{
 "cells": [
  {
   "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",
    "from sklearn.model_selection import train_test_split\n",
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_seoul = pd.read_feather(\"../data/data_for_modeling/df_seoul.feather\")\n",
    "df_busan = pd.read_feather(\"../data/data_for_modeling/df_busan.feather\")\n",
    "df_incheon = pd.read_feather(\"../data/data_for_modeling/df_incheon.feather\")\n",
    "df_daegu = pd.read_feather(\"../data/data_for_modeling/df_daegu.feather\")\n",
    "df_daejeon = pd.read_feather(\"../data/data_for_modeling/df_daejeon.feather\")\n",
    "df_gwangju = pd.read_feather(\"../data/data_for_modeling/df_gwangju.feather\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 48534, 1: 3941, 0: 109})"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_seoul['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 50069, 1: 2350, 0: 165})"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_busan['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 44944, 1: 6658, 0: 982})"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_incheon['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 50919, 1: 1610, 0: 55})"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_daegu['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 48047, 1: 4227, 0: 310})"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_daejeon['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({2: 48405, 1: 4015, 0: 164})"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(df_gwangju['multi_class'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(52584, 30)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_seoul.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_seoul = df_seoul.loc[df_seoul['year'].isin([2018, 2019, 2020, 2021]),:].copy()\n",
    "df_busan = df_busan.loc[df_busan['year'].isin([2018, 2019, 2020, 2021]),:].copy()\n",
    "df_incheon = df_incheon.loc[df_incheon['year'].isin([2018, 2019, 2020, 2021]),:].copy()\n",
    "df_daegu = df_daegu.loc[df_daegu['year'].isin([2018, 2019, 2020, 2021]),:].copy()\n",
    "df_daejeon = df_daejeon.loc[df_daejeon['year'].isin([2018, 2019, 2020, 2021]),:].copy()\n",
    "df_gwangju = df_gwangju.loc[df_gwangju['year'].isin([2018, 2019, 2020, 2021]),:].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [col for col in df_seoul.columns if col != \"multi_class\"] + [\"multi_class\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_seoul = df_seoul[cols]\n",
    "df_busan = df_busan[cols]\n",
    "df_incheon = df_incheon[cols]\n",
    "df_daegu = df_daegu[cols]\n",
    "df_daejeon = df_daejeon[cols]\n",
    "df_gwangju = df_gwangju[cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_seoul_train = df_seoul.loc[df_seoul['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_seoul_test = df_seoul.loc[df_seoul['year'].isin([2021]),:].copy()\n",
    "\n",
    "df_busan_train = df_busan.loc[df_busan['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_busan_test = df_busan.loc[df_busan['year'].isin([2021]),:].copy()\n",
    "\n",
    "df_incheon_train = df_incheon.loc[df_incheon['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_incheon_test = df_incheon.loc[df_incheon['year'].isin([2021]),:].copy()\n",
    "\n",
    "df_daegu_train = df_daegu.loc[df_daegu['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_daegu_test = df_daegu.loc[df_daegu['year'].isin([2021]),:].copy()\n",
    "\n",
    "df_daejeon_train = df_daejeon.loc[df_daejeon['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_daejeon_test = df_daejeon.loc[df_daejeon['year'].isin([2021]),:].copy()\n",
    "\n",
    "df_gwangju_train = df_gwangju.loc[df_gwangju['year'].isin([2018, 2019, 2020]),:].copy()\n",
    "df_gwangju_test = df_gwangju.loc[df_gwangju['year'].isin([2021]),:].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>temp_C</th>\n",
       "      <th>precip_mm</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>hm</th>\n",
       "      <th>vap_pressure</th>\n",
       "      <th>dewpoint_C</th>\n",
       "      <th>loc_pressure</th>\n",
       "      <th>sea_pressure</th>\n",
       "      <th>solarRad</th>\n",
       "      <th>...</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>hour</th>\n",
       "      <th>ground_temp - temp_C</th>\n",
       "      <th>hour_sin</th>\n",
