{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#! pip install tensorflow\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = pd.read_csv(\"train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0                                         poznan.wuoz.gov.pl\n",
       "1                                        vill.okawa.kochi.jp\n",
       "2                                      nationalfinance.co.om\n",
       "3                                     town.ozora.hokkaido.jp\n",
       "4                          open24.ie-news.irish/online/Login\n",
       "                                 ...                        \n",
       "6995051                                           ddht.co.kr\n",
       "6995052                                 www.upstartepoxy.com\n",
       "6995053    employeesalaryschedule70.000webhostapp.com/adb...\n",
       "6995054                                       dekalbtool.com\n",
       "6995055                                   helpinganimals.com\n",
       "Name: URL_clean, Length: 6995056, dtype: object"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 대괄호 [ ] 제거\n",
    "train['URL_clean'] = train['URL'].str.replace(r'[\\[\\]]', '', regex=True)\n",
    "train[\"URL_clean\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>ID</th>\n",
       "      <th>URL</th>\n",
       "      <th>label</th>\n",
       "      <th>URL_clean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>TRAIN_0000000</td>\n",
       "      <td>poznan[.]wuoz[.]gov[.]pl</td>\n",
       "      <td>0</td>\n",
       "      <td>poznan.wuoz.gov.pl</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>TRAIN_0000001</td>\n",
       "      <td>vill[.]okawa[.]kochi[.]jp</td>\n",
       "      <td>0</td>\n",
       "      <td>vill.okawa.kochi.jp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>TRAIN_0000002</td>\n",
       "      <td>nationalfinance[.]co[.]om</td>\n",
       "      <td>0</td>\n",
       "      <td>nationalfinance.co.om</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>TRAIN_0000003</td>\n",
       "      <td>town[.]ozora[.]hokkaido[.]jp</td>\n",
       "      <td>0</td>\n",
       "      <td>town.ozora.hokkaido.jp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>TRAIN_0000004</td>\n",
       "      <td>open24[.]ie-news[.]irish/online/Login</td>\n",
       "      <td>1</td>\n",
       "      <td>open24.ie-news.irish/online/Login</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995051</th>\n",
       "      <td>TRAIN_6995051</td>\n",
       "      <td>ddht[.]co[.]kr</td>\n",
       "      <td>0</td>\n",
       "      <td>ddht.co.kr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995052</th>\n",
       "      <td>TRAIN_6995052</td>\n",
       "      <td>www[.]upstartepoxy[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>www.upstartepoxy.com</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995053</th>\n",
       "      <td>TRAIN_6995053</td>\n",
       "      <td>employeesalaryschedule70[.]000webhostapp[.]com...</td>\n",
       "      <td>1</td>\n",
       "      <td>employeesalaryschedule70.000webhostapp.com/adb...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995054</th>\n",
       "      <td>TRAIN_6995054</td>\n",
       "      <td>dekalbtool[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>dekalbtool.com</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995055</th>\n",
       "      <td>TRAIN_6995055</td>\n",
       "      <td>helpinganimals[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>helpinganimals.com</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6995056 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    ID                                                URL  \\\n",
       "0        TRAIN_0000000                           poznan[.]wuoz[.]gov[.]pl   \n",
       "1        TRAIN_0000001                          vill[.]okawa[.]kochi[.]jp   \n",
       "2        TRAIN_0000002                          nationalfinance[.]co[.]om   \n",
       "3        TRAIN_0000003                       town[.]ozora[.]hokkaido[.]jp   \n",
       "4        TRAIN_0000004              open24[.]ie-news[.]irish/online/Login   \n",
       "...                ...                                                ...   \n",
       "6995051  TRAIN_6995051                                     ddht[.]co[.]kr   \n",
       "6995052  TRAIN_6995052                           www[.]upstartepoxy[.]com   \n",
       "6995053  TRAIN_6995053  employeesalaryschedule70[.]000webhostapp[.]com...   \n",
       "6995054  TRAIN_6995054                                   dekalbtool[.]com   \n",
       "6995055  TRAIN_6995055                               helpinganimals[.]com   \n",
       "\n",
       "         label                                          URL_clean  \n",
