{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4944982d",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Heel lab Heel brand</th>\n",
       "      <th>Forefoot lab Forefoot brand</th>\n",
       "      <th>Widths available</th>\n",
       "      <th>Orthotic friendly</th>\n",
       "      <th>Season</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily runningTempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>32.4 mm 36.0 mm</td>\n",
       "      <td>23.0 mm 26.0 mm</td>\n",
       "      <td>NormalWide</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "      <td>1</td>\n",
       "      <td>#301 Top 47%</td>\n",
       "      <td>#352 Bottom 45%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>34.3 mm 32.5 mm</td>\n",
       "      <td>26.6 mm 24.5 mm</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>SummerAll seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#72 Top 20%</td>\n",
       "      <td>#255 Bottom 30%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>33.3 mm 32.5 mm</td>\n",
       "      <td>24.4 mm 22.5 mm</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#104 Top 17%</td>\n",
       "      <td>#368 Bottom 42%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>31.8 mm 32.0 mm</td>\n",
       "      <td>21.2 mm 21.0 mm</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#126 Top 20%</td>\n",
       "      <td>#541 Bottom 16%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>32.6 mm 34.0 mm</td>\n",
       "      <td>22.7 mm 24.0 mm</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#116 Top 32%</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily runningTempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Heel lab Heel brand Forefoot lab Forefoot brand  \\\n",
       "0  HeelMid/forefoot  ...     32.4 mm 36.0 mm             23.0 mm 26.0 mm   \n",
       "1      Mid/forefoot  ...     34.3 mm 32.5 mm             26.6 mm 24.5 mm   \n",
       "2  HeelMid/forefoot  ...     33.3 mm 32.5 mm             24.4 mm 22.5 mm   \n",
       "3              Heel  ...     31.8 mm 32.0 mm             21.2 mm 21.0 mm   \n",
       "4  HeelMid/forefoot  ...     32.6 mm 34.0 mm             22.7 mm 24.0 mm   \n",
       "\n",
       "  Widths available Orthotic friendly             Season Removable insole  \\\n",
       "0       NormalWide                 1                  -                1   \n",
       "1           Normal                 1  SummerAll seasons                1   \n",
       "2           Normal                 1        All seasons                1   \n",
       "3           Normal                 1        All seasons                1   \n",
       "4           Normal                 1        All seasons                1   \n",
       "\n",
       "        Ranking       Popularity Gender Terrain  \n",
       "0  #301 Top 47%  #352 Bottom 45%    NaN     NaN  \n",
       "1   #72 Top 20%  #255 Bottom 30%    NaN     NaN  \n",
       "2  #104 Top 17%  #368 Bottom 42%    NaN     NaN  \n",
       "3  #126 Top 20%  #541 Bottom 16%    NaN     NaN  \n",
       "4  #116 Top 32%   #339 Bottom 7%    NaN     NaN  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv('../../data/SONIX utilities - Road.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d066ba9",
   "metadata": {},
   "source": [
    "value \"✗\" sama \"✓\" udah diubah ke 0 1 manual di sheet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bc8a931f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.DataFrame'>\n",
      "RangeIndex: 1170 entries, 0 to 1169\n",
      "Data columns (total 33 columns):\n",
      " #   Column                       Non-Null Count  Dtype\n",
      "---  ------                       --------------  -----\n",
      " 0   Brand                        1170 non-null   str  \n",
      " 1   Name                         1170 non-null   str  \n",
      " 2   Audience score               1164 non-null   str  \n",
      " 3   Price                        1170 non-null   str  \n",
      " 4   Pace                         1170 non-null   str  \n",
      " 5   Arch support                 1170 non-null   str  \n",
      " 6   Weight lab Weight brand      1170 non-null   str  \n",
      " 7   Lightweight                  1170 non-null   int64\n",
      " 8   Drop lab Drop brand          1170 non-null   str  \n",
      " 9   Strike pattern               1170 non-null   str  \n",
      " 10  Size                         1170 non-null   str  \n",
      " 11  Midsole softness             1170 non-null   str  \n",
      " 12  Toebox durability            1170 non-null   str  \n",
      " 13  Heel padding durability      1170 non-null   str  \n",
      " 14  Outsole durability           1170 non-null   str  \n",
      " 15  Breathability                1170 non-null   str  \n",
      " 16  Width / fit                  1170 non-null   str  \n",
      " 17  Toebox width                 1170 non-null   str  \n",
      " 18  Stiffness                    1170 non-null   str  \n",
      " 19  Torsional rigidity           1170 non-null   str  \n",
      " 20  Heel counter stiffness       1170 non-null   str  \n",
      " 21  Plate                        1170 non-null   str  \n",
      " 22  Rocker                       1170 non-null   int64\n",
      " 23  Heel lab Heel brand          1170 non-null   str  \n",
      " 24  Forefoot lab Forefoot brand  1170 non-null   str  \n",
      " 25  Widths available             1170 non-null   str  \n",
      " 26  Orthotic friendly            1170 non-null   int64\n",
      " 27  Season                       1170 non-null   str  \n",
      " 28  Removable insole             1170 non-null   int64\n",
      " 29  Ranking                      1170 non-null   str  \n",
      " 30  Popularity                   1170 non-null   str  \n",
      " 31  Gender                       10 non-null     str  \n",
      " 32  Terrain                      16 non-null     str  \n",
      "dtypes: int64(4), str(29)\n",
      "memory usage: 301.8 KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c0b39803",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Brand (32 unique)\n",
      "<StringArray>\n",
      "[      'Brooks',       'Adidas',     'Skechers',      'Salomon',\n",
      "         'Nike',       'NOBULL',         'Hoka',         'HOKA',\n",
      "         'Topo',      'Diadora',      'Saucony', 'Under Armour',\n",
      "           'On',           'on',          'On ',         'PUMA',\n",
      "         'Puma',         'NIke',        'ASICS',        'Altra',\n",
      "       'Reebok',  'New Balance',  'new Balance',       'Mizuno',\n",
      "        'Nike ',       'Jordan',        'Inov8',      'SAlomon',\n",
      "         'Xero',          'APL',     'Allbirds',      'Merrell']\n",
      "Length: 32, dtype: str\n",
      "\n",
      "Pace (5 unique)\n",
      "<StringArray>\n",
      "['Daily runningTempo',      'Daily running',              'Tempo',\n",
      "   'CompetitionTempo',        'Competition']\n",
      "Length: 5, dtype: str\n",
      "\n",
      "Arch support (3 unique)\n",
      "<StringArray>\n",
      "['Neutral', 'Motion control', 'Stability']\n",
      "Length: 3, dtype: str\n",
      "\n",
      "Lightweight (2 unique)\n",
      "[1 0]\n",
      "\n",
      "Strike pattern (5 unique)\n",
      "<StringArray>\n",
      "['HeelMid/forefoot', 'Mid/forefoot', 'Heel', '-', 'Heel Mid/forefoot']\n",
      "Length: 5, dtype: str\n",
      "\n",
      "Size (6 unique)\n",
      "<StringArray>\n",
      "[   'True to size',  'Slightly small', 'Half size small',  'Slightly large',\n",
      "               '-', 'Half size large']\n",
      "Length: 6, dtype: str\n",
      "\n",
      "Midsole softness (4 unique)\n",
      "<StringArray>\n",
      "['Balanced', 'Soft', 'Firm', '-']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Toebox durability (4 unique)\n",
      "<StringArray>\n",
      "['-', 'Good', 'Decent', 'Bad']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Heel padding durability (4 unique)\n",
      "<StringArray>\n",
      "['-', 'Good', 'Decent', 'Bad']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Outsole durability (4 unique)\n",
      "<StringArray>\n",
      "['-', 'Good', 'Decent', 'Bad']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Breathability (4 unique)\n",
      "<StringArray>\n",
      "['-', 'Breathable', 'Warm', 'Moderate']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Width / fit (3 unique)\n",
      "<StringArray>\n",
      "['Narrow', 'Medium', 'Wide']\n",
      "Length: 3, dtype: str\n",
      "\n",
      "Toebox width (4 unique)\n",
      "<StringArray>\n",
      "['-', 'Medium', 'Wide', 'Narrow']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Stiffness (4 unique)\n",
      "<StringArray>\n",
      "['Stiff', 'Moderate', 'Flexible', '-']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Torsional rigidity (4 unique)\n",
      "<StringArray>\n",
      "['Stiff', 'Moderate', 'Flexible', '-']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Heel counter stiffness (4 unique)\n",
      "<StringArray>\n",
      "['Flexible', 'Moderate', 'Stiff', '-']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Plate (3 unique)\n",
      "<StringArray>\n",
      "['0', 'Carbon plate', 'Carbon plateRock plate']\n",
      "Length: 3, dtype: str\n",
      "\n",
      "Rocker (2 unique)\n",
      "[0 1]\n",
      "\n",
      "Widths available (11 unique)\n",
      "<StringArray>\n",
      "[               'NormalWide',                    'Normal',\n",
      "    'NarrowNormalWideX-Wide',              'NormalX-Wide',\n",
      "          'NarrowNormalWide',          'NormalWideX-Wide',\n",
      " 'Narrow Normal Wide X-Wide',              'NarrowNormal',\n",
      "               'Normal Wide',        'NarrowNormalX-Wide',\n",
      "        'Normal Wide X-Wide']\n",
      "Length: 11, dtype: str\n",
      "\n",
      "Orthotic friendly (2 unique)\n",
      "[1 0]\n",
      "\n",
      "Season (4 unique)\n",
      "<StringArray>\n",
      "['-', 'SummerAll seasons', 'All seasons', 'Winter']\n",
      "Length: 4, dtype: str\n",
      "\n",
      "Removable insole (2 unique)\n",
      "[1 0]\n"
     ]
    }
   ],
   "source": [
    "observed_col = [\n",
    "    'Brand',\n",
    "    'Pace',\n",
    "    'Arch support',\n",
    "    'Lightweight',\n",
    "    'Strike pattern',\n",
    "    'Size',\n",
    "    'Midsole softness',\n",
    "    'Toebox durability',\n",
    "    'Heel padding durability',\n",
    "    'Outsole durability',\n",
    "    'Breathability',\n",
    "    'Width / fit',\n",
    "    'Toebox width',\n",
    "    'Stiffness',\n",
    "    'Torsional rigidity',\n",
    "    'Heel counter stiffness',\n",
    "    'Plate',\n",
    "    'Rocker',\n",
    "    'Widths available',\n",
    "    'Orthotic friendly',\n",
    "    'Season',\n",
    "    'Removable insole'\n",
    "]\n",
    "\n",
    "for col in observed_col:    \n",
    "    uniques = df[col].dropna().unique()\n",
    "    print(f\"\\n{col} ({len(uniques)} unique)\")\n",
    "    print(uniques)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "bbabcc2e",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Heel lab Heel brand</th>\n",
       "      <th>Forefoot lab Forefoot brand</th>\n",
       "      <th>Widths available</th>\n",
       "      <th>Orthotic friendly</th>\n",
       "      <th>Season</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>0 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Brand, Name, Audience score, Price, Pace, Arch support, Weight lab Weight brand, Lightweight, Drop lab Drop brand, Strike pattern, Size, Midsole softness, Toebox durability, Heel padding durability, Outsole durability, Breathability, Width / fit, Toebox width, Stiffness, Torsional rigidity, Heel counter stiffness, Plate, Rocker, Heel lab Heel brand, Forefoot lab Forefoot brand, Widths available, Orthotic friendly, Season, Removable insole, Ranking, Popularity, Gender, Terrain]\n",
       "Index: []\n",
       "\n",
       "[0 rows x 33 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check row dari filter masih kemasukan apa ngga\n",
    "df[df[\"Pace\"]== \"Select\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89492cc7",
   "metadata": {},
   "source": [
    "# Cleaning Brand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "23002f3b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Brand (24 uniques): \n",
      " ['Adidas', 'Allbirds', 'Altra', 'Apl', 'Asics', 'Brooks', 'Diadora', 'Hoka', 'Inov8', 'Jordan', 'Merrell', 'Mizuno', 'New Balance', 'Nike', 'Nobull', 'On', 'Puma', 'Reebok', 'Salomon', 'Saucony', 'Skechers', 'Topo', 'Under Armour', 'Xero']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Brand\n",
       "Asics           190\n",
       "Adidas          157\n",
       "Nike            148\n",
       "Brooks          130\n",
       "Saucony          83\n",
       "New Balance      82\n",
       "Hoka             67\n",
       "Mizuno           57\n",
       "On               52\n",
       "Altra            50\n",
       "Puma             42\n",
       "Under Armour     26\n",
       "Reebok           18\n",
       "Skechers         16\n",
       "Salomon          10\n",
       "Allbirds          9\n",
       "Nobull            7\n",
       "Xero              7\n",
       "Diadora           6\n",
       "Topo              5\n",
       "Inov8             4\n",
       "Merrell           2\n",
       "Jordan            1\n",
       "Apl               1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Brand\"] = (\n",
    "    df[\"Brand\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "brand_uniques = df[\"Brand\"].dropna().unique()\n",
    "# brand_uniques.sort()\n",
    "brand_uniques = sorted(brand_uniques)\n",
    "print(f\"Brand ({len(brand_uniques)} uniques): \\n\",brand_uniques)\n",
    "\n",
    "df[\"Brand\"].value_counts().head(25)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69438526",
   "metadata": {},
   "source": [
    "wow beda (cooked)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "402ada5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total sepatu (rows): 1170\n"
     ]
    }
   ],
   "source": [
    "total_rows = len(df)\n",
    "print(\"Total sepatu (rows):\", total_rows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "62f507b4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Jumlah sepatu dari seluruh brand: 1170\n",
      "Jumlah brand unik: 24\n"
     ]
    }
   ],
   "source": [
    "brand_counts = df[\"Brand\"].value_counts()\n",
    "print(\"Jumlah sepatu dari seluruh brand:\", brand_counts.sum())\n",
    "print(\"Jumlah brand unik:\", brand_counts.shape[0])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d7df55d3",
   "metadata": {},
   "source": [
    "terlihat sudah sama, lalu salahnya dimana? stay tuned"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "392e4487",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Heel lab Heel brand</th>\n",
       "      <th>Forefoot lab Forefoot brand</th>\n",
       "      <th>Widths available</th>\n",
       "      <th>Orthotic friendly</th>\n",
       "      <th>Season</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>839</th>\n",
       "      <td>Jordan</td>\n",
       "      <td>React Havoc</td>\n",
       "      <td>83\\n Good!</td>\n",
       "      <td>$130</td>\n",
       "      <td>Daily running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>9.5 oz / 268g 10.8 oz / 306g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.2 mm 9.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>32.3 mm 28.0 mm</td>\n",
       "      <td>22.1 mm 19.0 mm</td>\n",
       "      <td>Normal</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>#258 Bottom 29%</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Brand         Name Audience score Price           Pace Arch support  \\\n",
       "839  Jordan  React Havoc     83\\n Good!  $130  Daily running      Neutral   \n",
       "\n",
       "          Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "839  9.5 oz / 268g 10.8 oz / 306g            0      10.2 mm 9.0 mm   \n",
       "\n",
       "    Strike pattern  ... Heel lab Heel brand Forefoot lab Forefoot brand  \\\n",
       "839           Heel  ...     32.3 mm 28.0 mm             22.1 mm 19.0 mm   \n",
       "\n",
       "    Widths available Orthotic friendly Season Removable insole  \\\n",
       "839           Normal                 0      -                0   \n",
       "\n",
       "             Ranking      Popularity Gender Terrain  \n",
       "839  #258 Bottom 29%  #339 Bottom 7%    NaN     NaN  \n",
       "\n",
       "[1 rows x 33 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"Brand\"]== \"Jordan\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b45c770b",
   "metadata": {},
   "source": [
    "jujur bingung dan sudah ingin crash out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8fb7fb1d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Asics           : 190\n",
      "Adidas          : 157\n",
      "Nike            : 148\n",
      "Brooks          : 130\n",
      "Saucony         : 83\n",
      "New Balance     : 82\n",
      "Hoka            : 67\n",
      "Mizuno          : 57\n",
      "On              : 52\n",
      "Altra           : 50\n",
      "Puma            : 42\n",
      "Under Armour    : 26\n",
      "Reebok          : 18\n",
      "Skechers        : 16\n",
      "Salomon         : 10\n",
      "Allbirds        : 9\n",
      "Nobull          : 7\n",
      "Xero            : 7\n",
      "Diadora         : 6\n",
      "Topo            : 5\n",
      "Inov8           : 4\n",
      "Merrell         : 2\n",
      "Jordan          : 1\n",
      "Apl             : 1\n"
     ]
    }
   ],
   "source": [
    "brands = df[\"Brand\"].value_counts()\n",
    "\n",
    "for brand, count in brands.items():\n",
    "    print(f\"{brand:<15} : {count}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "fc1ea3e3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TOTAL sepatu (sum of brand counts): 1170\n"
     ]
    }
   ],
   "source": [
    "print(\"TOTAL sepatu (sum of brand counts):\", brand_counts.sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f4e70d6",
   "metadata": {},
   "source": [
    "kocak ternyata sudah benar"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "94e4aaaa",
   "metadata": {},
   "source": [
    "### Asumsi : \n",
    "Ada 24 unique brand dengan 1195 total sepatu. belum ada observasi lanjutan sih"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ab3a7e31",
   "metadata": {},
   "source": [
    "# Cleaning Pace"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "27408c18",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pace (5 uniques): \n",
      " ['Competition', 'Competitiontempo', 'Daily Running', 'Daily Runningtempo', 'Tempo']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pace\n",
       "Daily Running         813\n",
       "Daily Runningtempo    125\n",
       "Competition            88\n",
       "Tempo                  75\n",
       "Competitiontempo       69\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Pace\"] = (\n",
    "    df[\"Pace\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "pace_uniques = df[\"Pace\"].dropna().unique()\n",
    "# pace_uniques.sort()\n",
    "pace_uniques = sorted(pace_uniques)\n",
    "print(f\"Pace ({len(pace_uniques)} uniques): \\n\",pace_uniques)\n",
    "\n",
    "df[\"Pace\"].value_counts().head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4001f1bb",
   "metadata": {},
   "source": [
    "### Analisis Pace\n",
    "\n",
    "A. Lari Daily Running \n",
    "Tujuan: lari harian, easy run, long run \n",
    "Karakter: cushioning empuk, stabil, tahan lama \n",
    "Kelebihan: nyaman & aman untuk jarak jauh \n",
    "Kekurangan: berat, kurang responsif untuk ngebut \n",
    "\n",
    "B. Tempo \n",
    "Tujuan: tempo run, interval, latihan kecepatan \n",
    "Karakter: lebih ringan, responsif, midsole lebih firm \n",
    "Kelebihan: enak buat pace cepat tanpa lomba \n",
    "Kekurangan: kurang nyaman untuk lari santai jauh \n",
    "\n",
    "C. Competition \n",
    "Tujuan: race day, time trial \n",
    "Karakter: sangat ringan, agresif, sering pakai plate \n",
    "Kelebihan: paling cepat & efisien \n",
    "Kekurangan: durability rendah, tidak cocok dipakai sering"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4879a798",
   "metadata": {},
   "source": [
    "### Cleaning Code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "3595b5fb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "UNMAPPED Pace values:\n",
      " Series([], Name: count, dtype: int64)\n"
     ]
    }
   ],
   "source": [
    "# mapping si nilai kegabung itu\n",
    "\n",
    "pace_map = {\n",
    "    \"Competitiontempo\": \"Competition|Tempo\",\n",
    "    \"Daily Runningtempo\": \"Daily Running|Tempo\",\n",
    "    \"Competition\": \"Competition\",\n",
    "    \"Daily Running\": \"Daily Running\",\n",
    "    \"Tempo\": \"Tempo\",\n",
    "}\n",
    "\n",
    "df[\"Pace_norm\"] = df[\"Pace\"].map(pace_map)\n",
    "\n",
    "unmapped = df[df[\"Pace_norm\"].isna()][\"Pace\"].value_counts()\n",
    "print(\"UNMAPPED Pace values:\\n\", unmapped)\n",
    "assert df[\"Pace_norm\"].notna().all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "855d02a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pace - norm : (5) uniques\n",
      " <StringArray>\n",
      "['Daily Running|Tempo',       'Daily Running',               'Tempo',\n",
      "   'Competition|Tempo',         'Competition']\n",
      "Length: 5, dtype: str\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pace_norm\n",
       "Daily Running          813\n",
       "Daily Running|Tempo    125\n",
       "Competition             88\n",
       "Tempo                   75\n",
       "Competition|Tempo       69\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pace_norms_unique = df[\"Pace_norm\"].dropna().unique()\n",
    "print(f\"Pace - norm : ({len(pace_norms_unique)}) uniques\\n\", pace_norms_unique)\n",
    "\n",
    "\n",
    "df[\"Pace_norm\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "22a5e00c",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Widths available</th>\n",
