backpropagation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.optim as optim\n",
    "from torch.utils.data import DataLoader, TensorDataset\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix, recall_score\n",
    "import optuna\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df = pd.read_csv('./datasets/diabetes.csv')\n",
    "diabetes_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 768 entries, 0 to 767\n",
      "Data columns (total 9 columns):\n",
      " #   Column                    Non-Null Count  Dtype  \n",
      "---  ------                    --------------  -----  \n",
      " 0   Pregnancies               768 non-null    int64  \n",
      " 1   Glucose                   768 non-null    int64  \n",
      " 2   BloodPressure             768 non-null    int64  \n",
      " 3   SkinThickness             768 non-null    int64  \n",
      " 4   Insulin                   768 non-null    int64  \n",
      " 5   BMI                       768 non-null    float64\n",
      " 6   DiabetesPedigreeFunction  768 non-null    float64\n",
      " 7   Age                       768 non-null    int64  \n",
      " 8   Outcome                   768 non-null    int64  \n",
      "dtypes: float64(2), int64(7)\n",
      "memory usage: 54.1 KB\n"
     ]
    }
   ],
   "source": [
    "diabetes_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pregnancies                 0\n",
       "Glucose                     0\n",
       "BloodPressure               0\n",
       "SkinThickness               0\n",
       "Insulin                     0\n",
       "BMI                         0\n",
       "DiabetesPedigreeFunction    0\n",
       "Age                         0\n",
       "Outcome                     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.845052</td>\n",
       "      <td>120.894531</td>\n",
       "      <td>69.105469</td>\n",
       "      <td>20.536458</td>\n",
       "      <td>79.799479</td>\n",
       "      <td>31.992578</td>\n",
       "      <td>0.471876</td>\n",
       "      <td>33.240885</td>\n",
       "      <td>0.348958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.369578</td>\n",
       "      <td>31.972618</td>\n",
       "      <td>19.355807</td>\n",
       "      <td>15.952218</td>\n",
       "      <td>115.244002</td>\n",
       "      <td>7.884160</td>\n",
       "      <td>0.331329</td>\n",
       "      <td>11.760232</td>\n",
       "      <td>0.476951</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>0.078000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27.300000</td>\n",
       "      <td>0.243750</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>117.000000</td>\n",
       "      <td>72.000000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>30.500000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>0.372500</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>140.250000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>127.250000</td>\n",
       "      <td>36.600000</td>\n",
       "      <td>0.626250</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.000000</td>\n",
       "      <td>199.000000</td>\n",
       "      <td>122.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>846.000000</td>\n",
       "      <td>67.100000</td>\n",
       "      <td>2.420000</td>\n",
       "      <td>81.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Pregnancies     Glucose  BloodPressure  SkinThickness     Insulin  \\\n",
       "count   768.000000  768.000000     768.000000     768.000000  768.000000   \n",
       "mean      3.845052  120.894531      69.105469      20.536458   79.799479   \n",
       "std       3.369578   31.972618      19.355807      15.952218  115.244002   \n",
       "min       0.000000    0.000000       0.000000       0.000000    0.000000   \n",
       "25%       1.000000   99.000000      62.000000       0.000000    0.000000   \n",
       "50%       3.000000  117.000000      72.000000      23.000000   30.500000   \n",
       "75%       6.000000  140.250000      80.000000      32.000000  127.250000   \n",
       "max      17.000000  199.000000     122.000000      99.000000  846.000000   \n",
       "\n",
       "              BMI  DiabetesPedigreeFunction         Age     Outcome  \n",
       "count  768.000000                768.000000  768.000000  768.000000  \n",
       "mean    31.992578                  0.471876   33.240885    0.348958  \n",
       "std      7.884160                  0.331329   11.760232    0.476951  \n",
       "min      0.000000                  0.078000   21.000000    0.000000  \n",
       "25%     27.300000                  0.243750   24.000000    0.000000  \n",
       "50%     32.000000                  0.372500   29.000000    0.000000  \n",
       "75%     36.600000                  0.626250   41.000000    1.000000  \n",
       "max     67.100000                  2.420000   81.000000    1.000000  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Pregnancies</th>\n",
       "      <td>768.0</td>\n",
       "      <td>3.845052</td>\n",
       "      <td>3.369578</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>3.0000</td>\n",
       "      <td>6.00000</td>\n",
       "      <td>17.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Glucose</th>\n",
       "      <td>768.0</td>\n",
       "      <td>120.894531</td>\n",
       "      <td>31.972618</td>\n",