       "0            0                                 poznan.wuoz.gov.pl  \n",
       "1            0                                vill.okawa.kochi.jp  \n",
       "2            0                              nationalfinance.co.om  \n",
       "3            0                             town.ozora.hokkaido.jp  \n",
       "4            1                  open24.ie-news.irish/online/Login  \n",
       "...        ...                                                ...  \n",
       "6995051      0                                         ddht.co.kr  \n",
       "6995052      0                               www.upstartepoxy.com  \n",
       "6995053      1  employeesalaryschedule70.000webhostapp.com/adb...  \n",
       "6995054      0                                     dekalbtool.com  \n",
       "6995055      0                                 helpinganimals.com  \n",
       "\n",
       "[6995056 rows x 4 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['dot_count'] = train['URL_clean'].str.count('\\.')\n",
    "train['slash_count'] = train['URL_clean'].str.count('/')\n",
    "train['alpha_count'] = train['URL_clean'].str.count(r'[a-zA-Z]')\n",
    "train['dash_count'] = train['URL_clean'].str.count(r'-')\n",
    "train['underscore_count'] = train['URL_clean'].str.count(r'_')\n",
    "train['digit_count'] = train['URL_clean'].str.count(r'\\d')\n",
    "train['percent_count'] = train['URL_clean'].str.count(r'%')\n",
    "train['equal_count'] = train['URL_clean'].str.count(r'=')\n",
    "train['question_count'] = train['URL_clean'].str.count(r'\\?')\n",
    "train['at_count'] = train['URL_clean'].str.count(r'@')"
   ]
  },
  {
   "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>ID</th>\n",
       "      <th>URL</th>\n",
       "      <th>label</th>\n",
       "      <th>URL_clean</th>\n",
       "      <th>dot_count</th>\n",
       "      <th>slash_count</th>\n",
       "      <th>alpha_count</th>\n",
       "      <th>dash_count</th>\n",
       "      <th>underscore_count</th>\n",
       "      <th>digit_count</th>\n",
       "      <th>percent_count</th>\n",
       "      <th>equal_count</th>\n",
       "      <th>question_count</th>\n",
       "      <th>at_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>TRAIN_0000000</td>\n",
       "      <td>poznan[.]wuoz[.]gov[.]pl</td>\n",
       "      <td>0</td>\n",
       "      <td>poznan.wuoz.gov.pl</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>TRAIN_0000001</td>\n",
       "      <td>vill[.]okawa[.]kochi[.]jp</td>\n",
       "      <td>0</td>\n",
       "      <td>vill.okawa.kochi.jp</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>TRAIN_0000002</td>\n",
       "      <td>nationalfinance[.]co[.]om</td>\n",
       "      <td>0</td>\n",
       "      <td>nationalfinance.co.om</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>19</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>TRAIN_0000003</td>\n",
       "      <td>town[.]ozora[.]hokkaido[.]jp</td>\n",
       "      <td>0</td>\n",
       "      <td>town.ozora.hokkaido.jp</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>19</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>TRAIN_0000004</td>\n",
       "      <td>open24[.]ie-news[.]irish/online/Login</td>\n",
       "      <td>1</td>\n",
       "      <td>open24.ie-news.irish/online/Login</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>26</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995051</th>\n",
       "      <td>TRAIN_6995051</td>\n",
       "      <td>ddht[.]co[.]kr</td>\n",
       "      <td>0</td>\n",
       "      <td>ddht.co.kr</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995052</th>\n",
       "      <td>TRAIN_6995052</td>\n",
       "      <td>www[.]upstartepoxy[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>www.upstartepoxy.com</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995053</th>\n",
       "      <td>TRAIN_6995053</td>\n",
       "      <td>employeesalaryschedule70[.]000webhostapp[.]com...</td>\n",
       "      <td>1</td>\n",
       "      <td>employeesalaryschedule70.000webhostapp.com/adb...</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995054</th>\n",
       "      <td>TRAIN_6995054</td>\n",
       "      <td>dekalbtool[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>dekalbtool.com</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6995055</th>\n",
       "      <td>TRAIN_6995055</td>\n",
       "      <td>helpinganimals[.]com</td>\n",
       "      <td>0</td>\n",
       "      <td>helpinganimals.com</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6995056 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    ID                                                URL  \\\n",