       "      <th>Orthotic friendly</th>\n",
       "      <th>Season</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NormalWide</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "      <td>1</td>\n",
       "      <td>#301 Top 47%</td>\n",
       "      <td>#352 Bottom 45%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>SummerAll seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#72 Top 20%</td>\n",
       "      <td>#255 Bottom 30%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#104 Top 17%</td>\n",
       "      <td>#368 Bottom 42%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#126 Top 20%</td>\n",
       "      <td>#541 Bottom 16%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#116 Top 32%</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Widths available Orthotic friendly  \\\n",
       "0  HeelMid/forefoot  ...       NormalWide                 1   \n",
       "1      Mid/forefoot  ...           Normal                 1   \n",
       "2  HeelMid/forefoot  ...           Normal                 1   \n",
       "3              Heel  ...           Normal                 1   \n",
       "4  HeelMid/forefoot  ...           Normal                 1   \n",
       "\n",
       "              Season Removable insole       Ranking       Popularity Gender  \\\n",
       "0                  -                1  #301 Top 47%  #352 Bottom 45%    NaN   \n",
       "1  SummerAll seasons                1   #72 Top 20%  #255 Bottom 30%    NaN   \n",
       "2        All seasons                1  #104 Top 17%  #368 Bottom 42%    NaN   \n",
       "3        All seasons                1  #126 Top 20%  #541 Bottom 16%    NaN   \n",
       "4        All seasons                1  #116 Top 32%   #339 Bottom 7%    NaN   \n",
       "\n",
       "  Terrain            Pace_norm              Pace_lists  \n",
       "0     NaN  Daily Running|Tempo  [Daily Running, Tempo]  \n",
       "1     NaN        Daily Running         [Daily Running]  \n",
       "2     NaN        Daily Running         [Daily Running]  \n",
       "3     NaN        Daily Running         [Daily Running]  \n",
       "4     NaN        Daily Running         [Daily Running]  \n",
       "\n",
       "[5 rows x 35 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Pace_lists\"] = df[\"Pace_norm\"].str.split(\"|\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "16bae2d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = df.drop(labels=\"Pace_list\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "25796d54",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Widths available</th>\n",
       "      <th>Orthotic friendly</th>\n",
       "      <th>Season</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NormalWide</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "      <td>1</td>\n",
       "      <td>#301 Top 47%</td>\n",
       "      <td>#352 Bottom 45%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>SummerAll seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#72 Top 20%</td>\n",
       "      <td>#255 Bottom 30%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#104 Top 17%</td>\n",
       "      <td>#368 Bottom 42%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#126 Top 20%</td>\n",
       "      <td>#541 Bottom 16%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>Normal</td>\n",
       "      <td>1</td>\n",
       "      <td>All seasons</td>\n",
       "      <td>1</td>\n",
       "      <td>#116 Top 32%</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Widths available Orthotic friendly  \\\n",
       "0  HeelMid/forefoot  ...       NormalWide                 1   \n",
       "1      Mid/forefoot  ...           Normal                 1   \n",
       "2  HeelMid/forefoot  ...           Normal                 1   \n",
       "3              Heel  ...           Normal                 1   \n",
       "4  HeelMid/forefoot  ...           Normal                 1   \n",
       "\n",
       "              Season Removable insole       Ranking       Popularity Gender  \\\n",
       "0                  -                1  #301 Top 47%  #352 Bottom 45%    NaN   \n",
       "1  SummerAll seasons                1   #72 Top 20%  #255 Bottom 30%    NaN   \n",
       "2        All seasons                1  #104 Top 17%  #368 Bottom 42%    NaN   \n",
       "3        All seasons                1  #126 Top 20%  #541 Bottom 16%    NaN   \n",
       "4        All seasons                1  #116 Top 32%   #339 Bottom 7%    NaN   \n",
       "\n",
       "  Terrain            Pace_norm              Pace_lists  \n",
       "0     NaN  Daily Running|Tempo  [Daily Running, Tempo]  \n",
       "1     NaN        Daily Running         [Daily Running]  \n",
       "2     NaN        Daily Running         [Daily Running]  \n",
       "3     NaN        Daily Running         [Daily Running]  \n",
       "4     NaN        Daily Running         [Daily Running]  \n",
       "\n",
       "[5 rows x 35 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "97aed74a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# jujur ini vibe ah coding\n",
    "pace_exploded = df[\"Pace_lists\"].explode()\n",
    "\n",
    "pace_ohe = (\n",
    "    pd.crosstab(pace_exploded.index, pace_exploded)\n",
    "    .reindex(df.index, fill_value=0)   # jaga urutan index sama df\n",
    ")\n",
    "\n",
    "# rename kolom biar konsisten untuk ML pipeline\n",
    "pace_ohe = pace_ohe.rename(columns={\n",
    "    \"Competition\": \"pace_competition\",\n",
    "    \"Daily Running\": \"pace_daily_running\",\n",
    "    \"Tempo\": \"pace_tempo\"\n",
    "})\n",
    "\n",
    "# gabung ke df\n",
    "df = pd.concat([df, pace_ohe], axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7ce9dc57",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Removable insole</th>\n",
       "      <th>Ranking</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>#301 Top 47%</td>\n",
       "      <td>#352 Bottom 45%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>#72 Top 20%</td>\n",
       "      <td>#255 Bottom 30%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>#104 Top 17%</td>\n",
       "      <td>#368 Bottom 42%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>#126 Top 20%</td>\n",
       "      <td>#541 Bottom 16%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>#116 Top 32%</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 38 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Removable insole       Ranking       Popularity  \\\n",
       "0  HeelMid/forefoot  ...                1  #301 Top 47%  #352 Bottom 45%   \n",
       "1      Mid/forefoot  ...                1   #72 Top 20%  #255 Bottom 30%   \n",
       "2  HeelMid/forefoot  ...                1  #104 Top 17%  #368 Bottom 42%   \n",
       "3              Heel  ...                1  #126 Top 20%  #541 Bottom 16%   \n",
       "4  HeelMid/forefoot  ...                1  #116 Top 32%   #339 Bottom 7%   \n",
       "\n",
       "  Gender Terrain            Pace_norm              Pace_lists  \\\n",
       "0    NaN     NaN  Daily Running|Tempo  [Daily Running, Tempo]   \n",
       "1    NaN     NaN        Daily Running         [Daily Running]   \n",
       "2    NaN     NaN        Daily Running         [Daily Running]   \n",
       "3    NaN     NaN        Daily Running         [Daily Running]   \n",
       "4    NaN     NaN        Daily Running         [Daily Running]   \n",
       "\n",
       "  pace_competition pace_daily_running pace_tempo  \n",
       "0                0                  1          1  \n",
       "1                0                  1          0  \n",
       "2                0                  1          0  \n",
       "3                0                  1          0  \n",
       "4                0                  1          0  \n",
       "\n",
       "[5 rows x 38 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "53f241a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# make sure value-nya bener 0/1\n",
    "for c in [\"pace_competition\", \"pace_daily_running\", \"pace_tempo\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "7e51526a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                Pace          Pace_norm  pace_competition  pace_tempo  \\\n",
      "24  Competitiontempo  Competition|Tempo                 1           1   \n",
      "32  Competitiontempo  Competition|Tempo                 1           1   \n",
      "33  Competitiontempo  Competition|Tempo                 1           1   \n",
      "34  Competitiontempo  Competition|Tempo                 1           1   \n",
      "38  Competitiontempo  Competition|Tempo                 1           1   \n",
      "\n",
      "    pace_daily_running  \n",
      "24                   0  \n",
      "32                   0  \n",
      "33                   0  \n",
      "34                   0  \n",
      "38                   0  \n",
      "                  Pace            Pace_norm  pace_daily_running  pace_tempo  \\\n",
      "0   Daily Runningtempo  Daily Running|Tempo                   1           1   \n",
      "7   Daily Runningtempo  Daily Running|Tempo                   1           1   \n",
      "35  Daily Runningtempo  Daily Running|Tempo                   1           1   \n",
      "36  Daily Runningtempo  Daily Running|Tempo                   1           1   \n",
      "37  Daily Runningtempo  Daily Running|Tempo                   1           1   \n",
      "\n",
      "    pace_competition  \n",
      "0                  0  \n",
      "7                  0  \n",
      "35                 0  \n",
      "36                 0  \n",
      "37                 0  \n"
     ]
    }
   ],
   "source": [
    "print(df[df[\"Pace\"]==\"Competitiontempo\"][[\"Pace\",\"Pace_norm\",\"pace_competition\",\"pace_tempo\",\"pace_daily_running\"]].head())\n",
    "print(df[df[\"Pace\"]==\"Daily Runningtempo\"][[\"Pace\",\"Pace_norm\",\"pace_daily_running\",\"pace_tempo\",\"pace_competition\"]].head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "67cbfef0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "competition sum: 157\n",
      "daily sum: 938\n",
      "tempo sum: 269\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"competition sum:\", int(df[\"pace_competition\"].sum()))\n",
    "print(\"daily sum:\", int(df[\"pace_daily_running\"].sum()))\n",
    "print(\"tempo sum:\", int(df[\"pace_tempo\"].sum()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc4bd121",
   "metadata": {},
   "source": [
    "### Asumsi : \n",
    "ada 2 jenis kombinasi : competion tempo sama daily tempo, setelah dipisah jadi dapet gini\n",
    "Rows: 1195\n",
    "competition sum: 157\n",
    "daily sum: 963\n",
    "tempo sum: 272"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9cc22c3c",
   "metadata": {},
   "source": [
    "# Cleaning Arch Support"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "90afbf61",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Arch (3 uniques): \n",
      " ['Motion Control', 'Neutral', 'Stability']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Arch support\n",
       "Neutral           999\n",
       "Stability         170\n",
       "Motion Control      1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Arch support\"] = (\n",
    "    df[\"Arch support\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "arch_uniques = df[\"Arch support\"].dropna().unique()\n",
    "# arch_uniques.sort()\n",
    "arch_uniques = sorted(arch_uniques)\n",
    "print(f\"Arch ({len(arch_uniques)} uniques): \\n\",arch_uniques)\n",
    "\n",
    "df[\"Arch support\"].value_counts().head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e9c82b15",
   "metadata": {},
   "source": [
    "Neutral\n",
    "Untuk siapa: pelari dengan gait normal / netral\n",
    "Ciri: tidak ada koreksi khusus pada midsole\n",
    "Kelebihan: fleksibel, natural, nyaman untuk mayoritas pelari\n",
    "Catatan: ini adalah default dan paling umum di pasaran\n",
    "\n",
    "Stability\n",
    "Untuk siapa: pelari dengan overpronation ringan–sedang\n",
    "Ciri: ada struktur tambahan (medial support, geometry khusus)\n",
    "Kelebihan: membantu menjaga kaki tetap stabil tanpa terlalu kaku\n",
    "Catatan: masih nyaman untuk daily running\n",
    "\n",
    "Motion Control\n",
    "Untuk siapa: overpronation berat\n",
    "Ciri: sangat kaku dan korektif\n",
    "Kelebihan: kontrol maksimal\n",
    "Kekurangan: berat, kurang nyaman, sangat niche\n",
    "Catatan: di market modern, kategori ini hampir punah"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33f99ae3",
   "metadata": {},
   "source": [
    "bentar ya saya mengantuk"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cee5e7e6",
   "metadata": {},
   "source": [
    "------------------------- day 2 ------------------------------------"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e4a2846c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Arch_grouped\n",
      "Neutral      999\n",
      "Stability    171\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "arch_map = {\n",
    "    \"Neutral\": \"Neutral\",\n",
    "    \"Stability\": \"Stability\",\n",
    "    \"Motion Control\": \"Stability\" # cuma ada 1 makanya digabung ke stability, mereka sama sama buat low arch\n",
    "}\n",
    "\n",
    "df[\"Arch_grouped\"] = df[\"Arch support\"].map(arch_map)\n",
    "\n",
    "print(df[\"Arch_grouped\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "6026d0e4",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>Arch_grouped</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>HeelMid/forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 41 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Gender Terrain            Pace_norm  \\\n",
       "0  HeelMid/forefoot  ...    NaN     NaN  Daily Running|Tempo   \n",
       "1      Mid/forefoot  ...    NaN     NaN        Daily Running   \n",
       "2  HeelMid/forefoot  ...    NaN     NaN        Daily Running   \n",
       "3              Heel  ...    NaN     NaN        Daily Running   \n",
       "4  HeelMid/forefoot  ...    NaN     NaN        Daily Running   \n",
       "\n",
       "               Pace_lists pace_competition pace_daily_running pace_tempo  \\\n",
       "0  [Daily Running, Tempo]                0                  1          1   \n",
       "1         [Daily Running]                0                  1          0   \n",
       "2         [Daily Running]                0                  1          0   \n",
       "3         [Daily Running]                0                  1          0   \n",
       "4         [Daily Running]                0                  1          0   \n",
       "\n",
       "  Arch_grouped arch_neutral arch_stability  \n",
       "0      Neutral            1              0  \n",
       "1      Neutral            1              0  \n",
       "2      Neutral            1              0  \n",
       "3      Neutral            1              0  \n",
       "4      Neutral            1              0  \n",
       "\n",
       "[5 rows x 41 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# vibe ah coding\n",
    "arch_ohe = pd.get_dummies(df[\"Arch_grouped\"], prefix=\"arch\", dtype=int)\n",
    "\n",
    "# Rename kolom biar lowercase dan konsisten (opsional, tapi rapi)\n",
    "arch_ohe = arch_ohe.rename(columns={\n",
    "    \"arch_Neutral\": \"arch_neutral\",\n",
    "    \"arch_Stability\": \"arch_stability\"\n",
    "})\n",
    "\n",
    "\n",
    "\n",
    "df = pd.concat([df, arch_ohe], axis=1)\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "cc40c12f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# jujur arch grouped gaperlu jadi kita buang aja\n",
    "df = df.drop(labels=\"Arch_grouped\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "f7996392",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Validasi One-Hot Encoding Arch Support:\n",
      "     Arch support  arch_neutral  arch_stability\n",
      "0         Neutral             1               0\n",
      "1         Neutral             1               0\n",
      "2         Neutral             1               0\n",
      "3         Neutral             1               0\n",
      "4         Neutral             1               0\n",
      "5         Neutral             1               0\n",
      "6  Motion Control             0               1\n",
      "7         Neutral             1               0\n",
      "8         Neutral             1               0\n",
      "9         Neutral             1               0\n",
      "\n",
      "Total Neutral   : 999\n",
      "Total Stability : 171\n"
     ]
    }
   ],
   "source": [
    "# Pastikan setiap sepatu punya salah satu (tidak bisa 0 dua-duanya atau 1 dua-duanya, karena ini single choice)\n",
    "assert (df[\"arch_neutral\"] + df[\"arch_stability\"] == 1).all(), \"Error: Ada baris yang tidak punya kategori arch atau ganda!\"\n",
    "\n",
    "print(\"\\nValidasi One-Hot Encoding Arch Support:\")\n",
    "print(df[[\"Arch support\", \"arch_neutral\", \"arch_stability\"]].head(10))\n",
    "\n",
    "# Cek total count untuk laporan\n",
    "print(\"\\nTotal Neutral   :\", df[\"arch_neutral\"].sum())\n",
    "print(\"Total Stability :\", df[\"arch_stability\"].sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d85aa91e",
   "metadata": {},
   "source": [
    "harusnya sebenernya motion diubah ke stability tuh pas preprocessing aja"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "291b7806",
   "metadata": {},
   "source": [
    "# Cleaning Strike"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "462dfdeb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Strike pattern (5 uniques): \n",
      " ['-', 'Heel', 'Heel Mid/Forefoot', 'Heelmid/Forefoot', 'Mid/Forefoot']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Strike pattern\n",
       "Heelmid/Forefoot     539\n",
       "Mid/Forefoot         339\n",
       "Heel                 290\n",
       "-                      1\n",
       "Heel Mid/Forefoot      1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Strike pattern\"] = (\n",
    "    df[\"Strike pattern\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "strike_pattern_uniques = df[\"Strike pattern\"].dropna().unique()\n",
    "# strike_pattern_uniques.sort()\n",
    "strike_pattern_uniques = sorted(strike_pattern_uniques)\n",
    "print(f\"Strike pattern ({len(strike_pattern_uniques)} uniques): \\n\",strike_pattern_uniques)\n",
    "\n",
    "df[\"Strike pattern\"].value_counts().head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "06e495eb",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>301</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Flex Experience Run 10</td>\n",
       "      <td>79\\n Good!</td>\n",
       "      <td>$65</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.1 oz / 201g 8 oz / 227g</td>\n",
       "      <td>1</td>\n",
       "      <td>10.4 mm</td>\n",
       "      <td>-</td>\n",
       "      <td>...</td>\n",
       "      <td>#523 Bottom 18%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand                    Name Audience score Price           Pace  \\\n",
       "301  Nike  Flex Experience Run 10     79\\n Good!   $65  Daily Running   \n",
       "\n",
       "    Arch support    Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "301      Neutral  7.1 oz / 201g 8 oz / 227g            1             10.4 mm   \n",
       "\n",
       "    Strike pattern  ...       Popularity Gender Terrain      Pace_norm  \\\n",
       "301              -  ...  #523 Bottom 18%    NaN     NaN  Daily Running   \n",
       "\n",
       "          Pace_lists pace_competition pace_daily_running pace_tempo  \\\n",
       "301  [Daily Running]                0                  1          0   \n",
       "\n",
       "    arch_neutral arch_stability  \n",
       "301            1              0  \n",
       "\n",
       "[1 rows x 40 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"Strike pattern\"] == \"-\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c09196ce",
   "metadata": {},
   "source": [
    "seharusnya ga ada issue kalo kita hapus si FER 10 soalnya dia udah punya FER 12"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "9c31c1ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df[df[\"Name\"] == \"Flex Experience Run 12\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "dc940543",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1090</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Vomero Plus</td>\n",
       "      <td>91 Superb!</td>\n",
       "      <td>$180</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.2 oz / 289g 10.1 oz / 285g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.6 mm 10.0 mm</td>\n",
       "      <td>Heel Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#7 Top 2%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Brand         Name Audience score Price           Pace Arch support  \\\n",
       "1090  Nike  Vomero Plus     91 Superb!  $180  Daily Running      Neutral   \n",
       "\n",
       "            Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "1090  10.2 oz / 289g 10.1 oz / 285g            0      9.6 mm 10.0 mm   \n",
       "\n",
       "         Strike pattern  ... Popularity Gender Terrain      Pace_norm  \\\n",
       "1090  Heel Mid/Forefoot  ...  #7 Top 2%    NaN     NaN  Daily Running   \n",
       "\n",
       "           Pace_lists pace_competition pace_daily_running pace_tempo  \\\n",
       "1090  [Daily Running]                0                  1          0   \n",
       "\n",
       "     arch_neutral arch_stability  \n",
       "1090            1              0  \n",
       "\n",
       "[1 rows x 40 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"Strike pattern\"] == \"Heel Mid/Forefoot\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "a32a50e8",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Popularity</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#352 Bottom 45%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#368 Bottom 42%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#339 Bottom 7%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adidas Adizero SL2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$130</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>8.6 oz / 245g 8.4 oz / 238g</td>\n",
