.0672</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>19.9</td>\n",
       "      <td>13.8</td>\n",
       "      <td>15.0</td>\n",
       "      <td>16.2</td>\n",
       "      <td>2.9322</td>\n",
       "      <td>1.8792</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>159 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Weight  Length1  Length2  Length3   Height   Width\n",
       "0     242.0     23.2     25.4     30.0  11.5200  4.0200\n",
       "1     290.0     24.0     26.3     31.2  12.4800  4.3056\n",
       "2     340.0     23.9     26.5     31.1  12.3778  4.6961\n",
       "3     363.0     26.3     29.0     33.5  12.7300  4.4555\n",
       "4     430.0     26.5     29.0     34.0  12.4440  5.1340\n",
       "..      ...      ...      ...      ...      ...     ...\n",
       "154    12.2     11.5     12.2     13.4   2.0904  1.3936\n",
       "155    13.4     11.7     12.4     13.5   2.4300  1.2690\n",
       "156    12.2     12.1     13.0     13.8   2.2770  1.2558\n",
       "157    19.7     13.2     14.3     15.2   2.8728  2.0672\n",
       "158    19.9     13.8     15.0     16.2   2.9322  1.8792\n",
       "\n",
       "[159 rows x 6 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "intelligent-rogers",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.206240Z",
     "iopub.status.busy": "2021-07-02T05:42:28.205607Z",
     "iopub.status.idle": "2021-07-02T05:42:28.213985Z",
     "shell.execute_reply": "2021-07-02T05:42:28.214516Z",
     "shell.execute_reply.started": "2021-07-02T05:06:09.285039Z"
    },
    "papermill": {
     "duration": 0.033576,
     "end_time": "2021-07-02T05:42:28.214687",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.181111",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "scaler = StandardScaler()\n",
    "X = pd.DataFrame(scaler.fit_transform(X), columns = X.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "nutritional-syria",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.262001Z",
     "iopub.status.busy": "2021-07-02T05:42:28.261313Z",
     "iopub.status.idle": "2021-07-02T05:42:28.277882Z",
     "shell.execute_reply": "2021-07-02T05:42:28.278394Z",
     "shell.execute_reply.started": "2021-07-02T05:06:12.182241Z"
    },
    "papermill": {
     "duration": 0.041711,
     "end_time": "2021-07-02T05:42:28.278563",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.236852",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Weight</th>\n",
       "      <th>Length1</th>\n",
       "      <th>Length2</th>\n",
       "      <th>Length3</th>\n",
       "      <th>Height</th>\n",
       "      <th>Width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.438072</td>\n",
       "      <td>-0.305789</td>\n",
       "      <td>-0.282303</td>\n",
       "      <td>-0.106020</td>\n",
       "      <td>0.596579</td>\n",
       "      <td>-0.236529</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.303562</td>\n",
       "      <td>-0.225507</td>\n",
       "      <td>-0.198054</td>\n",
       "      <td>-0.002337</td>\n",
       "      <td>0.821261</td>\n",
       "      <td>-0.066579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.163448</td>\n",
       "      <td>-0.235542</td>\n",
       "      <td>-0.179332</td>\n",
       "      <td>-0.010977</td>\n",
       "      <td>0.797341</td>\n",
       "      <td>0.165793</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.098995</td>\n",
       "      <td>0.005302</td>\n",
       "      <td>0.054694</td>\n",
       "      <td>0.196390</td>\n",
       "      <td>0.879771</td>\n",
       "      <td>0.022621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.088759</td>\n",
       "      <td>0.025372</td>\n",
       "      <td>0.054694</td>\n",
       "      <td>0.239592</td>\n",
       "      <td>0.812835</td>\n",
       "      <td>0.426371</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>154</th>\n",
       "      <td>-1.082039</td>\n",
       "      <td>-1.479903</td>\n",
       "      <td>-1.517960</td>\n",
       "      <td>-1.540309</td>\n",
       "      <td>-1.610359</td>\n",
       "      <td>-1.799403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>-1.078676</td>\n",
       "      <td>-1.459833</td>\n",
       "      <td>-1.499238</td>\n",
       "      <td>-1.531669</td>\n",
       "      <td>-1.530878</td>\n",