       "0        TRAIN_0000000                           poznan[.]wuoz[.]gov[.]pl   \n",
       "1        TRAIN_0000001                          vill[.]okawa[.]kochi[.]jp   \n",
       "2        TRAIN_0000002                          nationalfinance[.]co[.]om   \n",
       "3        TRAIN_0000003                       town[.]ozora[.]hokkaido[.]jp   \n",
       "4        TRAIN_0000004              open24[.]ie-news[.]irish/online/Login   \n",
       "...                ...                                                ...   \n",
       "6995051  TRAIN_6995051                                     ddht[.]co[.]kr   \n",
       "6995052  TRAIN_6995052                           www[.]upstartepoxy[.]com   \n",
       "6995053  TRAIN_6995053  employeesalaryschedule70[.]000webhostapp[.]com...   \n",
       "6995054  TRAIN_6995054                                   dekalbtool[.]com   \n",
       "6995055  TRAIN_6995055                               helpinganimals[.]com   \n",
       "\n",
       "         label                                          URL_clean  dot_count  \\\n",
       "0            0                                 poznan.wuoz.gov.pl          3   \n",
       "1            0                                vill.okawa.kochi.jp          3   \n",
       "2            0                              nationalfinance.co.om          2   \n",
       "3            0                             town.ozora.hokkaido.jp          3   \n",
       "4            1                  open24.ie-news.irish/online/Login          2   \n",
       "...        ...                                                ...        ...   \n",
       "6995051      0                                         ddht.co.kr          2   \n",
       "6995052      0                               www.upstartepoxy.com          2   \n",
       "6995053      1  employeesalaryschedule70.000webhostapp.com/adb...          2   \n",
       "6995054      0                                     dekalbtool.com          1   \n",
       "6995055      0                                 helpinganimals.com          1   \n",
       "\n",
       "         slash_count  alpha_count  dash_count  underscore_count  digit_count  \\\n",
       "0                  0           15           0                 0            0   \n",
       "1                  0           16           0                 0            0   \n",
       "2                  0           19           0                 0            0   \n",
       "3                  0           19           0                 0            0   \n",
       "4                  2           26           1                 0            2   \n",
       "...              ...          ...         ...               ...          ...   \n",
       "6995051            0            8           0                 0            0   \n",
       "6995052            0           18           0                 0            0   \n",
       "6995053            2           41           0                 0            5   \n",
       "6995054            0           13           0                 0            0   \n",
       "6995055            0           17           0                 0            0   \n",
       "\n",
       "         percent_count  equal_count  question_count  at_count  \n",
       "0                    0            0               0         0  \n",
       "1                    0            0               0         0  \n",
       "2                    0            0               0         0  \n",
       "3                    0            0               0         0  \n",
       "4                    0            0               0         0  \n",
       "...                ...          ...             ...       ...  \n",
       "6995051              0            0               0         0  \n",
       "6995052              0            0               0         0  \n",
       "6995053              0            0               0         0  \n",
       "6995054              0            0               0         0  \n",
       "6995055              0            0               0         0  \n",
       "\n",
       "[6995056 rows x 14 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = train[[\n",
    "    'dot_count', 'slash_count', 'alpha_count',\n",
    "    'dash_count', 'underscore_count', 'digit_count',\n",
    "    'percent_count', 'equal_count', 'question_count', 'at_count'\n",
    "]]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = train['label']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x800 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# 피처 + label 포함해서 상관행렬 계산\n",
    "features = [\n",
    "    'dot_count', 'slash_count', 'alpha_count', \n",