       "      <td>1</td>\n",
       "      <td>8.2 mm 9.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#166 Top 46%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</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",
       "      <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>1154</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>WWave Horizon 7</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$170</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Stability</td>\n",
       "      <td>11.6 oz / 329g 11.8 oz / 334g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2 mm 8.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#294 Bottom 19%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1155</th>\n",
       "      <td>Reebok</td>\n",
       "      <td>Zig Dynamica 4</td>\n",
       "      <td>80\\n Good!</td>\n",
       "      <td>$85</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.4 oz / 352g 12.3 oz / 350g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.5 mm 9.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#533 Bottom 17%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1160</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 6</td>\n",
       "      <td>92\\n Superb!</td>\n",
       "      <td>$170</td>\n",
       "      <td>Competitiontempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>8.7 oz / 248g 8.6 oz / 244g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.6 mm 8.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#26 Top 8%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Competition|Tempo</td>\n",
       "      <td>[Competition, Tempo]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1161</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 6</td>\n",
       "      <td>92\\n Superb!</td>\n",
       "      <td>$170</td>\n",
       "      <td>Competitiontempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>8.7 oz / 248g 8.6 oz / 244g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.6 mm 8.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#26 Top 8%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Competition|Tempo</td>\n",
       "      <td>[Competition, Tempo]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1162</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 6</td>\n",
       "      <td>92\\n Superb!</td>\n",
       "      <td>$170</td>\n",
       "      <td>Competitiontempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>8.7 oz / 248g 8.6 oz / 244g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.6 mm 8.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>#26 Top 8%</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Competition|Tempo</td>\n",
       "      <td>[Competition, Tempo]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>539 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Brand                Name Audience score Price                Pace  \\\n",
       "0     Brooks            Launch 9    87\\n Great!  $110  Daily Runningtempo   \n",
       "2     Adidas               4DFWD   90\\n Superb!  $200       Daily Running   \n",
       "4     Adidas             4DFWD 3    88\\n Great!  $200       Daily Running   \n",
       "5     Adidas             4DFWD 3    88\\n Great!  $200       Daily Running   \n",
       "7     Adidas  Adidas Adizero SL2   90\\n Superb!  $130  Daily Runningtempo   \n",
       "...      ...                 ...            ...   ...                 ...   \n",
       "1154  Mizuno     WWave Horizon 7    88\\n Great!  $170       Daily Running   \n",
       "1155  Reebok      Zig Dynamica 4     80\\n Good!   $85       Daily Running   \n",
       "1160    Nike          Zoom Fly 6   92\\n Superb!  $170    Competitiontempo   \n",
       "1161    Nike          Zoom Fly 6   92\\n Superb!  $170    Competitiontempo   \n",
       "1162    Nike          Zoom Fly 6   92\\n Superb!  $170    Competitiontempo   \n",
       "\n",
       "     Arch support        Weight lab Weight brand  Lightweight  \\\n",
       "0         Neutral    7.9 oz / 225g 8.1 oz / 230g            1   \n",
       "2         Neutral  11.9 oz / 336g 11.5 oz / 327g            0   \n",
       "4         Neutral  12.3 oz / 348g 12.2 oz / 345g            0   \n",
       "5         Neutral  12.3 oz / 348g 12.2 oz / 345g            0   \n",
       "7         Neutral    8.6 oz / 245g 8.4 oz / 238g            1   \n",
       "...           ...                            ...          ...   \n",
       "1154    Stability  11.6 oz / 329g 11.8 oz / 334g            0   \n",
       "1155      Neutral  12.4 oz / 352g 12.3 oz / 350g            0   \n",
       "1160      Neutral    8.7 oz / 248g 8.6 oz / 244g            1   \n",
       "1161      Neutral    8.7 oz / 248g 8.6 oz / 244g            1   \n",
       "1162      Neutral    8.7 oz / 248g 8.6 oz / 244g            1   \n",
       "\n",
       "     Drop lab Drop brand    Strike pattern  ...       Popularity Gender  \\\n",
       "0         9.4 mm 10.0 mm  Heelmid/Forefoot  ...  #352 Bottom 45%    NaN   \n",
       "2         8.9 mm 10.0 mm  Heelmid/Forefoot  ...  #368 Bottom 42%    NaN   \n",
       "4         9.9 mm 10.0 mm  Heelmid/Forefoot  ...   #339 Bottom 7%    NaN   \n",
       "5         9.9 mm 10.0 mm  Heelmid/Forefoot  ...   #339 Bottom 7%    NaN   \n",
       "7          8.2 mm 9.0 mm  Heelmid/Forefoot  ...     #166 Top 46%    NaN   \n",
       "...                  ...               ...  ...              ...    ...   \n",
       "1154       7.2 mm 8.0 mm  Heelmid/Forefoot  ...  #294 Bottom 19%    NaN   \n",
       "1155       8.5 mm 9.0 mm  Heelmid/Forefoot  ...  #533 Bottom 17%    NaN   \n",
       "1160       9.6 mm 8.0 mm  Heelmid/Forefoot  ...       #26 Top 8%    NaN   \n",
       "1161       9.6 mm 8.0 mm  Heelmid/Forefoot  ...       #26 Top 8%    NaN   \n",
       "1162       9.6 mm 8.0 mm  Heelmid/Forefoot  ...       #26 Top 8%    NaN   \n",
       "\n",
       "     Terrain            Pace_norm              Pace_lists pace_competition  \\\n",
       "0        NaN  Daily Running|Tempo  [Daily Running, Tempo]                0   \n",
       "2        NaN        Daily Running         [Daily Running]                0   \n",
       "4        NaN        Daily Running         [Daily Running]                0   \n",
       "5        NaN        Daily Running         [Daily Running]                0   \n",
       "7        NaN  Daily Running|Tempo  [Daily Running, Tempo]                0   \n",
       "...      ...                  ...                     ...              ...   \n",
       "1154     NaN        Daily Running         [Daily Running]                0   \n",
       "1155     NaN        Daily Running         [Daily Running]                0   \n",
       "1160     NaN    Competition|Tempo    [Competition, Tempo]                1   \n",
       "1161     NaN    Competition|Tempo    [Competition, Tempo]                1   \n",
       "1162     NaN    Competition|Tempo    [Competition, Tempo]                1   \n",
       "\n",
       "     pace_daily_running pace_tempo arch_neutral arch_stability  \n",
       "0                     1          1            1              0  \n",
       "2                     1          0            1              0  \n",
       "4                     1          0            1              0  \n",
       "5                     1          0            1              0  \n",
       "7                     1          1            1              0  \n",
       "...                 ...        ...          ...            ...  \n",
       "1154                  1          0            0              1  \n",
       "1155                  1          0            1              0  \n",
       "1160                  0          1            1              0  \n",
       "1161                  0          1            1              0  \n",
       "1162                  0          1            1              0  \n",
       "\n",
       "[539 rows x 40 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"Strike pattern\"] == \"Heelmid/Forefoot\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0cc507c7",
   "metadata": {},
   "source": [
    "### Analisis Strike Pattern"
   ]
  },
  {
   "attachments": {
    "image.png": {
     "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAADICAYAAAAeGRPoAAAQAElEQVR4AeydB3xVxdLAJwmEEHoTEMQo2BALKjysYMGGBVFUVOwo+tmeXd+z92fvXREBC4pYAMWGqIhiRaRIkSpFpAiBAAn55r/3zs3J4d6bAElI2fzOZHZnZ/fsmTN3Znd2zzmp+fn52QqrPeR7GeR7GfjfgdcBrwNeByqoDmSnSuQvQ5EHES8DLwOvA14HvA54HaiIOiDm0NWfl8Lhm/QS8BLwEvAS8BLwEigTCXiHXiZi9ifxEvAS8BLwEvASKF0JVGSHXrqS8a17CXgJeAl4CXgJVCAJeIdegW6W76qXgJeAl4CXgJdAIgl4h55IMp7uJeAl4CXgJeAlUIEk4B16BbpZvqteAl4CXgJbQgLr80Wm5eTIsKVL5dkFC+W2OXPkxClTZI+ffy4E0P/Ozd0SXfTnVAl4h65C2AKHP6WXgJeAl0C5lQBOed66dTL6n3/kwT//lJ6/T5Gzpk6Vy//4Qy6ZMV1unTVLhixcKOO1PAgjly2Tpd6hb7H76h36FhO9P7GXgJeAl8CWl0Be3nrBgU9YvVpeX7zYzb6vUOfd+ddfpfP48XL1zJky5K+/ZIzOzqevWiW569dHOl2tmkiquhDDml6og4CaaWmRcv+/zCWgd6PMz+lPuBES0N+R/PLLRlSAdQvC2rW5sf5mZ+fJLbeKfPnlFuyQP7WXgJfABhIghG4O/Ia5c+SC6dOl+6RJcoXOwO/UcPoANTw4b1fRHLg6bJfnH2mjG1b6n2vXyuq8PKF9zfqjjCXgHXoZC3xjT3fVVSJffb2xtbYMPz/i51+oJg8+KO4HnZGRIlttJVK37pbpjz+rl4CXQOS3SPj8h5Ur3Rr4tRouP3DCr86BnzttmtyvDpzw+XQtX7hmjZuBV2PWHRQeDpy8YZy4pQ1rebqmp+hMPzVFM/4ocwl4h16GIsfh6cBXAGbdADRCXqSZyYKh0S34xo0T+W2iuDrQgrzwwwOdOqQB2jBgxkw5QFqjZwImb8BMGjqYNqnLeeCzPGVRfofgD5Zx/nz9kX87VmT6DJFfx4ukpaVKt6NF2rQpGLEH69FX15j+Iw0Eyzm/FvnDS8BLYCMlQAgdB04I/frZs+SyGTPklN9/d04cB27h89W23q2O2Jx4NU3HwuqadqfW33YhDD1Mcwwik9WhR5MelbEEvEMvQ4Hj8G65TeSgg0ROPVXkpptEctflyu13pMrR6vguuEAcvu7aSKdeeEF/HJNFXhq4XkhDvf76VFcXXtrofoK4EDcjYtomT1t33h05BzNm6gFvvFlNjjpKZPlyXfuCoIAjnjYtzdEvuihNrr9B5F9d1gvn+c9/qonlr7kuTXDy8L/3njh++sC5evVKk78Xi4wZkyqffqpYIwqcH4d8+hkiQ95JE/oXrnfeeSI4cO2GPPFkRC6XXSZCu/ThwQcL+gmPBy8BL4ENJcDvEgduIXRm4Kep88aB91VHjgN3M3Bb/8YZA6GmzIkbdsXmtI3fcAL6cg25r9SQu6vr/5W5BFLL/IxV/ITMQhs2Enn9dZG33soVnOwLz4s8/bTI99/nOTxokMiTT4ncoM51v/1FLj0/VS67LM857ilTRO67DyeeK8OHiyz5WxxGrHNn81/ka3Wo/V7Kk5NPEaGtCFXkvfdFDj5UpEkTo4hztP/8I/LHgvXSsqXIyI/y5MG7UuWBByI8Q98Ref7xVHlX8Zw5qaKDfbnoInFtjx4dOfffS0RYGtj/AJHjdYBBn+/XPq5blxJpRP/j3K+7TuSYY0SoRx+phwPXYndM1sHL+edH5HDLtanSv78IDp9BhGPw/7wEvAScBCyEzgycNXAc+OlqHHrpj+h+DamPXLxYCKHjYF0Fc8RkEjhjt8GNcuMNYqtj2Mosb1jrL1Gnvjo/X1P+KGsJeIdeRhI3p7Rmtchhh4nssYdIeno1+XhkxAkec6xIrVppctxxIqedJkLomq41aijSUIGydu3Wy4svimy7rciHH1ZzjhxnvGKFuNlzjZra7p4irbQc/nPOFufwCaHjGCdoGLyXOnnaDcN2zVLdzLhmZpocoIOInXcW+b//izj/3XeLrIMvXy4yXtvI2k7k2mvy3MCA6yCiwNLA6lV5sk0Lkdbbi2RliaxalRY7zbffRmbbt94aqUcf771HZOrUSN9XZYscqzI49NA8cX3QwQGVOSeze9IevASqogSwHThInDgO/PLp010InfVv4OF58wQHzuNjTj7qbKuxBq7Y5e2f5Q2bEy4OtjqGrY7lo5hwPQ59iYXy7dwel4kEvEMvEzGLmwnbqTJqRFLuh7pGHbk64qDTwoEvWxbhCf5nhnzxJZFQ+n3/E/nx54LSlOgPqn7dgnNts816abd7ZBY9TGfzRAZw1AW1Cqdq1SrIM1AI5q1kuc7mSeN0wQADDDAOPEevZ7UC+czMPJCDpUsdcoMWUlyvbZbLycmX6tVFGJCwkY4yeOgvGDmBSwAqdBPIAcM+LSdHWB8lxAomT1mFvjjf+YQS4Pfw1Pz5ssMPPwgO/KmFC2PPgLMG7kLk+vt3TjzaiqORVjrIzb7NCRsOlsGULG91DBuv5aOY8y7S2Tk73WnSQ9lKwDv0YsgbI8roGOPJm5JYrypGtUIs8QwuP9S9dEY95huJbXpj89kHw0RatopUJyxdt14k/XI/EWbZhKzZkPbUEyI4xXXrIuXh/zj53qeLC10Tej+mW2TGHeazfHZ2ZDCAM6dd8lYGrqf9yNLZ/8w/RNj0Bg0YMEAE52uh/Jo1oBaeoe+uAwvapd+RUnERBtJEE7gGohfkTVYsJ5BHTuCqBKyLBvWOmdkdc+fIZX/McC/4YH30wmnTNP+HDNR1nKV5uVVJPFXqWtGFFunpgvMGcJrOQZtTjUrD0aNpV0466mgFbPyGoYV5EuWtjmGra3nDWn+BhtwV+WMLSMA79ARCx5jiwDGkt8yeLedqbBgjeqOuT40lxp2gXiJyIqfUq1ckLM5mtltuFWGDGY7swj6Rlgi5P/G4uGe527QRwSn+T2fnhLmpo0tmjpFwt0uE/uFIIeGE2cBmzhJaGGxGjjPnPMFy8oS/DzxQ5FBdh6etG28UOfNMcev0fftGuIk+sDGOPQARSuR/VlZkaYGNfNQj0nDb/9bLJZdGyvnPDB1cYWEzO869WaXGEL0bvHSJ/G/uXLk+6rSviD4f/MLceTJGwx2sj4IdqD76t3NtpvDLcXWeFulav77sx4g6kSM1h2o4Hp/RDBtvcbDVMWx1LB/AvFxmuQ+5bxGN8g49IHZm3szAeR/xGb//7sJbfWfMEFujwohOXLVK5q5ZKxjfQNViJZkxH3GkyK67FrBnZYmMGCHS+SCRiZMiM3PyrE3DdccdIh06iIz/VaT3GSL33icyc7aIRt3kumtF3n1XhDVteI87VqRTJ1IRYBDBWjX1995bZLfdIzPwSGnB/222iThmo2A3ztcBRZMmee46t95a5BIN9UPnup9+Ok9u/I/I1OmRGmzwo2/kGKCwB4ABBHmiAszqqffIQ7mxeis1dP/mK6nyfxfDJcJAoUtnEWREvxlU4Ow5p1TCP+TBzIvID6/XZODIDPwEdeAMHNG7+3RtdMDff8sYHUktXL3aPR/sZl5qTF14VTGiYUbkDSiSqLzQIK2aHF6/vv6AoyY74EDdVYfzUd2QIN1ohoNlNJIsb3UMG6/lAzhHQ+4LCLnRpocylUBUO8r0nOXmZMzCMagYUzaaHDdpkpynBhVDymMe41eulOW6XulCWSisAunpa3JkjWz8Lk4cFQ6MjW9BIWRlidx9t8gbr4sQRscJY/DhwQn3e0Wk74XryTqnDh802gFok7A1TpW8Y9R/hO+//kqEDWs9T1ZCgiMrS9yOeguZZ2WJ3KbRAtqkSqPGkfKsLLUnKeLWwTkn/WAnOs4YPiArS+T++0VY46c9dupTzrWzCZB6g9+ILAME+0qaMvhohwEN+awscpUD0DfWu3Hgb/69WK7UUQ+RH9ZFceC36ix85JIlMl0HjexOJrwau/LUVGHDEXkwekgaBz9VdRQDajrj6P5fpZIAv4tjGjSQ1pmZEvtTe+TS8XA8h2s0w/Hq0WA8utUxbDyWN6z1s3V27p9FV0FsgaPKOXRm4YQ0+WLQBRqv3vvnn6W3zsYfmz9fCF/+rSNLDKmbAekNieGAAk9XA6pFJX7wo6VRMBBME3YjD1AGkE4EGPdPP01zz6wzQ+9xQp4UVSdeW9QBEpXFo0NLVIeyqgKEzxkwom8MGlm6uU6XbC7VqM8V6rzZ3BR04DjnuLKJ6p45ccPGi75iQL3MTSKVD/N7zsrIkH1r1iy4OHOi8XBUZ8p8hq69Qz/9s+gqiC1wVHqHbrMiQun2woVuOhPv+/sU4X3FvOowJnf9EaCM5BNhyghxzlsT3coNoRwCxn3ffcU9786rWG22XQ67Wim6RPicwSIzcHSNAePlc+fE9l70mjhReD54iK6V8HgRemc6FhOA6p9Lh7EZ7DDd8lo+OWe1e3TR1d+Uf75OuZYAv+dG1apJNw171UtPL+ir6UAYq044piDdaIaDZTAny1sdw8ZrecO0o8Cja9heTfqjDCVQKR06htVmRdfrbOhEnYkTSseg8rwm65FuNhRVykKGNUpz5dyIcF5pjD75CIEmy/Whv323Ng0u1x2toJ3DYKFrPD72wl9/CUs1zMAv19n3vzWc3m/BQvd8MHsvnD6hSwbBa4ZG3oxiGBdVrnVn56yRZfnrNeWPyioBZun71K4tuxZnlh5PZ4xmOKxnyfJWx7DxWt4wwtc0Dt0/i44wyhYqhUO32RFrk3y794qpU92Gtl7RUDpr4cyI4hpVVT4ncsOmqImw8rExriI4dHdd/l+JScAcOHrGDJwQOvsuOv7yi+DA2TzJDJw1cMLgDBTdko3qTKwTlg5i07UgjQqWL6pceVkGmllKS0Ha/OYevn4JSIBZ+vY1MmT/unVj+ymcTaNt0xXD8XTGaIaNtzjY6hi2OpY3TF807Z9FRxBlDxXWoWNcLbxprz48d9o0uWn2bGFnME48tn4UlGsiRVQldGxWngC7DUm5uTJv7VrH7v9VHQlMzM52n5lEz3DgvCObfRc4byDmwFUk6ImiyM50EqZPpmdBnKysqLrRcqJGbI4j66HySgCnzua4RryJicsM6lEwH0+njGY4Ud14dKtjGB5Lh7GWsSzJbne65KHsJFChHDohJ8KbzI4IpZ+lM3FC6cyMCKUT2sSwFhJfHGVz5WG65VUZXXkCjNGmfPbq1cKggrSHqiOBaXrfC+mZ6U1UBKYfhmMzKNMn4w/iZGW0W1S58rCZk0EmvxHNVq2jil3tPhmRWToTFhs4xvTM9CqezhjNsPEWB1sdw9SxdBjr/chW2pq8yGOvmvVHGUmg3Dt0DBQzcULpPX+fInyA4LrZs8TtSuf53DVrIrMgFMwA4ZEGq2KBUH6HE9Hhs7KisDY0Wc+7ShVWk/6oIhJgl3GXOnWkZnE2mrp+ggAAEABJREFUJZkOoVfIJ5w3OjhZWVF1KVfI1agRG+PWyMY/TqnV/VGBJJCp+tezUSPBiccGjugR12A4nk4ZzbDxFgdbHcNWx/IhvFj1kYgREQW65aFsJFDuHDoOnI1GbGpjJn7UpImyz/jxLpQ+5K+/hB3CPKMbVzwolSmaYWgwG05Ep9zKisLK+4uGX4Nv5+LjJ7qUKvSf03mofBJgl/G+9erJ1mpQY1dXDF1xvManuuPyQZysDOaiyuFRYGMcG5G8DqowSu4oly2xOS7pm+Pi6YzRDAd1kKtMlrc6ho3X8kGsZby/Y4pGs2jWQ9lJILXsTpX8TBghwum8LYtPAR44YYLwaBmhdBx4LJSuyhJrydKGUSpLG4ZGBcOJ6JRbWVFY22OTnb2di77z8RNeh3rfvQXvZVc2f1QyCWBI97B35HJtRekKehXks3wQWxtBGnUsn6zcyhSzMW66GlE/K0J4lRu2q57uNscxS3dXarpiWPVhA7rRDBtvcbDVMWx1LB/G7uT+X1lLoNw4dIzQBJ31urdlLV4sq9l0hpIAJhVLGzalMgzd0oahUd9wIjrlVlYUVl7Wrr5fmU3L7oUt/ywX+fNPEd5TzjvW33vPFfl/lUwCLWrUkP007N5Usbu0YuhKIT7VHZcPYmsjSIPJ8snKrUz52Rjnn75QQVSkYxP7youmOtetG3lznOmA6Qs4GS1eGf2gXiJsdQwbr+XDWNuZtnKlj1iqHMryKDcOnVkus5/9GjSIXD8KA5AzHFYaoxum3NKGodGG4Xh0o4GLA9G2JmavpGUHS5Y45P6N+Vrk+ONF+ACJrhI4mv9XOSRQMyVFOtSuLa0zMiIXhL6QSoSjupJwJkW51SVNW2GcrNzKtB5RIx/mVEFUkWNP1UMXLTIdCOpNMlq8MmQWrB/OWx3Dxmv5MNb6PLrmvwKogijDo9w4dGbobdRI9ohu9nAyMKUxHFYaoxum3NKGodEYGCCdWV0kCBlpIsYPjgfUA+DVurmK5+bmQnGwcKFDhf49/aTInnuKvDpAhPeqFyr0mQorgV0zMyPhTq4AXUmGTeeMz/JBnKws2HawDnTyobo2K2KADIuHyiuBFtWry+H16kvNatUKLhKdIBfRC7dxjqwbUBrNsPEWB1sdw1bH8mGsJ+XRteA+IyX5o5QlUG4cul1nFw0jxTZ7mNIYDiuN0Q1TbmkwQMPqgEUdsKSlScrKVVL751oOagxpLAbyWGuRR7YThy/dvTC2Mi03ftoY+fU6IbSOw162jBNtCIThz+wt0qtXmrBpbkMOT6loEmBzHOHOWNidCzBdC2N0Mlhu+SC2OkEadSyfrDxUNkMHmfNz17llIJrwULklsE/tWrKDToRiV5lMZ0xXDBtvcbDVMUwdSyfAPLrmn0WP3ZkySZQ7h75nzcyCzwSiNIjBcFhxjG44WI4DV8CBmxOWvrtI/nUdZd1VbWXlee1kzV2tYyCDm0sMfq4bSRuOltX4uGmMn/oAofU+l66XkV8mf+3m+++L/KvLerfG7sPw3NSKDbFwp+leImw6aeWWD+JkZYgpWbmVwafAxrgFa8r3dwa0m/4oIQm0r1VbeJSSPT2uSdMr0wvLg41mGBqVioOtjmHqWDoe1nL2dPhn0RFw2UG5c+gpqgi8Ccl9JtAURWlOJJYHG80ws3CYtKz2ZHXI97YSOW8XST/lkJgTFhy0wpplm3bZiepBBzh9MoDnnntE/Ka5ZFKqGGXNUtPc5rjYM+mmh2Gs+uiuyOiWD+JkZVQubrny8oIZnv/VpD+qgARYqjy8YUPZ4M1x8XTGaIaDOoiskuWtjmHjtXwYa3v/5OUJn/Wlj5r1RxlIYNM8Wyl2jJvPCzy61atXsP4TT3mgoUQ6C2f9mxB4jeFNRS7d3c2+mU3jwHGi4e7WqL9eANnzH4lBz/kiRUGAn/oAbRsmXRywTXM9TxEfhi+OwMohT1paqhysOhoLd6KP9DOM0dEg3fJBbHWCNOpYvrjlWocXjfDGOP8WQxVGFTkOqV+/YJMm14zexNMZoxmGz/iLwlbHsNW1fBhrezxqvEKduiY35fB1NkEC5c6hcw2sUTLqjK1RhpUHJmbkul5IOF2e2ME5cULoOHGKg47cOVyccc/5UuM/06X6gxMdpNz3ncjj4yNw2XSRK/4QAV8/WyQIRoP3xUkij/4sa979yrVR+8UJct3lGy9G+rRmtcisWfTWQ0WUQOuaNaVj3ToFH8rgIkxXDZuhC+eNDk5WFmwTXvJBbHWjmNDrz8uXCy+YgdVD5ZcAT16c2WSrwht7o/rAZMdJAJ0xmmFoFBYHWx3DVsfyYRxsl7SHMpHAxnuiMumWSKc6deTYRg0jZwsqD45c886RX76nyJPbRda7I5wF/0MOHCeMk15z+DxZ2WaJrNz5H8mvnSlu96cpo7brGli1TmSlrkMCpCEGsfLzFa28tivl6q71pE0bGIoHxx4r8sSTIt+OSpV33lkvx2i+eDU9V3mTALuMD61bT1y403QnjFVXXL+NbvkgTlZG5WTlVhbFzNDZGOfX0RFc1YH969WV3evqUqNdclQfnH2Dhr4ZzTA0KysKWx3DVtfyYUx75Rkqad/KrUNnlo6xdLN0lAfQGTmhdcLqzpGH1sOZ9YrOwpk1u9n3JVNlTY/FsnLP7IjjxinTDo95BBWQNHSAGw0G4LM8GICumHdnr05PkZHLlsk3Y5WQ5Nh5Z5G77xb5+WeR117Lk4suEtljD5E0DduyxJCkqi8qxxLIy1sv7WrVijzCFtWLQgaUvqNbYCu3fBAnKytuXWtD+X9bvVr8OroKogodvBfhCN7hYXpl+mB5sNEMQ0NGxcFWxzB1LJ0Ia9vLc/P0vz/KSgLl1qEjgAN1jZJv//LImdvo9kQktE5YPRhSZx2cUPraNz5zIfOVOy6LzL5xyDhxZto0CKB8poyGjUZ5MjA+MKBts6v4pfrTI2vygbo48Yv+T2T0aJHfJorccEPEideqlSbeiQcEVYGTDMi2T0uT3TMzpZ693x2d4poMoyfx8kYHh3mhUcdwsnIrM6z1eFUyL5jxz6KrMKrIQdjdPUqpy0Dukk0fTIfARjMMDebiYKtjmDqWToS17elrcoSBryar0rHFrjV1i525GCcmpMmLEwivr3y8lQiPjwXraVi9hq6JE05fc/TCiBNH0QBTMvhx7GCjhzG8YVpx8rSpsPeo1sIAAyfeu7fIu+9GHPlTT4gceKB4B64yqqwHX75ic9y25tDRGy7WMLoVL290cJgXGnUMJyu3MsPRerxgxg8cEUbVgdijlMFLNh0Cm44YhgZvcbDVMUwdSyfC2vb8VatkrVdElUTZHOXaofMilv4nNXWPnTErj4kk6sgJqxNSd2FOFMwgxljMBApJ3Y3Fup6/aOly2UOX8p/QdfERI0T69xc57jiRJk2KeW7PVuEl0KFOHbc5zm1AQo+4IsPoVLy80cFhXmjUMZys3MoMU0+B1276mZEKogodbgJUv378N8ehS6YjhqEhn+Jgq2OYOpZOhJUHPfSfmUbIJQhJmiq3Dv3Jp0T4ehmPeBXqv66RO0d+5HzJb1xHRMPerlyVxzl2lymjf3ru/MwMWXfldDn1glzJyiqj8/rTlCsJEO5kv0fsmXR6hz6CzdiF80YHJyujjeKWG5/WYSno68C3BpTkj0ouAZZYeNNm7FFKrhf9Mmz6YThYZjyJsNUxTF1LJ8LKw+tf/dviEGrZQLlz6DNnivQ8ReSS/4t8vSwmBp2Vs9lNLpkaCa1ToA4V5By5Ko9Ll+W/qCLPzllTlmf15yqHEmBz3IF16xY8wmb6GNURN3un35YP4jBvsIw6xS0P8PHVtUmrVgtGniY8VH4JENnmTZs8Shm72qAumX4YDpZRIVne6hiG19KJsPIsXLdOVvtn0ZFumUAJOPSS6yfvRT/qKJG33ixok53rbCi77K2/3KNmznlTrMoCcnkUivyWwHpOXnHo+uL/VVkJsDluPw291wru10Aaqh8gp6ckLB/E6G6iMujFLTc+rbNO2/9+1UpZI/ma80dVkQAbNYkWxd2kafphWHXEyaU42OoYpo6lE2FtnC8AKvJHGUmgXDh0vkTGK1F5nGvy5IIr329/kY/fS3WPfJ3ZtGnB25BQJgBF2tJYu8sodL6ORDXpjyoqATbH8fnf2OY49BJZoKPgcN7o4GRlRdUNlls7SuN5dCJH/gUzKowqdhynkaJd2e1u+oCOIQPLGzZ6cbDVMUwdSyfCUR6iRZzeQ+lLYIs79JkzxX2J7MYbC4fYL9KQ+9B3RNgljhj2rl1b3OtgyaAoAIq0pTH9UVjiHbpKoWof7DIuFO5EHOgoGD0FWz6Ik5VRJ1m5lYWx1mP90oc7VRBV7Mioni49GjWSDaJCYR0J6iAySpaPVzdMC+ej7XmHjnDLBraoQ//ySxFC7HyJzC53661F+r8qwiNf4Z3iJyrBvWgGRQFQoC2NteOLc3PFK60KoooffLBln8za4nTUZIGOkkZPwZYP4mRl1ElWbmVhrPWIHC1X3dSkP6qQBFhLZ3Oc+8CVXTf6FtYRaJQXB8erG6aF89F2+bYAp/FQ+hLYIg6djTrvvSdywQUi4RD78OEivc+If+EHaSipq87UXSnKggJtFl4fGcVuZju8yGO5fyOSuy1V+R/rl/vUriV71KpVIAZ0ixx6CrZ8ECcro06ycisLY63Hl9ey7Tya90fVkUDsA1d2yehBWEegUV4cHK9umBbO067SZq9ezVk8lIEEytyhs15+220ixx9f2JnzQhZC7Lvtnvyq+7RoEXnOEmVJzlo2paqwon1ZsG5t2ZzPn6VcS6CtOnM2x/GRlFhHozri8qRJBLHqD6RYiDRYRkGycisLY63H64mJHDGA1qw/qpAEeHX2vvXqFY4WhXUkrGfJ8vHqhmnhfLS9uRol8jpYNspXpg79r79Ezj43TW5Xh26Xxy52XsrS75XIy1gIF1lZGKMUvMTjKN5ZHC7cUvmoEi9Zu6FD31Jd8ufdchKoISnCm+PcB1usG+hI1Lgx+HNkaCTAycrgKW658RnWuj9mZ+t/f1RFCbBJs1C0yPTCMLqHYIqDrY5h6lg6EYZH22cvh3/aQgVRBkeZOfSZM0W6n1D4kTTWy9nF3vfC9cV6PSrOnpd49GzUqOB53zIQUrJT2EwMh746Pz8Zqy+rAhJARxl0um8Q2PVi8KLGLe4sPFkZbRS33PgMa11evTk/d52m/FHVJLB9jQwhWlTTHqU0vTCMXiKU4mCrY5g6lk6EaVuBlxwp8kcZSKDMHPry5SIz/yi4Ih5JY718/wPEfXWsoKToFB9tOU6dupvtoEymXFsA83gQPeYVh2X7iBBn9VAeJZCuoSS+QRDbHGc6SmdJhzF6G6YF88nKrSwBnqHhzgVr/IuPEGdVAwaXRIu2Luo7A/F0EmEF6WH9srIwPZzXdv7JyxP/+lcVRBkcZebQ+Vzo11+LMCvHmQ8cIJx6U98AABAASURBVFLUenmi63fvLK5XX6oFR54oEkq2JbCek7CSf0Qo0R2rWnTbHMcnLS2C4wafiEF1BVRopo7eQoxXBj1ZuZXFw9oeO90XrFsnOsagJQ9VTAJEi/a1Z9LDOqL64cRRHJyobpgezrsT6GQuJyea8qg0JVBmDh2DkpUlglNn81tWlrgwO6PITbnAQ+vXk4516ogEFQjFJF/WWC8Aw7lcZ0OarBSHv4hNlwC6vkt6uhB2r44u0pRh9JN8ECcrg7e45cZnWOuyKW7y6tXut6ZZf1QxCbCno1uTJgWTH67f9COog9CT5a2OYeO1fCKs7fLWQgaVmvRHKUugzBy6Oe6srMjmt829rjYZGe7lCbFZOg2akgUxika+NLGemw8Q8IgQxlyz/qjCEkDXeXNc57p1JRbuRAeRCXoYxsnK4C1uufEZ1rqrNT05Z7V4vVRhVMEDXWSJcoPJD7KIp4uJ6KpHFIlhq2v5RFgrsSw5d43fNKyiKPWjzBx6aVzJEQ0aSNvMzMgs3RQsjEvjxOE2VZnXKjAb4gcULvb5sASqRn4nDXUS7oyF3bls1RNQzDCSN50lTWEYJyu3skRY25qYvcq/0x25VlHghUeH16+vIdGouTddUd1wIikOtjqGrY7li8AL/GO9TtSl/S96h0v7NKXTPh/E4BWHbpZuCrYlcFSZeSNSXt760rlY32qFk0CLGjXkgAYNpdAjbFFdKZM19KjEWA6a5zfGRaVR9VBaWqp7lDL25jizkfF0EfHEo1sdw8Zj+SLwtJUradlDKUugQjt0wprs4txWw+9OTqZkRWGYq1eXFNbgM6uLaBpSISMLoah2rBxeBQznWj9FV0ls2aO8nJ1HLHlzHJvjYn2KZ/hMj+KVUTFZuZUlwlp/Vk6OfzWxyqEqH7tqJJNokZOB6UoifYtHtzqG4bF0UVh5eQrIndv/K1UJpJZq62XQOIrKR1tcWFMVx52yKKwOPGX5Csn/8UeRXyZKiqadMy+qXqJyPSlrlUvzciV/nX/mV8Xhj6gEeHMcm+Oi2QgKG0DTqzDd8snKrSwR1jOyhjlOZ0i8J8GvpatAquDBm+OIFrnPqpqumH4VB1sdw9SxdFFY5c1TQF73VBClfFR4h46iHt6woRR7lq7OXNTp5t95u8i550bgq9EiGWkRUaOopDYW5+bKknW5strq0YaHSiiBjbskZulsjitkSMMG0HQmTLd8snIrKwL3X7RI+i9c5He7b9ztq1TcPBm0a82aBddk+lUcHNYvqxOmJ8izYZgJT8HJfao0JFDhHTpC6aShc8JJxZqla4XUxYv1f8GR/+qrIkysUUZT1I3F2tzKvDxZqo5dk/7wEohJgM+qHlqvXizvokHk0Dew6ZrlwzhZuZUVgcf/849MzF4pfpaEwKsm8GSQixaF9as4+bB+WZ0wPUEe2zhfJ1JVU/Jld9WVwqEzS+dZyyI3H0Xlmr/ddpKy667RXBTxgHyaztJNUTcWazMorX8WXQXhj0ISaJCf717B2dRmR2GjZ7q2fr24iptabu2EsWtUZK4ONv0Wj6gwoohNrGvX5kZzlRsxmDulUSOpF3whF5cc1rd4edMp+IlyEtE0WjExezmo7qH0JFApHDri4VlLN/okA8RTSujRUWLKEUeIZGVBEZk5U2TsWEmxzXVQE9VPRFelZlPcgmj7NOHBSwAJsHmzQ+3a4jbHmf6ovlDmZuvxaBQaT3HLjS+MaUuBdUwcmCb9EZUAO8CrVa8WzVVuxGCOFx65aJHpiOlYURh+deRsJHZ7jn6ZGBEW9SgjlwhrGa9/XaERTAYVmvVHKUmg0jh0ex2sW6s0YaFspEM4Pztb1jdvLrLNNpRGYNw4SfnjDxFm6VBCdZzhTUaPKjNKC5sHL4GgBNi8uU9mZsEbu6L6ImDTNdJUCmMrpwwIlltZUVjrrczLkz/888AqicIHjq4wpfLmMqqnCx+3itmzoC5x2fHy6JZC6vz5Im+/Lew/qtanj8iUKeL2HmkZVWNthvNauFqjQ1P8GwtVEqV7VBqHjpjY9PEvnQmRdhBPOSlQupuNd+8u1aIOvNqcOW7Xu6OjkMoDqzO4JIrKax1CSstz8+D24CVQSAIN0qrJvrqOHtu8SanqDCimY5Y3bDOiWrUij1iaDlo52GhFYT3RrLVrBaOqSX9UUQkweOGzqvupLibUO/QK+RhGtzTEvn7pUkm7+26RL7+UXJ1tp3z3nUhOwN7BR70wjtL4IiVJD6UngQrh0IcPHy7bZmVJ165dZcGCBQmlwecCeSNS7HOBcJpShnD+ihUiHTtKbmCWnj9qlDg6Tj7En3D0GeVjQ16ujkJXrg8oOOf34CWgEjBDyuZNzUYOM3xRHYoZWEp5P8LEiZKvg04DwYCqk4/xUd/qFgNnq37OLcVXcNJtD+VfArzwyC1Pms6gR3Q7EYaPTcOtW0tujx5wOsj/8ENJWbnKpWP/4CUTxkpjD4cif5SiBFJLse0SaXqsrm1369ZNZs+aJZ988om8+eabkmgdBqPZpW5d2aE4a+EonBrHlCOPdP1kxFnjhx9Epk6NrKUnUu4EdJ71xemzMW6VzoRco/6fl0BAAhjSPXVmtMGykOkUOgm/5lPSMiS1QQNyQvQIYJ+HI/AvwEtWtE5SrIV+wKlC8IfYo5TuzXGmN6ZPYYy84Fm3TlJUd6VTJygRmDlTxB75tXrwUhrGSsM2KvJHKUqg3Dv0Xdu2lZ49e4r9Pf/887J82VLLboD31pA773jHubpCU7QwRuEIGx1xhNTQtU3Hq/8II+Xn5IirH65TVF7rz9U1Sv8sugrCHxtIAEPKgHPb9PSCMvTQ9Ip0tMTt82jVXKRDBxfeZMAp48aJW8fUgWjMgVvdYuCUnLXCxs3oKSoY8t0tSQnwKOUeupTj7BwNm+6FcUCv8vNyJHX77UUOPJAaDohqukd+XU7/Bfg1F7GjLiGCQ/9bo0TRrEelIIFy79Dr6Iy7V69esbXuyZMmyZAhQ5KKgkcz3I5iuMIKavmo4q1v3FjW7L03nLJm1SpxYSTeHEfY3XiLi7WV2TlrhC+vadIfXgIbSIA3x3WpU6eAjh6afpG2EqUxS2dGFBtwzpzp9nlIdWUyXuXTXOQDRSQS5bUsPyNdfsnOFh9BUmFU8YNNxPupHha5PBnUJ10vDz/y66KaujQU20wc5EfGltc0g0n/ng4VRCke5d6hc+1dunSRrocfTtLNVh555BFJ9uwos/SD69dz/LERqBlAw6ZozHZ0nRLmaurECW3mTxhPtmB0aXWKwtomjwZFKvv/XgIbSoBZOpvjmtaoESlUnYnpaDCtuuYiRfvsI2u22irCq//zR42KvARJ0+5QvmJh2lZG9PPPaFqz/ohKoCoiokXtmaXbxZtehLHpWJSe37GjSFaWq5XHR39GjIgsU0Ix3jDWMmboflOmCqIUjwrh0BvoWuKJJ54YE8PUGTPk9dcHxfLxEn23airOaEaVMBaitDwKR1pnOy6MlJXlBgsutKnr9rweNtYufGSKwtomO4lh9eAlkEgC7dSIuk1JxmB6pfpTSE+j65a2z8Oxz5kjojOiFG3D5a1uUZi2FdDPP/0eDye6qv5vz5qZ0rZWZoEYVD9cJoxNt7SQpSDZo23skV9nL3UpSBb+Je4jV8YbxtrmwtWrZbKCNuOPUpJAaim1W+LN9ujRQ/beay/XLqHx119/3aXj/WPTXPtataWrrqfHylWhXNowCkd6nUYrmzeXoNGsMWyYuNfD6oy9UB34ISTCWsZO4gWMWjXtDy+BeBLYXvVq98xMiW2OM30ynaRSlMYsnRlRMOzOPg9YHET5YrP8RHna1grLc3LEO3QVRJke5fNkvFSne4OGBXoY1ZFCg8qwPilPSlqGpGjUNKiTbI5zj/xyqeE6lteyyTmr9b8/SksCFcahu1n6SSfF1tI/++ILeeedd+LKhd3uQJ8WLYTHyRyTKmIhTAYas6CMDAkaTQYM+R99JLG1SviMPxmmTGGqGk1F/vASiCsB3hx3cL164jbHoVuA6B+Gz9KGVT9lp53E9nkol+T/9pvkL1+u+qnhJeMrCtM2lRX8uxJUCP5wEjhYIz2FPthiemI4rFdai1l6/mGHuaWgajo4VZKwFOQe+WUJM1zH8so4MXuVTPP2USVROkdq6TRbOq2ec845snXLlq5x1m4GDx4seXnrXT7eP97OdVyjRgVFpqQhzCxIWreOGU2UNP/DDwu/NIFWQvU2mBUpT3XlmedDmioJfySTQOuaNYXNcdXsvdowY/hUf0gW0q2MtELfHnAbkaZPj6xbxuOngTCdtqErVNZ3JRCZ08srdMSjGUOyMuOpCHhz+piiDph3d8TaMD0Bh3XI8lrGI2xENXPz8gR76XTSHvk1vjj4uxUrfIQoJuyST1Qoh96sWTM5+6yznBRQpA81ND5u3HeS6IfJR1t4zWHCWboqpmtMZ0FOQTWMRJ62ayxaFHm/u45goTkDa/yJsDKu0zJ2c2rSH14CCSXQJD/FvTlugw8Kqf64SkGsy0J8e8BCnESQCLu7gahj1n9Bfs1KOG/GVcsqi37yu88LDOjz9ZqDedLQ9JLdQR5wGf2Xuy5XaEOTVfZgk+ZOOriM7XY3PQGrPJ1gwliJ6B46iTPPVace08nsbC2NHnHq8S6ESat82D0qoRJHFcqhc/W9e/eWpk2bkpSl//wjzNKDP1pXEPjXtX59OURBUC6UlLI42Ckoa/RZWXC4R9hiL/KAn/qUkE6CecHM/FWhtyfB78FLICCB9PRqEndzXDz9UoO5fqutYhEkHDsRpBR7vJJ249UL0k1/lYZ+rs7P11TFPlhWYx3YroI0UNw894A2jL+qYl7E5Xa7oyMAgjCcGnURYf1CJ5s3l9z99oPbgdNJ3hxHGD7Mb3nl/H7VSqkM+qeXUu6O6N0qd/1K2KE2bdrI6aefHit/+YUXZNLE32L5cIJZeo+GjSIfxTAljYdR0OiLPGJtjIvzwZZ4dalgdE2PX7NGJvjdnCoJfySTwC7pNYTNcbEIEkbP9CiISWMko49XMhtyj1fOm1PQPDzkEmHaplwx+rnEv+ADaXhQCeySnh7Z7a66odnCj+sm0iej6zKoq8M/3pNgj/xaeRjrOT5ftly8/iGwkocK59ARwfnnny8N6tYl6WbpAwclf4Tt0Pr1pGOdOpJ0lk5rGtqM9yKP2O5NlFMVElYXgicRzitt/MqV8vbixZryh5dAYgkwmzymQQOJfbAF/YI9rFPRvD1eCQthThkxQkQHok4XozwuDUM4b21rGSH31dTTtD+8BGqkVZOdM2pK7KkL0xVwWI9C+ZQW24hkZRUIcehQEZ3QJNRD5Zy+apXYk0Ca9UcJSqBCOvQdd9xJTj/zzJgYXn75ZVm6NPHrYLerni49GhUxS6c1jFynTm73JlnA7d60HcUQUPJkmDKFIX//LT+oY9ekP7wEEkogKyND+GBLkbN0bWF9w4buVbB4zqE2AAAQAElEQVSajBxEkCzEWZRemiHWmjwPvNzP0FUS/kACDCw71K4tGSkpkUkPRNOXZHql9jK/Xh33yC/LQFTjS2wyfbq4N8fRRri+YxL5fmVgrT1K82jzJVAhHToKeEKPHrF3sC9cuFB4e1wicaSoYvFWpLaZmQUsSnMZw2RU+XhhB7s3yQLVxowRFNTN0o23KKwVmaV/oIOMqr7pRkXhjyQSqJ+SKgc0aFj0LD26cZMIUqy5YIjTiIl0U3UbFjdwUB7/aCXS8GASaFi9ujRVENUNR0NfLJ0IKyN2kUd+NekO59g1cgQ9XkTU6Z+2PXL5Mil92+i6VKX+VUiHzh3qfFBn6XH88SQdvPbaa26WHk9J2PjStlYtN0t3zPxTpQJJCLvNcYEPthDadDuKk+3eDLXh2tV/zNJ/yl6pKX94CcSXAIPTfWrXEr494IwdbBjQODoV+zhGVlZsMCtDh0YeX0tUz9qhTeVh0yY67x+tVGH4IyaB5urMm6Wnuxl6TA9NdxJhrY29lLZtZU23bprTaLuG0/mIUKI3xzn9U138+p9/ZI1U/I2Z7qLL0b8K69AxhHyFzY0IVaB/zJghL730kuC8NbvBka6enpd5uE8GUqpKBYqNSC2vYSS3oziqoPCwezOVx9jYmGR8RWGtOFGV+w0NvfsdnSoMfySUAJuS+PIV7zBwTBjQePplH8c48sjIUxgwz5kjKX/8IbHXbsarB1+ozck5q0V/EpR48BIQNg/vHP2+gHO6yCSRLhkdnVI+ZuMpO++sqcjBhk1552317msieqmDBVdi9TTzt0acJgYnSUqraEd57G9qeexUcft0hDrdA6OPTTCTHjp0qJulx6uflpYq++h6Zbd60Y+2RJVR4mEct66lx9rR0OZ6HTDE8iTi1QvSNc0P44n58+V6res/G6gC8UdcCWRUT5e9NIK0dXSG5Jji6VeUlr/DDgUzdNXN/B9/lCLfaogxjdanfd7YBfbgJWASaIj+WSaoL6Y3YYyj1gnQYUOGyMv33ScdWIPX+tjifZ59Vr48+GDpOnx4ZOMmvFYfHk0z2dGkP0pQAqkl2FaZN8UrNE899dSYcfvqq6/k3XffTdgPDOfhDRtKkbN0bSGl3e4iGtrUpHsTEqFNt6MYAoDCR3G1aNrhaNpm/qtzc+WxefPkiqlTxTt1BOYhLAGiSjwLXGgNM6RHpk+EONHNQq+CHTWq8BfYOEG4vhpQa4Pi6Tk5PuSJIDzEJNBMB5b1dNLjCAF9iWfX0KVq6szPeeYZuef226Vjfr7sVq2aq8q/aXXqyHTNP3rPPQKPKC91KHNY22dJcp7O1B3N/wtJYNOyFdqhc8m9eveWdoFwzxAdLa7Q9RnKwoDh7KSKRnjTlalSxcWqfLZ7s5rO1hlx8mpDF3Z3FURqqsFE0atF8yBm5BvM+JUPBR7w11/OqRN+96FOpOUhKIFmGu7cJzNT0ClHT6SbGMCmTTZ8FWzwC2w0EK6PHhpNywl5jluxQrwuqjD84SSwS2bNwjvdo/oS166pXTz4o4/k/159VVarbv2tNvMgnaEHHycerU5+leorPF2V1+1850y0q3Wmr1wpj/75p9dBZFJCUOEdOrP08/r0iYljhIZ4vtSZeowQSrBWtJ869dgzl5SrcoFwvA7rP9aF2L2ZpoZWs27Nkg+21NNRJ0Z3tSolim4QqxtuS/moTzlO/bI/ZviZkROI/xeUQAsNSbaqWVNi6+hhPQrkmaWjm7Z/hHbYuAmOQYDf0QJ6SJ5XcD6qy0EMcsl7qNoSYKZ819y5sjDZM+RRncL+ifL10MmTSa2m6le7tWuljQ4SjfarRicnaBg/U3Xb8Wod7KCDKBOz9Ik5q6M5jzZXAsV16Jt7nlKtf8Zpp0mrbbcVm00PGDBAcpJsuOARttiXrlBSVUbXwQDGaIquVRLaNMOZ/+GHslxHnbkwGy/1g3mjG7ZyeDT9wtx5csvs2X5Uijw8FJIAellXZz6C7gCUxsM665E92gq6CQtvjuMLbG5ncWZ1cQYzXE91D17XtkuIsNOYdyX4WXpUIFUUsRR42YwZMjL4Miz0JaxD0Xyu6mjbKVOknUaFmJ0jNsP/p86bPDBObSWYWTq81HGz9Gg76Cmz9P6LFonXQSS1+VApHHqdunXlsksvFULjiGSIrqP//OuvJOMCL/PYnZl3UGmjnIw+mb3X0/BRis7k+e4vBpNi98GWr78WnlUXNZyUOwWlHQCmMEZ5jRYtv3/OHPn3jOn+M4LIw0NMAoTdY8tBUE1v4uF1skHYPX/eHElJy3CPHon9Wd2gHkJT4AUz/RcuTPhkiDXhceWVAI70+tmzZIjqAQ42dqVhfaFAdQZE9LKFzuZJMzMHAzj11jorr6YOnzzwpA4+oZN2dXS8STp4Lhy6f7zXSWWz/5UPh77ZlyFy/PHHu1k6TeGAn3vqqYSjPsLuBzRoKLEvDGkl0k3VyRPyXKvKDNTVEFFK9IMtKCntsjmurq77tP1hvLC7M1XDlm4d3ZRY62pzBUaVH4HRSFOomI1yR+oIt4869tG65p8X+GoULB6qngQa6nIO3x1oqqF3d/WmN2HsCkX42pVt3EQ3Y2F3ZkmqY8Kf1SVvacNaPmz5cv/dAZVDVT3umDtHiBrGHCx6gjDApichTPRyXsuWbtMbrEHAwZ9J3SiRWTqb48hSR3Qg6s5lbSqvDSwZXMDnYdMlUGkcOh9tOTv6aVWc76C335aJExLP0nmZh9tZrE4cR85nT//JyxMwO9MBXo+Zv912Ih06xGb/bI6799pr5dm+feXmO++UL048UR6/8MLI4xkYUoD7oYoKEhQ3mIYYpRFu4seEYz96ymR5XUNebJqDxUPVkwCfsqxXLU1q2+DQ9CaMo6JZ37y5yDbbRHMiLAkxyKy3ZEmEhi5a3ajOuQKjKea92t0nTRIGla7M/6syEnh2wUK5U6OFzsGqLrgLR09IgI0WxlqOc169446aKnwwGz9H7Sg2mBIwm+MmtG0rk7ZVWwrRINpuNR3IPqURgq9W/GMlHm+iBCqNQ+f6u3fv7mbpuapQzFiefe45WZ8vFG0Ae9euLYTdGR3ysQo2t+HEwYTdrQJv55Kjjoo9Gke743T9qJEZXWXsMGGCc+7nv/jihs9corT8OJTP/XDCWMtXr13r1q96TZ4su/30kzyoEQC+1jYtJ0fYrMIa1yrlKe0RLIMJzgVwXoA+APQHYM2VPGX0icvxUHIS+DE7W3CyrkXTmwS47fjxcoCuU2I0Hf/MmXL6vffKB8cc4x4Vco5d9TSmz+F2VPeox8Dyc52pk/ZQNSQwbOlSuU5D7WyOdFdsuhHVCWerjBbGGkZf26CB/LDvvq4qs3KX0H+Wbq910EtsMZvj4OXJIdG6omXKKoaxufSDTXl5PlLpRLOp/yqVQ99jz/Zy3LHHxmTx3vvvy4zp02L5cKJ5ZvTd7lEFM8OHgjmFjlZoq+tC9XU9PZoVFJTHNEx5GZVS1vf556Urj2eQsR8GbQfTlEEDG11HqHY+jPnV06bJbuPGye4//yx7KxynM6jef/whF/4xXa6dNcs5fGbz/CiZWZmTxdEWBThl6lCXNhil36aj9MunT5cLdEBx2u+/yyE6QDn6t9+k86+/ygEK9GO3H35wfdrnxx9lh++/d2UnaD85H5fiYfMlwABpjeqa6YJr0XQkgNm7wQs7iBLdM2aMYDwdr/5jNqRIrnn9dSGShFPPzUiDFNksR8raMj1U2pgVK4SBnCb9UcklwO//PP3tLtcJQ0zXwjphumH0EF6dkiIvnHGGvHfYYU5aQVtIms1xuTqxopCw+4vNmpHcUAetXbWBIzVC+cjCBRE+/3+TJFCpHDqP4PDRFnsWcrY6vxeZNScQTee6daVmenqs1Dlyy0UVOiUtQ056803ppmHMasx2FIzFOXLLKCbPDAkj6jbLKc39YKJtubTRwEY3bMoNViBiQARhjI6m2bRCeP5+vSYcfi9dfz9Gne5x6oRPUSdM2L44cJg6a/iOUUdNG31/nyK36mCBNX0eq+NHNV7X9AFmbpyfftBd13/tF2kGHvCe5V+YgzhKBHjx0VwcOmAtmm5EMRsyeTMcjwFZlCj4Qo+XmAFpXQacRI4uf+ghkZXRV3BG27CZkbufygv+bNkyGatOnayHyisBBvTnqjPnd819d1fKb9p0gzREw0YPY/RMlytvv+kmebJ3b/csOo4coDqb4zqo0ycN5I8aJVKdVBTC7ZHXc940e7ZbeoxyebSREkjdSP5yz37IwQfLYUccEevnBx98ILNVSWKEaILw9Z61a0vsdZuqTK4ogNnsxga45gsWyMWqwC+oMwceUkU1xXV1ov+g8Sym280ZpTnjaW2itNANG91wmA4vZYlAy5drKB7HW1zgh+wcdKI249H1PLGDcstomsHGE/PnG8XjTZQA+jhjTY78oiH3WBMqX5eOYosgnfP559JZl31w2pTzQg8wwKDzZdVTdJF8188+E/e4EBmDaHtB3WQw+5jeRwy+sXlcuSTAktqj8/8UbEXMmXOJ2J2gToRpVhbGahNFnfrrF18snd9+W264+Wbn3HHwt//3vzLupJNoyQF7j+SXiRKb6EANt6c0lh8fVz30kT8VxiYclc6hI4Ozzz7brXlj3CbojHTo0KGCwaTMgNk8L/Nwr9uEiFKHcF6tWoJz5hlKinDWAGlm4+AgQAP203C5o5vCWtuWN2x0w2F6aqprptCPL0Ip/J96GrJyfGFMWRTYfAKPOYbCjWgOPkXwgOLicF+VkZdDKPLHZkgAffx02fLI+rndB5N1FPP8LwPMjj/9FDuTOW6bDVmYEwZ0kfJC+kjb0fbc/bW0VmCWfp+uw3tjqsKohAcfQ/nunxXCfY/ZAPSBazU9sDzYaIkwPOrUeclWDQ2pf3XUUfJy377yqsInPXoIe4+CT2HIiBGRLwNSL3hOax+alv2kg1p+C2Q9bJwEKqVDP/roo6XDXnvFdqYPHjxY5s6ZHVcy+2vYHQV3AIcqFCgI7NAkj4EESCeDWc2bR4pNUa1Nyxs2uuEw3fJg40mE4eGsQRziZRYGi+ENrjlYF8Z4eWvTyjTPpkLW8aniYdMkwOxp5PJlsY1CG9wblXOwZV7WYXkGmcGwe3+9N7yhy8rzWCuNrmeKlhk9lo62jV6w7MIyir+fMSlVmsQHS5cKX4DkgrjX4LAOxPLoSVQvEuoiPK4REaJ+APV58RaPtvFZVXsKowb7lXSi474MqBGkhG1qe7TT/69F4geWKoyNPCqlQ0cGV155pXtzHGk+2jJq1CiSGwDr6G60asppWDlRyok77aQpEV5f6BKhf8yAjGRpHulwNPtBWJuWN2x0w2G65cHGkwjDw0mDOMwbLIO3qPIwP3mrQ5o2FHjcbypOQ9P+2DQJMHsaoQY3ZuhMzmEcat4GmMGwO7N0NsfZGnsaH9ywdqhv986wlZFXGLN8udyoy1RsnoLdQ8WXAM5x9aN6/AAAEABJREFU5LJlwm5ydzV6nwvhoA5QQLnREmF44LVyy0PTmTsvoEnp0sVFS3k6iBdzsf8Deiz0bnUNU1eBWfq7S5Zoyh8bI4FK69CPOvxw6RR9rAKBvPrqq3E/rcrHWniZDDwxY2qKqbOalHr13OMZrFeaw3a80X9mUKNZ+fiQQ2TiLrtYNoKtPVNaw0Y3HKZbHmw8iTA8nC2Iw7zBMniLKg/zk7c6pGlDcbrRyHvYJAkwe2L9MFbZZBrA1VQflzdtKN+1b19ogIkOhjch8SSGzeLHdOggwjPpeq9c+2Fs5zC6MrHh8dIZM4SnITTrjwosAZYbv1+5Un5bvdqF292l2L02HNYB6EZLhOGhMSu3fBTna+g8/8gjZc1WW8HlIH/UKMkPb760+oaVk98CAxAGIpr1RzElkFpMvgrHlqHr3+edd16s35988ol88803sbwlCjnpqCISNrJylPIFXZPHUUMrxA9BARpAmPOtk08WHiuK97zlBgOG8PlMoY1uebDREmF4tC+FzhHmDfMUVR7mJ291SHM+Bd6qV4cwmqYDh08WUwI804/xirEjW5NzABPKTEnLkG8PPFDCA0z0Lxh2py30cVy7doVf6EHbFAaxnSNI0/R4dQI3zprlnDpLAjgGqnqoWBKYn7tOBv/9t7jH1Oi63ltQXFsRLDO9SISN18otbxi62oUUdeqcz83Sf/hBZOrUyFo6RHjhI22YtNJH6gz9uYULBd2D5KFoCVRah86lH6mKtLeupZMGnnjiCVm7FrNILgIpzFwiych/VSSXAJuCqVLecc117plLZkOEMjGgAGn4MZz/0/YndewoDAKgFfrBQLD2DHMO6IbDdMuDjScRhoe2gjjMGyyDt6jyMD95q0OaNhQOrFtXDqlfX1P+2BQJTNeZE2HumL6YbE3WhpXO7Gbi7rvL7f/9b+xRITsnYfdqqqvkefaXsPvjl10m+Y3riBtgUqBtgGKDVvKB9oNlLEXh1Hk88ozff5c3/17sXnTkePy/CiEBBmHol3t6IsF9droQr8xoiTC6gxSs3PKGoWtUiVcU12ANXXlx6ryimOVMp+/wwqdlLh/Emua7F3zMyr8jQYVRjKNSO/RmzZpJ8NOqH48cKT/++L2g5Allg4JRCEbRwKqUvOXo9vvulAufeUbuP/VU59x5qcLrnTu7xzUuevJJcc6ccBJ1rK61BYYWxPCRN2zl4Tx0oyXC8NBWEId5g2XwFlUe5idvdUhrG/V0ffbuVq2E15ZqtuyOSnImdPH5efNkA2OGfE3Whu2aVR8/Pvpo59QZSDKwpIjNccGXzLzUqZO4PSDrtJT2AE1ucC5rP1Qe2zildYb89Zf01RA8X+XihUSEQvP8W71UMuX7WCP58rbeO/eomnU1dJ+dPsTTAaMlwtaOlVvecJS+vnFj4cuA5tR5RXHK8hXi1tHhjfJJGFOmfWaW/sT8+eKdugqjiKNSO3Suvethh0k7DTuSzlVD+NBDD8W+LoUxhR6DqAI5BYeIgkEDa13JyXNOm+cumbEDt995p7hHNGrUKLw2RB3q0o5haOQNG91wmG55sPEkwvAE2yYf5oUW5CmqPMxP3urw8hPN39SypfAaXZr1sPESIBz6vg0Cqa4yBTnjZrIOY3hUHz8+/mi5/n//cwPKZ/r0cc8A19h/f1fd/fvyS5Hp0wvCm9SjIIyt/SDdaIa1HiFbHHtvna3/nzr3wUuXbLKR3eC3p+37o+QlMG/NGvl+1arCDQfvMyXk7T6TDtOsLIyN1+iWNwxd024Jsnt3YXZO0zJzpuRPGO+SReq5cqF39+mgt9+iRZusb9pMlTgqvUPnoy3HHHNM7GaOHj1axo4d6/I8++sS9k+VzyUNRxXSOfgojZAnz10yY8+oW9u9ux1aLKRJHRoBR+s4pTVaECcqNzptGL/REuEgb6I6YZ5wW+HyeHnqKPBFsGd23EmuaNpMKqFxRoJlAh/8vUR4OVDsZEGZq5wdPYzhgaYDzOUNGwqO/YXzzhMGmmOuusrtKnb19J8Lb2Zna0oP6ily+hzEtBXMw2c0w9AA5WPmzvombxr81/jx7lXE7APYmLXO4G8P/QG0aX+UsAQaVKsmzextmNH7t8H9hx68z/QhSLOyMIYHXqNb3nCUTng9pd3uIllZcEdg6FBnO11fonwSxtaO4tVr18rTCxYI+sZrqokQRRry/4MSqPQOnYs9+eSTZYcddiApCxculBdfesmlNzAiqjiuwDAKRjqIYSC/bp179pKsA/hIUGbYaIaDZfAY3bCVh/PQjZYIw0ObQRzmDZbBW1R5mJ9ZudY7o0kT+Wq33eTCZk01apYai3hokT82UgI8bxszZNQNyjx8fyxvPPDrTJ3IEQNK3q/twpvdulHiwIU3V+oMjbV1qxfG4XYpN5phaK7FwD8t4xXA1+uMi/f+/2/uXOH5dUKjG/y2AtXiJcMOPh6Pp228BDL1vjeszjsvta7dw3hY76VyFLwHAR6jJcLwUMnKLQ82GlhtpTRtIrY5jiqi0aNUnXGrARHn1CHCG8SBdngp1qycHAF4TTXfl+AbFLzZcGN1jVNUVqgSDr19+/bSuUuX2HPpI3Ut/aefftrQEaFA3GnDwbTR4ildkC9YbnUMB8uCdcLl4Tz1jJYIw0ObQRzmDZbBW1R5kF95d69bV17beWd5TqGNrp3ThIdNkEC0Cs95F3qUKChveFTmoJjDt7zxkQcck/7DcLLJU9fONRc51Nm68GZ1zVq9MLY2gnSjGQ6WaVNBI8yMHcdOWJTvClwxdao8rwNnc+6wJ4OgM4/H5w12PKkUj8beln0yawsOMVYj3r2Md5+NlghbO1ZuebDRDOvJ8zt2FMnK0lTkWD9okCR9v3ugHXTMAN1jxn7rH38I36bo+fsUwbnze9qYKFGkF5Xrf2rlupzEV3PeuedKo8aNHQMfbXnzzTddeoN/KBHERNgU1HCYz+jgZGXxzkGdIN3y4HBb4Tw81A3ioniKKqctBcb3l7VoIcN33VVOVRliJDiVh82TAJuVWB+MtaKydmnD4ftj+XA5ecoAbSB1++1FsrI0FT1YYtLwfDRXeBYGMVqv0MDBaIY5B7yJsJbxhi82Xw34+2/598w/5Nxp0+T2WbOEL/rh3ItrbOM5eHPqYEBP549iSqBljXSppaH3QveXusF7Ge8+Gy0RtvpWbnmw0aKYsHvwzXGcXnhz3OIVLun+RXlx2C5POyTCdPJR4NsUQ3TwiHPnQ1WdfvnFfZGyqobkq4xD76SzloMOOgj1cMBHW6apwakhKS4f+2dKlAijSDAbDvMZHZysjDYSlRudNuADGy0Rhsd4DYd5wzzhcupBAzRdT9fe9mvQQIbusos82rq1tGD2p3R/bL4EWHMexWa48D0J5qP3YQNDbDxWTncK0rKeF3l06BCLSDnDSdgdPsDqG7a6lgcbzTC0eHUT0HHuPPLGB1+umz1LLtPZ1PUzZrgvaREmxbkX1zHj4AF3+vDPNV/HJwqUeYgvgW01mtYYh27F8e5ZvPtstETY2rFyy4ONZlijR+4Ncd27Wy+k2pw5Il+NFr4g6IjGa5h2KLB8GFMGTxTYi8JXInnUbZcff5QjJk50+sZvrbi6RpMVGaqMQ+cmBV8Hy0dbPv7kE8iSjkK4lP6zdCIcVqowX7A8WZmeKjYSNT6rG85DN1oiDA9tBnGYN1gGr5VDV+C549a1awtr5A/oLO/Ttm3ly3a7SbcGDeD2UIIS+HL58th7tV2zKv8NsN2fMDbeeHRdU3cGUgewPNXh2tSwO4bTrVdCsPqGrR3Lg41mGFq8umG68cMbBQwtz9k/pTOpK9SxX6gD6QsmT5aH5//pXlqDwY2yFguZc4c5386vmapitPVSN+rYJb2GXNSsmdTUAbobHJrMgtjuWzyalYWx8Rrd8oaNHsXM0sOb4/J5c5yujTtbGOVzaa4wQTux8jA/daI0wvO2cZP9HdfroJIoESyVGaqUQ99rr32k6+GHx+7nU08+KXy05Z8aNWI0p/DkTJnCOKowMaVKVp6sLN45rG2rZ3mw0RJheGgziMO8wTJ4c3MFJ84s/NbttnMz8Q/Vib+qM/Krtt7aPY4WNJ5U8VAyEvgxO7vgvdo0Gb435MP3z/KUUcfyhqFrOj8vR5zhPPBAuBxgON0MiRx8Qax1yMZ0mnKjGYYGU1E4Eb/WxcguXLNGxixdKq8rXK8DjZ5TpsjRv/0mvSdNcrvledUsM3g21mmVIo+0tNRCe2G8U99QZMjo4ubN5eGs7YSnU2IcwXsZ774ZLRG2+lZuecNGN6yz9ODmODfgZJauM2nJSIt1K2aDE7Vj7YWx8RumRU2zDHS/Lv10Ux2r7Dvkq5RDT0+vJpdccgm32cFkvcHDhg+XrdaudY7NEVUBkuKilChYHm4rWMZJEpUbPchvtEQ4yEvblicNkAc03VRD5z2aNBEeO/upfXv5eKed5KaW27iZuN/spgIq5YNwM6eoFgyDRu9NzJiRL+peh8utzqp14gznrrtyGgc1fvhB3Jeu9N4XOgel1g71yYONZhialSXDifiNrnW5bpw7wOYmwqR85Q0Hf57O3pnBM6N68M8/hY1Oq/T3qdWKPBh8AkUyVkEG9r2c1LiRXNOihbSOvrWtkB7Y/QneZ6MlwsZr5ZY3bPQAZrDJ5jh7yYzooM59VjUto+CuGH+Sdhyz8Rk2frDRwFFgMMkO+SN1AMEmuuLqlTtXBflXpRw692TfffeVww47jKQwQnzx+eeFjRV8a9oRUQYSiTDKQbnhMJ/RwcnKaCNRudFpAz6w0RJheIwXDB+g6aYagWCH+jXbbCMfqJGfscce8rY6cR47a1ezpmRqKM4bQhVUGR0Y1zUaHUn45Su7l9H7V8jw0sdE5ZRZHU3n77BD7Jl0XuqR/9FHkZfMWH3DVsfyYKMZhqZtFprFx8sn4je61sGRK4oMorVdHDzt5q5fLxhdZvAv/Dlfrldjf646+K46i79WZ1g4940Nz3MeDxEJNNIB5EWNG8s1W7eQ3WvXlpheUWz3R+8HWe5HrNzKwth4jW55w0YP4pw8SdlrL+HNcdXSorPyceNEFv4lbkmIusZPms5Yvihs/OAwLzTaUsyM/VbVp90nTHBr7DbApriiQ5Vz6A10Pbh3796x+/bDjz+KfP99LO8UmZzeeNAG+SSK4viD5eE2gmUwJyo3elH8xkdb6iDcD1AxDpww+vktW8gzbXaQYbvsIj/tsaf8b9tt3SwcB04VD1tGAswMVqXoue3+he+z5a08jCkP00J51itln32c4dQzuSNfQ9uOboaUdiixupYHG80wNHiLwvH4jRbC5tgN07yDKB/06atWyXcrVsjD8+ZJ5/HjhfVQc+7I0fH7f8WWAL/9M5tuJXerLThcnfsGFYP3N3ofNrCBRjfecB660cJYy5wOdu/uJlScn8+qssfDLQlpeex8pGEIt5Eob/zgMA80aytaxjPtvBypu7ruOYUAABAASURBVEZqGSxSXNGhyjl0btjhuo5+wAEHkIzA448X/daioEJQK6oUzomSj1duNMNWx7DRDYfpljdsfIbVeXP+mjryxoFfoz/S13QNHAdOGP3Z7Vq7l7/walY/A+cmlQ+IfRDI7iPdsnscxFYexvCEaeG8rlfy6d8UjcjQvAPWK7/+OjJLh0A7YKtrebDRDEODtygcj99oYVxUW5xPAccOaFKYXbEeerLO2i+fO0c2aqMTDXhw3104sm49eXC77dyA//CGDYVJwAaiCd+vcN7un9EtDzZaGHMSNm4G3hznokeTJ0dm6cElIdqBP9xGorzxg8M80IJtadrplNJHLl4shOFZXycCVJH3YVRJh85HW3r27Km3NHK4EeLYsZHHJ/QGO2oinEhRjD9YbjTDwTJOYnTDVh7OQweoo4ADJ2TGs+Ef7LabjN9zT3lPZ+HMwE9u1Fja16rtw+gqp/J4YCzy1dkuWZdbuHt2f4PY9CCM4QnT4uT56l/wS1esV6ZMnVpwXtohZ3UtDzaaYWjwFoXj8RstjIvbVrAeaQWWyfotWCiP6CCluBvo6L6HiATYKMdyG8tug3bcUd7UJTiebDl/6+YuHO8cvMo5wh36b3S7f+E8dKMlwLw6u9Cb4wYPlpRVK8W9aMbq0A6ntnxR2PjBYV5oidpSXvZysL5OBIiXIvE7hb2iQWpF63BJ9be7hnz4aAvrOIwQZehQcaEgO4EpQBjrzXcshpOVJyujkUTlQbqmeR6cNfDLmjcX3tQ2de+9XQidZ8N5pIyNbKyP0SQzcYC0h/InAe4Nn+B1PTMdSoT13ju+MIY/TIuXV9p61RnWK107+o+wu1uvZCZEO0ojygOKhTqha11HMwwNQlE4Hr/Rwri4bcWrp3WZYX2zerXMzMmRcmCAkU6FBGzHQXXrCk+2PLPtdvL2zjtHHHxWlrB5lslD0xqBJ4GikUGJd1+QgN6bDcrCvNVFCg02RYQ9Hu41xpp2B+2QCNdNlDd+cJgHWrK2NMqJ/hMB6jttqhw1aaLwcpqKpldV1qG3atVK+GgLG+Nw6uwCFsKRtWpx24Wb6xKmCIYTKUq8cqMZLk5deBSYhVsY/T39gbEGjgPnTW284AXH4Prn/1VICazUsGORRs/0JoxVPxLqZ5hXpZPSpYv+jxzVxoxxX7qKrVdCtjq0Sx5sNMPQrCwZjsdvtDAuqs0wv+WtnvZjsTqXqerQ/e9BhVECBzN3Jgg4+H8331rebLNDzMHfqkt6bKxl7Z0JBo/A8dirOy33RO+F02nSEO1+hTFlOXmSn1lb1sT77gDlQFHthNs1fnCisjDd8lYnmicMf9+f8wo9EkmXyjtUWYfOjTnvvPOklSopTj1vzRoRDbu7WTqzF24wTGEcveExg5qsPFlZuO0oL06cZ8J5Hpx1cMLo/Li8wUJglQNy8vPFOfSwLoXzUZ1wRpJLtzx8li4Ka72UvfYS0dmWJt1GJMLuTs9pB7A2SMMENpphaFaWDMfjN1oYF9VmmN/yVk/7sVZpddLSpKLNpLTrG3dsAW5sjjn4A+rUlVu22UbuabmNEKJnFs9enVc1XO9C9S1bSI+mTQVHz2RE+NN7A5JEuGkTkU6dHIv7N3Ome3Oceybd7jE4Uf0wHV4aAicqC9MtH6xDWtuZmL1K/1eso0o79DZt2shxxx7r7hhOvcawYSITJxZsGqIkenOL5cDhNwUBF6cufFqPUe8Xu+/u1sL54eDE2ZGqRf6oZBLISEmR7QnxRe99QoOXGv15hjH1wrREeY0ErG/YUKRDh5gU+QJb6vz54h4TCrZFGi5wuD1oVpYMW70gv9HCOMgTr80wv+Wtntapq84ch47z0aw/SkkCJl8cPCF6ZvFstmXPDqH6J1tuK8+1bu1m8y+pXWV5kFB9zLkH+8V91HvIM+nh7w7kjxoV4dRylwDDT6YoDC984DAvNMrCdMtTHkwr78J166Si7c+IWgztfRU9LrzgAmmg60dcPmvpse9Hc3MBbjSFhqGRN2x0w0YHG80wNKsLTUNUjGhZFx++086CE+fHAouHyisB7nEfXvBhzwIH9YLLtjw6Qj6MKQ/TkuVZ/wzMhHiH9voZMwoGrlaXdjkf2GiGoVlZMhyP32hhXFSbYX7LWz3Nt87IkFqa9zN0bsomwyZXNEfPS7vQaxw9Tp7lQWbxD2dtJ6zD8zIbF57XexYbwBJ23247CW6Oc0ufv0wUIUqq99V1jDokisLGDw7zQkvWBuVWh7QCyzljVwQ+HkP9cg6p5bx/pd69XdruKieeckrsPOn9+0vqokUbzl70Bjsmu+mGjW7Y6GCjGYZGI+rIeWf6AzqS/axdO2FdnJGv+L8qIwFCmL2bNIl81tL0IoxNb8IYvjCtiHxwJkQ0yi0vZWeLizxZXdrlDoCNZhialSXD8fiNFsZFtRnmt7zV03zbWpmyi38xEnek3IA5eZx7Hw3Dv7Zda2HWfq8u+7CkyCZf59Sj95E3x4mWxS5gxIiCwSZEvc8gp6skEuWj7bm2wzxWFqZbnvJgWs/DNwjmrlmrqYpzpFacrpZOT3GkfFrVXkXILN3ttuR03GBuNGnD0MgbNrpho4ONFsAoM8+Ls0ZOqIpRLc15qFoSwOid2LixdKxTR5wB4vLRmSAO6A3kQnyJyhLQ12+1VeGZkC4vpdgX2KxO8PxGMxwsozOJ8vH4jRbGidowepjf8pRrmpDuoXXruUc06ZKH8icB9Dw9vZqLPmLvXtlhB3lm++2FJUZsYT4z4LZtRXR9nt5jf/k6oHsSQ5dToMX0Xu950jx6AQM4zAuNsjDd8pQH01He73mUjnQFgSrv0LlPu++1l/Q4/niSDlhjTFkeDbVwo6Eatptu2OiGjW6Yupom3MSb277abTf3xjZGrxR5qLoS4DngS5s3j3wwQ3VkA8NlOhXG8CK2MD1RXtcC+QIbr4KlGuAM51ejxa2jQ6BNgLRGkECx/pCxsqKw9SHIZ7QwDvKEzxHmtTx82j+Wqm5o2VJ6NmgIxUMFkcD2NTKEkPw7Gp3EsfPcO09cpHTpEntNsXsviOomdHdZdu+LwkF9CvNaWZhuecqDaXdikQZp1aKpioG8Q9f7lJmeLuf36aOp6DFzpsg7bwtGMGbUuOEU2003bHTDQbrSeH6TF8BM0kEDz3hixGnGg5cAEmC55RFdR2TGssEGItUfeBLqYKJy6AFgMFl3zRqpt8suIqEvsB2uEQLWOAmF8sYwAGe5X716wrIQsyiAvtHOBn2hg5wLDKizBRUCKw9j+63Ew0Fe0tF26Qu7qR/XWR6yI8JW6Fw+U64lwIwdyKieLjj2R1tuI6NU/0/v1UvWaBSJzjPYzB81SngxkltL5/5TEB/Hj3CFeU3HwnTLh9tXOo/lnRntE8UVAbxDj96lDnvvLcdGd7zzXDqzdBf2MUUwrDfaVTFsdMMYHi3DKPL42Q977ilsEGFG7o2Pk5z/F5IAjolHgQbvtFNsAxEO1LGpLjkc/AfNADppsAL1GETijHHORIX+q+FMZkNf6Szo+v33Vy4RdLzV7NnySEqK2538Sbt28pKGQ+kH+zoeUyM7VAcAvAOBurYGes222wo7mM9o0kRoH8ePrnNOnG29jAzhD+cPFBoAWD/BQPS3IomwNkS7tI8T5znogdpHdlOzgVSL/VFBJYBTBzJ1MsW9fETv6/WnnlpwNXPmiEyZ4tbS0SPAOXfsrEEBdySFTpECw0PacIjmdFXPjX6RNszmPfSN3w/OvKJNwFK5Zg8iderWlR49ejhRsGkoFvaxF82gEJSaghg2etQoMdPhs6TDd91V+CQpL4GhmgcvgWQSYC8F79fGWeE8r2vRQnCYGBdz0hgdgLVj9AwnR8gSJ4uz40M8D2dt597yhTPGORMVQg+ZDbEj/HhdWmratKmg47NnzZLhw4cLYUW+AIeu0g+AR5IwZhhb6gKsgd7balu5V2fHr6qzp/03d95Z0HWeScb543D5ot8T27cW94yyhlZ5TvlWHSDQT15MwiDDgGswIEoBUAY/T3/wSlLaH7DjjsLjnLwZkf4lk6Uvq3gS4J5edNFFIrY5buZM6arwfqtWTo/Qpddat5ZnVK+e0UHjrTpIdQPLRo3kjHjQoIH7/Rxev77DbuCZmeleawvtWI1M3Vetmtym6/RBfI2K7mK16YNTUuQCXapasGCBLIjCbB0AA+SnTZsmP/30k4wdO1Y++/xzB/yWgBX//KOtbJnDO/SA3E/t2VPsoy2EffYaNkx2y8+XFL35jOIcViUohHWURx4j9IXOxpnp8H5kjCMj0EDzPlmKEuCxpWSQl7deShPWrs2VzQX6Vz8lVTplZMo16nRf1/V1nPuXOnvGseE0gYE6k/9A148fU8d6f4MWcnvjxnJdw4ZyTsNGclad2tJRjVQbNUq1NMy+KnulLF+21EHuihWSpQZzB50NMUMHhg4dKnPnzHZGC2OFoQrDlMmTBJjw668Oz5w8WUjPnzRJlmp60YQJUuOPP6TO9Omy9cyZDjrO/1Oy1Ojtr0awvc60jpg3T46cMcNBr1mz5YTJUxycp3WAMyZOlL7KBxz9y3jpoOeq+913svKrr+S7Dz6QD4cOlTffeMPBwIEDxaB///4C9OvXT/opvPjii2Lw9DPPSBAee+wxCcKDDz4oQbjnnnskDLfccouE4YYbbpAwXHXVVRKESy+9VMLQ54ILJAjnnnmmy4MNTjvtNDE4+eSTxYDJhsFxxx0nBkcffbQEoWvXrhKEA3WJJRHso1HJRLDbbrsJZSWBaaM40OOEE4RHKs1MfP/II3L9QQfJA0ccIXcdfLCDJ7oeJs/r8uhbet0jjjpKvtUBqsHoaB4MTFYeg7kafV3WvbsA0Kjz4KmnisHdOpkDLH/KKac4uf6rUycxOFD7ArTV39/gwYOlffv27vfUVge3bXSwsZcuq/I68Rr6+7VrKGtcag6dTxsuXbpUGK0ApIsCRj7wBDHp4gDGCD5wcQHDBS8Y4AX95tC5ERPUWPXVEdhv6rQZxT2dlyeM7Aw/+c03Lv+DGs8r16yVrRctEozdJDV0GDzDpMPA6A4aOAiM+MLACBAaOAyMCKGBg/DOO+9IGMwggs0ggjGIAAYRMIMIDhpE0kGDSDpsEMmXpVHso0YSY3j+WWeKwRmnnyZBOPWUk6VXr1OlZ8+TYpj0CSd0F+DYY4/R5ZYCOPLIIyQIXbp0ljD8q2MHRwMD++37LwnC3nu3lyC0a9dWwrDDjm0kDC1abC2tWrWUXXRGuosaim46w+3aooV01xkJGDioWTNpnZUlu6kjb9aykWy99dZSX9f6mjVp5LDl6+g6eJPmzaW5On+gSfPmkqWGZxyfDFYFf0Ed/47ffit7qvFurmWtdYDQbo89BNhFZ94Gu2t5+332cQaMNIAx20eNHbhjhw6uDByEAw84QLoceqgcfcwxQvoIdTYGPXTwDHTr1k3Avc44QwCcFhg6cLw6r5NGIPznAAAQAElEQVSVFzj99NPlFDXCZ591lpyh/MBZmgbOOeccAc4//3wxuFhnfEG4/PLLJQhXX321BOHGG2+UMNx+++1y9113Cdjg3nvvlTA89NBDEoQnnnhCwvDC889Lv5deEjDw8quvujTY4LXXXhMDnIZB8Lf8/vvvi8GIESMkCJ988okEYazaKOArHRiFgU9H//LLLwKQDsIEHaSRLwk8GXuo7dFWEKADRuN8uWpjeS9IB50hr8jOFsqgg+EFLP+HDhCnTp0qBkScSIP/nDtXANLxAL4gGG+QRjpe3aU6A8/JydFfkAgf+gJ4lbhhnsl3hUX/K3GOUnPo7+gIputhh0mPE090YCNNsI0uw7in/nCpY/gY/bGHITj6tPRBOnI6TM9lmLQBIyqDjh07CmkwgPM2TBoD+uxTT8WEzOtg/60jb4zZDTpC7Ksj2gFt24phyl5XY8fIrK3SmfmAgd12310Mkw4DdaCBg4DhM9h3330FOPSQQxw2Y0jeAKNHGhwEDKABRhLAIAJmFM0wYhABDCJgBhF82SWXCGCGMWgQSYcNIvmwUcQgGphRfOD++4s0is88/XSRRtEMoxlEsBlEw0GjSNqMY3GNYtgQkseoGMYgAtAMzACBAYxD2ACZEQkajb8XL5aFCxcKNDB5DFsYMCoAkaREGEWmPB5Q1m7tWnlRw4oPq3Fito4xNV7SAHxg6JY2bDTyQYCfPBgegHQQoAHwgQ0sDwaCdUgbDVxWYOctifOVZFvF6Q/nAxLxUgYkKi8JeqL2oQOcA/0DSLfRSNLTGhllwIlzByirE13+JM9jxuRJxwPKGumAl7KmGu2KB7z2GzoYXnA8wK4HgTab6QCYvpY3KDWH/vvvv7uR3yhdXwiOGEknGjGagTSMkQTMSIIxjmGIZyyhARhGAwwkaTCGEhwGjKPdpDN1nfxZXRvHsWNQjW4YI2QKabTNxbRnEG4rET3MR954weQB0kA4TT4RwA8kKi8OnfoGxk/e0olwIp5E9ETtlDad/gDh84RpReWpn4jH6GAA3qKgKL5M3saljZyljv1zNaDMijCUQcAwYsAAS4MxhNAwhGGgbGuNCoSNY9AoBtOEKcmDDfbeay+NaLQTcBgYfEMDxwMG89DBQThKQ7JBOFbDsAYnnHCCRmsKgEmFQa9evTSyUxjO6d1bDM7v08elwUG4RAfD5MFBuPLKKyUeXH/99Y4ONrj55pslHtx9990SDx544AEJw6OPPipBeEoHyuTBQXjhhRckCC+//LIE4ZVXXhFgwIABEoQ3Xn9d4sGQIUMkEQzT5UzKwMC7770nwKeffSaDNJKxd506gl5+vXq1vKhLKR99/LG8pcsuhofrMgx5g+EffeTKwQZDlZ802CAYzRiqUUzyhodp5IM02OBDjYC8++67EoSvNWp7qobkWeLTn0+5Ogo59JLuGQYFCLcbjxbmCeYZnRUF8BfFEyxPxI8xM75zNPyDUmHsMGJWRl3A+KBvDmAYqQ8OA8YxHoSNJXmMYhjMQAYxxjAIGD/y4HgQNIqW3ljDGDaKZgwNY/jCEDSClg4bQjN8YAyfYdIARs8w6SAEDR8GLghBQ0c6nqHDuAHJjBtGKwwYsCBgxMiD48GXGi79RkOnhkkDP2ro3ODX8eMlmCafCBjoPqghYnTY4ABdNnqlWjWZoOvMEzQMa4Dx+u6HHyQMDLqhOaxr3Ya/0zTw5ejREgYG82EYrXxcO/hjNdoGH6jBJw0OwscaUibKYvg9dQRhePPNNwUaeMjbb4tB2OkMVMf0poa4wYM0/B2E/urMgH7K85I6mBfUqfTr118MnnnhJTF48omn5PmX+8kzTz9TCB597HF5/rnnBPz444+LActS9z/woACkDViqIg02uO222+SWW28TcBBYw7/u+hsEIG0QXMe39GWXXSZBuKhvX5cHB4GPVQXh7LPPlrMDcKau+QNE+YJwsjq3eMAg6fjuJwhAOghH6/o2ebDBkUcdLft26SJtNBJqerlLRoac8MwzckiDBnKIRkkTQSdd/qGs4786CelEsMee7SUILBkZtNNoK2mwAVHbnXbeRcBBaKD9KY97pErNoR+lo2EMJsbQIGgUSTP6wyAC8Ywi67vAmxq+DwIjOfJgA0ZupMFhwBAmgu/GjZMgfK+jr/G//upoB2gYH8XC2C3RGQzGbrqu28yaNUsA0sDvukY0c/p0CcN8XccJwl/z54vBMl1vB5YsXSp//vmngOf+9ZdLgw1oc8bs2TJ79lzXPpj81N+nyZTffhOwwYQJE+Vnt1Y1UdeeIvDDDz9JGMZ8860YfPvdOPn008/FMOlRo76QIHz44UcybNgIARu8//4Huo4XgXfeGarr9UNl6LvvyeDBb8XgrbeHyOtvvOlgwMBBAgwaNEiAF17pLwYv9e/vDB/GLwhmAIMYgxcEM3xgDJ5h0gAGD2wGL4jN4IGDBo900NCRjmfoMG5AMuOG0QqDGTDDGCLS4HiQyDhhfAwwQMF023a7CbR4wEeJLjjvPMFYot8Gu2j4vc2//y1tvv5a4AEwYuBkwPoh5WCDFi1aiqWTYdYdW27TSrZq2iwG0BIBhpSyIK5Xv4GQjwc8vVKrTl0Bx4MMDeNSDk7PrCXgIGSmpzsamLXRRMAjqWEwg2/Y5AyGBpAuChLxQQeKqr8ly+kfUJw+wFdDUkTUDsb4NfwuI0eKnHSSiA7OYvQECdpIUOTIlAfBEYv4B38RLOWmOLW0eoIRwlBiDCPQV8459zwJG0YMIrAxRhHjh5EEG2AISYPDwKitQ4eOAgbom4EZQcMYQoxYe11/CcsGY9dKBwAYICBoqDAyGCWwQdjABA2KGQ0MBWkwEEwH8xgSysDQwZYnbWBlli8KY4TgMWxp8kFIRA/yoPjhPLQgmEzj0aysJDHnKcn2KkpbRV13xpIl8S8FA3rppSIXXCA52dnxeYpBRQ+KweZY6GsQHHEj/lE3GXtxy4viS3YOX1bCEkAPg03qhEnOOUfkv/91T6sEi3y6QAKpBcnST22pHwznxcCAgWRXWqgcJTJmFAxQpUq96b+ydtWGxq5QXavnsZdARZMAeq5h5owePUR4wUdF67/vb4WVQFIbil7edZekXdTX62WCO1ymDj1BH0qEXGaNRJXKG7syk7g/UWlI4O+/RdDlZG3rur3ouqXo2nYyNl/mJVBSEnAbzf75J3lzOtiU888X+fnn5HxVsNQ79E296Wbsfv55U1vw9bwEtpwEWKesUyf5+XH4ixaJnHiiyCuvJOf1pV4CJSABN0NfubLolmxd3Q82C8nKO/RC4ohk8vLWRxKxkHskW+i/GbuDDirWZo1CdX3GS6A8SAAdLqof8ABnny2sXxbF7su9BDZbAsuXF68J7DODzcce8+vqUYl5hx4VRBCx3i6EJIPEeGkMHaDr6hg7Xv0Zj83TvATKnQT+/LP4XWImf/jhIu3bb9ZGueKf0HNWaQkQFULniiME7O/ll0vak08Uh7vS83iHXhK3GKW66y5Jv+TiTTJ4JdEF34aXwEZJoDizoNatRf7zH5HRoyVv+AgXeufJio06j2f2EtgUCWBTi1OPgWa/fiInnFAc7krP4x16olvMGmOisjCd0SSK1bOne2Y1XOzzXgIVTgI487feErnzTpE99xQXtapwF+E7XNEk4JY7maEn6zj2tk8fkZ9+EvnoI5GzzhLZZptkNapMmXfoiW51UTstqYcTZwbz228RxeraFWo5A98dL4E4EggbTRw4+mysrE/+8ovlPPYSKBMJrMtZXfR59t1X1j7xlIgONItmrloc3qEnut/F2Wl59dVuBpO3dYtErXi6l0D5lIA5dJz4o4+KfP655AwZIsLsx3o8aJBfQjJZeFx2Epg1q+Bc6COTJmbkRh05UtLff9dyHgck4B16QBiFkuE1RmYwQaWC+Ysv+F+lw5FOAP5fxZPA/vuLe6XmCy+IXHaZC1m69XFC7HY1ajgzxoyxnMdeAqUugdgbDLG3DDRHj3aTJrn44oLBJk7+uedKvS8V8QTeoSe6a8xgUJzoDCZvyu8iN90kgqJZnddf9zMYk4XHFUsCZ50lwhJReO2RzUVBHX/ggYp1Xb63FVoCLtp5330iGjFyA00Lq4MZeHJ1bJjjPSA//+wfV0MeAfAOPSCMQsnOnUVeflnWvj/MzWDcpiCMH8pmjOr0M1580XIel7gEfINlLgF03AwnJ9dZun8jF4LwUBYScHYW540ehk/IB1pssIlTf+opHx0Nycg79JBAYllmLyeeKHyUJEbTRM6RR4owa9e0e3XmsGF+lo4sPFQeCfCyJDOcXJUaTpAHL4EtKgEc/SGHFHThs89EdJZeQPAp79A3UgfcOuNppxXU0hlMxocfFuR9qsJIwHc0gQQwnKeeWlDoDWeBLHxqy0oguJbOkxg8Wrlle1Suzu4d+qbcDkaJzGBYY6e+36CBFDxUJgmw5GT67Q1nZbqzFftaGGzuu2/BBrnXX/dfXgvcUe/QA8IodpL1HWYwrONQiQ0a/iMBSMJDTAIVPMGSEzrOZeDYveFEEh7KgwR4XNj6wWCTCJLlqzj2Dn1TFeDCCwt2vOPYBw/e1JZ8PS+B8imBI46IzITQbwznO++Uz376XlUpCeQdcqgIs3S76kGD/Cw9Kgvv0KOC2GjELJ3Qu1VklOg3aJg0PC5lCZRJ8yeeWNhwDhvmDWeZCN6fJJkE3E740D4mmTw5WZUqU+Yd+ubcar9BY3Ok5+tWBAl4w1kR7lLV6yOTKXvaiKt/4AH/TLrKwTt0FcKmHnm77S5i64w04tcZkYKHCi+BggtY2+v0gqUlyGo4c7KzSXnwEthiEnAvoOnWreD8I0dK2q/jC/JVNOUd+mbceBf66dkzss5IO6wzEnon7cFLoBJIwL2HIfiimW++Ef862EpwYyv4JTjbG+d9Ce5rbRX82jan+96hb470tG7OfvsVXme84w5ZuzZXS/zhJVBJJBB8HSwb5DZzA2glkYq/jC0tAR5hC0VIq/os3Tv0zVRK96KZCy4oaGXRIv8loAJp+FRlkAAbQEOG07+hqzLc2EpwDbwOlscquRQGm1X8RTPeoaMImwsdOxZ+Hax/0czmStTXL28SqDCGs7wJzvenNCXg9zEVlq536IXlsWk5ZjDBDRq6zij+RTObJktfq3xKIE54s3x21PeqKknAraWH9zE9+2xVEkGha/UOvZA4NiMTXmd8wH92cjOk6auWRwnwopl+/URmzxapoqHN8nhbqnqfNnjRTBUWiHfoJXXzmaUH1xlpd84c/2wkcvBQKSSQ1/0EkbPOEvfIEDP2SnFV/iIqugTcLP3qqyVn5UpZu2ad5N12e0W/pE3uv3fomyy6OBVZZ+zTR+Q//xH56CMRdfJO2eKwepKXQEWTgOmy4YrW//LfX9/DTZZA167CBmUes6zK+ukd+iZrUJyKzFrYEHfnnXEKPclLwEvAS8BLwEug9CRQJRw6z4UPHz5cKYOYHQAAEABJREFUJvz6a6lJctXatfLOO+/IpEmTNvkctLE+P3516J99/rkAcHAtXBPXRt5D1ZEA9930IN5V//TTTwKPla345x95+pln5NJLL5WxY8caebMwL/BAXze1EfQWSFSft9H1799fpk2b5li4Hq7LZfy/TZIAlbhv2KmrrrrK2Svy0Esa0I2BAwcK5+HelUT7tJlMZ4o6B3WBRHzo3JtvvBHzE/zGgET85ZFeJRx6dvYKufmmm+SjkSNL7R78s2SJ3HzzzTLqiy826Rw33HCDPP3445K/fn3c+qkpIsM++EA+jl7D+5rmmtbkrIrL74mVUwIY4BEjRsi3SRzzgAED5J577okJ4PJLLpF/qwH/ZswYmT1rVoy+qYkFCxZI795nyNivv96kJmbPni1nnHGafPX1lwnrL1uxQl599VWZPWeO4+F6hg4d6tL+36ZLYODAAXJyz57y/vvvy4wZM0ptjw+27OyzzpKRaq9m6f3e9B5HauJszz7jDBk27P0IYSP/M6g1nWNyFK86Ove6OvSJEye64icef1yeefppl64o/1IrSkcrez+///57+UdnUsnWfx588MFChrqyy8Rf34YSQD8eV0PDAHDD0gglPT3dJcxwjdMZ+//17Svf//CDnHzKKa5sc/6tXLlSvtbBQWbNmpvUzJ9//imjR4+WBvXrJ6zfrFkz+fjjj+WQgw92b15cvcoPXBMKayMKvvzqK+l6+OHy+++/u9kza84bUT0Ja0ERs+AfVNd6n3aa/KpR0YtU9wpKNy01d/58+fa772TVJugBv4OFixa5+pydyRE4DOjckCFD3G+EgXNubsV742eVcuhrNSxO6LFHjx7S54ILJBzCI09Y0srD4cmlS5c6h3ryySfLaaqshARRlrBixMsTLnrxxRddPdpnxkF71If+pRpIlAmnTX1ohMZuueUWV4fQD+GggQMHUrwBENai7/SZNmGAn35yPtphZgXdQ/mRAPeLex7UPe4xRrFfv37CveujumpLOdxbdIN7a1dBXXjgRb/R84yMDFm0cIHT16k6E/ti1CiXRueoh26de+aZrv14usGSDvpEm2D6ST106L7//U8W/vWX3KRRL/SSPlEWBELlDDqOO+44p7+cDz7O/9hjj8nfixfLtdde636DzJ6QATrMb4swLbN4+kU/GMTUzMyMNc9sjTZon/YooF/wUx+dD8qHcg8iyJgZ8286A0XGplPcW+6x3Wv0yeRFGXYOveJe0gZlyBsbRh2TN06QsrvuusMN+BhI0i680NEV09Pg+SkD7J7TJrqJPkDnt4DOo3PP6NKR6RJlQUCPgn2iz5Rnr9Alp6eflj/nzpUH7r/fLUehN7RJW/SJfnLdXB/XnJK6oWuEn37TT9rlfOghOgdwPmiUbSnYsNdbqidlcN5HH31UBqlDrF+7tgsFdT/hBLGbg/KQ//nnn6VR48YyWdfCTzn1VLfORNdQShT65ZdfltoZGcLo7SYNsV9z9VUUFwmEoP7D7nfl5Pz333uvnH766ZK7LlcW6egxb80a+UuNJLMXZZFPP/1UemmIaYw6+oxq1SDJh8OGachpmGAYmYVh5GrVqesU9Nxzz5W///5bdtppJ2EEirG77PLLJScnx10Pg4WeGmqz63UN+n9bXALTp0+X/6geXXbZZe7+oQOXXnyxC0ljQNCV9997T3qrLpjBfPfdd+Vj1Q/0AONz1FFHyU86I4L3qSeflCfV6FWvXl2YSc/44w9Bt+bOmyemWxg9dGuOznpw/P1eeUWO6dZN0HEEguE9rGtXGaWDANoEH33EEU7PaqljXagh9zU6U5ql4fvFqrvoG/UMMJYXXXSRvP3229JUZ9pcE0b6tUEDHcucaBid8y1dtkyyta27br9drrvuOqev6Da6TL+m6ho6Dp0ZOn1FBtdcf73cqoOJXXbZRRo0aOD6Tf/R8Xr167s20H1+A+6E/p+TAPd/jdqDFToxwZnn6QyUe929e/dC9xp9gk6l3377Ta649FJ5+KGHyDrgvmFLsIXoBzYGed9++20umvKn6hXn4L6jI1RigHVar14xPSXkf/zxx8f2dNCfbqqDzz77rNDmVNXbM5Sf3wDLigtVf9HjhQsXygIF2gwCenGhRgKe0frYb/rEMhODvNy8PJmvfQKje4t1MLlCl3SefuopOe/ss2WeOvoctb9rFPr16yffaSQAna4Wtbuch99M3wsvlK233lpatGgpOO7zzj9fHlS5wAfcqzad5S0GnNTZElClHPoOO+wgw9UpvtS/v6CMKPeECROEG8ANO+7YY2XUqC/kySeeUof6uZx04onykN4wbt7TOsLDqBAqfOKFF6SfrlOiEG+p0cKo1qhRI+H9Y4T52qBBstdee8kL/foJ5x/+0UfSoUMHQVmvvfY66bTvvnLOOecII0QaYsDQqkULt44IP6HHHP0BUoaygenPs88+IxepA2BwMGDgIGfg+DEOeu01oc+DB7/lrofwJfzQqOuh/EggUw3HaTq4G6Q6Mkr1r3HTpm5zpekqOjFDHdu8eXMLdZr9FrerI9xtt900nDjO6dUw1W/aW7dunWzfuo08/9xzsrM6vgvVGBGqnzlzpjCwveW//3Uhbc75oa7J/4OBUx13v4W773a6OkbXyNG9b3WwcJg6dH4jdOC+++6TVttuKxjPeCH8n3RQ/IMaxTvvuEOeffY5d56ntG36hAO+X2dJGN3nn38+GlJfKyuys+WYY46Roe++5yIJjRo10t9GDqdzwOAVQ9znnLPlPV3/HaD6faZGGCikPcrRcX676Dx6zm+A3wI8HkT+97/75WgNt+/dsaMbnLVTvbn26qvdvf7551+c/vzww0+CPt2ig0wGjAyilupS4COPPCLv6cCSGSryRp6ffPKJPP9yP2Eg9dijj+q9flZ+++1Xp3MHdO4sx2p0hjoMAq/RwRrn/l51yenUt98KNhP7SlsPPfywoIM/q+5Q/uWXX8o56jBtEnTrnXfK1i1bCg6aEL7ZQOoCq7JXyhAd6DJoeObpZ1yfnlOdq1u3rrOJN95wg9NZfi+mN2s0Ytv9+OPl/fc/cH3OysqiKamenu6w/WMWzgTsxZdecssUDDBf7tdP6OvQd95RGz1A+B298frrMnzkSBmhgOysflniKuXQjz76aKmjNxgBt2ndWrjZK9WQLdKZ7W/jx6szHyVHHnmEHHrowdKt21F6o9+XcT/+KNN0FjVu3DhhltO7d2854tBD5XgdTWLg2GT0+eefS82QEnAOA9apzjzrLGFD2y477uh2G1PviiuuiPXHeA3j0A/o1Em2atrMSIVwZq1a8ssvv7jNTgxMLtfZuCk5YUrCS/xY7HqYweMU6MNa/zW4QrLckpk8nT3gwLsedpjrBsaiqTp0Bnimq811VlBHZ6L/LF/uoi8wZugAEiNG+LSHDjypB73lNq3kRF0nZ4ZCPgzoDDRmWGCAmW7nLl1kjEaD/pg9W36fOtUZYzt/RvV0Ofvss2Wq0vktMPtH56gbD9rvuad02n9/IcLV+aADnRGGdtppZ8TY165e7dIYPpYIcPAd1dGYDlNYQyNhYAP0+eVXX5XD1SnxW4bOUhYzqtk66+e3yW8Xnb9LHQC/gZ/09wufB5GUaBiZ+yf6x7LIX2r7+vTpI6Y/2CruNfJcvmypcomgjzuq3SLD5IbZNLpw3nnnSZcunaWrRnMef+IJYVMZa+Z5eethjQE6Q+YMnbCAAQZ2nJe2iBoSEcUZN9OIDuXAOapz6MA4HQSQT6ZzmbVqy2n6O2CW/K+OHYToTMtttpErrvg3VWPAIMIyzMg77LefpKWluqin0depoydNpGDw4MFy1ZVXOn0+oXt3yA5+1YngYo0UEFlD3w488EBhCQoZfPXVVxLUY1ehjP6lltF5ysVp0kNO125uts4OVunsl5HpfnqDDznkENlnn32kl4Z8Hn7wQcnKypJFevNa6ow5WH7AAQfIAw88oIOAI2V1VAkSXWjfvhfLuzrCPfSgg4QZBsaOED4KbT+mcN00NWiJFAOlS1Ojfp2OsOnXrTrjsvpcD2Ud1UDSX/pJNIBQ5bW6bpnofFbf47KXQG1dBgqeNUPvLc7OaBizNJ3JWx6cq4MB6DVVT8gD6EvdOnVIxoXVGnJlIBv+LXA+KhCGBQfboE1oQcDQBvPBNMaatU4iAczw7tPfyIH6W7nllpscm/3uyATbDtLpH9cGjwERNp4kefuNN9wME3o1SZVly5ZJKzXe6Lr9drvpbP92jRCQh8+DSFDW6FZOdFAVlDty4v6BcXjVVefQF/IAOke4mnsRlDdyJuqDnckLOXTaoW54E6W1y0CVcsuTBjJq1pQaarNj/QzoOeVBwKYROSXySvToWQ2nH6p2vFevU91O/vBvx+qm69IU6aBsqqdHZugr9bdCWzfqUikD5wEaQYMXyF65UhiIY1uRg2FkgO7BsyWgSjn0sIBN0VDg+moEO+mM+LbbbhOA2TcjUNakKd9anXmDhg1dmZXfeeddwuyG2b61FT4HeWbEgwe/4YwO4aQpui716WefCVGBRI/iMEOnLj88cBgIX7bbeWe5TpUNwzVUw02sU8HXvHlzIex6voasrK/ggw8+WNq2bRsbjcProfxJACfIml7QyMRzoESFmjRpIuwotqtA18ZrtMnyYHSTNklv26qVMLOwWRM0YPLkyUJbjbU9nPmPoZktA0/6QCgc/mQArwuZ6gyLMPiyRYvk6muukYcfe0xYf6VuuhprcCJg1h4u66UD7FtuvU0Ik7LeTlvp6dVkG3Xm/EbRcYDf7tVXXSX/6tRJ+C2E26mq+aAtQbe21WWTGuq8vtXwt8kEHu4ddGbL6OGawGSlXv0GTqbI+wadHITlTR3aMvtFmgkRa+pEUsgbjFYbWL9+fSH0X0ftL+cNDgZ+1Jk5umrRAasXD6MLb2nIm3V5lgBmacTmBV0aZYl03LjvxKIS8eoGafxWLE+U6186KeIaz9YI62233uqWwig3vWKCRDk6d/PNtwg2Fn8Aj0FZ4irj0FHKeEYChUUJWb++VtdZuDEYJHY/HqZh0Ed0bWethqiv+Pe/hZ3o7OhkzRzo2fMkt35NKN5GucycwzeQ0WO/fv2E0Cib7+bOny9TpkxxbDurUyaBweXRNcJg5A1YJ7W0/Uj40dm15OXkCOFHwqysUxG+Qql33X13AXMdXA/rsGxsKs1n8a2fHhdfAusD7x3gvlITQwI2sBmKzZ6ho7cZuuxy8f/9nwzs39+tO7PUwiyYtU30yXQH3bQ2u6hOEw5H39ENdvayy3eULhudccYZwm/h7LPPdhvr+C3QJmuI1+saKCHRlhrS5/wYaJ6FZwMc+SAs16UB1lrZIET9aTNm6Nrqb9JOdZ2BM7M+drl/rWv0/LaCdS3NDN3SYPZ/gHFErKdieNmUCu2SSy6RkZ9+KuyM5nr4bZ6u18I1shkKHg8RCdg+HHIsqZyoYWoiKNxj7tXDDz3oBoWfeaUAABAASURBVF7Q4WHiEIyUIH8GVsj74osuck8pmLzRDzYzpusgi7oAOo1OYZ/uvvtuwQ5ynltuuUUGvf22dO/eHTbBYX72xRdy7bXXuDaZnLDRjrV49oI4Jv3HQBPnrclCBzqOPhD1pD/YZNa4GYSykQ3mGjp4YdBgOrsmMFChHJtKO2bDsbf2u2HiRFTiggsugFV69uwpPGbM3iX2aXBNfS/qK110OTY8WHYVyuhflXDo1dLShJux1VZbFRJrmzZthJEhREZa/77sMrfRh1EWu3T33HNPYQNQuioom9LYZPG7OmKUEGAXJw6fWToGZrvttpN4MxgcOj8YnDdr2YRn2DXK7uYTTjiB08uRRx4pbCQ655xz3E5RRs+NGzWKrXvBtI3ORBgZ8qPiWggHVddro+x/bFTScnaFMnrmfO3atROuY/9OndyGlUt1zZ7nkeH3UD4kUK9ePeFei/5xXxW5GefWGmUhDTTUyBAh5Qyd1WIg4bfy8849X1hKIdR4kIa1WSPHwW2j9dE76qM3ppeZatTQjf11aQndOFTXzsd+840MHDjQDQzhR0cIHT7z7LNCm+zkZYbNb4Q+bt2qlTNcN954oxBap04QOv6rk9x1113CY0vUZ8f8ag3vPvHkk+592y1atpSjjj5aGCS8+NILwnIDv0+uj3a4RjC0evXrk5TtW7eO/bZa6fnZcEe/ceAMaPltcj6uh98mRptNq+3bt3f1/b9IyB3dQf4mj9tuu0Owe0/oGjj36lm95+Shw4PusRQZHGBhs57RezleI43Im4kC8mYTIjaVWTbnwH6hL7SDfcIJ3nLrrcJ5XnvtNeHJhn9feRXF7tlvljd5rI42mZywie65555zSwXNmm3tnD5PcNyokQHO4SpG/9WtW0/4DTDw4/4frNFIXqR0P3axVStp1SpLjjjiCDdYufnmm53d33GHHaROYKkLXxD8rbRWnUNeon/8btgMSPsMNjqpTX3ppZeE5QcGMug4+vii9rdLl4O1Rlkdhc9TJRw6GybYpcmjM3b5KAjG6DAdUUHDCTIj+XL0aOFNXGxseO21111InXKA3ZFsgKMc+PjDDwXlpqxJk62EHwU75cmHAaf/+ltvidUnFMQsxvhQ7K/HjhWMEDR2dwY3ukG7RsOWAGmuhWuqnlGTrNvJyQYONgah7Bgydvtyvk9HjXIv8rhNlxOY1bkK/l+5kAD6xyAM/bEOsbEHZ2v5PXfbzRkrjBIGEt2wcgabbABiVs59Hjr0PWEnL7NYq4+eoxeWx+gOGDjI6SJ10MWTTyl44Qw6QpvMwCnnN8Fvg98IbWDcBr36qnyjAwFmKNCCQB9ZriLcTv1PPv5YhuhsDCMIH+0MHDBAvhs3Ttho1LBhY3d9+2l4k3LqIw8MdIe994bk9qoEr+Gkk09xj3AywIWB3ybXYefjCQEcPWUeCiSATbkpsN8G/WHp0PQHzL2GTi30kycGeFSLvMHZZ58tH3/yiSDv0V995Z4e6nxQZ1eckpoqd9x+u3AuR9B/3PNHHnlU0CVXZ/Rowf5xr7XYHRf17SumM59q2+ygZ3ZPIf0hxP+92shrNJLKOaAbMHhl0vWVtottBrB9ptfUZ6f6N9pX+sUAgOviET1ro1atOm6AanrD7wywcvSXN8mxYRUafOgZ+s350D9+D8Frgq8soUo4dG42o3qUyoTLDYZG2MloYGh77NleMHrUgxYE+HGWQIaGPK0MXupSbrQwxhDi2GnfFNV4UALKWE+ib5QDVg4mD5DmWjgf5yUPUBbsN2W0SV8pg8dD+ZIA+hK+j+SD9ws9476iF/SeMoC0AXW4z/CYblhZSw2TQ7M82PSNOuEyygHOga7SNvkg0CcMXLwy46M+7aPTXKfRweQp4ykO+sz10SZlALoLDT7ynCfYT/oPjXNQDlBOm/HOR7kHcUsqyC0oC2QNDdmBg2XIn/sAT5BOup6up6Mfbdvt5p7WMR7uDfcFgM+ActqnTrjMeKDTj3jnRD84FzaNc1idIIaH+gB9j1dmbYODPOgh/UOPqEdfANIG1IHH8tSnT5zP6lnZlsAl7dC3xDWU+DkTKUtJnai02y+pfvp2KocENkffNqducaRX2u0Xpw+eZ9MkwL0z2JgWqLMx/EHezakbbKck0+WpT96hl+Sd9W15CXgJeAl4CXgJbCEJVCyHvoWE5E/rJeAl4CXgJeAlUN4l4B16eb9Dvn9eAl4CXgJeAl4CxZCAd+gFQvIpLwEvAS8BLwEvgQorAe/QK+yt8x33EvAS8BLwEvASKJCAd+gFsijdlG/dS8BLwEvAS8BLoBQl4B16KQq3MjXN27uefug7OeHQQRvAJWd9IJ99OKPQF4uys/Pkv//+RB65e0xMDBPHL5LTjx0se2U9Kddc9KHAM2zIFDlwt+cdbfCACTHeLZngxTz0ddnSgs93hvvz18JV7vriyQMa1znrj2Xhapudp00gWUPcq2+/miPnnfyOky3yPbLTK+5ehK+J6+Bak7WHPO7+zxcCkKYObXPPk9XblDJ0jL4iwyBwPvSD829Mu8iC6wte99q1uQIN/duYtjyvl0B5l4B36OX9DhWvf6XOxbOW34+dJ6M+nyGZmdVjIPo35otZcuLRg+S6iz90r61VUuyokVHNpTGsd6lT+PLzmdK+49bScf+WsnjRCrnozPcke8Va2a/zttIqq57j3dL/vvh4phy53yvy55x/EnZl1aq18sUnf8gP386LySIsl4SVN7EAJ33CwQNl+pQlSVt4e+AEOfKgV+T3SYtlx10aS6cDtpGatarLQ3d/Lace9YbgkGkAh3bBaUPl5ad/JJsQcKKZWr969VT3KmKu/ePh02TOrOWFBnEJG9iIgina52+/m+NqNGxUMyZbruWCM4fK9ZeMdGXF/TfinSnSo+ugQvfy9utGyX90sLlu7briNuP5vAQqhARSK0QvfSfLhQRyVufKdq0aSP+hJ8rA93s6eOfT02Tc9Ivk/y7vJC88+7289vKvrq+1aqXJnQ8fJhdd2dHlc9atlUm/LpLjTtxFXnzzBOl5RjvnyHEUdzx0mDzxyjHyL3U8jnkL//t78api9+CU3rs5OZg8gnjb7eoXu53iMGavXCerVq+TWrWrJ2THSd901SfS5eDt5f3RvZ2s73/6SOE+PfjMUYKzHPjiz64+Dm119jqxQZcjxvnHG7SuuHE/uebWA4WBHQMwif6RjyZLBOWuXe907LlB3V3fTZ5f/tpHTu+9p7zx6q/CwKa4J1v81ypZpdcY5F+Tkytcd/X0xHIM8vu0l0BFkYB36BXlTm3JfkbPnVEzMtvOycmPUiIoLS1V/nvnvs6JvPDE90J4My9vvQvxEiYlRHzL5Z/JYnWUzOYJxd9/65fCjB1j+/j/xgp56tEiBpuQPGHreKFW2gReefYnF8KnPZt1DtMQPksA1AWTp00DQroA56AcPurPiobHCcU+dt83smLVGtc/zmN14+HVq3KFa41XFqQRnr6iz3DXX85Lv4haBHk4N32hT1w312cyoezx+8c653TvLV8K9YN1LY2TXvjXSmnRsq7Ub5BhZIe7dmsjdz9wuOywcyMXSXng9q9k4oRFLtLAeTkX52GZhP7SB/oKjb4gNxqqVSddGIiRNqAcXuRq10U6eB/hIdxtdeLhaumpbtASr6xHr7aOPPm3xQ7zj37aOZAb10F/KQOjj6QfvPNr4V4Cn46YLjP/WKoRpRHCfef+0S/KuGba4V7Rf+oCyIbrR+7I5wRdeuJ6qG+8lFOXNuCjngF9oW9WDi9tWrnHXgIlIQHv0EtCilWgDYyeXWaa5FgyhnmHcudDs2TCbwtl+bIc5+Tefu03IXzNjO7XnxY6J8kMk1D15ImLZfbMZY6GcSW/TmdnGNWzTnxbMLo0Pm/2P3JV3xGFQq1ffzHb0e65+Qv5W2dgy5bkSHV1BBhJQvi//DifqgImjwF2BP331eez5MarR8pFZ7wn8+b+4+o/+ehYubDXuy58vOKfNc7IK6uLKHB+0slgXc5qV7xW12aBoKwowPCffdLb8uF7v5MVBjVnnDRYnn34O5fnH87jjOMGS//nf5JVq9a5cPkVFw2T/17xiaxau1YW/LlSZk1f6uQ1SZ3w7JnLqbYB4MSP7raTvPf2JLdPAUdCn2CkjIhJtx47kZU/pkXawyn9Nn6Ro3Ge2/77mVytMufap03529FHfjBNRg6b5gYCEBiIgQHkS19Jb79DIzeLx6GF7yORgyv7fOh0A954wAw9s2b8mfMU1RkGEo2bZLqq3G/kiq4w2EQXuJfIMTs7LyIzHagxOPvpuz+F65mp1/zH7KVuYMR9QDdpjDA8IX14yI/++A/peeTrsYHTOtXNd9+c5JaI0Gt4VunMf/qUJfLKiz86fRr08i+Q5WtdguL+MtiAgHwvPP1deWvQBLKuH+jgVReOSCoLx+z/eQlshAS8Q98IYVVl1jSdhRNyRwZ5UnjmBw1o0aouSBbMWyG5sl5q1Up3+Z12bSxDPz3JhVKPPG5HIXxK2P0BDQU3bVJb7njwMBdeXaXr0vf89ws576K95ceZ/+dC2cO/OUv6vXWivD9kcsy41q6d7hzbg08fJR+OPcuF66f89pc8et8YIaw86ufzXF3OQ9vPPPqd2wRlM0c6RZj/HV0uoP41NxzoQtGTdUlgn31buDbgGfBeTyHUTDoecH0DX/1Z9tu1n9vU12nHZwXo0Prp2KAAh8rAo+vRbWTc1HNdv1iiOP/CfdzAgvI8jWYw62bmS5/f0X6BH3m6m9D+sDd/l0OO3F7oc53MGvLUK8cJjjlen6A98kI34XzIbP89n5M2DR92GxkZWCxdutQNXNLTqwl87XZtKiwbcE4cPvWBk05v52SLfNrs3BCSsEcAPSCTqWvqYJzqQ7o2jwxZNmnSNNOt0d97y2g56bR2sftIO4M/PFU++XCaDHltIlXjgs3Qf/1pgbtnDHQABg04wV3abSVHHr+DG1iwp+PAg7Nk7O8XOv3hHEQgFi9eJaM+mhaRmeoWMrN7ybIBofu22s5nP50nbXffyvUHZ/v28NPcNRPm/1H1r+/lHeWmKz9xEac6tSNRqcaNM4W23hp5aqF7wL6Qj8eeJq+qzgz5+DRp2qS2jHg3MoD77uu5bqDLfaNt6ye/p7k6YI0rCE/0EtgECXiHvglCq6pVmAUlu3ZmLFZeTQpUCydQPaOmFW2AcRQQMXwY43Xr1guOAmAWO/7HBW5GNeLdqc4ZwYuRPvSIliQdfDpihuNhhvXco9/H6i/9e7UQgmaGaeu927VqIF2Pae3q8a/Tgds4A8zslL5CKw5kZ691g5RDj2otR5+wk4AB0pmZ6a4JZr6c/4LL9nFfpIKYkpoq51y0lzvnuG/mCUadzYannbOHBNfdjz95F/lXx210Zj+ValIzs7rDydbQYcCpMmDCsTAoYN8Ca8bMog9tP0gYuMBXXaMaYIM8HVhYeo+9m1kyIX70njEpICkMAAALD0lEQVRuUMLg4epb9nd8tPHd13NiAxruocGP3813PB++F7kel4nzD3mxyXJ/HYz01FkyG/z6P/eT9DhpV7nr4cOEe5SuAxKuEQe5Kjs35vxnTF3iWlylUQ6XSPIvIz3PlaJ3mRoVQM+srwx+Fi3KFmbzDBYZxGbr/WbzJveIPrjK0X+nn7uHEKVCx7Zt3UgYeKzW5RiKW2XVA8kt13zq9HLYkCnCgIm+05Yr9P+8BEpAAgVWtwQa801Ubgkwo+AKU6pHDCHpIJhDb9aiTpDs0hh6l4jzz4zv4kWr3Mz7rYET5PnHxrkZNxhjzsxo65Z1BINJE8wQMbKkgaVLVru68FKH2Tq4vzoCZqENGtWMDQa2alabKjFYXQzjH2MOJXDebDpjAyAYII1ThRWZMFurU7cGWQdcQ5OmtaXJVrVk0fyVbnMgBWb4SQPMmNvs1EiW6KBkrYbzoRkkkifhXWa0rM8y+zzrwvYugkGEZMBbPYUlD/Yu0F5a2lprzmGcFLKgv423yiwUDrbBnJ2X66ItZEs4e9rkiCOljcW6DEKYm1kv9wCw+8E1N9R74U6Y4B+DNfr64eizhFk9+J3PT5enBxzrZtRWjegG69XHHvSq28mO82fTHOc2nmQY/UEOyBfHbbpDf4mqEHbn+mgjTSLLTDUzI/tIoCUC4129ep2TIZs9n+vf3bETZTjjpMFyxL9edvtGsnVpwBX4f14CJSAB79BLQIhVpQkz6vnr0ja45JzsbLfGigFs2CjVhdw3YEpAsBk6xRjzpwccJ2N+O1u+HH+BEBb9YnxvwaBffPW/nIGELww1MqoJdeGDf+zkvvLRt+e4+kM+OV2Y7eJIrR6Ox9I1ozNfy4NpC1wUsH5vTi7MC52Bxypda2VtPlj+18KII68dcPQ4wiAPMmWdH/kE+wtPOA8NYLbJ2vXHw6aRjQGzR9bOWfL44bt5snzpWklNqxUrDyboLzvqg+ewwVyQRkj6vdEnCUsFV14wwoXBaYdrBhNiJhzOffhm8lmxe/Gfu7tIsj8Gbx3338Y99YAzBJjJMiu3egxcOCeDiRN77Spu+WXMWW75hgGJ8SXDDEytTSIh6A56R3/Rn09/Ok3QnX10GSZn7YY6z/219oNRk/XVI5EUKwPzVMfwr0+Rr3++QIiaMKi8+/Yv5K0B4yn24CVQIhJILZFWfCNVQgJm1KtXj6wn2kVn6yzj8ft/dM+on3/JPi60vDZ7vRUXwtWrJVa5zodlCc7gtVd+ldTqNYRZLrPUJX+vlxsv+1i+/nyWC7dag8F+7Kthc+jv6Ppsnbp1hXrUn6Jr6zxrDabcIGiMmZUa3XAxZ3nGHhfj/GzW/f7bUwrxEHZlVrhXx+bCGjUDoaFvTnLrtcb46UdznUwPOHhbd93WT5yt8YRxx/1buqWHF5/4IRb2Nh5mtMw69+7YQuo1SBebSVo52AY3QQcF3SAoN6IeDRo0kOtvO0jYLf/UA985tl11XZpljYEvRTaJcR/gW74sR644f5gw2AjuZ3CVov/YFBdNJkUTflro9j3c8dBhbp8DgxUiEuPGzHNLLFYZfUp0L01HDzo0y7VFm+mZtWJ698mweYLuLFkcmZ1bm4a5v5YO3hMb8NbUMD7lhPF5WQ56zH4SoibPvXkwRW6DnEv4f14CJSCBxNa1BBr3TVQuCTBDxwmxU5lHhQAeVTpw12eE2QbPovc8Z1d30YRzWXN0meg/QrS2rhglOedjIXcM8pnnt3e7ho87aKALSfKoD2864xn27do0cNXW5OS6euvWpbg8/zDorBWzQ5tHg+6/9Uu3y5v1V9aP2X0NH+cK9wt6EJgRk+dRJ9upTD4MtkM6TA/mmV1eenUnYfc1/WJzFxh5sTGuvTp0Zok4RdbRj9XwMX2/os9wt6OamSPrrbTZWMPgOKcXn/zBPYsdzykyk2VjIA72iE79nAw4J/eqR9dBLuR+2XWdhHMy62ysYX92icND+DnZoAHZ0Y8wHHXCTnJmn/aC7An3cx/7XNZBhrz1mxwXuI/0h/vIICcYLQm3xz6KMC2cb9e+qdu/wKY13mCHzNCT996e5FhZvnGJ6L+nHvzOvc2QbP2GGc6BP/XAt27Qc/zJuwjP7RMK73PKO4IsCOWz653lgYaNM4Rn1rnf63ILD1RNXrQLcE9soETIHRoDVe4HLwW67+Yvhf5ecPLnbg/FoUdtD4sHL4ESkYB36CUixqrRyG57NnWGb9qUv+VXnSEBhIQPPaq1sEOYZ9Ezqqc7YRDO7XzYdrLrHlu5PLOZw45sE8tDrKPhZjZUYeDJAzfe1VlYb2zUJFNe6zfePSPNLmx2FuMo4Gmn/aBecIYO/YGnDnbhTB5foi79Y/d1v6FHCLNEePbTmTz9oj/kgcbqKPfvvK0027q2C+nvrzNi6vH40XtvT4ZlA2DT20FdC65vA4YA4dJr9nL9wiGy4x7Mbuw7HjjQOVZYGZAgQ97sRt9/GDtP+l7eUZ597fhY3/do39C9wAen+NbA3yR3XS5VNwDCu4M/PFWO7bGzjP1qjrA2DGbXORvlGGRQiSjGpdd0EsK/8Myft1IYNCFbZAGPwZ57NxNkh9y4dni22baekxfO+eqbD3Cb1kZ/MtPR2IXPOjhvqON6eFSR/nAf7fzWdhCjLwzMqqWvEZxjsCyYZuDC0swuu20lbw2cINwn7uuHGnY/67y9Yqw8e89Ak0fURkR3nZ92zu5Oj6nHrBw58CKbG2/uLGyqRBZg7tGDzx7loiPr87Ldpsf2+zQv1C/kdXS3nZzucFJkQci9Q6cWwu8F2s7aR57UYCc85wRatKorr7x9oltWgMeDl0BJSMA79JKQYhVp4+KrO8rLb/UQNli9PuIUh98YcbKwEazLEdsL67QYNMRRMzPNvWzmrEv2JOuMIg73vEsKjC2G7smXD5f2Okt1TNF/OKQXXz/arYG/P7q3a9+cOUa+1zm7CfWYZUarOES4tPcF7YX+sQ5KH6+/s7M0a9bMlfPv/278l+sXjok80EHXa2mPcCh0DDy7tlnDv/V/h8CyATTSQcC9j3QWro86GzAECMiFfr323vFuX8DAEScJDg96gM09ZvX4gG6x62Zwg+MyHvhve+AQV/6fu7tIteqJN2hxTfc+cbgM13VbZIEcb9fwtMnR2uS+mbyat6gtyOCRFw51ywDGg5wZlCA7rpUZKzwHHNLK3Vf4kBl973N5B7IOGKSgH3Z++sM9d4UJ/qEfdz5ymNSr3yC2ATIBq3OGz799vJMH14lsuD7u2TkX7uqq0a+b7+vieG6+bz9Hg4d7Qb/sSQmu6apbDpTBI09wvMiEe0R9KtWqU1dufaCrEIEyHYfOcsmT/Y8tJK8MHdReeeM+csHV+zj5wM9jh2zqY08I8JwO1JINbGjbg5fAxkrAO/SNlVgV5sewY+BwLIahIRKMFtiAPHyZ6ZEZO3Tyxk/eeII06AC8zKo5D3kD6sBPudEMUwZQZnXJWzmY/lBO2gAeaDgro3EOa8NoQWx1aC9IT5Q2fgYCyepQluy89NHKaTPZ+eBlP0ECfleVNrh2eLhmq0PaMUT/wUPfyCbioZz7RTl8AO3QttE5H/READ+8RfFZfc5J+1ynnZf69Nd4aNN4jEY5NDA06nJO2gnSKQMoq1UrTTgfeQPa5nxgo8FLu4l44ed8xu+xl0BJScA79JKSpG/HS6AYEsDYF4PNs3gJeAl4CWy0BLxD32iR+QpeAl4CRUrAM3gJeAmUuQTMofNchgdxb4/wcvBy8DrgdcDrgNeBiqYD8v8AAAD///owXcQAAAAGSURBVAMA3wvXgZDGzS4AAAAASUVORK5CYII="
    }
   },
   "cell_type": "markdown",
   "id": "2f00986c",
   "metadata": {},
   "source": [
    "![image.png](attachment:image.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9c3ed8b",
   "metadata": {},
   "source": [
    "A. Heel Strike (Pendaratan Tumit)\n",
    "Artinya: Pelari mendarat dengan tumit terlebih dahulu menyentuh tanah.\n",
    "Populasi: Sangat umum, mencakup sekitar 75-90% pelari rekreasional/pemula.\n",
    "Kebutuhan Sepatu: Membutuhkan bantalan (cushioning) yang tebal di bagian tumit untuk meredam benturan (impact). Biasanya memiliki High Drop (8mm - 12mm).\n",
    "\n",
    "B. Mid/Forefoot Strike (Pendaratan Tengah/Depan)\n",
    "Artinya: Pelari mendarat dengan bagian tengah atau depan kaki (jinjit).\n",
    "Populasi: Lebih umum pada pelari cepat, atlet elite, atau pelari minimalis.\n",
    "Kebutuhan Sepatu: Tidak butuh tumit tebal (karena tumit jarang menyentuh tanah keras). Biasanya butuh sepatu yang responsif dengan Low Drop (0mm - 6mm) agar pendaratan lebih natural.\n",
    "\n",
    "C. Heel/Mid/Forefoot (Versatile / All-Rounder)\n",
    "Artinya: Sepatu ini didesain fleksibel untuk mengakomodasi semua gaya lari.\n",
    "Teknologi: Biasanya menggunakan desain Rocker (lengkungan sol seperti kursi goyang) yang membuat transisi dari tumit ke ujung kaki menjadi mulus (smooth transition).\n",
    "Cocok untuk: Pelari yang gaya larinya berubah-ubah tergantung kelelahan (misal: awal lari midfoot, pas capek jadi heel strike)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cabe5a60",
   "metadata": {},
   "source": [
    "### Cleaning code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "bdbee9f5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "UNMAPPED strike values:\n",
      " Series([], Name: count, dtype: int64)\n"
     ]
    }
   ],
   "source": [
    "#  ['-' 'Heel' 'Heel Mid/Forefoot' 'Heelmid/Forefoot' 'Mid/Forefoot']\n",
    "\n",
    "\n",
    "strike_map = {\n",
    "    \"Mid/Forefoot\": \"Mid|Forefoot\",\n",
    "    \"Heelmid/Forefoot\": \"Heel|Mid|Forefoot\",\n",
    "    \"Heel Mid/Forefoot\": \"Heel|Mid|Forefoot\",\n",
    "    \"-\": \"-\",\n",
    "    \"Heel\": \"Heel\",\n",
    "}\n",
    "\n",
    "df[\"Strike_norm\"] = df[\"Strike pattern\"].map(strike_map)\n",
    "\n",
    "unmapped = df[df[\"Strike_norm\"].isna()][\"Strike pattern\"].value_counts()\n",
    "print(\"UNMAPPED strike values:\\n\", unmapped)\n",
    "assert df[\"Strike_norm\"].notna().all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "6ce0b921",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Strike - norm : (4) uniques\n",
      " <StringArray>\n",
      "['Heel|Mid|Forefoot', 'Mid|Forefoot', 'Heel', '-']\n",
      "Length: 4, dtype: str\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Strike_norm\n",
       "Heel|Mid|Forefoot    540\n",
       "Mid|Forefoot         339\n",
       "Heel                 290\n",
       "-                      1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strike_norm_unique = df[\"Strike_norm\"].dropna().unique()\n",
    "print(f\"Strike - norm : ({len(strike_norm_unique)}) uniques\\n\", strike_norm_unique)\n",
    "\n",
    "\n",
    "df[\"Strike_norm\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "e31dde3b",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Terrain</th>\n",
       "      <th>Pace_norm</th>\n",
       "      <th>Pace_lists</th>\n",
       "      <th>pace_competition</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "      <th>Strike_norm</th>\n",
       "      <th>Strike_lists</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running|Tempo</td>\n",
       "      <td>[Daily Running, Tempo]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Mid|Forefoot</td>\n",
       "      <td>[Mid, Forefoot]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel</td>\n",
       "      <td>[Heel]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>[Daily Running]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 42 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... Terrain            Pace_norm              Pace_lists  \\\n",
       "0  Heelmid/Forefoot  ...     NaN  Daily Running|Tempo  [Daily Running, Tempo]   \n",
       "1      Mid/Forefoot  ...     NaN        Daily Running         [Daily Running]   \n",
       "2  Heelmid/Forefoot  ...     NaN        Daily Running         [Daily Running]   \n",
       "3              Heel  ...     NaN        Daily Running         [Daily Running]   \n",
       "4  Heelmid/Forefoot  ...     NaN        Daily Running         [Daily Running]   \n",
       "\n",
       "  pace_competition pace_daily_running pace_tempo arch_neutral arch_stability  \\\n",
       "0                0                  1          1            1              0   \n",
       "1                0                  1          0            1              0   \n",
       "2                0                  1          0            1              0   \n",
       "3                0                  1          0            1              0   \n",
       "4                0                  1          0            1              0   \n",
       "\n",
       "         Strike_norm           Strike_lists  \n",
       "0  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  \n",
       "1       Mid|Forefoot        [Mid, Forefoot]  \n",
       "2  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  \n",
       "3               Heel                 [Heel]  \n",
       "4  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  \n",
       "\n",