       "      <td>-1.873547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156</th>\n",
       "      <td>-1.082039</td>\n",
       "      <td>-1.419692</td>\n",
       "      <td>-1.443072</td>\n",
       "      <td>-1.505748</td>\n",
       "      <td>-1.566687</td>\n",
       "      <td>-1.881402</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>-1.061022</td>\n",
       "      <td>-1.309305</td>\n",
       "      <td>-1.321378</td>\n",
       "      <td>-1.384784</td>\n",
       "      <td>-1.427243</td>\n",
       "      <td>-1.398568</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>-1.060461</td>\n",
       "      <td>-1.249094</td>\n",
       "      <td>-1.255851</td>\n",
       "      <td>-1.298381</td>\n",
       "      <td>-1.413341</td>\n",
       "      <td>-1.510440</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>159 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Weight   Length1   Length2   Length3    Height     Width\n",
       "0   -0.438072 -0.305789 -0.282303 -0.106020  0.596579 -0.236529\n",
       "1   -0.303562 -0.225507 -0.198054 -0.002337  0.821261 -0.066579\n",
       "2   -0.163448 -0.235542 -0.179332 -0.010977  0.797341  0.165793\n",
       "3   -0.098995  0.005302  0.054694  0.196390  0.879771  0.022621\n",
       "4    0.088759  0.025372  0.054694  0.239592  0.812835  0.426371\n",
       "..        ...       ...       ...       ...       ...       ...\n",
       "154 -1.082039 -1.479903 -1.517960 -1.540309 -1.610359 -1.799403\n",
       "155 -1.078676 -1.459833 -1.499238 -1.531669 -1.530878 -1.873547\n",
       "156 -1.082039 -1.419692 -1.443072 -1.505748 -1.566687 -1.881402\n",
       "157 -1.061022 -1.309305 -1.321378 -1.384784 -1.427243 -1.398568\n",
       "158 -1.060461 -1.249094 -1.255851 -1.298381 -1.413341 -1.510440\n",
       "\n",
       "[159 rows x 6 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "collect-adventure",
   "metadata": {
    "papermill": {
     "duration": 0.02294,
     "end_time": "2021-07-02T05:42:28.324427",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.301487",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Model "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "stone-phone",
   "metadata": {
    "papermill": {
     "duration": 0.023006,
     "end_time": "2021-07-02T05:42:28.370595",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.347589",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Logistic Regression Model 📏"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "federal-budget",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.419842Z",
     "iopub.status.busy": "2021-07-02T05:42:28.419182Z",
     "iopub.status.idle": "2021-07-02T05:42:28.427025Z",
     "shell.execute_reply": "2021-07-02T05:42:28.426376Z",
     "shell.execute_reply.started": "2021-07-02T05:07:10.684596Z"
    },
    "papermill": {
     "duration": 0.033334,
     "end_time": "2021-07-02T05:42:28.427162",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.393828",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, train_size = 0.7)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abandoned-questionnaire",
   "metadata": {
    "papermill": {
     "duration": 0.02281,
     "end_time": "2021-07-02T05:42:28.472831",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.450021",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Logistic Regression Score 🎯"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "paperback-russian",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.526535Z",
     "iopub.status.busy": "2021-07-02T05:42:28.525490Z",
     "iopub.status.idle": "2021-07-02T05:42:28.555527Z",
     "shell.execute_reply": "2021-07-02T05:42:28.554959Z",
     "shell.execute_reply.started": "2021-07-02T05:37:22.563551Z"
    },
    "papermill": {
     "duration": 0.060082,
     "end_time": "2021-07-02T05:42:28.555664",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.495582",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "83.33333333333334%\n"
     ]
    }
   ],
   "source": [
    "logistic_model = LogisticRegression()\n",
    "logistic_model.fit(X_train, y_train)\n",
    "\n",
    "print(str(logistic_model.score(X_test, y_test) * 100) + \"%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "prompt-lemon",
   "metadata": {
    "papermill": {
     "duration": 0.022928,