    "    'dash_count', 'underscore_count', 'digit_count',\n",
    "    'percent_count', 'equal_count', 'question_count', 'at_count', 'label'\n",
    "]\n",
    "\n",
    "corr_df = train[features].corr(numeric_only=True)\n",
    "\n",
    "# X축에서 label 제거\n",
    "corr_df = corr_df.drop(columns=['label'])\n",
    "\n",
    "# 히트맵 그리기\n",
    "plt.figure(figsize=(10, 8))\n",
    "sns.heatmap(corr_df, annot=True, cmap='coolwarm', fmt=\".2f\", linewidths=0.5)\n",
    "plt.title(\"Feature Correlation Heatmap (label dropped from X-axis)\", fontsize=14)\n",
    "plt.xticks(rotation=45)\n",
    "plt.tight_layout()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# 스케일링\n",
    "scaler = StandardScaler()\n",
    "X_scaled = scaler.fit_transform(X)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# 1단계: 전체에서 테스트 세트 먼저 떼어내기 (20%)\n",
    "X_train_full, X_test, y_train_full, y_test = train_test_split(\n",
    "    X_scaled, y, test_size=0.2, random_state=42, stratify=y\n",
    ")\n",
    "\n",
    "# 2단계: 남은 80% 중에서 훈련 / 검증으로 다시 나누기 (검증 20% = 전체의 16%)\n",
    "X_train, X_val, y_train, y_val = train_test_split(\n",
    "    X_train_full, y_train_full, test_size=0.2, random_state=42, stratify=y_train_full)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\human\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\layers\\core\\dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Dense\n",
    "model = Sequential()\n",
    "model.add(Dense(64, input_dim=10, activation='relu'))\n",
    "model.add(Dense(32, activation='relu'))  \n",
    "model.add(Dense(1, activation='sigmoid'))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 모델 컴파일\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "optimizer = Adam(learning_rate=0.001)  # 학습률을 너무 크게 설정하면 빨리 수렴할 수 있음\n",
    "\n",
    "model.compile(optimizer, loss='binary_crossentropy', metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# EarlyStopping 콜백을 사용하여 검증 손실이 개선되지 않으면 학습을 멈추도록 설정\n",
    "from tensorflow.keras.callbacks import EarlyStopping\n",
    "early_stopping = EarlyStopping(monitor='val_loss', patience=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "\u001b[1m139902/139902\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m217s\u001b[0m 2ms/step - accuracy: 0.8756 - loss: 0.3075 - val_accuracy: 0.8803 - val_loss: 0.2991\n",
      "Epoch 2/10\n",
      "\u001b[1m139902/139902\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m205s\u001b[0m 1ms/step - accuracy: 0.8801 - loss: 0.2996 - val_accuracy: 0.8815 - val_loss: 0.2976\n",
      "Epoch 3/10\n",
      "\u001b[1m139863/139902\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8812 - loss: 0.2984"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mKeyboardInterrupt\u001b[39m                         Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[19]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;66;03m# 모델 학습 (Epoch마다 정확도 출력)\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m history = \u001b[43mmodel\u001b[49m\u001b[43m.\u001b[49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[32m      3\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mepochs\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m10\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m               \u001b[49m\u001b[38;5;66;43;03m# 최대 epoch 수\u001b[39;49;00m\n\u001b[32m      4\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m32\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m            \u001b[49m\u001b[38;5;66;43;03m# 배치 크기\u001b[39;49;00m\n\u001b[32m      5\u001b[39m \u001b[43m                    \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[43m=\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_val\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# 검증 데이터\u001b[39;49;00m\n\u001b[32m      6\u001b[39m \u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\utils\\traceback_utils.py:117\u001b[39m, in \u001b[36mfilter_traceback.<locals>.error_handler\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m    115\u001b[39m filtered_tb = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m    116\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m117\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    118\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m    119\u001b[39m     filtered_tb = _process_traceback_frames(e.__traceback__)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\backend\\tensorflow\\trainer.py:395\u001b[39m, in \u001b[36mTensorFlowTrainer.fit\u001b[39m\u001b[34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)\u001b[39m\n\u001b[32m    384\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33m_eval_epoch_iterator\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m    385\u001b[39m     \u001b[38;5;28mself\u001b[39m._eval_epoch_iterator = TFEpochIterator(\n\u001b[32m    386\u001b[39m         x=val_x,\n\u001b[32m    387\u001b[39m         y=val_y,\n\u001b[32m   (...)