       "      <td>0.000</td>\n",
       "      <td>99.00000</td>\n",
       "      <td>117.0000</td>\n",
       "      <td>140.25000</td>\n",
       "      <td>199.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BloodPressure</th>\n",
       "      <td>768.0</td>\n",
       "      <td>69.105469</td>\n",
       "      <td>19.355807</td>\n",
       "      <td>0.000</td>\n",
       "      <td>62.00000</td>\n",
       "      <td>72.0000</td>\n",
       "      <td>80.00000</td>\n",
       "      <td>122.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SkinThickness</th>\n",
       "      <td>768.0</td>\n",
       "      <td>20.536458</td>\n",
       "      <td>15.952218</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>23.0000</td>\n",
       "      <td>32.00000</td>\n",
       "      <td>99.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Insulin</th>\n",
       "      <td>768.0</td>\n",
       "      <td>79.799479</td>\n",
       "      <td>115.244002</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>30.5000</td>\n",
       "      <td>127.25000</td>\n",
       "      <td>846.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BMI</th>\n",
       "      <td>768.0</td>\n",
       "      <td>31.992578</td>\n",
       "      <td>7.884160</td>\n",
       "      <td>0.000</td>\n",
       "      <td>27.30000</td>\n",
       "      <td>32.0000</td>\n",
       "      <td>36.60000</td>\n",
       "      <td>67.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <td>768.0</td>\n",
       "      <td>0.471876</td>\n",
       "      <td>0.331329</td>\n",
       "      <td>0.078</td>\n",
       "      <td>0.24375</td>\n",
       "      <td>0.3725</td>\n",
       "      <td>0.62625</td>\n",
       "      <td>2.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>768.0</td>\n",
       "      <td>33.240885</td>\n",
       "      <td>11.760232</td>\n",
       "      <td>21.000</td>\n",
       "      <td>24.00000</td>\n",
       "      <td>29.0000</td>\n",
       "      <td>41.00000</td>\n",
       "      <td>81.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Outcome</th>\n",
       "      <td>768.0</td>\n",
       "      <td>0.348958</td>\n",
       "      <td>0.476951</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          count        mean         std     min       25%  \\\n",
       "Pregnancies               768.0    3.845052    3.369578   0.000   1.00000   \n",
       "Glucose                   768.0  120.894531   31.972618   0.000  99.00000   \n",
       "BloodPressure             768.0   69.105469   19.355807   0.000  62.00000   \n",
       "SkinThickness             768.0   20.536458   15.952218   0.000   0.00000   \n",
       "Insulin                   768.0   79.799479  115.244002   0.000   0.00000   \n",
       "BMI                       768.0   31.992578    7.884160   0.000  27.30000   \n",
       "DiabetesPedigreeFunction  768.0    0.471876    0.331329   0.078   0.24375   \n",
       "Age                       768.0   33.240885   11.760232  21.000  24.00000   \n",
       "Outcome                   768.0    0.348958    0.476951   0.000   0.00000   \n",
       "\n",
       "                               50%        75%     max  \n",
       "Pregnancies                 3.0000    6.00000   17.00  \n",
       "Glucose                   117.0000  140.25000  199.00  \n",
       "BloodPressure              72.0000   80.00000  122.00  \n",
       "SkinThickness              23.0000   32.00000   99.00  \n",
       "Insulin                    30.5000  127.25000  846.00  \n",
       "BMI                        32.0000   36.60000   67.10  \n",
       "DiabetesPedigreeFunction    0.3725    0.62625    2.42  \n",
       "Age                        29.0000   41.00000   81.00  \n",
       "Outcome                     0.0000    1.00000    1.00  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin    BMI  \\\n",
       "0        False    False          False          False    False  False   \n",
       "1        False    False          False          False    False  False   \n",
       "2        False    False          False          False    False  False   \n",
       "3        False    False          False          False    False  False   \n",
       "4        False    False          False          False    False  False   \n",
       "5        False    False          False          False    False  False   \n",
       "6        False    False          False          False    False  False   \n",
       "7        False    False          False          False    False  False   \n",
       "8        False    False          False          False    False  False   \n",
       "9        False    False          False          False    False  False   \n",
       "\n",
       "   DiabetesPedigreeFunction    Age  Outcome  \n",
       "0                     False  False    False  \n",
       "1                     False  False    False  \n",
       "2                     False  False    False  \n",
       "3                     False  False    False  \n",
       "4                     False  False    False  \n",
       "5                     False  False    False  \n",
       "6                     False  False    False  \n",
       "7                     False  False    False  \n",
       "8                     False  False    False  \n",