     "end_time": "2021-07-02T05:42:28.601668",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.578740",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Neural Network Model 🧠"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "jewish-reform",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:28.656756Z",
     "iopub.status.busy": "2021-07-02T05:42:28.655887Z",
     "iopub.status.idle": "2021-07-02T05:42:39.527782Z",
     "shell.execute_reply": "2021-07-02T05:42:39.527039Z",
     "shell.execute_reply.started": "2021-07-02T05:30:46.336784Z"
    },
    "papermill": {
     "duration": 10.902874,
     "end_time": "2021-07-02T05:42:39.527938",
     "exception": false,
     "start_time": "2021-07-02T05:42:28.625064",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/150\n",
      "3/3 [==============================] - 1s 316ms/step - loss: 1.8936 - accuracy: 0.2092 - val_loss: 1.8884 - val_accuracy: 0.4783\n",
      "Epoch 2/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.8505 - accuracy: 0.3920 - val_loss: 1.8347 - val_accuracy: 0.4783\n",
      "Epoch 3/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.7820 - accuracy: 0.4616 - val_loss: 1.7908 - val_accuracy: 0.4783\n",
      "Epoch 4/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.7740 - accuracy: 0.4304 - val_loss: 1.7548 - val_accuracy: 0.4783\n",
      "Epoch 5/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.7471 - accuracy: 0.4631 - val_loss: 1.7222 - val_accuracy: 0.6087\n",
      "Epoch 6/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.7349 - accuracy: 0.5671 - val_loss: 1.6892 - val_accuracy: 0.6087\n",
      "Epoch 7/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.7080 - accuracy: 0.5632 - val_loss: 1.6621 - val_accuracy: 0.6087\n",
      "Epoch 8/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.6565 - accuracy: 0.6101 - val_loss: 1.6318 - val_accuracy: 0.6087\n",
      "Epoch 9/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.6583 - accuracy: 0.5614 - val_loss: 1.6054 - val_accuracy: 0.5652\n",
      "Epoch 10/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 1.5944 - accuracy: 0.5653 - val_loss: 1.5743 - val_accuracy: 0.5652\n",
      "Epoch 11/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.6062 - accuracy: 0.5341 - val_loss: 1.5425 - val_accuracy: 0.6087\n",
      "Epoch 12/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.5937 - accuracy: 0.5380 - val_loss: 1.5093 - val_accuracy: 0.6087\n",
      "Epoch 13/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 1.5417 - accuracy: 0.5692 - val_loss: 1.4743 - val_accuracy: 0.6087\n",
      "Epoch 14/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.4895 - accuracy: 0.5927 - val_loss: 1.4387 - val_accuracy: 0.6087\n",
      "Epoch 15/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.5143 - accuracy: 0.5575 - val_loss: 1.4122 - val_accuracy: 0.6087\n",
      "Epoch 16/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 1.4554 - accuracy: 0.5810 - val_loss: 1.3832 - val_accuracy: 0.6087\n",
      "Epoch 17/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3689 - accuracy: 0.6122 - val_loss: 1.3520 - val_accuracy: 0.6087\n",
      "Epoch 18/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3965 - accuracy: 0.5732 - val_loss: 1.3104 - val_accuracy: 0.6087\n",
      "Epoch 19/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3966 - accuracy: 0.5732 - val_loss: 1.2731 - val_accuracy: 0.6087\n",
      "Epoch 20/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.3379 - accuracy: 0.5888 - val_loss: 1.2271 - val_accuracy: 0.6522\n",
      "Epoch 21/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3216 - accuracy: 0.5945 - val_loss: 1.1804 - val_accuracy: 0.6522\n",
      "Epoch 22/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3093 - accuracy: 0.6001 - val_loss: 1.1272 - val_accuracy: 0.6522\n",
      "Epoch 23/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.3072 - accuracy: 0.6097 - val_loss: 1.0739 - val_accuracy: 0.6522\n",
      "Epoch 24/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.2408 - accuracy: 0.6445 - val_loss: 1.0239 - val_accuracy: 0.6957\n",
      "Epoch 25/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.2110 - accuracy: 0.6832 - val_loss: 0.9779 - val_accuracy: 0.6957\n",
      "Epoch 26/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.2374 - accuracy: 0.6403 - val_loss: 0.9387 - val_accuracy: 0.7391\n",
      "Epoch 27/150\n",