\u001b[39m\u001b[32m    393\u001b[39m         shuffle=\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[32m    394\u001b[39m     )\n\u001b[32m--> \u001b[39m\u001b[32m395\u001b[39m val_logs = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mevaluate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    396\u001b[39m \u001b[43m    \u001b[49m\u001b[43mx\u001b[49m\u001b[43m=\u001b[49m\u001b[43mval_x\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    397\u001b[39m \u001b[43m    \u001b[49m\u001b[43my\u001b[49m\u001b[43m=\u001b[49m\u001b[43mval_y\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    398\u001b[39m \u001b[43m    \u001b[49m\u001b[43msample_weight\u001b[49m\u001b[43m=\u001b[49m\u001b[43mval_sample_weight\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    399\u001b[39m \u001b[43m    \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m=\u001b[49m\u001b[43mvalidation_batch_size\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    400\u001b[39m \u001b[43m    \u001b[49m\u001b[43msteps\u001b[49m\u001b[43m=\u001b[49m\u001b[43mvalidation_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    401\u001b[39m \u001b[43m    \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    402\u001b[39m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    403\u001b[39m \u001b[43m    \u001b[49m\u001b[43m_use_cached_eval_dataset\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    404\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    405\u001b[39m val_logs = {\n\u001b[32m    406\u001b[39m     \u001b[33m\"\u001b[39m\u001b[33mval_\u001b[39m\u001b[33m\"\u001b[39m + name: val \u001b[38;5;28;01mfor\u001b[39;00m name, val \u001b[38;5;129;01min\u001b[39;00m val_logs.items()\n\u001b[32m    407\u001b[39m }\n\u001b[32m    408\u001b[39m epoch_logs.update(val_logs)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\utils\\traceback_utils.py:117\u001b[39m, in \u001b[36mfilter_traceback.<locals>.error_handler\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m    115\u001b[39m filtered_tb = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m    116\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m117\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    118\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m    119\u001b[39m     filtered_tb = _process_traceback_frames(e.__traceback__)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\backend\\tensorflow\\trainer.py:483\u001b[39m, in \u001b[36mTensorFlowTrainer.evaluate\u001b[39m\u001b[34m(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, return_dict, **kwargs)\u001b[39m\n\u001b[32m    481\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m step, iterator \u001b[38;5;129;01min\u001b[39;00m epoch_iterator:\n\u001b[32m    482\u001b[39m     callbacks.on_test_batch_begin(step)\n\u001b[32m--> \u001b[39m\u001b[32m483\u001b[39m     logs = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtest_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    484\u001b[39m     callbacks.on_test_batch_end(step, logs)\n\u001b[32m    485\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.stop_evaluating:\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\keras\\src\\backend\\tensorflow\\trainer.py:219\u001b[39m, in \u001b[36mTensorFlowTrainer._make_function.<locals>.function\u001b[39m\u001b[34m(iterator)\u001b[39m\n\u001b[32m    215\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mfunction\u001b[39m(iterator):\n\u001b[32m    216\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\n\u001b[32m    217\u001b[39m         iterator, (tf.data.Iterator, tf.distribute.DistributedIterator)\n\u001b[32m    218\u001b[39m     ):\n\u001b[32m--> \u001b[39m\u001b[32m219\u001b[39m         opt_outputs = \u001b[43mmulti_step_on_iterator\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    220\u001b[39m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m opt_outputs.has_value():\n\u001b[32m    221\u001b[39m             \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\util\\traceback_utils.py:150\u001b[39m, in \u001b[36mfilter_traceback.<locals>.error_handler\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m    148\u001b[39m filtered_tb = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m    149\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m150\u001b[39m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    151\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m    152\u001b[39m   filtered_tb = _process_traceback_frames(e.__traceback__)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\polymorphic_function.py:833\u001b[39m, in \u001b[36mFunction.