       "9                     False  False    False  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df.isnull().head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "diabetes_df_copy = diabetes_df.copy(deep = True)\n",
    "diabetes_df_copy[\n",
    "    ['Glucose',\n",
    "     'BloodPressure',\n",
    "     'SkinThickness',\n",
    "     'Insulin',\n",
    "     'BMI']] = diabetes_df_copy[\n",
    "        ['Glucose',\n",
    "         'BloodPressure',\n",
    "         'SkinThickness',\n",
    "         'Insulin',\n",
    "         'BMI']].replace(0,np.NaN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pregnancies                   0\n",
      "Glucose                       5\n",
      "BloodPressure                35\n",
      "SkinThickness               227\n",
      "Insulin                     374\n",
      "BMI                          11\n",
      "DiabetesPedigreeFunction      0\n",
      "Age                           0\n",
      "Outcome                       0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(diabetes_df_copy.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x2000 with 9 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "p = diabetes_df.hist(figsize = (20,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "diabetes_df_copy['Glucose'].fillna(diabetes_df_copy['Glucose'].mean(), inplace = True)\n",
    "diabetes_df_copy['BloodPressure'].fillna(diabetes_df_copy['BloodPressure'].mean(), inplace = True)\n",
    "diabetes_df_copy['SkinThickness'].fillna(diabetes_df_copy['SkinThickness'].median(), inplace = True)\n",
    "diabetes_df_copy['Insulin'].fillna(diabetes_df_copy['Insulin'].median(), inplace = True)\n",
    "diabetes_df_copy['BMI'].fillna(diabetes_df_copy['BMI'].median(), inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x2000 with 9 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "p = diabetes_df_copy.hist(figsize = (20,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Outcome\n",
      "0    500\n",
      "1    268\n",
      "Name: count, dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "color_wheel = {1: \"#0392cf\", 2: \"#7bc043\"}\n",
    "colors = diabetes_df[\"Outcome\"].map(lambda x: color_wheel.get(x + 1))\n",
    "print(diabetes_df.Outcome.value_counts())\n",
    "p=diabetes_df.Outcome.value_counts().plot(kind=\"bar\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\1587213579.py:1: UserWarning: \n",
      "\n",
      "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
      "\n",
      "Please adapt your code to use either `displot` (a figure-level function with\n",
      "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "\n",
      "For a guide to updating your code to use the new functions, please see\n",
      "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
      "\n",
      "  plt.subplot(121), sns.distplot(diabetes_df['Insulin'])\n",
      "c:\\Users\\Hammam\\Lib\\site-packages\\seaborn\\_oldcore.py:1498: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
      "  if pd.api.types.is_categorical_dtype(vector):\n",
      "c:\\Users\\Hammam\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n",
      "  with pd.option_context('mode.use_inf_as_na', True):\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.subplot(121), sns.distplot(diabetes_df['Insulin'])\n",
    "plt.subplot(122), diabetes_df['Insulin'].plot.box(figsize=(16,5))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,10))\n",
    "p = sns.heatmap(diabetes_df.corr(), annot=True,cmap ='RdYlGn')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>94.0</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>168.0</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6    148.0           72.0           35.0    125.0  33.6   \n",
       "1            1     85.0           66.0           29.0    125.0  26.6   \n",
       "2            8    183.0           64.0           29.0    125.0  23.3   \n",
       "3            1     89.0           66.0           23.0     94.0  28.1   \n",
       "4            0    137.0           40.0           35.0    168.0  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df_copy.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = diabetes_df_copy.drop(columns=['Outcome']).values\n",
    "y = diabetes_df_copy['Outcome'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert data to PyTorch tensors\n",
    "X_train = torch.FloatTensor(X_train)\n",
    "y_train = torch.LongTensor(y_train)\n",
    "X_test = torch.FloatTensor(X_test)\n",
    "y_test = torch.LongTensor(y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Build Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "class DiabetesModel(nn.Module):\n",
    "    def __init__(self, input_size, hidden_size, output_size):\n",
    "        super(DiabetesModel, self).__init__()\n",
    "        self.fc1 = nn.Linear(input_size, hidden_size)\n",
    "        self.relu = nn.ReLU()\n",
    "        self.fc2 = nn.Linear(hidden_size, output_size)\n",
    "        self.sigmoid = nn.Sigmoid()\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.fc1(x)\n",
    "        x = self.relu(x)\n",
    "        x = self.fc2(x)\n",
    "        x = self.sigmoid(x)\n",
    "        return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def train(model, train_loader, optimizer, criterion):\n",
    "    model.train()\n",
    "    running_loss = 0.0\n",
    "    for inputs, labels in train_loader:\n",
    "        optimizer.zero_grad()\n",