      "3/3 [==============================] - 0s 27ms/step - loss: 1.2752 - accuracy: 0.6246 - val_loss: 0.9064 - val_accuracy: 0.7826\n",
      "Epoch 28/150\n",
      "3/3 [==============================] - 0s 36ms/step - loss: 1.1854 - accuracy: 0.6325 - val_loss: 0.8812 - val_accuracy: 0.7826\n",
      "Epoch 29/150\n",
      "3/3 [==============================] - 0s 35ms/step - loss: 1.1831 - accuracy: 0.6364 - val_loss: 0.8555 - val_accuracy: 0.7826\n",
      "Epoch 30/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.1050 - accuracy: 0.6598 - val_loss: 0.8302 - val_accuracy: 0.7826\n",
      "Epoch 31/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.1317 - accuracy: 0.6598 - val_loss: 0.8072 - val_accuracy: 0.7826\n",
      "Epoch 32/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 1.1828 - accuracy: 0.6207 - val_loss: 0.7842 - val_accuracy: 0.7826\n",
      "Epoch 33/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.1022 - accuracy: 0.6481 - val_loss: 0.7630 - val_accuracy: 0.7826\n",
      "Epoch 34/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 1.1154 - accuracy: 0.6286 - val_loss: 0.7429 - val_accuracy: 0.7826\n",
      "Epoch 35/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.1221 - accuracy: 0.6207 - val_loss: 0.7228 - val_accuracy: 0.8261\n",
      "Epoch 36/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.0771 - accuracy: 0.6325 - val_loss: 0.7031 - val_accuracy: 0.8261\n",
      "Epoch 37/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.0276 - accuracy: 0.6637 - val_loss: 0.6827 - val_accuracy: 0.8261\n",
      "Epoch 38/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.0366 - accuracy: 0.6403 - val_loss: 0.6644 - val_accuracy: 0.8261\n",
      "Epoch 39/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 1.0550 - accuracy: 0.6129 - val_loss: 0.6485 - val_accuracy: 0.8261\n",
      "Epoch 40/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.9918 - accuracy: 0.6520 - val_loss: 0.6334 - val_accuracy: 0.8261\n",
      "Epoch 41/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.9494 - accuracy: 0.6715 - val_loss: 0.6208 - val_accuracy: 0.8261\n",
      "Epoch 42/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.9255 - accuracy: 0.6559 - val_loss: 0.6084 - val_accuracy: 0.8261\n",
      "Epoch 43/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.9297 - accuracy: 0.6598 - val_loss: 0.5967 - val_accuracy: 0.8261\n",
      "Epoch 44/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.9240 - accuracy: 0.6481 - val_loss: 0.5862 - val_accuracy: 0.8261\n",
      "Epoch 45/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.8675 - accuracy: 0.6754 - val_loss: 0.5760 - val_accuracy: 0.8261\n",
      "Epoch 46/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.9025 - accuracy: 0.6559 - val_loss: 0.5659 - val_accuracy: 0.8261\n",
      "Epoch 47/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.9039 - accuracy: 0.6538 - val_loss: 0.5561 - val_accuracy: 0.8261\n",
      "Epoch 48/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.9491 - accuracy: 0.6321 - val_loss: 0.5476 - val_accuracy: 0.8261\n",
      "Epoch 49/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.8161 - accuracy: 0.7216 - val_loss: 0.5379 - val_accuracy: 0.8261\n",
      "Epoch 50/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.8343 - accuracy: 0.7230 - val_loss: 0.5285 - val_accuracy: 0.8261\n",
      "Epoch 51/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.8451 - accuracy: 0.7074 - val_loss: 0.5201 - val_accuracy: 0.8696\n",
      "Epoch 52/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.8217 - accuracy: 0.7152 - val_loss: 0.5116 - val_accuracy: 0.8696\n",
      "Epoch 53/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.8251 - accuracy: 0.7347 - val_loss: 0.5050 - val_accuracy: 0.8696\n",
      "Epoch 54/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7874 - accuracy: 0.7113 - val_loss: 0.4992 - val_accuracy: 0.8696\n",
      "Epoch 55/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.7386 - accuracy: 0.7212 - val_loss: 0.4920 - val_accuracy: 0.8696\n",
      "Epoch 56/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7630 - accuracy: 0.7134 - val_loss: 0.4862 - val_accuracy: 0.8696\n",
      "Epoch 57/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7476 - accuracy: 0.7134 - val_loss: 0.4811 - val_accuracy: 0.8696\n",