       "[5 rows x 42 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Strike_lists\"] = df[\"Strike_norm\"].str.split(\"|\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "752457fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n# jujur ini vibe ah coding\\npace_exploded = df[\"Pace_lists\"].explode()\\n\\npace_ohe = (\\n    pd.crosstab(pace_exploded.index, pace_exploded)\\n    .reindex(df.index, fill_value=0)   # jaga urutan index sama df\\n)\\n\\n# rename kolom biar konsisten untuk ML pipeline\\npace_ohe = pace_ohe.rename(columns={\\n    \"Competition\": \"pace_competition\",\\n    \"Daily Running\": \"pace_daily_running\",\\n    \"Tempo\": \"pace_tempo\"\\n})\\n\\n# gabung ke df\\ndf = pd.concat([df, pace_ohe], axis=1)\\n# make sure value-nya bener 0/1\\nfor c in [\"pace_competition\", \"pace_daily_running\", \"pace_tempo\"]:\\n    assert set(df[c].unique()).issubset({0, 1})\\nprint(df[df[\"Pace\"]==\"Competitiontempo\"][[\"Pace\",\"Pace_norm\",\"pace_competition\",\"pace_tempo\",\"pace_daily_running\"]].head())\\nprint(df[df[\"Pace\"]==\"Daily Runningtempo\"][[\"Pace\",\"Pace_norm\",\"pace_daily_running\",\"pace_tempo\",\"pace_competition\"]].head())\\nprint(\"Rows:\", len(df))\\nprint(\"competition sum:\", int(df[\"pace_competition\"].sum()))\\nprint(\"daily sum:\", int(df[\"pace_daily_running\"].sum()))\\nprint(\"tempo sum:\", int(df[\"pace_tempo\"].sum()))\\n'"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''\n",
    "# jujur ini vibe ah coding\n",
    "pace_exploded = df[\"Pace_lists\"].explode()\n",
    "\n",
    "pace_ohe = (\n",
    "    pd.crosstab(pace_exploded.index, pace_exploded)\n",
    "    .reindex(df.index, fill_value=0)   # jaga urutan index sama df\n",
    ")\n",
    "\n",
    "# rename kolom biar konsisten untuk ML pipeline\n",
    "pace_ohe = pace_ohe.rename(columns={\n",
    "    \"Competition\": \"pace_competition\",\n",
    "    \"Daily Running\": \"pace_daily_running\",\n",
    "    \"Tempo\": \"pace_tempo\"\n",
    "})\n",
    "\n",
    "# gabung ke df\n",
    "df = pd.concat([df, pace_ohe], axis=1)\n",
    "# make sure value-nya bener 0/1\n",
    "for c in [\"pace_competition\", \"pace_daily_running\", \"pace_tempo\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "print(df[df[\"Pace\"]==\"Competitiontempo\"][[\"Pace\",\"Pace_norm\",\"pace_competition\",\"pace_tempo\",\"pace_daily_running\"]].head())\n",
    "print(df[df[\"Pace\"]==\"Daily Runningtempo\"][[\"Pace\",\"Pace_norm\",\"pace_daily_running\",\"pace_tempo\",\"pace_competition\"]].head())\n",
    "print(\"Rows:\", len(df))\n",
    "print(\"competition sum:\", int(df[\"pace_competition\"].sum()))\n",
    "print(\"daily sum:\", int(df[\"pace_daily_running\"].sum()))\n",
    "print(\"tempo sum:\", int(df[\"pace_tempo\"].sum()))\n",
    "'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "3f553259",
   "metadata": {},
   "outputs": [],
   "source": [
    "strike_exploded = df[\"Strike_lists\"].explode()\n",
    "\n",
    "strike_ohe = (\n",
    "    pd.crosstab(strike_exploded.index, strike_exploded)\n",
    "    .reindex(df.index, fill_value=0)   # jaga urutan index sama df\n",
    ")\n",
    "\n",
    "strike_ohe = strike_ohe.rename(columns={\n",
    "    \"Heel\": \"strike_heel\",\n",
    "    \"Mid\": \"strike_mid\",\n",
    "    \"Forefoot\": \"strike_forefoot\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, strike_ohe], axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "89c7f686",
   "metadata": {},
   "outputs": [],
   "source": [
    "for c in [\"strike_heel\", \"strike_mid\", \"strike_forefoot\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "536b9e6c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "Heels sum: 830\n",
      "Mid sum: 879\n",
      "Forefoot sum: 879\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"Heels sum:\", int(df[\"strike_heel\"].sum()))\n",
    "print(\"Mid sum:\", int(df[\"strike_mid\"].sum()))\n",
    "print(\"Forefoot sum:\", int(df[\"strike_forefoot\"].sum()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "0ef394bc",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>pace_daily_running</th>\n",
       "      <th>pace_tempo</th>\n",
       "      <th>arch_neutral</th>\n",
       "      <th>arch_stability</th>\n",
       "      <th>Strike_norm</th>\n",
       "      <th>Strike_lists</th>\n",
       "      <th>-</th>\n",
       "      <th>strike_forefoot</th>\n",
       "      <th>strike_heel</th>\n",
       "      <th>strike_mid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Mid|Forefoot</td>\n",
       "      <td>[Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel</td>\n",
       "      <td>[Heel]</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Heel|Mid|Forefoot</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 46 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... pace_daily_running pace_tempo arch_neutral  \\\n",
       "0  Heelmid/Forefoot  ...                  1          1            1   \n",
       "1      Mid/Forefoot  ...                  1          0            1   \n",
       "2  Heelmid/Forefoot  ...                  1          0            1   \n",
       "3              Heel  ...                  1          0            1   \n",
       "4  Heelmid/Forefoot  ...                  1          0            1   \n",
       "\n",
       "  arch_stability        Strike_norm           Strike_lists  - strike_forefoot  \\\n",
       "0              0  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  0               1   \n",
       "1              0       Mid|Forefoot        [Mid, Forefoot]  0               1   \n",
       "2              0  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  0               1   \n",
       "3              0               Heel                 [Heel]  0               0   \n",
       "4              0  Heel|Mid|Forefoot  [Heel, Mid, Forefoot]  0               1   \n",
       "\n",
       "  strike_heel strike_mid  \n",
       "0           1          1  \n",
       "1           0          1  \n",
       "2           1          1  \n",
       "3           1          0  \n",
       "4           1          1  \n",
       "\n",
       "[5 rows x 46 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a89f428",
   "metadata": {},
   "source": [
    "# Cleaning Size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "485f039e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = df.drop(labels=\"fit_category\", axis=1)\n",
    "# df = df.drop(labels=\"fit_large\", axis=1)\n",
    "# df = df.drop(labels=\"fit_small\", axis=1)\n",
    "# df = df.drop(labels=\"fit_true\", axis=1)\n",
    "# df = df.drop(labels=\"fit_missing\", axis=1)\n",
    "\n",
    "# df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "139c3649",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Size (6 uniques): \n",
      " ['-', 'Half Size Large', 'Half Size Small', 'Slightly Large', 'Slightly Small', 'True To Size']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Size\n",
       "True To Size       797\n",
       "Slightly Small     231\n",
       "Half Size Small     59\n",
       "-                   44\n",
       "Slightly Large      31\n",
       "Half Size Large      8\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Size\"] = (\n",
    "    df[\"Size\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "size_uniques = df[\"Size\"].dropna().unique()\n",
    "# size_uniques.sort()\n",
    "size_uniques = sorted(size_uniques)\n",
    "print(f\"Size ({len(size_uniques)} uniques): \\n\",size_uniques)\n",
    "\n",
    "df[\"Size\"].value_counts().head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "fe9461ff",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Size</th>\n",
       "      <th>Size_repr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Air Zoom Pegasus 38 FlyEase</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>73</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Allday Knit</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Allday Knit</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Anthem 4</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>Diadora</td>\n",
       "      <td>Atomo Star</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>186</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudsurfer Max</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>Altra</td>\n",
       "      <td>Experience Flow 2</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>331</th>\n",
       "      <td>Saucony</td>\n",
       "      <td>Freedom 4</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>Asics</td>\n",
       "      <td>Gel Kayano Lite 2</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>474</th>\n",
       "      <td>Asics</td>\n",
       "      <td>Gel Nimbus Lite 3</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>556</th>\n",
       "      <td>Asics</td>\n",
       "      <td>GT 1000 9</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>575</th>\n",
       "      <td>Saucony</td>\n",
       "      <td>Hurricane 25</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>585</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Hyperion Elite 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>586</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Hyperion Elite 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>587</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Hyperion Elite 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>614</th>\n",
       "      <td>Under Armour</td>\n",
       "      <td>Infinite Pro</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>634</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Journey</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>635</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Journey</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>636</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Journey</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>637</th>\n",
       "      <td>Nobull</td>\n",
       "      <td>Journey</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>668</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate Stealthfit 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate Stealthfit 6</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>692</th>\n",
       "      <td>Hoka</td>\n",
       "      <td>Mach X 3</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>839</th>\n",
       "      <td>Jordan</td>\n",
       "      <td>React Havoc</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>866</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Ricochet 3</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>915</th>\n",
       "      <td>Salomon</td>\n",
       "      <td>S/Lab Phantasm 2</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>916</th>\n",
       "      <td>Salomon</td>\n",
       "      <td>S/Lab Spectur</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>954</th>\n",
       "      <td>Asics</td>\n",
       "      <td>Sonicblast</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>955</th>\n",
       "      <td>Asics</td>\n",
       "      <td>Sonicblast</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>956</th>\n",
       "      <td>Salomon</td>\n",
       "      <td>Spectur 2</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1006</th>\n",
       "      <td>Under Armour</td>\n",
       "      <td>Surge 4</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1095</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Vomero Premium</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1129</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1130</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1131</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1132</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1133</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1134</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1135</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1136</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1137</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 29</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1156</th>\n",
       "      <td>Reebok</td>\n",
       "      <td>Zig Dynamica 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1157</th>\n",
       "      <td>Reebok</td>\n",
       "      <td>Zig Dynamica 5</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Brand                         Name Size Size_repr\n",
       "71            Nike  Air Zoom Pegasus 38 FlyEase    -       '-'\n",
       "73          Nobull                  Allday Knit    -       '-'\n",
       "74          Nobull                  Allday Knit    -       '-'\n",
       "92          Brooks                     Anthem 4    -       '-'\n",
       "98         Diadora                   Atomo Star    -       '-'\n",
       "186             On              Cloudsurfer Max    -       '-'\n",
       "298          Altra            Experience Flow 2    -       '-'\n",
       "331        Saucony                    Freedom 4    -       '-'\n",
       "454          Asics            Gel Kayano Lite 2    -       '-'\n",
       "474          Asics            Gel Nimbus Lite 3    -       '-'\n",
       "556          Asics                    GT 1000 9    -       '-'\n",
       "575        Saucony                 Hurricane 25    -       '-'\n",
       "585         Brooks             Hyperion Elite 5    -       '-'\n",
       "586         Brooks             Hyperion Elite 5    -       '-'\n",
       "587         Brooks             Hyperion Elite 5    -       '-'\n",
       "614   Under Armour                 Infinite Pro    -       '-'\n",
       "634         Nobull                      Journey    -       '-'\n",
       "635         Nobull                      Journey    -       '-'\n",
       "636         Nobull                      Journey    -       '-'\n",
       "637         Nobull                      Journey    -       '-'\n",
       "668         Brooks                   Levitate 5    -       '-'\n",
       "680         Brooks        Levitate Stealthfit 5    -       '-'\n",
       "681         Brooks        Levitate Stealthfit 6    -       '-'\n",
       "692           Hoka                     Mach X 3    -       '-'\n",
       "839         Jordan                  React Havoc    -       '-'\n",
       "866         Brooks                   Ricochet 3    -       '-'\n",
       "915        Salomon             S/Lab Phantasm 2    -       '-'\n",
       "916        Salomon                S/Lab Spectur    -       '-'\n",
       "954          Asics                   Sonicblast    -       '-'\n",
       "955          Asics                   Sonicblast    -       '-'\n",
       "956        Salomon                    Spectur 2    -       '-'\n",
       "1006  Under Armour                      Surge 4    -       '-'\n",
       "1095          Nike               Vomero Premium    -       '-'\n",
       "1129        Mizuno                Wave Rider 29    -       '-'\n",
       "1130        Mizuno                Wave Rider 29    -       '-'\n",
       "1131        Mizuno                Wave Rider 29    -       '-'\n",
       "1132        Mizuno                Wave Rider 29    -       '-'\n",
       "1133        Mizuno                Wave Rider 29    -       '-'\n",
       "1134        Mizuno                Wave Rider 29    -       '-'\n",
       "1135        Mizuno                Wave Rider 29    -       '-'\n",
       "1136        Mizuno                Wave Rider 29    -       '-'\n",
       "1137        Mizuno                Wave Rider 29    -       '-'\n",
       "1156        Reebok               Zig Dynamica 5    -       '-'\n",
       "1157        Reebok               Zig Dynamica 5    -       '-'"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask = df[\"Size\"].astype(str).str.strip() == \"-\"\n",
    "df.loc[mask, [\"Brand\",\"Name\", \"Size\"]].assign(\n",
    "    Size_repr=df.loc[mask, \"Size\"].apply(repr)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "007b5d56",
   "metadata": {},
   "source": [
    "kenapaaaaaaaa............dia.........strip....doang..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "cc19d779",
   "metadata": {},
   "outputs": [],
   "source": [
    "size_map = {\n",
    "    \"Half Size Small\": \"small\",\n",
    "    \"Slightly Small\": \"small\",\n",
    "    \"True To Size\": \"true\",\n",
    "    \"Slightly Large\": \"large\",\n",
    "    \"Half Size Large\": \"large\",\n",
    "}\n",
    "\n",
    "df[\"fit_category\"] = df[\"Size\"].map(size_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "db763764",
   "metadata": {},
   "outputs": [],
   "source": [
    "fit_ohe = pd.get_dummies(df[\"fit_category\"], prefix=\"fit\").astype(int)\n",
    "\n",
    "for col in [\"fit_missing\", \"fit_true\", \"fit_small\", \"fit_large\"]:\n",
    "    if col not in fit_ohe.columns:\n",
    "        fit_ohe[col] = 0\n",
    "\n",
    "fit_ohe[\"fit_missing\"] = df[\"fit_category\"].isna().astype(int)\n",
    "\n",
    "df = pd.concat([df, fit_ohe], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "a4499637",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fit_missing     44\n",
      "fit_true       797\n",
      "fit_small      290\n",
      "fit_large       39\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(df[[\"fit_missing\",\"fit_true\",\"fit_small\",\"fit_large\"]].sum())\n",
    "assert (\n",
    "    df[[\"fit_missing\",\"fit_true\",\"fit_small\",\"fit_large\"]].sum(axis=1) == 1\n",
    ").all()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "526b6a24",
   "metadata": {},
   "source": [
    "yang slightly sama half size gitu langsung dimasukin ke kolom kegedean apa kekecilan. hasilnya begitu"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "27e44d2b",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>Strike_lists</th>\n",
       "      <th>-</th>\n",
       "      <th>strike_forefoot</th>\n",
       "      <th>strike_heel</th>\n",
       "      <th>strike_mid</th>\n",
       "      <th>fit_category</th>\n",
       "      <th>fit_large</th>\n",
       "      <th>fit_small</th>\n",
       "      <th>fit_true</th>\n",
       "      <th>fit_missing</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>[Heel]</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>small</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Heel, Mid, Forefoot]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 51 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ...           Strike_lists  - strike_forefoot  \\\n",
       "0  Heelmid/Forefoot  ...  [Heel, Mid, Forefoot]  0               1   \n",
       "1      Mid/Forefoot  ...        [Mid, Forefoot]  0               1   \n",
       "2  Heelmid/Forefoot  ...  [Heel, Mid, Forefoot]  0               1   \n",
       "3              Heel  ...                 [Heel]  0               0   \n",
       "4  Heelmid/Forefoot  ...  [Heel, Mid, Forefoot]  0               1   \n",
       "\n",
       "  strike_heel strike_mid fit_category fit_large fit_small fit_true fit_missing  \n",
       "0           1          1         true         0         0        1           0  \n",
       "1           0          1         true         0         0        1           0  \n",
       "2           1          1         true         0         0        1           0  \n",
       "3           1          0        small         0         1        0           0  \n",
       "4           1          1         true         0         0        1           0  \n",
       "\n",
       "[5 rows x 51 columns]"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "4416dafe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.DataFrame'>\n",
      "RangeIndex: 1170 entries, 0 to 1169\n",
      "Data columns (total 51 columns):\n",
      " #   Column                       Non-Null Count  Dtype \n",
      "---  ------                       --------------  ----- \n",
      " 0   Brand                        1170 non-null   str   \n",
      " 1   Name                         1170 non-null   str   \n",
      " 2   Audience score               1164 non-null   str   \n",
      " 3   Price                        1170 non-null   str   \n",
      " 4   Pace                         1170 non-null   str   \n",
      " 5   Arch support                 1170 non-null   str   \n",
      " 6   Weight lab Weight brand      1170 non-null   str   \n",
      " 7   Lightweight                  1170 non-null   int64 \n",
      " 8   Drop lab Drop brand          1170 non-null   str   \n",
      " 9   Strike pattern               1170 non-null   str   \n",
      " 10  Size                         1170 non-null   str   \n",
      " 11  Midsole softness             1170 non-null   str   \n",
      " 12  Toebox durability            1170 non-null   str   \n",
      " 13  Heel padding durability      1170 non-null   str   \n",
      " 14  Outsole durability           1170 non-null   str   \n",
      " 15  Breathability                1170 non-null   str   \n",
      " 16  Width / fit                  1170 non-null   str   \n",
      " 17  Toebox width                 1170 non-null   str   \n",
      " 18  Stiffness                    1170 non-null   str   \n",
      " 19  Torsional rigidity           1170 non-null   str   \n",
      " 20  Heel counter stiffness       1170 non-null   str   \n",
      " 21  Plate                        1170 non-null   str   \n",
      " 22  Rocker                       1170 non-null   int64 \n",
      " 23  Heel lab Heel brand          1170 non-null   str   \n",
      " 24  Forefoot lab Forefoot brand  1170 non-null   str   \n",
      " 25  Widths available             1170 non-null   str   \n",
      " 26  Orthotic friendly            1170 non-null   int64 \n",
      " 27  Season                       1170 non-null   str   \n",
      " 28  Removable insole             1170 non-null   int64 \n",
      " 29  Ranking                      1170 non-null   str   \n",
      " 30  Popularity                   1170 non-null   str   \n",
      " 31  Gender                       10 non-null     str   \n",
      " 32  Terrain                      16 non-null     str   \n",
      " 33  Pace_norm                    1170 non-null   str   \n",
      " 34  Pace_lists                   1170 non-null   object\n",