    "        outputs = model(inputs)\n",
    "        loss = criterion(outputs, labels.float().view(-1, 1))\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        running_loss += loss.item()\n",
    "    return running_loss / len(train_loader)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "def evaluate(model, data_loader, criterion, metric_fn):\n",
    "    model.eval()\n",
    "    running_loss = 0.0\n",
    "    running_metric = 0.0\n",
    "    all_predictions = []\n",
    "    all_labels = []\n",
    "    with torch.no_grad():\n",
    "        for inputs, labels in data_loader:\n",
    "            outputs = model(inputs)\n",
    "            loss = criterion(outputs, labels.float().view(-1, 1))\n",
    "            running_loss += loss.item()\n",
    "            predictions = (outputs >= 0.5).float()\n",
    "            metric = metric_fn(predictions, labels)\n",
    "            running_metric += metric\n",
    "            all_predictions.extend(predictions.cpu().numpy())\n",
    "            all_labels.extend(labels.cpu().numpy())\n",
    "    return running_loss / len(data_loader), running_metric / len(data_loader), all_predictions, all_labels"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_dataset = TensorDataset(X_test, y_test)\n",
    "test_loader = DataLoader(test_dataset, batch_size=32)\n",
    "\n",
    "# Define a function to create and train the model with hyperparameters\n",
    "def objective(trial):\n",
    "    input_size = X_train.shape[1]\n",
    "    hidden_size = trial.suggest_int('hidden_size', 16, 128)\n",
    "    output_size = 1\n",
    "    lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
    "\n",
    "    model = DiabetesModel(input_size, hidden_size, output_size)\n",
    "    optimizer = optim.Adam(model.parameters(), lr=lr)\n",
    "    criterion = nn.BCELoss()  # Binary Cross-Entropy Loss\n",
    "\n",
    "    train_dataset = TensorDataset(X_train, y_train)\n",
    "    train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
    "\n",
    "    num_epochs = 100\n",
    "    best_accuracy = 0.0\n",
    "\n",
    "    for epoch in tqdm(range(num_epochs)):\n",
    "        train_loss = train(model, train_loader, optimizer, criterion)\n",
    "\n",
    "        _, accuracy, _, _ = evaluate(model, train_loader, criterion, accuracy_score)\n",
    "\n",
    "        if accuracy > best_accuracy:\n",
    "            best_accuracy = accuracy\n",
    "\n",
    "    _, test_accuracy, test_predictions, test_labels = evaluate(model, test_loader, criterion, accuracy_score)\n",
    "    recall = recall_score(test_labels, test_predictions)\n",
    "\n",
    "    return -test_accuracy  # Negative because Optuna aims to minimize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[I 2023-10-19 12:02:19,359] A new study created in memory with name: no-name-faa1cd4d-30e0-4437-8554-b99d395a04ec\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.91it/s]\n",
      "[I 2023-10-19 12:02:35,106] Trial 0 finished with value: -0.6495192307692308 and parameters: {'hidden_size': 103, 'lr': 0.0008786759209658257}. Best is trial 0 with value: -0.6495192307692308.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.25it/s]\n",
      "[I 2023-10-19 12:02:48,937] Trial 1 finished with value: -0.7038461538461538 and parameters: {'hidden_size': 118, 'lr': 0.0005331062619586419}. Best is trial 1 with value: -0.7038461538461538.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.07it/s]\n",
      "[I 2023-10-19 12:03:03,111] Trial 2 finished with value: -0.7009615384615385 and parameters: {'hidden_size': 59, 'lr': 0.0010646151377251044}. Best is trial 1 with value: -0.7038461538461538.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.28it/s]\n",
      "[I 2023-10-19 12:03:16,891] Trial 3 finished with value: -0.7149038461538462 and parameters: {'hidden_size': 73, 'lr': 0.0022956671561660032}. Best is trial 3 with value: -0.7149038461538462.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.03it/s]\n",
      "[I 2023-10-19 12:03:31,150] Trial 4 finished with value: -0.7677884615384615 and parameters: {'hidden_size': 43, 'lr': 0.0004003459805212366}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.50it/s]\n",
      "[I 2023-10-19 12:03:44,540] Trial 5 finished with value: -0.7615384615384615 and parameters: {'hidden_size': 109, 'lr': 0.00793044556674096}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.59it/s]\n",
      "[I 2023-10-19 12:03:59,752] Trial 6 finished with value: -0.6774038461538462 and parameters: {'hidden_size': 66, 'lr': 0.0033211724415576427}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.39it/s]\n",
      "[I 2023-10-19 12:04:13,324] Trial 7 finished with value: -0.7274038461538461 and parameters: {'hidden_size': 93, 'lr': 0.002274738094190658}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.46it/s]\n",
      "[I 2023-10-19 12:04:26,755] Trial 8 finished with value: -0.6947115384615385 and parameters: {'hidden_size': 26, 'lr': 0.00082727181271812}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.31it/s]\n",
      "[I 2023-10-19 12:04:42,649] Trial 9 finished with value: -0.7100961538461539 and parameters: {'hidden_size': 122, 'lr': 0.004554698971265675}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.40it/s]\n",
      "[I 2023-10-19 12:04:58,335] Trial 10 finished with value: -0.7043269230769231 and parameters: {'hidden_size': 16, 'lr': 0.00015632648045912445}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:12<00:00,  7.74it/s]\n",
      "[I 2023-10-19 12:05:11,317] Trial 11 finished with value: -0.7163461538461539 and parameters: {'hidden_size': 45, 'lr': 0.00994890427252868}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.55it/s]\n",
      "[I 2023-10-19 12:05:26,645] Trial 12 finished with value: -0.3596153846153846 and parameters: {'hidden_size': 40, 'lr': 0.0002829014775799674}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.98it/s]\n",
      "[I 2023-10-19 12:05:41,048] Trial 13 finished with value: -0.6850961538461539 and parameters: {'hidden_size': 86, 'lr': 0.0003323785635462593}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.24it/s]\n",
      "[I 2023-10-19 12:05:57,147] Trial 14 finished with value: -0.7350961538461538 and parameters: {'hidden_size': 39, 'lr': 0.007671864525593585}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.26it/s]\n",
      "[I 2023-10-19 12:06:10,971] Trial 15 finished with value: -0.6774038461538462 and parameters: {'hidden_size': 104, 'lr': 0.001402511200498827}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:11<00:00,  8.59it/s]\n",
      "[I 2023-10-19 12:06:22,675] Trial 16 finished with value: -0.6245192307692308 and parameters: {'hidden_size': 56, 'lr': 0.00011761787833070536}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:12<00:00,  7.82it/s]\n",
      "[I 2023-10-19 12:06:35,526] Trial 17 finished with value: -0.7649038461538462 and parameters: {'hidden_size': 84, 'lr': 0.005287991388926615}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.75it/s]\n",
      "[I 2023-10-19 12:06:50,392] Trial 18 finished with value: -0.3596153846153846 and parameters: {'hidden_size': 78, 'lr': 0.0005548299257555193}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.66it/s]\n",
      "[I 2023-10-19 12:07:05,487] Trial 19 finished with value: -0.7149038461538462 and parameters: {'hidden_size': 52, 'lr': 0.0017081062119477506}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.09it/s]\n",
      "[I 2023-10-19 12:07:19,674] Trial 20 finished with value: -0.6836538461538462 and parameters: {'hidden_size': 85, 'lr': 0.005004688489935229}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.02it/s]\n",
      "[I 2023-10-19 12:07:36,343] Trial 21 finished with value: -0.7427884615384615 and parameters: {'hidden_size': 108, 'lr': 0.00667271246814791}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.73it/s]\n",
      "[I 2023-10-19 12:07:53,866] Trial 22 finished with value: -0.3596153846153846 and parameters: {'hidden_size': 128, 'lr': 0.009901390363345954}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.89it/s]\n",
      "[I 2023-10-19 12:08:08,453] Trial 23 finished with value: -0.7072115384615385 and parameters: {'hidden_size': 97, 'lr': 0.003679317940594723}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.67it/s]\n",
      "[I 2023-10-19 12:08:26,148] Trial 24 finished with value: -0.7100961538461539 and parameters: {'hidden_size': 113, 'lr': 0.006100612365473701}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.10it/s]\n",
      "[I 2023-10-19 12:08:42,602] Trial 25 finished with value: -0.6961538461538461 and parameters: {'hidden_size': 68, 'lr': 0.0030205024757070788}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:25<00:00,  3.88it/s]\n",
      "[I 2023-10-19 12:09:08,496] Trial 26 finished with value: -0.7288461538461538 and parameters: {'hidden_size': 82, 'lr': 0.004749312952023946}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:22<00:00,  4.48it/s]\n",
      "[I 2023-10-19 12:09:30,906] Trial 27 finished with value: -0.7211538461538461 and parameters: {'hidden_size': 27, 'lr': 0.0069690118430370575}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.01it/s]\n",
      "[I 2023-10-19 12:09:47,606] Trial 28 finished with value: -0.6634615384615385 and parameters: {'hidden_size': 92, 'lr': 0.003636422444182857}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.50it/s]\n",
      "[I 2023-10-19 12:10:01,003] Trial 29 finished with value: -0.7211538461538461 and parameters: {'hidden_size': 101, 'lr': 0.002659759029711315}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.39it/s]\n",
      "[I 2023-10-19 12:10:14,596] Trial 30 finished with value: -0.7024038461538462 and parameters: {'hidden_size': 72, 'lr': 0.0018220971026132174}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.51it/s]\n",
      "[I 2023-10-19 12:10:30,026] Trial 31 finished with value: -0.6586538461538461 and parameters: {'hidden_size': 117, 'lr': 0.006175597831553498}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.16it/s]\n",
      "[I 2023-10-19 12:10:46,324] Trial 32 finished with value: -0.7302884615384615 and parameters: {'hidden_size': 108, 'lr': 0.008130259128178061}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.45it/s]\n",
      "[I 2023-10-19 12:11:04,754] Trial 33 finished with value: -0.6899038461538461 and parameters: {'hidden_size': 111, 'lr': 0.0053348161160246335}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:19<00:00,  5.05it/s]\n",
      "[I 2023-10-19 12:11:24,666] Trial 34 finished with value: -0.7100961538461539 and parameters: {'hidden_size': 124, 'lr': 0.007520480094053052}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:19<00:00,  5.02it/s]\n",