      "Epoch 58/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7289 - accuracy: 0.7017 - val_loss: 0.4762 - val_accuracy: 0.8696\n",
      "Epoch 59/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7496 - accuracy: 0.7017 - val_loss: 0.4723 - val_accuracy: 0.8696\n",
      "Epoch 60/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.7583 - accuracy: 0.6744 - val_loss: 0.4665 - val_accuracy: 0.8696\n",
      "Epoch 61/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.6584 - accuracy: 0.7251 - val_loss: 0.4615 - val_accuracy: 0.8696\n",
      "Epoch 62/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.6657 - accuracy: 0.7447 - val_loss: 0.4573 - val_accuracy: 0.8696\n",
      "Epoch 63/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.6580 - accuracy: 0.7273 - val_loss: 0.4547 - val_accuracy: 0.8696\n",
      "Epoch 64/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.7337 - accuracy: 0.6822 - val_loss: 0.4547 - val_accuracy: 0.8696\n",
      "Epoch 65/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.6358 - accuracy: 0.7408 - val_loss: 0.4525 - val_accuracy: 0.8696\n",
      "Epoch 66/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.6928 - accuracy: 0.6900 - val_loss: 0.4504 - val_accuracy: 0.8696\n",
      "Epoch 67/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.6571 - accuracy: 0.6939 - val_loss: 0.4455 - val_accuracy: 0.8696\n",
      "Epoch 68/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.6346 - accuracy: 0.6921 - val_loss: 0.4425 - val_accuracy: 0.8696\n",
      "Epoch 69/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.6756 - accuracy: 0.6804 - val_loss: 0.4395 - val_accuracy: 0.8696\n",
      "Epoch 70/150\n",
      "3/3 [==============================] - 0s 27ms/step - loss: 0.6725 - accuracy: 0.6999 - val_loss: 0.4368 - val_accuracy: 0.8261\n",
      "Epoch 71/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5784 - accuracy: 0.7290 - val_loss: 0.4356 - val_accuracy: 0.8261\n",
      "Epoch 72/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.6273 - accuracy: 0.7134 - val_loss: 0.4367 - val_accuracy: 0.8261\n",
      "Epoch 73/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.6459 - accuracy: 0.6978 - val_loss: 0.4322 - val_accuracy: 0.8261\n",
      "Epoch 74/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.6008 - accuracy: 0.7134 - val_loss: 0.4309 - val_accuracy: 0.8261\n",
      "Epoch 75/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5849 - accuracy: 0.7290 - val_loss: 0.4287 - val_accuracy: 0.8261\n",
      "Epoch 76/150\n",
      "3/3 [==============================] - 0s 27ms/step - loss: 0.5686 - accuracy: 0.7251 - val_loss: 0.4252 - val_accuracy: 0.8261\n",
      "Epoch 77/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5995 - accuracy: 0.6999 - val_loss: 0.4231 - val_accuracy: 0.8261\n",
      "Epoch 78/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5587 - accuracy: 0.7390 - val_loss: 0.4227 - val_accuracy: 0.8261\n",
      "Epoch 79/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5477 - accuracy: 0.7369 - val_loss: 0.4242 - val_accuracy: 0.8261\n",
      "Epoch 80/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5760 - accuracy: 0.7134 - val_loss: 0.4211 - val_accuracy: 0.8261\n",
      "Epoch 81/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5272 - accuracy: 0.7525 - val_loss: 0.4159 - val_accuracy: 0.8261\n",
      "Epoch 82/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5729 - accuracy: 0.7116 - val_loss: 0.4155 - val_accuracy: 0.8261\n",
      "Epoch 83/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5960 - accuracy: 0.6843 - val_loss: 0.4176 - val_accuracy: 0.8261\n",
      "Epoch 84/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5648 - accuracy: 0.7056 - val_loss: 0.4182 - val_accuracy: 0.8261\n",
      "Epoch 85/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5764 - accuracy: 0.7173 - val_loss: 0.4149 - val_accuracy: 0.8261\n",
      "Epoch 86/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5526 - accuracy: 0.7290 - val_loss: 0.4154 - val_accuracy: 0.8261\n",
      "Epoch 87/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5129 - accuracy: 0.7290 - val_loss: 0.4108 - val_accuracy: 0.8261\n",
      "Epoch 88/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5389 - accuracy: 0.7330 - val_loss: 0.4076 - val_accuracy: 0.8261\n",