       "      <th>hour_cos</th>\n",
       "      <th>month_sin</th>\n",
       "      <th>month_cos</th>\n",
       "      <th>visi</th>\n",
       "      <th>multi_class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.6</td>\n",
       "      <td>360</td>\n",
       "      <td>35.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>-12.6</td>\n",
       "      <td>1015.8</td>\n",
       "      <td>1024.6</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>-5.4</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.3</td>\n",
       "      <td>360</td>\n",
       "      <td>33.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>-13.9</td>\n",
       "      <td>1015.5</td>\n",
       "      <td>1024.3</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-5.4</td>\n",
       "      <td>0.258819</td>\n",
       "      <td>9.659258e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.5</td>\n",
       "      <td>20</td>\n",
       "      <td>34.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>-13.9</td>\n",
       "      <td>1015.7</td>\n",
       "      <td>1024.5</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-5.4</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>8.660254e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>320</td>\n",
       "      <td>37.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>-12.9</td>\n",
       "      <td>1015.9</td>\n",
       "      <td>1024.7</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>-5.0</td>\n",
       "      <td>0.707107</td>\n",
       "      <td>7.071068e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>340</td>\n",
       "      <td>42.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>-11.5</td>\n",
       "      <td>1016.0</td>\n",
       "      <td>1024.9</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>-4.3</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>5.000000e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>-0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.8</td>\n",
       "      <td>50</td>\n",
       "      <td>43.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>-11.2</td>\n",
       "      <td>1016.0</td>\n",
       "      <td>1024.9</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>-4.0</td>\n",
       "      <td>0.965926</td>\n",
       "      <td>2.588190e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>-0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>20</td>\n",
       "      <td>45.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>-11.0</td>\n",
       "      <td>1016.5</td>\n",
       "      <td>1025.4</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>-4.1</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>6.123234e-17</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>-0.8</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>340</td>\n",
       "      <td>45.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>-11.2</td>\n",
       "      <td>1017.1</td>\n",
       "      <td>1026.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>-4.5</td>\n",
       "      <td>0.965926</td>\n",
       "      <td>-2.588190e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>-0.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>360</td>\n",
       "      <td>43.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>-11.5</td>\n",
       "      <td>1017.4</td>\n",
       "      <td>1026.3</td>\n",
       "      <td>0.03</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>-4.0</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>-5.000000e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>20</td>\n",
       "      <td>39.0</td>\n",
       "      <td>2.7</td>\n",
       "      <td>-10.8</td>\n",
       "      <td>1018.1</td>\n",
       "      <td>1026.9</td>\n",
       "      <td>0.46</td>\n",
       "      <td>...</td>\n",
       "      <td>2018</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>2.8</td>\n",
       "      <td>0.707107</td>\n",
       "      <td>-7.071068e-01</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.866025</td>\n",
       "      <td>1953.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   temp_C  precip_mm  wind_speed wind_dir    hm  vap_pressure  dewpoint_C  \\\n",
       "0     1.2        0.0         1.6      360  35.0           2.3       -12.6   \n",