      "[I 2023-10-19 12:11:44,708] Trial 35 finished with value: -0.7225961538461538 and parameters: {'hidden_size': 61, 'lr': 0.004446685499838493}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.26it/s]\n",
      "[I 2023-10-19 12:12:00,748] Trial 36 finished with value: -0.6995192307692307 and parameters: {'hidden_size': 91, 'lr': 0.003961478215557844}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:19<00:00,  5.17it/s]\n",
      "[I 2023-10-19 12:12:20,159] Trial 37 finished with value: -0.7677884615384615 and parameters: {'hidden_size': 103, 'lr': 0.005854233761906965}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.83it/s]\n",
      "[I 2023-10-19 12:12:34,858] Trial 38 finished with value: -0.7475961538461539 and parameters: {'hidden_size': 99, 'lr': 0.0023441231579713158}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:12<00:00,  7.80it/s]\n",
      "[I 2023-10-19 12:12:47,736] Trial 39 finished with value: -0.6975961538461538 and parameters: {'hidden_size': 76, 'lr': 0.002943245272452357}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.13it/s]\n",
      "[I 2023-10-19 12:13:04,107] Trial 40 finished with value: -0.6759615384615385 and parameters: {'hidden_size': 119, 'lr': 0.0010223172936864207}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.87it/s]\n",
      "[I 2023-10-19 12:13:21,296] Trial 41 finished with value: -0.7086538461538462 and parameters: {'hidden_size': 99, 'lr': 0.0022472231833956515}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.28it/s]\n",
      "[I 2023-10-19 12:13:37,313] Trial 42 finished with value: -0.7024038461538462 and parameters: {'hidden_size': 94, 'lr': 0.005486831861140072}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:12<00:00,  7.81it/s]\n",
      "[I 2023-10-19 12:13:50,181] Trial 43 finished with value: -0.6697115384615385 and parameters: {'hidden_size': 101, 'lr': 0.004014140704694039}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.12it/s]\n",
      "[I 2023-10-19 12:14:06,601] Trial 44 finished with value: -0.7024038461538462 and parameters: {'hidden_size': 88, 'lr': 0.0030041091706594926}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.35it/s]\n",
      "[I 2023-10-19 12:14:22,430] Trial 45 finished with value: -0.7475961538461539 and parameters: {'hidden_size': 105, 'lr': 0.008452988074883701}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:19<00:00,  5.08it/s]\n",
      "[I 2023-10-19 12:14:42,217] Trial 46 finished with value: -0.7086538461538462 and parameters: {'hidden_size': 81, 'lr': 0.00565186213577232}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.01it/s]\n",
      "[I 2023-10-19 12:14:56,551] Trial 47 finished with value: -0.6884615384615385 and parameters: {'hidden_size': 115, 'lr': 0.00444662333107407}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.13it/s]\n",
      "[I 2023-10-19 12:15:12,956] Trial 48 finished with value: -0.7100961538461539 and parameters: {'hidden_size': 97, 'lr': 0.0008297078712319008}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.42it/s]\n",
      "[I 2023-10-19 12:15:31,478] Trial 49 finished with value: -0.6725961538461538 and parameters: {'hidden_size': 32, 'lr': 0.002491369874711178}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.39it/s]\n",
      "[I 2023-10-19 12:15:50,109] Trial 50 finished with value: -0.6447115384615385 and parameters: {'hidden_size': 48, 'lr': 0.0012327722312977338}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.85it/s]\n",
      "[I 2023-10-19 12:16:04,766] Trial 51 finished with value: -0.7274038461538461 and parameters: {'hidden_size': 104, 'lr': 0.008364762979337099}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.17it/s]\n",
      "[I 2023-10-19 12:16:21,028] Trial 52 finished with value: -0.7052884615384615 and parameters: {'hidden_size': 108, 'lr': 0.00863561335043462}. Best is trial 4 with value: -0.7677884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.15it/s]\n",
      "[I 2023-10-19 12:16:35,074] Trial 53 finished with value: -0.7927884615384615 and parameters: {'hidden_size': 18, 'lr': 0.006165430613730611}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.29it/s]\n",
      "[I 2023-10-19 12:16:51,058] Trial 54 finished with value: -0.7692307692307693 and parameters: {'hidden_size': 19, 'lr': 0.006797724930615609}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.36it/s]\n",
      "[I 2023-10-19 12:17:06,854] Trial 55 finished with value: -0.7254807692307692 and parameters: {'hidden_size': 19, 'lr': 0.006653452174499847}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.66it/s]\n",
      "[I 2023-10-19 12:17:21,931] Trial 56 finished with value: -0.7447115384615385 and parameters: {'hidden_size': 22, 'lr': 0.006127606078901067}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.41it/s]\n",
      "[I 2023-10-19 12:17:40,529] Trial 57 finished with value: -0.7100961538461539 and parameters: {'hidden_size': 33, 'lr': 0.0053336030169600255}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.09it/s]\n",
      "[I 2023-10-19 12:17:57,039] Trial 58 finished with value: -0.7894230769230769 and parameters: {'hidden_size': 17, 'lr': 0.009094166485255762}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.30it/s]\n",
      "[I 2023-10-19 12:18:12,956] Trial 59 finished with value: -0.7413461538461539 and parameters: {'hidden_size': 17, 'lr': 0.0099837347723638}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.88it/s]\n",