      "Epoch 89/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5952 - accuracy: 0.6687 - val_loss: 0.4087 - val_accuracy: 0.8261\n",
      "Epoch 90/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5334 - accuracy: 0.7212 - val_loss: 0.4089 - val_accuracy: 0.8261\n",
      "Epoch 91/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5805 - accuracy: 0.6900 - val_loss: 0.4096 - val_accuracy: 0.8261\n",
      "Epoch 92/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5783 - accuracy: 0.6900 - val_loss: 0.4089 - val_accuracy: 0.8261\n",
      "Epoch 93/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5163 - accuracy: 0.7251 - val_loss: 0.4064 - val_accuracy: 0.8261\n",
      "Epoch 94/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5467 - accuracy: 0.7095 - val_loss: 0.4053 - val_accuracy: 0.8261\n",
      "Epoch 95/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5407 - accuracy: 0.7195 - val_loss: 0.4039 - val_accuracy: 0.8261\n",
      "Epoch 96/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5334 - accuracy: 0.7212 - val_loss: 0.4023 - val_accuracy: 0.8261\n",
      "Epoch 97/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5176 - accuracy: 0.6978 - val_loss: 0.4035 - val_accuracy: 0.8261\n",
      "Epoch 98/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4886 - accuracy: 0.7290 - val_loss: 0.4034 - val_accuracy: 0.8261\n",
      "Epoch 99/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5075 - accuracy: 0.7134 - val_loss: 0.4016 - val_accuracy: 0.8261\n",
      "Epoch 100/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5457 - accuracy: 0.6978 - val_loss: 0.4027 - val_accuracy: 0.8261\n",
      "Epoch 101/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4927 - accuracy: 0.7056 - val_loss: 0.4017 - val_accuracy: 0.8261\n",
      "Epoch 102/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4497 - accuracy: 0.7564 - val_loss: 0.3985 - val_accuracy: 0.8261\n",
      "Epoch 103/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5330 - accuracy: 0.7056 - val_loss: 0.3963 - val_accuracy: 0.8261\n",
      "Epoch 104/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.5126 - accuracy: 0.7212 - val_loss: 0.3957 - val_accuracy: 0.8261\n",
      "Epoch 105/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.5225 - accuracy: 0.7290 - val_loss: 0.3937 - val_accuracy: 0.8261\n",
      "Epoch 106/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4832 - accuracy: 0.7369 - val_loss: 0.3958 - val_accuracy: 0.8261\n",
      "Epoch 107/150\n",
      "3/3 [==============================] - 0s 34ms/step - loss: 0.5039 - accuracy: 0.7230 - val_loss: 0.3969 - val_accuracy: 0.8261\n",
      "Epoch 108/150\n",
      "3/3 [==============================] - 0s 38ms/step - loss: 0.4473 - accuracy: 0.7678 - val_loss: 0.3988 - val_accuracy: 0.8261\n",
      "Epoch 109/150\n",
      "3/3 [==============================] - 0s 35ms/step - loss: 0.4991 - accuracy: 0.7521 - val_loss: 0.3989 - val_accuracy: 0.8261\n",
      "Epoch 110/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.5097 - accuracy: 0.7344 - val_loss: 0.3989 - val_accuracy: 0.8261\n",
      "Epoch 111/150\n",
      "3/3 [==============================] - 0s 36ms/step - loss: 0.4978 - accuracy: 0.7557 - val_loss: 0.3961 - val_accuracy: 0.8261\n",
      "Epoch 112/150\n",
      "3/3 [==============================] - 0s 31ms/step - loss: 0.5077 - accuracy: 0.7752 - val_loss: 0.3935 - val_accuracy: 0.8261\n",
      "Epoch 113/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4963 - accuracy: 0.7440 - val_loss: 0.3934 - val_accuracy: 0.8261\n",
      "Epoch 114/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4884 - accuracy: 0.7809 - val_loss: 0.3949 - val_accuracy: 0.8261\n",
      "Epoch 115/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4310 - accuracy: 0.8004 - val_loss: 0.3967 - val_accuracy: 0.8261\n",
      "Epoch 116/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4284 - accuracy: 0.8100 - val_loss: 0.3947 - val_accuracy: 0.8261\n",
      "Epoch 117/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4633 - accuracy: 0.7848 - val_loss: 0.3901 - val_accuracy: 0.8261\n",
      "Epoch 118/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4482 - accuracy: 0.7944 - val_loss: 0.3897 - val_accuracy: 0.8261\n",
      "Epoch 119/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4790 - accuracy: 0.7766 - val_loss: 0.3877 - val_accuracy: 0.8261\n",