       "1     0.5        0.0         1.3      360  33.0           2.1       -13.9   \n",
       "2     0.1        0.0         1.5       20  34.0           2.1       -13.9   \n",
       "3     0.0        0.0         2.1      320  37.0           2.3       -12.9   \n",
       "4    -0.1        0.0         2.3      340  42.0           2.5       -11.5   \n",
       "5    -0.1        0.0         2.8       50  43.0           2.6       -11.2   \n",
       "6    -0.5        0.0         2.1       20  45.0           2.6       -11.0   \n",
       "7    -0.8        0.0         2.5      340  45.0           2.6       -11.2   \n",
       "8    -0.5        0.0         1.2      360  43.0           2.5       -11.5   \n",
       "9     1.7        0.0         2.1       20  39.0           2.7       -10.8   \n",
       "\n",
       "   loc_pressure  sea_pressure  solarRad  ...  year month hour  \\\n",
       "0        1015.8        1024.6      0.00  ...  2018     1    0   \n",
       "1        1015.5        1024.3      0.00  ...  2018     1    1   \n",
       "2        1015.7        1024.5      0.00  ...  2018     1    2   \n",
       "3        1015.9        1024.7      0.00  ...  2018     1    3   \n",
       "4        1016.0        1024.9      0.00  ...  2018     1    4   \n",
       "5        1016.0        1024.9      0.00  ...  2018     1    5   \n",
       "6        1016.5        1025.4      0.00  ...  2018     1    6   \n",
       "7        1017.1        1026.0      0.00  ...  2018     1    7   \n",
       "8        1017.4        1026.3      0.03  ...  2018     1    8   \n",
       "9        1018.1        1026.9      0.46  ...  2018     1    9   \n",
       "\n",
       "   ground_temp - temp_C  hour_sin      hour_cos  month_sin  month_cos    visi  \\\n",
       "0                  -5.4  0.000000  1.000000e+00        0.5   0.866025  2000.0   \n",
       "1                  -5.4  0.258819  9.659258e-01        0.5   0.866025  2000.0   \n",
       "2                  -5.4  0.500000  8.660254e-01        0.5   0.866025  2000.0   \n",
       "3                  -5.0  0.707107  7.071068e-01        0.5   0.866025  2000.0   \n",
       "4                  -4.3  0.866025  5.000000e-01        0.5   0.866025  2000.0   \n",
       "5                  -4.0  0.965926  2.588190e-01        0.5   0.866025  2000.0   \n",
       "6                  -4.1  1.000000  6.123234e-17        0.5   0.866025  2000.0   \n",
       "7                  -4.5  0.965926 -2.588190e-01        0.5   0.866025  2000.0   \n",
       "8                  -4.0  0.866025 -5.000000e-01        0.5   0.866025  2000.0   \n",
       "9                   2.8  0.707107 -7.071068e-01        0.5   0.866025  1953.0   \n",
       "\n",
       "   multi_class  \n",
       "0            2  \n",
       "1            2  \n",
       "2            2  \n",
       "3            2  \n",
       "4            2  \n",
       "5            2  \n",
       "6            2  \n",
       "7            2  \n",
       "8            2  \n",
       "9            2  \n",
       "\n",
       "[10 rows x 30 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_busan_train.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>temp_C</th>\n",
       "      <th>precip_mm</th>\n",
       "      <th>wind_speed</th>\n",
       "      <th>wind_dir</th>\n",
       "      <th>hm</th>\n",
       "      <th>vap_pressure</th>\n",
       "      <th>dewpoint_C</th>\n",
       "      <th>loc_pressure</th>\n",
       "      <th>sea_pressure</th>\n",
       "      <th>solarRad</th>\n",
       "      <th>...</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>hour</th>\n",
       "      <th>ground_temp - temp_C</th>\n",
       "      <th>hour_sin</th>\n",
       "      <th>hour_cos</th>\n",
       "      <th>month_sin</th>\n",
       "      <th>month_cos</th>\n",
       "      <th>visi</th>\n",
       "      <th>multi_class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>26294</th>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.3</td>\n",
       "      <td>270</td>\n",
       "      <td>37.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>-12.9</td>\n",
       "      <td>1013.3</td>\n",
       "      <td>1022.1</td>\n",
       "      <td>2.07</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>14</td>\n",
       "      <td>5.8</td>\n",