      "[I 2023-10-19 12:18:27,559] Trial 60 finished with value: -0.7350961538461538 and parameters: {'hidden_size': 23, 'lr': 0.007367337560832112}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.85it/s]\n",
      "[I 2023-10-19 12:18:44,721] Trial 61 finished with value: -0.7225961538461538 and parameters: {'hidden_size': 28, 'lr': 0.006429119488812348}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.43it/s]\n",
      "[I 2023-10-19 12:19:03,270] Trial 62 finished with value: -0.7350961538461538 and parameters: {'hidden_size': 39, 'lr': 0.009925732637172672}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.19it/s]\n",
      "[I 2023-10-19 12:19:19,487] Trial 63 finished with value: -0.7461538461538462 and parameters: {'hidden_size': 44, 'lr': 0.004846383248641872}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.64it/s]\n",
      "[I 2023-10-19 12:19:37,307] Trial 64 finished with value: -0.7490384615384615 and parameters: {'hidden_size': 33, 'lr': 0.0074802764448914285}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.15it/s]\n",
      "[I 2023-10-19 12:19:53,641] Trial 65 finished with value: -0.7427884615384615 and parameters: {'hidden_size': 21, 'lr': 0.006214539678709311}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.54it/s]\n",
      "[I 2023-10-19 12:20:11,765] Trial 66 finished with value: -0.6884615384615385 and parameters: {'hidden_size': 30, 'lr': 0.008794358719378101}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:18<00:00,  5.41it/s]\n",
      "[I 2023-10-19 12:20:30,328] Trial 67 finished with value: -0.6975961538461538 and parameters: {'hidden_size': 64, 'lr': 0.0033904269865087473}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.03it/s]\n",
      "[I 2023-10-19 12:20:46,979] Trial 68 finished with value: -0.7865384615384615 and parameters: {'hidden_size': 16, 'lr': 0.004194178581599231}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.28it/s]\n",
      "[I 2023-10-19 12:21:00,826] Trial 69 finished with value: -0.7163461538461539 and parameters: {'hidden_size': 16, 'lr': 0.004477026991234128}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.35it/s]\n",
      "[I 2023-10-19 12:21:14,496] Trial 70 finished with value: -0.6620192307692307 and parameters: {'hidden_size': 24, 'lr': 0.0040221559922397265}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.62it/s]\n",
      "[I 2023-10-19 12:21:29,685] Trial 71 finished with value: -0.7615384615384615 and parameters: {'hidden_size': 19, 'lr': 0.0071770394140912045}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.33it/s]\n",
      "[I 2023-10-19 12:21:45,554] Trial 72 finished with value: -0.7024038461538462 and parameters: {'hidden_size': 26, 'lr': 0.005450439571230883}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.25it/s]\n",
      "[I 2023-10-19 12:22:01,617] Trial 73 finished with value: -0.6307692307692307 and parameters: {'hidden_size': 36, 'lr': 0.007236804782219386}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:27<00:00,  3.61it/s]\n",
      "[I 2023-10-19 12:22:29,352] Trial 74 finished with value: -0.7072115384615385 and parameters: {'hidden_size': 55, 'lr': 0.005967696319657054}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:20<00:00,  4.96it/s]\n",
      "[I 2023-10-19 12:22:49,591] Trial 75 finished with value: -0.7490384615384615 and parameters: {'hidden_size': 69, 'lr': 0.004769735243768367}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.45it/s]\n",
      "[I 2023-10-19 12:23:05,163] Trial 76 finished with value: -0.7865384615384615 and parameters: {'hidden_size': 16, 'lr': 0.009053508213310994}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.61it/s]\n",
      "[I 2023-10-19 12:23:20,380] Trial 77 finished with value: -0.7379807692307693 and parameters: {'hidden_size': 16, 'lr': 0.009034461517496057}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  5.97it/s]\n",
      "[I 2023-10-19 12:23:37,215] Trial 78 finished with value: -0.7413461538461539 and parameters: {'hidden_size': 20, 'lr': 0.008228424196275477}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.72it/s]\n",
      "[I 2023-10-19 12:23:54,759] Trial 79 finished with value: -0.6788461538461539 and parameters: {'hidden_size': 24, 'lr': 0.006597466040213891}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.78it/s]\n",
      "[I 2023-10-19 12:24:09,592] Trial 80 finished with value: -0.6975961538461538 and parameters: {'hidden_size': 30, 'lr': 0.005265822370169954}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.48it/s]\n",
      "[I 2023-10-19 12:24:23,039] Trial 81 finished with value: -0.7163461538461539 and parameters: {'hidden_size': 26, 'lr': 0.00796433393727067}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:16<00:00,  6.09it/s]\n",
      "[I 2023-10-19 12:24:39,537] Trial 82 finished with value: -0.7629807692307693 and parameters: {'hidden_size': 19, 'lr': 0.009260820584777394}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:17<00:00,  5.84it/s]\n",
      "[I 2023-10-19 12:24:56,746] Trial 83 finished with value: -0.7072115384615385 and parameters: {'hidden_size': 19, 'lr': 0.006879640975019332}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.62it/s]\n",
      "[I 2023-10-19 12:25:11,953] Trial 84 finished with value: -0.7399038461538462 and parameters: {'hidden_size': 16, 'lr': 0.007382724909920139}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.75it/s]\n",