__call__\u001b[39m\u001b[34m(self, *args, **kwds)\u001b[39m\n\u001b[32m    830\u001b[39m compiler = \u001b[33m\"\u001b[39m\u001b[33mxla\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m._jit_compile \u001b[38;5;28;01melse\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mnonXla\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m    832\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m OptionalXlaContext(\u001b[38;5;28mself\u001b[39m._jit_compile):\n\u001b[32m--> \u001b[39m\u001b[32m833\u001b[39m   result = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    835\u001b[39m new_tracing_count = \u001b[38;5;28mself\u001b[39m.experimental_get_tracing_count()\n\u001b[32m    836\u001b[39m without_tracing = (tracing_count == new_tracing_count)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\polymorphic_function.py:878\u001b[39m, in \u001b[36mFunction._call\u001b[39m\u001b[34m(self, *args, **kwds)\u001b[39m\n\u001b[32m    875\u001b[39m \u001b[38;5;28mself\u001b[39m._lock.release()\n\u001b[32m    876\u001b[39m \u001b[38;5;66;03m# In this case we have not created variables on the first call. So we can\u001b[39;00m\n\u001b[32m    877\u001b[39m \u001b[38;5;66;03m# run the first trace but we should fail if variables are created.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m878\u001b[39m results = \u001b[43mtracing_compilation\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    879\u001b[39m \u001b[43m    \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_variable_creation_config\u001b[49m\n\u001b[32m    880\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    881\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m._created_variables:\n\u001b[32m    882\u001b[39m   \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33m\"\u001b[39m\u001b[33mCreating variables on a non-first call to a function\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m    883\u001b[39m                    \u001b[33m\"\u001b[39m\u001b[33m decorated with tf.function.\u001b[39m\u001b[33m\"\u001b[39m)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\tracing_compilation.py:139\u001b[39m, in \u001b[36mcall_function\u001b[39m\u001b[34m(args, kwargs, tracing_options)\u001b[39m\n\u001b[32m    137\u001b[39m bound_args = function.function_type.bind(*args, **kwargs)\n\u001b[32m    138\u001b[39m flat_inputs = function.function_type.unpack_inputs(bound_args)\n\u001b[32m--> \u001b[39m\u001b[32m139\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_call_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# pylint: disable=protected-access\u001b[39;49;00m\n\u001b[32m    140\u001b[39m \u001b[43m    \u001b[49m\u001b[43mflat_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaptured_inputs\u001b[49m\u001b[43m=\u001b[49m\u001b[43mfunction\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcaptured_inputs\u001b[49m\n\u001b[32m    141\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\concrete_function.py:1322\u001b[39m, in \u001b[36mConcreteFunction._call_flat\u001b[39m\u001b[34m(self, tensor_inputs, captured_inputs)\u001b[39m\n\u001b[32m   1318\u001b[39m possible_gradient_type = gradients_util.PossibleTapeGradientTypes(args)\n\u001b[32m   1319\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m (possible_gradient_type == gradients_util.POSSIBLE_GRADIENT_TYPES_NONE\n\u001b[32m   1320\u001b[39m     \u001b[38;5;129;01mand\u001b[39;00m executing_eagerly):\n\u001b[32m   1321\u001b[39m   \u001b[38;5;66;03m# No tape is watching; skip to running the function.\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1322\u001b[39m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_inference_function\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcall_preflattened\u001b[49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1323\u001b[39m forward_backward = \u001b[38;5;28mself\u001b[39m._select_forward_and_backward_functions(\n\u001b[32m   1324\u001b[39m     args,\n\u001b[32m   1325\u001b[39m     possible_gradient_type,\n\u001b[32m   1326\u001b[39m     executing_eagerly)\n\u001b[32m   1327\u001b[39m forward_function, args_with_tangents = forward_backward.forward()\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\atomic_function.py:216\u001b[39m, in \u001b[36mAtomicFunction.call_preflattened\u001b[39m\u001b[34m(self, args)\u001b[39m\n\u001b[32m    214\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcall_preflattened\u001b[39m(\u001b[38;5;28mself\u001b[39m, args: Sequence[core.Tensor]) -> Any:\n\u001b[32m    215\u001b[39m \u001b[38;5;250m  \u001b[39m\u001b[33;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m216\u001b[39m   flat_outputs = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mcall_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    