      "Epoch 120/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4013 - accuracy: 0.8335 - val_loss: 0.3853 - val_accuracy: 0.8261\n",
      "Epoch 121/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4714 - accuracy: 0.7866 - val_loss: 0.3855 - val_accuracy: 0.8261\n",
      "Epoch 122/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4510 - accuracy: 0.7905 - val_loss: 0.3879 - val_accuracy: 0.8261\n",
      "Epoch 123/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4869 - accuracy: 0.7802 - val_loss: 0.3897 - val_accuracy: 0.8261\n",
      "Epoch 124/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4070 - accuracy: 0.8505 - val_loss: 0.3865 - val_accuracy: 0.8261\n",
      "Epoch 125/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4054 - accuracy: 0.8487 - val_loss: 0.3839 - val_accuracy: 0.8261\n",
      "Epoch 126/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4404 - accuracy: 0.8214 - val_loss: 0.3808 - val_accuracy: 0.8261\n",
      "Epoch 127/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4234 - accuracy: 0.8288 - val_loss: 0.3797 - val_accuracy: 0.8261\n",
      "Epoch 128/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.4311 - accuracy: 0.8288 - val_loss: 0.3787 - val_accuracy: 0.8261\n",
      "Epoch 129/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.4231 - accuracy: 0.8054 - val_loss: 0.3820 - val_accuracy: 0.8261\n",
      "Epoch 130/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4192 - accuracy: 0.8366 - val_loss: 0.3827 - val_accuracy: 0.8261\n",
      "Epoch 131/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4529 - accuracy: 0.8327 - val_loss: 0.3814 - val_accuracy: 0.8261\n",
      "Epoch 132/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4006 - accuracy: 0.8384 - val_loss: 0.3814 - val_accuracy: 0.8696\n",
      "Epoch 133/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4320 - accuracy: 0.8384 - val_loss: 0.3789 - val_accuracy: 0.8696\n",
      "Epoch 134/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3808 - accuracy: 0.8793 - val_loss: 0.3772 - val_accuracy: 0.8696\n",
      "Epoch 135/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4560 - accuracy: 0.8267 - val_loss: 0.3790 - val_accuracy: 0.8696\n",
      "Epoch 136/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4409 - accuracy: 0.8189 - val_loss: 0.3791 - val_accuracy: 0.8696\n",
      "Epoch 137/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4109 - accuracy: 0.8210 - val_loss: 0.3784 - val_accuracy: 0.8696\n",
      "Epoch 138/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4194 - accuracy: 0.8423 - val_loss: 0.3752 - val_accuracy: 0.8696\n",
      "Epoch 139/150\n",
      "3/3 [==============================] - 0s 31ms/step - loss: 0.3819 - accuracy: 0.8210 - val_loss: 0.3717 - val_accuracy: 0.8696\n",
      "Epoch 140/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4391 - accuracy: 0.8171 - val_loss: 0.3686 - val_accuracy: 0.8696\n",
      "Epoch 141/150\n",
      "3/3 [==============================] - 0s 28ms/step - loss: 0.3532 - accuracy: 0.8658 - val_loss: 0.3669 - val_accuracy: 0.8696\n",
      "Epoch 142/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.4009 - accuracy: 0.8423 - val_loss: 0.3687 - val_accuracy: 0.8696\n",
      "Epoch 143/150\n",
      "3/3 [==============================] - 0s 30ms/step - loss: 0.3954 - accuracy: 0.8480 - val_loss: 0.3695 - val_accuracy: 0.8696\n",
      "Epoch 144/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3742 - accuracy: 0.8384 - val_loss: 0.3710 - val_accuracy: 0.8696\n",
      "Epoch 145/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3953 - accuracy: 0.8384 - val_loss: 0.3729 - val_accuracy: 0.8696\n",
      "Epoch 146/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.4067 - accuracy: 0.8228 - val_loss: 0.3699 - val_accuracy: 0.8696\n",
      "Epoch 147/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3375 - accuracy: 0.8754 - val_loss: 0.3715 - val_accuracy: 0.8696\n",
      "Epoch 148/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3640 - accuracy: 0.8459 - val_loss: 0.3732 - val_accuracy: 0.8696\n",
      "Epoch 149/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3408 - accuracy: 0.8888 - val_loss: 0.3776 - val_accuracy: 0.8261\n",
      "Epoch 150/150\n",