       "      <td>-0.500000</td>\n",
       "      <td>-8.660254e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26295</th>\n",
       "      <td>1.2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.9</td>\n",
       "      <td>270</td>\n",
       "      <td>35.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>-12.6</td>\n",
       "      <td>1013.2</td>\n",
       "      <td>1022.0</td>\n",
       "      <td>1.71</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "      <td>5.6</td>\n",
       "      <td>-0.707107</td>\n",
       "      <td>-7.071068e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26296</th>\n",
       "      <td>1.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>290</td>\n",
       "      <td>34.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>-12.6</td>\n",
       "      <td>1012.8</td>\n",
       "      <td>1021.6</td>\n",
       "      <td>1.14</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>16</td>\n",
       "      <td>1.4</td>\n",
       "      <td>-0.866025</td>\n",
       "      <td>-5.000000e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26297</th>\n",
       "      <td>1.2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>250</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>-11.5</td>\n",
       "      <td>1012.8</td>\n",
       "      <td>1021.6</td>\n",
       "      <td>0.48</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>17</td>\n",
       "      <td>-0.4</td>\n",
       "      <td>-0.965926</td>\n",
       "      <td>-2.588190e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26298</th>\n",
       "      <td>0.9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>270</td>\n",
       "      <td>40.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>-11.2</td>\n",
       "      <td>1013.1</td>\n",
       "      <td>1021.9</td>\n",
       "      <td>0.02</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>18</td>\n",
       "      <td>-0.8</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.836970e-16</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26299</th>\n",
       "      <td>0.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.2</td>\n",
       "      <td>270</td>\n",
       "      <td>41.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>-11.1</td>\n",
       "      <td>1014.0</td>\n",
       "      <td>1022.8</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>19</td>\n",
       "      <td>-1.1</td>\n",
       "      <td>-0.965926</td>\n",
       "      <td>2.588190e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26300</th>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>270</td>\n",
       "      <td>44.0</td>\n",
       "      <td>2.7</td>\n",
       "      <td>-10.7</td>\n",
       "      <td>1014.8</td>\n",
       "      <td>1023.6</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>20</td>\n",
       "      <td>-0.9</td>\n",
       "      <td>-0.866025</td>\n",
       "      <td>5.000000e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26301</th>\n",
       "      <td>-0.2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>290</td>\n",
       "      <td>48.0</td>\n",
       "      <td>2.9</td>\n",
       "      <td>-9.9</td>\n",
       "      <td>1014.6</td>\n",
       "      <td>1023.4</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>21</td>\n",
       "      <td>-0.8</td>\n",
       "      <td>-0.707107</td>\n",
       "      <td>7.071068e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26302</th>\n",
       "      <td>-0.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.7</td>\n",
       "      <td>270</td>\n",
       "      <td>51.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-9.6</td>\n",
       "      <td>1014.8</td>\n",
       "      <td>1023.6</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>22</td>\n",
       "      <td>-0.6</td>\n",
       "      <td>-0.500000</td>\n",
       "      <td>8.660254e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26303</th>\n",
       "      <td>-0.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>250</td>\n",
       "      <td>55.0</td>\n",
       "      <td>3.2</td>\n",
       "      <td>-8.6</td>\n",
       "      <td>1015.1</td>\n",
       "      <td>1024.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>...</td>\n",