      " 35  pace_competition             1170 non-null   int64 \n",
      " 36  pace_daily_running           1170 non-null   int64 \n",
      " 37  pace_tempo                   1170 non-null   int64 \n",
      " 38  arch_neutral                 1170 non-null   int64 \n",
      " 39  arch_stability               1170 non-null   int64 \n",
      " 40  Strike_norm                  1170 non-null   str   \n",
      " 41  Strike_lists                 1170 non-null   object\n",
      " 42  -                            1170 non-null   int64 \n",
      " 43  strike_forefoot              1170 non-null   int64 \n",
      " 44  strike_heel                  1170 non-null   int64 \n",
      " 45  strike_mid                   1170 non-null   int64 \n",
      " 46  fit_category                 1126 non-null   str   \n",
      " 47  fit_large                    1170 non-null   int64 \n",
      " 48  fit_small                    1170 non-null   int64 \n",
      " 49  fit_true                     1170 non-null   int64 \n",
      " 50  fit_missing                  1170 non-null   int64 \n",
      "dtypes: int64(17), object(2), str(32)\n",
      "memory usage: 466.3+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "dc1856f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.rename(columns={\"-\": \"strike_missing\"}, inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9aff0dc",
   "metadata": {},
   "source": [
    "# Cleaning Midsole"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "7a77b6f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Midsole (4 uniques): \n",
      " ['-', 'Balanced', 'Firm', 'Soft']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Midsole softness\n",
       "Balanced    543\n",
       "Soft        504\n",
       "-            72\n",
       "Firm         51\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Midsole softness\"] = (\n",
    "    df[\"Midsole softness\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "midsole_uniques = df[\"Midsole softness\"].dropna().unique()\n",
    "# midsole_uniques.sort()\n",
    "midsole_uniques = sorted(midsole_uniques)\n",
    "print(f\"Midsole ({len(midsole_uniques)} uniques): \\n\",midsole_uniques)\n",
    "\n",
    "df[\"Midsole softness\"].value_counts().head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "b8050c57",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Midsole softness</th>\n",
       "      <th>midsole_repr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adizero Adios Pro 2.0</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Adrenaline GTS 22</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Air Zoom Pegasus 38</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Air Zoom Pegasus 38 FlyEase</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Anthem 4</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</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>1050</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Ultraboost 21</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1071</th>\n",
       "      <td>Merrell</td>\n",
       "      <td>Vapor Glove 6</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1072</th>\n",
       "      <td>Merrell</td>\n",
       "      <td>Vapor Glove 6</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1124</th>\n",
       "      <td>Mizuno</td>\n",
       "      <td>Wave Rider 25</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1158</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 4</td>\n",
       "      <td>-</td>\n",
       "      <td>'-'</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>72 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Brand                         Name Midsole softness midsole_repr\n",
       "25     Adidas        Adizero Adios Pro 2.0                -          '-'\n",
       "53     Brooks            Adrenaline GTS 22                -          '-'\n",
       "70       Nike          Air Zoom Pegasus 38                -          '-'\n",
       "71       Nike  Air Zoom Pegasus 38 FlyEase                -          '-'\n",
       "92     Brooks                     Anthem 4                -          '-'\n",
       "...       ...                          ...              ...          ...\n",
       "1050   Adidas                Ultraboost 21                -          '-'\n",
       "1071  Merrell                Vapor Glove 6                -          '-'\n",
       "1072  Merrell                Vapor Glove 6                -          '-'\n",
       "1124   Mizuno                Wave Rider 25                -          '-'\n",
       "1158     Nike                   Zoom Fly 4                -          '-'\n",
       "\n",
       "[72 rows x 4 columns]"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask = df[\"Midsole softness\"].astype(str).str.strip() == \"-\"\n",
    "df.loc[mask, [\"Brand\",\"Name\", \"Midsole softness\"]].assign(\n",
    "    midsole_repr=df.loc[mask, \"Midsole softness\"].apply(repr)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "9cb14667",
   "metadata": {},
   "outputs": [],
   "source": [
    "# midsole_map = {\n",
    "   \n",
    "# }\n",
    "\n",
    "# df[\"midsole_category\"] = df[\"Midsole softness\"].map(midsole_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "27c8c72b",
   "metadata": {},
   "outputs": [],
   "source": [
    "soft_ohe = pd.get_dummies(df[\"Midsole softness\"], prefix=\"midsole\").astype(int)\n",
    "\n",
    "# pastikan kolom konsisten untuk pipeline\n",
    "for col in [\"midsole_Soft\", \"midsole_Balanced\", \"midsole_Firm\"]:\n",
    "    if col not in soft_ohe.columns:\n",
    "        soft_ohe[col] = 0\n",
    "\n",
    "# jujur enakan lowercase\n",
    "soft_ohe = soft_ohe.rename(columns={\n",
    "    \"midsole_Soft\": \"midsole_soft\",\n",
    "    \"midsole_Balanced\": \"midsole_balanced\",\n",
    "    \"midsole_Firm\": \"midsole_firm\"\n",
    "})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "5f2d647e",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>strike_heel</th>\n",
       "      <th>strike_mid</th>\n",
       "      <th>fit_category</th>\n",
       "      <th>fit_large</th>\n",
       "      <th>fit_small</th>\n",
       "      <th>fit_true</th>\n",
       "      <th>fit_missing</th>\n",
       "      <th>midsole_soft</th>\n",
       "      <th>midsole_balanced</th>\n",
       "      <th>midsole_firm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>small</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>true</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 54 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... strike_heel strike_mid fit_category fit_large  \\\n",
       "0  Heelmid/Forefoot  ...           1          1         true         0   \n",
       "1      Mid/Forefoot  ...           0          1         true         0   \n",
       "2  Heelmid/Forefoot  ...           1          1         true         0   \n",
       "3              Heel  ...           1          0        small         0   \n",
       "4  Heelmid/Forefoot  ...           1          1         true         0   \n",
       "\n",
       "  fit_small fit_true fit_missing midsole_soft midsole_balanced midsole_firm  \n",
       "0         0        1           0            0                1            0  \n",
       "1         0        1           0            1                0            0  \n",
       "2         0        1           0            0                0            1  \n",
       "3         1        0           0            0                0            1  \n",
       "4         0        1           0            0                0            1  \n",
       "\n",
       "[5 rows x 54 columns]"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.concat([df, soft_ohe[[\"midsole_soft\",\"midsole_balanced\",\"midsole_firm\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "1bd6f66d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "Soft: 504\n",
      "Balanced: 543\n",
      "Firm: 51\n",
      "Missing midsole softness rows: 72\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"Soft:\", int(df[\"midsole_soft\"].sum()))\n",
    "print(\"Balanced:\", int(df[\"midsole_balanced\"].sum()))\n",
    "print(\"Firm:\", int(df[\"midsole_firm\"].sum()))\n",
    "\n",
    "missing_midsole = (df[[\"midsole_soft\",\"midsole_balanced\",\"midsole_firm\"]].sum(axis=1) == 0).sum()\n",
    "print(\"Missing midsole softness rows:\", int(missing_midsole))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "341e1a94",
   "metadata": {},
   "source": [
    "maaf kalo kurang berprinsip, nanti deh analisis asumsi rangkuman itunya"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31a9f82e",
   "metadata": {},
   "source": [
    "### Analisis Midsole Softness \n",
    "A. Soft\n",
    "Rasa: empuk, plush, compressible\n",
    "Cocok untuk: easy run, long run, recovery\n",
    "Kelebihan: nyaman, ramah kaki, menyerap impact\n",
    "Kekurangan: responsivitas lebih rendah, bisa terasa “tenggelam” saat ngebut\n",
    "\n",
    "B. Balanced\n",
    "Rasa: seimbang antara empuk dan firm\n",
    "Cocok untuk: daily running serbaguna, tempo ringan\n",
    "Kelebihan: stabil, fleksibel, paling aman untuk mayoritas pelari\n",
    "Kekurangan: tidak se-empuk soft, tidak se-responsif firm\n",
    "\n",
    "C. Firm\n",
    "Rasa: padat, minim kompresi\n",
    "Cocok untuk: tempo run, interval, racing\n",
    "Kelebihan: responsif, efisien energi, stabil saat pace cepat\n",
    "Kekurangan: kurang nyaman untuk jarak jauh santai"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a6e28c3a",
   "metadata": {},
   "source": [
    "# Cleaning Toebox durability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "13d90252",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Toebox (4 uniques): \n",
      " ['-', 'Bad', 'Decent', 'Good']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Toebox durability\n",
       "Decent    486\n",
       "Bad       263\n",
       "Good      247\n",
       "-         174\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Toebox durability\"] = (\n",
    "    df[\"Toebox durability\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "toebox_uniques = df[\"Toebox durability\"].dropna().unique()\n",
    "# toebox_uniques.sort()\n",
    "toebox_uniques = sorted(toebox_uniques)\n",
    "print(f\"Toebox ({len(toebox_uniques)} uniques): \\n\",toebox_uniques)\n",
    "\n",
    "df[\"Toebox durability\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "1a7d7688",
   "metadata": {},
   "outputs": [],
   "source": [
    "toe_ohe = pd.get_dummies(df[\"Toebox durability\"], prefix=\"toebox\").astype(int)\n",
    "\n",
    "for col in [\"toebox_Bad\", \"toebox_Decent\", \"toebox_Good\"]:\n",
    "    if col not in toe_ohe.columns:\n",
    "        toe_ohe[col] = 0\n",
    "\n",
    "toe_ohe = toe_ohe.rename(columns={\n",
    "    \"toebox_Bad\": \"toebox_bad\",\n",
    "    \"toebox_Decent\": \"toebox_decent\",\n",
    "    \"toebox_Good\": \"toebox_good\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, toe_ohe[[\"toebox_bad\",\"toebox_decent\",\"toebox_good\"]]], axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "98e49c7a",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>fit_large</th>\n",
       "      <th>fit_small</th>\n",
       "      <th>fit_true</th>\n",
       "      <th>fit_missing</th>\n",
       "      <th>midsole_soft</th>\n",
       "      <th>midsole_balanced</th>\n",
       "      <th>midsole_firm</th>\n",
       "      <th>toebox_bad</th>\n",
       "      <th>toebox_decent</th>\n",
       "      <th>toebox_good</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 57 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... fit_large fit_small fit_true fit_missing  \\\n",
       "0  Heelmid/Forefoot  ...         0         0        1           0   \n",
       "1      Mid/Forefoot  ...         0         0        1           0   \n",
       "2  Heelmid/Forefoot  ...         0         0        1           0   \n",
       "3              Heel  ...         0         1        0           0   \n",
       "4  Heelmid/Forefoot  ...         0         0        1           0   \n",
       "\n",
       "  midsole_soft midsole_balanced midsole_firm toebox_bad toebox_decent  \\\n",
       "0            0                1            0          0             0   \n",
       "1            1                0            0          0             0   \n",
       "2            0                0            1          0             0   \n",
       "3            0                0            1          0             0   \n",
       "4            0                0            1          0             0   \n",
       "\n",
       "  toebox_good  \n",
       "0           0  \n",
       "1           1  \n",
       "2           0  \n",
       "3           0  \n",
       "4           1  \n",
       "\n",
       "[5 rows x 57 columns]"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "1e4ee12e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "Bad: 263\n",
      "Decent: 486\n",
      "Good: 247\n",
      "Missing toebox rows: 174\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"Bad:\", int(df[\"toebox_bad\"].sum()))\n",
    "print(\"Decent:\", int(df[\"toebox_decent\"].sum()))\n",
    "print(\"Good:\", int(df[\"toebox_good\"].sum()))\n",
    "print(\"Missing toebox rows:\",\n",
    "      int((df[[\"toebox_bad\",\"toebox_decent\",\"toebox_good\"]].sum(axis=1) == 0).sum()))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c40a81d",
   "metadata": {},
   "source": [
    "### Analisis Toebox Durability\n",
    "Toebox durability menggambarkan ketahanan bagian depan sepatu (area jari kaki) terhadap aus, robek, atau jebol akibat gesekan dan tekanan saat berlari. Fitur ini tidak berhubungan dengan kenyamanan, tapi umur pakai sepatu, terutama untuk pelari dengan tekanan forefoot tinggi atau mileage besar.\n",
    "\n",
    "A. Bad = Toebox mudah aus / cepat rusak\n",
    "Umum pada sepatu:\n",
    "- sangat ringan\n",
    "- racing-oriented\n",
    "Risiko: cepat jebol jika dipakai intens\n",
    "Trade-off: biasanya lebih breathable & ringan\n",
    "\n",
    "B. Decent = Ketahanan cukup untuk pemakaian normal\n",
    "Aman untuk:\n",
    "- daily running\n",
    "- latihan reguler\n",
    "Trade-off: tidak sekuat kategori “Good”, tapi seimbang\n",
    "\n",
    "C. Good = Toebox kuat dan tahan lama\n",
    "Cocok untuk:\n",
    "- mileage tinggi\n",
    "- forefoot striker\n",
    "- pemakaian kasar / jangka panjang\n",
    "Trade-off: kadang sedikit lebih berat atau kurang breathable"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db78fbae",
   "metadata": {},
   "source": [
    "# Cleaning Heel padding durability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "0e7f91f1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Heel padding (4 uniques): \n",
      " ['-', 'Bad', 'Decent', 'Good']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Heel padding durability\n",
       "Good      555\n",
       "Decent    248\n",
       "Bad       191\n",
       "-         176\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Heel padding durability\"] = (\n",
    "    df[\"Heel padding durability\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "heel_padding_uniques = df[\"Heel padding durability\"].dropna().unique()\n",
    "# heel_padding_uniques.sort()\n",
    "heel_padding_uniques = sorted(heel_padding_uniques)\n",
    "print(f\"Heel padding ({len(heel_padding_uniques)} uniques): \\n\",heel_padding_uniques)\n",
    "\n",
    "df[\"Heel padding durability\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "7c9c18c7",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>fit_missing</th>\n",
       "      <th>midsole_soft</th>\n",
       "      <th>midsole_balanced</th>\n",
       "      <th>midsole_firm</th>\n",
       "      <th>toebox_bad</th>\n",
       "      <th>toebox_decent</th>\n",
       "      <th>toebox_good</th>\n",
       "      <th>heelpad_bad</th>\n",
       "      <th>heelpad_decent</th>\n",
       "      <th>heelpad_good</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 60 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... fit_missing midsole_soft midsole_balanced  \\\n",
       "0  Heelmid/Forefoot  ...           0            0                1   \n",
       "1      Mid/Forefoot  ...           0            1                0   \n",
       "2  Heelmid/Forefoot  ...           0            0                0   \n",
       "3              Heel  ...           0            0                0   \n",
       "4  Heelmid/Forefoot  ...           0            0                0   \n",
       "\n",
       "  midsole_firm toebox_bad toebox_decent toebox_good heelpad_bad  \\\n",
       "0            0          0             0           0           0   \n",
       "1            0          0             0           1           0   \n",
       "2            1          0             0           0           0   \n",
       "3            1          0             0           0           0   \n",
       "4            1          0             0           1           0   \n",
       "\n",
       "  heelpad_decent heelpad_good  \n",
       "0              0            0  \n",
       "1              0            1  \n",
       "2              0            1  \n",
       "3              0            0  \n",
       "4              0            1  \n",
       "\n",
       "[5 rows x 60 columns]"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hpd_ohe = pd.get_dummies(df[\"Heel padding durability\"], prefix=\"heel_pad\").astype(int)\n",
    "\n",
    "\n",
    "for col in [\"heel_pad_Bad\", \"heel_pad_Decent\", \"heel_pad_Good\"]:\n",
    "    if col not in hpd_ohe.columns:\n",
    "        hpd_ohe[col] = 0\n",
    "\n",
    "\n",
    "hpd_ohe = hpd_ohe.rename(columns={\n",
    "    \"heel_pad_Bad\": \"heelpad_bad\",\n",
    "    \"heel_pad_Decent\": \"heelpad_decent\",\n",
    "    \"heel_pad_Good\": \"heelpad_good\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, hpd_ohe[[\"heelpad_bad\", \"heelpad_decent\", \"heelpad_good\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "0cdc7d72",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "Bad: 191\n",
      "Decent: 248\n",
      "Good: 555\n",
      "Missing heelpad durability rows: 176\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"Bad:\", int(df[\"heelpad_bad\"].sum()))\n",
    "print(\"Decent:\", int(df[\"heelpad_decent\"].sum()))\n",
    "print(\"Good:\", int(df[\"heelpad_good\"].sum()))\n",
    "print(\"Missing heelpad durability rows:\",\n",
    "      int((df[[\"heelpad_bad\",\"heelpad_decent\",\"heelpad_good\"]].sum(axis=1) == 0).sum()))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44af6117",
   "metadata": {},
   "source": [
    "makin banyak missingnya bre"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b7225f80",
   "metadata": {},
   "source": [
    "### Analisis Heel Padding Durability\n",
    "Heel padding durability menggambarkan ketahanan bantalan di area tumit bagian dalam sepatu terhadap aus, kempes, atau rusak akibat gesekan dan tekanan berulang saat berlari. Fitur ini berpengaruh pada kenyamanan jangka panjang, stabilitas tumit, dan umur pakai sepatu, terutama bagi pelari yang dominan heel strike.\n",
    "\n",
    "Bad: \n",
    "Bantalan tumit cepat aus atau kempes\n",
    "Berpotensi menyebabkan:\n",
    "rasa tidak nyaman\n",
    "gesekan berlebih di tumit\n",
    "Umum pada sepatu:\n",
    "ringan\n",
    "fokus ke performa jangka pendek\n",
    "Trade-off: bobot lebih ringan, tapi durability rendah\n",
    "\n",
    "Decent: \n",
    "Ketahanan bantalan cukup untuk pemakaian normal\n",
    "Aman untuk:\n",
    "daily running\n",
    "latihan reguler\n",
    "Trade-off: tidak sekuat kategori “Good”, tapi seimbang\n",
    "\n",
    "Good: \n",
    "Bantalan tumit kuat dan tahan lama\n",
    "Cocok untuk:\n",
    "mileage tinggi\n",
    "pemakaian jangka panjang\n",
    "pelari heel strike\n",
    "Trade-off: kadang sedikit lebih berat atau kurang breathable"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00d5e6f9",
   "metadata": {},
   "source": [
    "# Cleaning Outsole Durability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "cc9ba6e9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Outsole (4 uniques): \n",
      " ['-', 'Bad', 'Decent', 'Good']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Outsole durability\n",
       "Good      631\n",
       "Decent    253\n",
       "-         209\n",
       "Bad        77\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Outsole durability\"] = (\n",
    "    df[\"Outsole durability\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "outsole_uniques = df[\"Outsole durability\"].dropna().unique()\n",
    "# outsole_uniques.sort()\n",
    "outsole_uniques = sorted(outsole_uniques)\n",
    "print(f\"Outsole ({len(outsole_uniques)} uniques): \\n\",outsole_uniques)\n",
    "\n",
    "df[\"Outsole durability\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "28bf5e69",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>midsole_firm</th>\n",
       "      <th>toebox_bad</th>\n",
       "      <th>toebox_decent</th>\n",
       "      <th>toebox_good</th>\n",
       "      <th>heelpad_bad</th>\n",
       "      <th>heelpad_decent</th>\n",
       "      <th>heelpad_good</th>\n",
       "      <th>outsole_bad</th>\n",
       "      <th>outsole_decent</th>\n",
       "      <th>outsole_good</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>1</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 63 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... midsole_firm toebox_bad toebox_decent toebox_good  \\\n",
       "0  Heelmid/Forefoot  ...            0          0             0           0   \n",
       "1      Mid/Forefoot  ...            0          0             0           1   \n",
       "2  Heelmid/Forefoot  ...            1          0             0           0   \n",
       "3              Heel  ...            1          0             0           0   \n",
       "4  Heelmid/Forefoot  ...            1          0             0           1   \n",
       "\n",
       "  heelpad_bad heelpad_decent heelpad_good outsole_bad outsole_decent  \\\n",