      "[I 2023-10-19 12:25:26,877] Trial 85 finished with value: -0.7663461538461538 and parameters: {'hidden_size': 28, 'lr': 0.009139925349903327}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.13it/s]\n",
      "[I 2023-10-19 12:25:41,003] Trial 86 finished with value: -0.7225961538461538 and parameters: {'hidden_size': 23, 'lr': 0.008987259915513468}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:15<00:00,  6.64it/s]\n",
      "[I 2023-10-19 12:25:56,130] Trial 87 finished with value: -0.7865384615384615 and parameters: {'hidden_size': 35, 'lr': 0.005993833364749315}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.37it/s]\n",
      "[I 2023-10-19 12:26:09,764] Trial 88 finished with value: -0.7225961538461538 and parameters: {'hidden_size': 43, 'lr': 0.00626528819269036}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.68it/s]\n",
      "[I 2023-10-19 12:26:22,843] Trial 89 finished with value: -0.7259615384615385 and parameters: {'hidden_size': 38, 'lr': 0.005702262668702366}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.46it/s]\n",
      "[I 2023-10-19 12:26:36,302] Trial 90 finished with value: -0.7475961538461539 and parameters: {'hidden_size': 36, 'lr': 0.007958077346701377}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  7.02it/s]\n",
      "[I 2023-10-19 12:26:50,602] Trial 91 finished with value: -0.7038461538461538 and parameters: {'hidden_size': 28, 'lr': 0.005134370409910534}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.22it/s]\n",
      "[I 2023-10-19 12:27:04,526] Trial 92 finished with value: -0.7456730769230769 and parameters: {'hidden_size': 21, 'lr': 0.006720635503803114}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.51it/s]\n",
      "[I 2023-10-19 12:27:17,912] Trial 93 finished with value: -0.7302884615384615 and parameters: {'hidden_size': 26, 'lr': 0.005713747297838442}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.60it/s]\n",
      "[I 2023-10-19 12:27:31,139] Trial 94 finished with value: -0.7350961538461538 and parameters: {'hidden_size': 48, 'lr': 0.009321250334620489}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:14<00:00,  6.93it/s]\n",
      "[I 2023-10-19 12:27:45,653] Trial 95 finished with value: -0.7288461538461538 and parameters: {'hidden_size': 30, 'lr': 0.004249048075390148}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.18it/s]\n",
      "[I 2023-10-19 12:27:59,658] Trial 96 finished with value: -0.7322115384615385 and parameters: {'hidden_size': 18, 'lr': 0.0036810575183480044}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.38it/s]\n",
      "[I 2023-10-19 12:28:13,255] Trial 97 finished with value: -0.7379807692307693 and parameters: {'hidden_size': 35, 'lr': 0.0050503908668657815}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.30it/s]\n",
      "[I 2023-10-19 12:28:27,017] Trial 98 finished with value: -0.7225961538461538 and parameters: {'hidden_size': 24, 'lr': 0.007951322241340715}. Best is trial 53 with value: -0.7927884615384615.\n",
      "C:\\Users\\Hammam\\AppData\\Local\\Temp\\ipykernel_13100\\3017595126.py:9: FutureWarning: suggest_loguniform has been deprecated in v3.0.0. This feature will be removed in v6.0.0. See https://github.com/optuna/optuna/releases/tag/v3.0.0. Use suggest_float(..., log=True) instead.\n",
      "  lr = trial.suggest_loguniform('lr', 1e-4, 1e-2)\n",
      "100%|██████████| 100/100 [00:13<00:00,  7.48it/s]\n",
      "[I 2023-10-19 12:28:40,457] Trial 99 finished with value: -0.7177884615384615 and parameters: {'hidden_size': 22, 'lr': 0.004687714254973949}. Best is trial 53 with value: -0.7927884615384615.\n"
     ]
    }
   ],
   "source": [
    "# Create a study and optimize hyperparameters\n",
    "study = optuna.create_study(direction='minimize')\n",
    "study.optimize(objective, n_trials=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the best hyperparameters\n",
    "best_params = study.best_params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "best_model = DiabetesModel(X_train.shape[1], best_params['hidden_size'], 1)\n",
    "best_optimizer = optim.Adam(best_model.parameters(), lr=best_params['lr'])\n",
    "best_criterion = nn.BCELoss()\n",
    "train_dataset = TensorDataset(X_train, y_train)\n",
    "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 100/100 [00:06<00:00, 16.24it/s]\n"
     ]
    }
   ],
   "source": [
    "for epoch in tqdm(range(100)):\n",
    "    train_loss = train(best_model, train_loader, best_optimizer, best_criterion)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "best_loss, best_accuracy, best_predictions, best_labels = evaluate(best_model, test_loader, best_criterion, accuracy_score)\n",
    "best_recall = recall_score(best_labels, best_predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Hyperparameters: {'hidden_size': 18, 'lr': 0.006165430613730611}\n",
      "Best Test Accuracy: 0.7413461538461539\n",
      "Best Test Recall: 0.45454545454545453\n"
     ]
    }
   ],
   "source": [
    "print(\"Best Hyperparameters:\", best_params)\n",
    "print(\"Best Test Accuracy:\", best_accuracy)\n",
    "print(\"Best Test Recall:\", best_recall)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "confusion = confusion_matrix(best_labels, best_predictions)\n",
    "sns.heatmap(confusion, annot=True, fmt='d')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}