      "3/3 [==============================] - 0s 29ms/step - loss: 0.3552 - accuracy: 0.8636 - val_loss: 0.3821 - val_accuracy: 0.8261\n"
     ]
    }
   ],
   "source": [
    "inputs = tf.keras.Input(shape = (6, ))\n",
    "x = tf.keras.layers.Dense(64, activation = 'relu')(inputs)\n",
    "x = tf.keras.layers.Dense(16, activation = 'relu')(x)\n",
    "x = tf.keras.layers.Dense(16, activation = 'relu')(x)\n",
    "outputs = tf.keras.layers.Dense(7, activation = 'softmax')(x)\n",
    "\n",
    "model = tf.keras.Model(inputs, outputs)\n",
    "\n",
    "model.compile(\n",
    "    optimizer = 'adam',\n",
    "    loss = 'sparse_categorical_crossentropy',\n",
    "    metrics = ['accuracy']\n",
    ")\n",
    "\n",
    "batch_size = 32\n",
    "epochs = 150\n",
    "\n",
    "history = model.fit(\n",
    "    X_train,\n",
    "    y_train,\n",
    "    validation_split = 0.2,\n",
    "    batch_size = batch_size,\n",
    "    epochs = epochs\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "younger-dressing",
   "metadata": {
    "papermill": {
     "duration": 0.116329,
     "end_time": "2021-07-02T05:42:39.761673",
     "exception": false,
     "start_time": "2021-07-02T05:42:39.645344",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Loss Graph 📈"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "simple-dinner",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:40.060191Z",
     "iopub.status.busy": "2021-07-02T05:42:40.059512Z",
     "iopub.status.idle": "2021-07-02T05:42:40.228514Z",
     "shell.execute_reply": "2021-07-02T05:42:40.227872Z",
     "shell.execute_reply.started": "2021-07-02T05:30:59.837678Z"
    },
    "papermill": {
     "duration": 0.352197,
     "end_time": "2021-07-02T05:42:40.228707",
     "exception": false,
     "start_time": "2021-07-02T05:42:39.876510",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (14, 10))\n",
    "\n",
    "epochs_range = range(1, epochs + 1)\n",
    "train_loss = history.history['loss']\n",
    "val_loss = history.history['val_loss']\n",
    "\n",
    "plt.plot(epochs_range, train_loss, label = 'Training_loss')\n",
    "plt.plot(epochs_range, val_loss, label = 'Validation_loss')\n",
    "\n",
    "plt.xlabel('Epochs')\n",
    "plt.ylabel('Loss')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "suburban-latex",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:40.466436Z",
     "iopub.status.busy": "2021-07-02T05:42:40.465555Z",
     "iopub.status.idle": "2021-07-02T05:42:40.469185Z",
     "shell.execute_reply": "2021-07-02T05:42:40.469647Z",
     "shell.execute_reply.started": "2021-07-02T05:30:29.898799Z"
    },
    "papermill": {
     "duration": 0.125378,
     "end_time": "2021-07-02T05:42:40.469826",
     "exception": false,
     "start_time": "2021-07-02T05:42:40.344448",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "140"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.argmin(val_loss)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "chinese-people",
   "metadata": {
    "papermill": {
     "duration": 0.115593,
     "end_time": "2021-07-02T05:42:40.701362",
     "exception": false,
     "start_time": "2021-07-02T05:42:40.585769",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Neural Network Score 🎯"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "personalized-diving",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-07-02T05:42:40.940732Z",
     "iopub.status.busy": "2021-07-02T05:42:40.939751Z",
     "iopub.status.idle": "2021-07-02T05:42:40.999234Z",
     "shell.execute_reply": "2021-07-02T05:42:40.998549Z",
     "shell.execute_reply.started": "2021-07-02T05:31:04.277299Z"
    },
    "papermill": {
     "duration": 0.181937,
     "end_time": "2021-07-02T05:42:40.999409",
     "exception": false,
     "start_time": "2021-07-02T05:42:40.817472",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2/2 [==============================] - 0s 2ms/step - loss: 0.2812 - accuracy: 0.8542\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.28119513392448425, 0.8541666865348816]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.evaluate(X_test, y_test)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.10"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 31.862623,
   "end_time": "2021-07-02T05:42:43.208769",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2021-07-02T05:42:11.346146",
   "version": "2.3.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}