       "      <td>2020</td>\n",
       "      <td>12</td>\n",
       "      <td>23</td>\n",
       "      <td>-0.6</td>\n",
       "      <td>-0.258819</td>\n",
       "      <td>9.659258e-01</td>\n",
       "      <td>-2.449294e-16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       temp_C  precip_mm  wind_speed wind_dir    hm  vap_pressure  dewpoint_C  \\\n",
       "26294     0.1        0.0         6.3      270  37.0           2.3       -12.9   \n",
       "26295     1.2        0.0         5.9      270  35.0           2.3       -12.6   \n",
       "26296     1.6        0.0         3.6      290  34.0           2.3       -12.6   \n",
       "26297     1.2        0.0         3.8      250  38.0           2.5       -11.5   \n",
       "26298     0.9        0.0         3.8      270  40.0           2.6       -11.2   \n",
       "26299     0.6        0.0         6.2      270  41.0           2.6       -11.1   \n",
       "26300     0.1        0.0         6.0      270  44.0           2.7       -10.7   \n",
       "26301    -0.2        0.0         5.0      290  48.0           2.9        -9.9   \n",
       "26302    -0.7        0.0         2.7      270  51.0           3.0        -9.6   \n",
       "26303    -0.7        0.0         3.8      250  55.0           3.2        -8.6   \n",
       "\n",
       "       loc_pressure  sea_pressure  solarRad  ...  year month hour  \\\n",
       "26294        1013.3        1022.1      2.07  ...  2020    12   14   \n",
       "26295        1013.2        1022.0      1.71  ...  2020    12   15   \n",
       "26296        1012.8        1021.6      1.14  ...  2020    12   16   \n",
       "26297        1012.8        1021.6      0.48  ...  2020    12   17   \n",
       "26298        1013.1        1021.9      0.02  ...  2020    12   18   \n",
       "26299        1014.0        1022.8      0.00  ...  2020    12   19   \n",
       "26300        1014.8        1023.6      0.00  ...  2020    12   20   \n",
       "26301        1014.6        1023.4      0.00  ...  2020    12   21   \n",
       "26302        1014.8        1023.6      0.00  ...  2020    12   22   \n",
       "26303        1015.1        1024.0      0.00  ...  2020    12   23   \n",
       "\n",
       "       ground_temp - temp_C  hour_sin      hour_cos     month_sin  month_cos  \\\n",
       "26294                   5.8 -0.500000 -8.660254e-01 -2.449294e-16        1.0   \n",
       "26295                   5.6 -0.707107 -7.071068e-01 -2.449294e-16        1.0   \n",
       "26296                   1.4 -0.866025 -5.000000e-01 -2.449294e-16        1.0   \n",
       "26297                  -0.4 -0.965926 -2.588190e-01 -2.449294e-16        1.0   \n",
       "26298                  -0.8 -1.000000 -1.836970e-16 -2.449294e-16        1.0   \n",
       "26299                  -1.1 -0.965926  2.588190e-01 -2.449294e-16        1.0   \n",
       "26300                  -0.9 -0.866025  5.000000e-01 -2.449294e-16        1.0   \n",
       "26301                  -0.8 -0.707107  7.071068e-01 -2.449294e-16        1.0   \n",
       "26302                  -0.6 -0.500000  8.660254e-01 -2.449294e-16        1.0   \n",
       "26303                  -0.6 -0.258819  9.659258e-01 -2.449294e-16        1.0   \n",
       "\n",
       "         visi  multi_class  \n",
       "26294  5000.0            2  \n",
       "26295  5000.0            2  \n",
       "26296  5000.0            2  \n",
       "26297  5000.0            2  \n",
       "26298  5000.0            2  \n",
       "26299  5000.0            2  \n",
       "26300  5000.0            2  \n",
       "26301  5000.0            2  \n",
       "26302  5000.0            2  \n",
       "26303  5000.0            2  \n",
       "\n",
       "[10 rows x 30 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_busan_train.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 26304 entries, 0 to 26303\n",
      "Data columns (total 30 columns):\n",
      " #   Column                Non-Null Count  Dtype   \n",
      "---  ------                --------------  -----   \n",
      " 0   temp_C                26304 non-null  float64 \n",
      " 1   precip_mm             26304 non-null  float64 \n",
      " 2   wind_speed            26304 non-null  float64 \n",
      " 3   wind_dir              26304 non-null  category\n",
      " 4   hm                    26304 non-null  float64 \n",