217\u001b[39m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m.function_type.pack_output(flat_outputs)\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\atomic_function.py:251\u001b[39m, in \u001b[36mAtomicFunction.call_flat\u001b[39m\u001b[34m(self, *args)\u001b[39m\n\u001b[32m    249\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m record.stop_recording():\n\u001b[32m    250\u001b[39m   \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m._bound_context.executing_eagerly():\n\u001b[32m--> \u001b[39m\u001b[32m251\u001b[39m     outputs = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_bound_context\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    252\u001b[39m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    253\u001b[39m \u001b[43m        \u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    254\u001b[39m \u001b[43m        \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mfunction_type\u001b[49m\u001b[43m.\u001b[49m\u001b[43mflat_outputs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    255\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    256\u001b[39m   \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m    257\u001b[39m     outputs = make_call_op_in_graph(\n\u001b[32m    258\u001b[39m         \u001b[38;5;28mself\u001b[39m,\n\u001b[32m    259\u001b[39m         \u001b[38;5;28mlist\u001b[39m(args),\n\u001b[32m    260\u001b[39m         \u001b[38;5;28mself\u001b[39m._bound_context.function_call_options.as_attrs(),\n\u001b[32m    261\u001b[39m     )\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\context.py:1688\u001b[39m, in \u001b[36mContext.call_function\u001b[39m\u001b[34m(self, name, tensor_inputs, num_outputs)\u001b[39m\n\u001b[32m   1686\u001b[39m cancellation_context = cancellation.context()\n\u001b[32m   1687\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m cancellation_context \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m1688\u001b[39m   outputs = \u001b[43mexecute\u001b[49m\u001b[43m.\u001b[49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m   1689\u001b[39m \u001b[43m      \u001b[49m\u001b[43mname\u001b[49m\u001b[43m.\u001b[49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mutf-8\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1690\u001b[39m \u001b[43m      \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m=\u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1691\u001b[39m \u001b[43m      \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtensor_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1692\u001b[39m \u001b[43m      \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m=\u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m   1693\u001b[39m \u001b[43m      \u001b[49m\u001b[43mctx\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m   1694\u001b[39m \u001b[43m  \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1695\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m   1696\u001b[39m   outputs = execute.execute_with_cancellation(\n\u001b[32m   1697\u001b[39m       name.decode(\u001b[33m\"\u001b[39m\u001b[33mutf-8\u001b[39m\u001b[33m\"\u001b[39m),\n\u001b[32m   1698\u001b[39m       num_outputs=num_outputs,\n\u001b[32m   (...)\u001b[39m\u001b[32m   1702\u001b[39m       cancellation_manager=cancellation_context,\n\u001b[32m   1703\u001b[39m   )\n",
      "\u001b[36mFile \u001b[39m\u001b[32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tensorflow\\python\\eager\\execute.py:53\u001b[39m, in \u001b[36mquick_execute\u001b[39m\u001b[34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[39m\n\u001b[32m     51\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m     52\u001b[39m   ctx.ensure_initialized()\n\u001b[32m---> \u001b[39m\u001b[32m53\u001b[39m   tensors = \u001b[43mpywrap_tfe\u001b[49m\u001b[43m.\u001b[49m\u001b[43mTFE_Py_Execute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mctx\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mop_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m     54\u001b[39m \u001b[43m                                      \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m     55\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m core._NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m     56\u001b[39m   \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "\u001b[31mKeyboardInterrupt\u001b[39m: "
     ]
    }
   ],
   "source": [
    "# 모델 학습 (Epoch마다 정확도 출력)\n",
    "history = model.fit(X_train, y_train, \n",
    "                    epochs=10,               # 최대 epoch 수\n",
    "                    batch_size=32,            # 배치 크기\n",
    "                    validation_data=(X_val, y_val),  # 검증 데이터\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 모델 평가\n",