      " 5   vap_pressure          26304 non-null  float64 \n",
      " 6   dewpoint_C            26304 non-null  float64 \n",
      " 7   loc_pressure          26304 non-null  float64 \n",
      " 8   sea_pressure          26304 non-null  float64 \n",
      " 9   solarRad              26304 non-null  float64 \n",
      " 10  snow_cm               26304 non-null  float64 \n",
      " 11  cloudcover            26304 non-null  category\n",
      " 12  lm_cloudcover         26304 non-null  category\n",
      " 13  low_cloudbase         26304 non-null  float64 \n",
      " 14  groundtemp            26304 non-null  float64 \n",
      " 15  O3                    26304 non-null  float64 \n",
      " 16  NO2                   26304 non-null  float64 \n",
      " 17  PM10                  26304 non-null  float64 \n",
      " 18  PM25                  26304 non-null  float64 \n",
      " 19  binary_class          26304 non-null  int64   \n",
      " 20  year                  26304 non-null  int64   \n",
      " 21  month                 26304 non-null  int64   \n",
      " 22  hour                  26304 non-null  int64   \n",
      " 23  ground_temp - temp_C  26304 non-null  float64 \n",
      " 24  hour_sin              26304 non-null  float64 \n",
      " 25  hour_cos              26304 non-null  float64 \n",
      " 26  month_sin             26304 non-null  float64 \n",
      " 27  month_cos             26304 non-null  float64 \n",
      " 28  visi                  26304 non-null  float64 \n",
      " 29  multi_class           26304 non-null  int64   \n",
      "dtypes: category(3), float64(22), int64(5)\n",
      "memory usage: 5.7 MB\n"
     ]
    }
   ],
   "source": [
    "df_busan_train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_seoul_train.to_csv(\"../data/data_for_modeling/seoul_train.csv\")\n",
    "df_seoul_test.to_csv(\"../data/data_for_modeling/seoul_test.csv\")\n",
    "\n",
    "df_busan_train.to_csv(\"../data/data_for_modeling/busan_train.csv\")\n",
    "df_busan_test.to_csv(\"../data/data_for_modeling/busan_test.csv\")\n",
    "\n",
    "df_incheon_train.to_csv(\"../data/data_for_modeling/incheon_train.csv\")\n",
    "df_incheon_test.to_csv(\"../data/data_for_modeling/incheon_test.csv\")\n",
    "\n",
    "df_daegu_train.to_csv(\"../data/data_for_modeling/daegu_train.csv\")\n",
    "df_daegu_test.to_csv(\"../data/data_for_modeling/daegu_test.csv\")\n",
    "\n",
    "df_daejeon_train.to_csv(\"../data/data_for_modeling/daejeon_train.csv\")\n",
    "df_daejeon_test.to_csv(\"../data/data_for_modeling/daejeon_test.csv\")\n",
    "\n",
    "df_gwangju_train.to_csv(\"../data/data_for_modeling/gwangju_train.csv\")\n",
    "df_gwangju_test.to_csv(\"../data/data_for_modeling/gwangju_test.csv\")\n",
    "\n",
    "df_seoul_train = pd.read_csv(\"../data/data_for_modeling/seoul_train.csv\")\n",
    "df_seoul_test = pd.read_csv(\"../data/data_for_modeling/seoul_test.csv\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({2: 8266, 1: 481, 0: 13})\n",
      "Counter({2: 23686, 1: 2579, 0: 39})\n",
      "Counter({2: 8455, 1: 281, 0: 24})\n",
      "Counter({2: 24694, 1: 1516, 0: 94})\n",
      "Counter({2: 7373, 1: 1205, 0: 182})\n",
      "Counter({2: 21893, 1: 3892, 0: 519})\n",
      "Counter({2: 8631, 1: 128, 0: 1})\n",
      "Counter({2: 25149, 1: 1107, 0: 48})\n",
      "Counter({2: 8089, 1: 618, 0: 53})\n",
      "Counter({2: 23471, 1: 2660, 0: 173})\n",
      "Counter({2: 8087, 1: 643, 0: 30})\n",
      "Counter({2: 23798, 1: 2411, 0: 95})\n"
     ]
    }
   ],
   "source": [
    "print(Counter(df_seoul_test['multi_class']))\n",
    "print(Counter(df_seoul_train['multi_class']))\n",
    "\n",
    "print(Counter(df_busan_test['multi_class']))\n",
    "print(Counter(df_busan_train['multi_class']))\n",
    "\n",
    "print(Counter(df_incheon_test['multi_class']))\n",
    "print(Counter(df_incheon_train['multi_class']))\n",
    "\n",
    "print(Counter(df_daegu_test['multi_class']))\n",
    "print(Counter(df_daegu_train['multi_class']))\n",
    "\n",
    "print(Counter(df_daejeon_test['multi_class']))\n",
    "print(Counter(df_daejeon_train['multi_class']))\n",
    "\n",
    "print(Counter(df_gwangju_test['multi_class']))\n",
    "print(Counter(df_gwangju_train['multi_class']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}