    "from sklearn.metrics import accuracy_score\n",
    "val_loss, val_accuracy = model.evaluate(X_val, y_val)\n",
    "print(f'Validation Accuracy: {val_accuracy:.4f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 언더샘플링 적용\n",
    "rus = RandomUnderSampler(random_state=42)\n",
    "\n",
    "# X_train과 y_train을 언더샘플링하여 균형 맞추기\n",
    "X_train_under, y_train_under = rus.fit_resample(X_train, y_train)\n",
    "\n",
    "# 언더샘플링 후 클래스 분포 확인\n",
    "print(\"After undersampling:\", Counter(y_train_under))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m34976/34976\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 662us/step\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import f1_score, accuracy_score\n",
    "\n",
    "# 확률 예측값이 y_val_proba라고 가정\n",
    "# 예: y_val_proba = model.predict(X_val).ravel()\n",
    "\n",
    "# 0.1 ~ 0.89 범위에서 0.01 간격으로 threshold 후보 생성\n",
    "thresholds = np.arange(0.1, 0.9, 0.01)\n",
    "\n",
    "# 각 threshold마다 F1 점수 계산\n",
    "threshold_range = [i * 0.01 for i in range(100)]\n",
    "f1_scores = []\n",
    "accuracies = []\n",
    "thresholds = []\n",
    "\n",
    "y_val_proba = model.predict(X_val).flatten()\n",
    "\n",
    "for t in thresholds:\n",
    "    y_pred = (y_val_proba > t).astype(int)  # 임계값 기준으로 이진 분류\n",
    "    score = f1_score(y_val, y_pred)\n",
    "    f1_scores.append(score)\n",
    "    acc = accuracy_score(y_val, y_pred)   \n",
    "\n",
    "for t in [i * 0.01 for i in range(100)]:\n",
    "    y_pred = (y_val_proba > t).astype(int)\n",
    "\n",
    "    try:\n",
    "        f1 = f1_score(y_val, y_pred)\n",
    "        acc = accuracy_score(y_val, y_pred)\n",
    "\n",
    "        thresholds.append(t)         # 여기서 같이 append!\n",
    "        f1_scores.append(f1)\n",
    "        accuracies.append(acc)\n",
    "    except:\n",
    "        continue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Threshold: 0.34\n",
      "Best F1 Score: 0.7248\n",
      "Accuracy at Best Threshold: 0.8735\n"
     ]
    }
   ],
   "source": [
    "# 최고 F1 점수 기준 인덱스\n",
    "best_idx = f1_scores.index(max(f1_scores))\n",
    "best_threshold = thresholds[best_idx]\n",
    "best_f1 = f1_scores[best_idx]\n",
    "best_acc = accuracies[best_idx]  \n",
    "\n",
    "print(f\"Best Threshold: {best_threshold:.2f}\")\n",
    "print(f\"Best F1 Score: {best_f1:.4f}\")\n",
    "print(f\"Accuracy at Best Threshold: {best_acc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 5))\n",
    "plt.plot(thresholds, f1_scores, label='F1 Score', color='blue')\n",
    "plt.plot(thresholds, accuracies, label='Accuracy', color='green')\n",
    "plt.axvline(x=best_threshold, color='red', linestyle='--', label=f'Best Threshold: {best_threshold:.2f}')\n",
    "plt.xlabel(\"Threshold\")\n",
    "plt.ylabel(\"Score\")\n",
    "plt.title(\"F1 Score & Accuracy by Threshold\")\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m43720/43720\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 656us/step\n"
     ]
    }
   ],
   "source": [
    "# 테스트 데이터 예측 확률\n",
    "y_test_proba = model.predict(X_test).ravel()\n",
    "\n",
    "# 최적 임계값 적용해서 예측값 변환\n",
    "y_test_pred = (y_test_proba > best_threshold).astype(int)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m43720/43720\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 944us/step\n",
      "Test Accuracy: 0.8695279239920745\n",
      "Test ROC AUC: 0.8996866936610067\n"
     ]
    }
   ],
   "source": [
    "y_test_pred = model.predict(X_test)  # 테스트 데이터에 대해 예측\n",
    "y_test_pred = (y_test_pred > 0.3).astype(int)  # 이진 분류이므로 0.5를 기준으로 0과 1로 변환\n",
    "\n",
    "# 성능 평가\n",
    "from sklearn.metrics import accuracy_score, roc_auc_score\n",
    "\n",
    "print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n",
    "print(\"Test ROC AUC:\", roc_auc_score(y_test, y_test_proba))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report:\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      1.00      0.89    868826\n",
      "           1       0.99      0.17      0.30    250383\n",
      "\n",
      "    accuracy                           0.81   1119209\n",
      "   macro avg       0.90      0.59      0.59   1119209\n",
      "weighted avg       0.85      0.81      0.76   1119209\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report, ConfusionMatrixDisplay\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "# 평가 지표 출력\n",
    "print(\"Classification Report:\\n\")\n",
    "print(classification_report(y_val, y_pred))\n",
    "\n",
    "# 혼동 행렬 시각화\n",
    "ConfusionMatrixDisplay.from_predictions(y_val, y_pred, cmap='Blues')\n",
    "plt.title(\"Confusion Matrix\")\n",
    "plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}