       "0           0              0            0           0              0   \n",
       "1           0              0            1           0              0   \n",
       "2           0              0            1           0              0   \n",
       "3           0              0            0           0              0   \n",
       "4           0              0            1           0              0   \n",
       "\n",
       "  outsole_good  \n",
       "0            0  \n",
       "1            1  \n",
       "2            0  \n",
       "3            0  \n",
       "4            1  \n",
       "\n",
       "[5 rows x 63 columns]"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "out_ohe = pd.get_dummies(df[\"Outsole durability\"], prefix=\"outsole\").astype(int)\n",
    "\n",
    "for col in [\"outsole_Bad\", \"outsole_Decent\", \"outsole_Good\"]:\n",
    "    if col not in out_ohe.columns:\n",
    "        out_ohe[col] = 0\n",
    "\n",
    "out_ohe = out_ohe.rename(columns={\n",
    "    \"outsole_Bad\": \"outsole_bad\",\n",
    "    \"outsole_Decent\": \"outsole_decent\",\n",
    "    \"outsole_Good\": \"outsole_good\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, out_ohe[[\"outsole_bad\",\"outsole_decent\",\"outsole_good\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "6e11f54a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "outsole_bad        77\n",
      "outsole_decent    253\n",
      "outsole_good      631\n",
      "dtype: int64\n",
      "Missing outsole rows: 209\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"outsole_bad\",\"outsole_decent\",\"outsole_good\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"outsole_bad\",\"outsole_decent\",\"outsole_good\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"outsole_bad\",\"outsole_decent\",\"outsole_good\"]].sum())\n",
    "print(\"Missing outsole rows:\",\n",
    "      int((df[[\"outsole_bad\",\"outsole_decent\",\"outsole_good\"]].sum(axis=1) == 0).sum()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74ad3110",
   "metadata": {},
   "source": [
    "### Analisis Outsole Durability\n",
    "\n",
    "Outsole durability menggambarkan ketahanan sol bagian bawah sepatu terhadap aus akibat kontak langsung dengan permukaan lari (aspal, beton, treadmill, track).\n",
    "\n",
    "Fitur ini berhubungan langsung dengan umur pakai sepatu dan efisiensi biaya, terutama bagi pelari dengan mileage tinggi atau yang sering berlari di permukaan keras.\n",
    "\n",
    "- Bad: \n",
    "Outsole cepat aus\n",
    "Grip dan perlindungan cepat menurun\n",
    "Umum pada sepatu:\n",
    "ringan\n",
    "racing-oriented\n",
    "Trade-off: bobot ringan, tapi umur pakai pendek\n",
    "\n",
    "- Decent: \n",
    "Ketahanan cukup untuk pemakaian normal\n",
    "Aman untuk:\n",
    "daily running\n",
    "latihan reguler\n",
    "Trade-off: bukan yang paling awet, tapi seimbang\n",
    "\n",
    "- Good: \n",
    "Outsole sangat tahan lama\n",
    "Cocok untuk:\n",
    "mileage tinggi\n",
    "pemakaian jangka panjang\n",
    "lari di permukaan kasar\n",
    "Trade-off: kadang lebih berat atau kurang fleksibel"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f0da23b5",
   "metadata": {},
   "source": [
    "# Cleaning Breathability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "5953a816",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = df.drop(labels=\"breathable\", axis=1)\n",
    "# df = df.drop(labels=\"moderate\", axis=1)\n",
    "# df = df.drop(labels=\"warm\", axis=1)\n",
    "# df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "b90e8e6c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breathability (4 uniques): \n",
      " ['-', 'Breathable', 'Moderate', 'Warm']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Breathability\n",
       "Moderate      642\n",
       "Breathable    347\n",
       "Warm          118\n",
       "-              63\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Breathability\"] = (\n",
    "    df[\"Breathability\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "breathability_uniques = df[\"Breathability\"].dropna().unique()\n",
    "# breathability_uniques.sort()\n",
    "breathability_uniques = sorted(breathability_uniques)\n",
    "print(f\"Breathability ({len(breathability_uniques)} uniques): \\n\",breathability_uniques)\n",
    "\n",
    "df[\"Breathability\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "61b2650b",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>toebox_good</th>\n",
       "      <th>heelpad_bad</th>\n",
       "      <th>heelpad_decent</th>\n",
       "      <th>heelpad_good</th>\n",
       "      <th>outsole_bad</th>\n",
       "      <th>outsole_decent</th>\n",
       "      <th>outsole_good</th>\n",
       "      <th>breath_breathable</th>\n",
       "      <th>breath_moderate</th>\n",
       "      <th>breath_warm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 66 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... toebox_good heelpad_bad heelpad_decent heelpad_good  \\\n",
       "0  Heelmid/Forefoot  ...           0           0              0            0   \n",
       "1      Mid/Forefoot  ...           1           0              0            1   \n",
       "2  Heelmid/Forefoot  ...           0           0              0            1   \n",
       "3              Heel  ...           0           0              0            0   \n",
       "4  Heelmid/Forefoot  ...           1           0              0            1   \n",
       "\n",
       "  outsole_bad outsole_decent outsole_good breath_breathable breath_moderate  \\\n",
       "0           0              0            0                 0               0   \n",
       "1           0              0            1                 1               0   \n",
       "2           0              0            0                 0               0   \n",
       "3           0              0            0                 0               0   \n",
       "4           0              0            1                 0               0   \n",
       "\n",
       "  breath_warm  \n",
       "0           0  \n",
       "1           0  \n",
       "2           1  \n",
       "3           1  \n",
       "4           1  \n",
       "\n",
       "[5 rows x 66 columns]"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "breath_ohe = pd.get_dummies(df[\"Breathability\"], prefix=\"breath\").astype(int)\n",
    "\n",
    "for col in [\"breath_Breathable\", \"breath_Moderate\", \"breath_Warm\"]:\n",
    "    if col not in breath_ohe.columns:\n",
    "        breath_ohe[col] = 0\n",
    "\n",
    "breath_ohe = breath_ohe.rename(columns={\n",
    "    \"breath_Breathable\": \"breath_breathable\",\n",
    "    \"breath_Moderate\": \"breath_moderate\",\n",
    "    \"breath_Warm\": \"breath_warm\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, breath_ohe[[\"breath_breathable\",\"breath_moderate\",\"breath_warm\"]]], axis=1)\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "06e99a17",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "breath_breathable    347\n",
      "breath_moderate      642\n",
      "breath_warm          118\n",
      "dtype: int64\n",
      "Missing breathability rows: 63\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"breath_breathable\",\"breath_moderate\",\"breath_warm\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"breath_breathable\",\"breath_moderate\",\"breath_warm\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"breath_breathable\",\"breath_moderate\",\"breath_warm\"]].sum())\n",
    "print(\"Missing breathability rows:\",\n",
    "      int((df[[\"breath_breathable\",\"breath_moderate\",\"breath_warm\"]].sum(axis=1) == 0).sum()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d08520e",
   "metadata": {},
   "source": [
    "### Analisis Breathability\n",
    "\n",
    "Breathability menggambarkan seberapa baik sepatu memungkinkan sirkulasi udara di bagian upper, yang berpengaruh pada suhu kaki, kenyamanan, dan manajemen kelembapan saat berlari.\n",
    "\n",
    "Fitur ini penting terutama untuk:\n",
    "\n",
    "lari jarak jauh\n",
    "\n",
    "cuaca panas\n",
    "\n",
    "pelari dengan kaki mudah berkeringat\n",
    "\n",
    "Breathable\n",
    "\n",
    "Sirkulasi udara sangat baik\n",
    "\n",
    "Kaki terasa lebih sejuk dan kering\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "cuaca panas\n",
    "\n",
    "long run\n",
    "\n",
    "Trade-off: biasanya material lebih tipis → durability bisa lebih rendah\n",
    "\n",
    "Moderate\n",
    "\n",
    "Sirkulasi udara cukup / seimbang\n",
    "\n",
    "Aman untuk pemakaian umum\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "daily running\n",
    "\n",
    "berbagai kondisi cuaca\n",
    "\n",
    "Trade-off: tidak seadem “Breathable”, tidak sehangat “Warm”\n",
    "\n",
    "Warm\n",
    "\n",
    "Ventilasi minim\n",
    "\n",
    "Menjaga kaki tetap hangat\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "cuaca dingin\n",
    "\n",
    "winter running\n",
    "\n",
    "Trade-off: kaki bisa terasa panas di cuaca hangat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b7c347e",
   "metadata": {},
   "source": [
    "# Cleaning Width / fit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "4c25ac2d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Width / fit (3 uniques): \n",
      " ['Medium', 'Narrow', 'Wide']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Width / fit\n",
       "Medium    786\n",
       "Narrow    287\n",
       "Wide       97\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Width / fit\"] = (\n",
    "    df[\"Width / fit\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "width_uniques = df[\"Width / fit\"].dropna().unique()\n",
    "# width_uniques.sort()\n",
    "width_uniques = sorted(width_uniques)\n",
    "print(f\"Width / fit ({len(width_uniques)} uniques): \\n\",width_uniques)\n",
    "\n",
    "df[\"Width / fit\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "d33d3ef6",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>heelpad_good</th>\n",
       "      <th>outsole_bad</th>\n",
       "      <th>outsole_decent</th>\n",
       "      <th>outsole_good</th>\n",
       "      <th>breath_breathable</th>\n",
       "      <th>breath_moderate</th>\n",
       "      <th>breath_warm</th>\n",
       "      <th>width_narrow</th>\n",
       "      <th>width_medium</th>\n",
       "      <th>width_wide</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 69 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... heelpad_good outsole_bad outsole_decent outsole_good  \\\n",
       "0  Heelmid/Forefoot  ...            0           0              0            0   \n",
       "1      Mid/Forefoot  ...            1           0              0            1   \n",
       "2  Heelmid/Forefoot  ...            1           0              0            0   \n",
       "3              Heel  ...            0           0              0            0   \n",
       "4  Heelmid/Forefoot  ...            1           0              0            1   \n",
       "\n",
       "  breath_breathable breath_moderate breath_warm width_narrow width_medium  \\\n",
       "0                 0               0           0            1            0   \n",
       "1                 1               0           0            1            0   \n",
       "2                 0               0           1            1            0   \n",
       "3                 0               0           1            1            0   \n",
       "4                 0               0           1            1            0   \n",
       "\n",
       "  width_wide  \n",
       "0          0  \n",
       "1          0  \n",
       "2          0  \n",
       "3          0  \n",
       "4          0  \n",
       "\n",
       "[5 rows x 69 columns]"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "width_ohe = pd.get_dummies(df[\"Width / fit\"], prefix=\"width\").astype(int)\n",
    "\n",
    "for col in [\"width_Narrow\", \"width_Medium\", \"width_Wide\"]:\n",
    "    if col not in width_ohe.columns:\n",
    "        width_ohe[col] = 0\n",
    "\n",
    "width_ohe = width_ohe.rename(columns={\n",
    "    \"width_Narrow\": \"width_narrow\",\n",
    "    \"width_Medium\": \"width_medium\",\n",
    "    \"width_Wide\": \"width_wide\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, width_ohe[[\"width_narrow\",\"width_medium\",\"width_wide\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "1ec7610a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "width_narrow    287\n",
      "width_medium    786\n",
      "width_wide       97\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"width_narrow\",\"width_medium\",\"width_wide\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# HARUS tepat satu (tidak ada missing)\n",
    "assert (df[[\"width_narrow\",\"width_medium\",\"width_wide\"]].sum(axis=1) == 1).all()\n",
    "\n",
    "print(df[[\"width_narrow\",\"width_medium\",\"width_wide\"]].sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf698833",
   "metadata": {},
   "source": [
    "### Analisis Width / Fit\n",
    "\n",
    "Width / fit menggambarkan lebar sepatu pada bagian forefoot (area depan kaki), yang memengaruhi kenyamanan, stabilitas, dan risiko lecet saat berlari.\n",
    "\n",
    "Fitur ini bukan soal ukuran panjang (EU/US), melainkan ruang horizontal untuk kaki.\n",
    "\n",
    "Narrow\n",
    "\n",
    "Sepatu terasa lebih sempit dari standar\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "kaki ramping\n",
    "\n",
    "pelari yang suka fit ketat\n",
    "\n",
    "Risiko: tekanan di sisi kaki jika dipakai oleh kaki lebar\n",
    "\n",
    "Medium\n",
    "\n",
    "Lebar standar / normal\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "mayoritas pelari\n",
    "\n",
    "Catatan: ini adalah default fit di pasaran\n",
    "\n",
    "Wide\n",
    "\n",
    "Sepatu menyediakan ruang lebih lega\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "kaki lebar\n",
    "\n",
    "pelari yang sering merasa jari tertekan\n",
    "\n",
    "Trade-off: bisa terasa kurang “locked-in” untuk kaki sempit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "928c5523",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.DataFrame'>\n",
      "RangeIndex: 1170 entries, 0 to 1169\n",
      "Data columns (total 69 columns):\n",
      " #   Column                       Non-Null Count  Dtype \n",
      "---  ------                       --------------  ----- \n",
      " 0   Brand                        1170 non-null   str   \n",
      " 1   Name                         1170 non-null   str   \n",
      " 2   Audience score               1164 non-null   str   \n",
      " 3   Price                        1170 non-null   str   \n",
      " 4   Pace                         1170 non-null   str   \n",
      " 5   Arch support                 1170 non-null   str   \n",
      " 6   Weight lab Weight brand      1170 non-null   str   \n",
      " 7   Lightweight                  1170 non-null   int64 \n",
      " 8   Drop lab Drop brand          1170 non-null   str   \n",
      " 9   Strike pattern               1170 non-null   str   \n",
      " 10  Size                         1170 non-null   str   \n",
      " 11  Midsole softness             1170 non-null   str   \n",
      " 12  Toebox durability            1170 non-null   str   \n",
      " 13  Heel padding durability      1170 non-null   str   \n",
      " 14  Outsole durability           1170 non-null   str   \n",
      " 15  Breathability                1170 non-null   str   \n",
      " 16  Width / fit                  1170 non-null   str   \n",
      " 17  Toebox width                 1170 non-null   str   \n",
      " 18  Stiffness                    1170 non-null   str   \n",
      " 19  Torsional rigidity           1170 non-null   str   \n",
      " 20  Heel counter stiffness       1170 non-null   str   \n",
      " 21  Plate                        1170 non-null   str   \n",
      " 22  Rocker                       1170 non-null   int64 \n",
      " 23  Heel lab Heel brand          1170 non-null   str   \n",
      " 24  Forefoot lab Forefoot brand  1170 non-null   str   \n",
      " 25  Widths available             1170 non-null   str   \n",
      " 26  Orthotic friendly            1170 non-null   int64 \n",
      " 27  Season                       1170 non-null   str   \n",
      " 28  Removable insole             1170 non-null   int64 \n",
      " 29  Ranking                      1170 non-null   str   \n",
      " 30  Popularity                   1170 non-null   str   \n",
      " 31  Gender                       10 non-null     str   \n",
      " 32  Terrain                      16 non-null     str   \n",
      " 33  Pace_norm                    1170 non-null   str   \n",
      " 34  Pace_lists                   1170 non-null   object\n",
      " 35  pace_competition             1170 non-null   int64 \n",
      " 36  pace_daily_running           1170 non-null   int64 \n",
      " 37  pace_tempo                   1170 non-null   int64 \n",
      " 38  arch_neutral                 1170 non-null   int64 \n",
      " 39  arch_stability               1170 non-null   int64 \n",
      " 40  Strike_norm                  1170 non-null   str   \n",
      " 41  Strike_lists                 1170 non-null   object\n",
      " 42  -                            1170 non-null   int64 \n",
      " 43  strike_forefoot              1170 non-null   int64 \n",
      " 44  strike_heel                  1170 non-null   int64 \n",
      " 45  strike_mid                   1170 non-null   int64 \n",
      " 46  fit_category                 1126 non-null   str   \n",
      " 47  fit_large                    1170 non-null   int64 \n",
      " 48  fit_small                    1170 non-null   int64 \n",
      " 49  fit_true                     1170 non-null   int64 \n",
      " 50  fit_missing                  1170 non-null   int64 \n",
      " 51  midsole_soft                 1170 non-null   int64 \n",
      " 52  midsole_balanced             1170 non-null   int64 \n",
      " 53  midsole_firm                 1170 non-null   int64 \n",
      " 54  toebox_bad                   1170 non-null   int64 \n",
      " 55  toebox_decent                1170 non-null   int64 \n",
      " 56  toebox_good                  1170 non-null   int64 \n",
      " 57  heelpad_bad                  1170 non-null   int64 \n",
      " 58  heelpad_decent               1170 non-null   int64 \n",
      " 59  heelpad_good                 1170 non-null   int64 \n",
      " 60  outsole_bad                  1170 non-null   int64 \n",
      " 61  outsole_decent               1170 non-null   int64 \n",
      " 62  outsole_good                 1170 non-null   int64 \n",
      " 63  breath_breathable            1170 non-null   int64 \n",
      " 64  breath_moderate              1170 non-null   int64 \n",
      " 65  breath_warm                  1170 non-null   int64 \n",
      " 66  width_narrow                 1170 non-null   int64 \n",
      " 67  width_medium                 1170 non-null   int64 \n",
      " 68  width_wide                   1170 non-null   int64 \n",
      "dtypes: int64(35), object(2), str(32)\n",
      "memory usage: 630.8+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9df086d9",
   "metadata": {},
   "source": [
    "# Cleaning Toebox Width"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "d88dbf71",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Toebox width (4 uniques): \n",
      " ['-', 'Medium', 'Narrow', 'Wide']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Toebox width\n",
       "Medium    669\n",
       "Wide      179\n",
       "Narrow    170\n",
       "-         152\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Toebox width\"] = (\n",
    "    df[\"Toebox width\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "toebox_uniques = df[\"Toebox width\"].dropna().unique()\n",
    "# toebox_uniques.sort()\n",
    "toebox_uniques = sorted(toebox_uniques)\n",
    "print(f\"Toebox width ({len(toebox_uniques)} uniques): \\n\",toebox_uniques)\n",
    "\n",
    "df[\"Toebox width\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "8cb44aed",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>outsole_good</th>\n",
       "      <th>breath_breathable</th>\n",
       "      <th>breath_moderate</th>\n",
       "      <th>breath_warm</th>\n",
       "      <th>width_narrow</th>\n",
       "      <th>width_medium</th>\n",
       "      <th>width_wide</th>\n",
       "      <th>toeboxwidth_narrow</th>\n",
       "      <th>toeboxwidth_medium</th>\n",
       "      <th>toeboxwidth_wide</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</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>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</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>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 72 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... outsole_good breath_breathable breath_moderate  \\\n",
       "0  Heelmid/Forefoot  ...            0                 0               0   \n",
       "1      Mid/Forefoot  ...            1                 1               0   \n",
       "2  Heelmid/Forefoot  ...            0                 0               0   \n",
       "3              Heel  ...            0                 0               0   \n",
       "4  Heelmid/Forefoot  ...            1                 0               0   \n",
       "\n",
       "  breath_warm width_narrow width_medium width_wide toeboxwidth_narrow  \\\n",
       "0           0            1            0          0                  0   \n",
       "1           0            1            0          0                  0   \n",
       "2           1            1            0          0                  0   \n",
       "3           1            1            0          0                  0   \n",
       "4           1            1            0          0                  0   \n",
       "\n",
       "  toeboxwidth_medium toeboxwidth_wide  \n",
       "0                  0                0  \n",
       "1                  1                0  \n",
       "2                  0                0  \n",
       "3                  0                0  \n",
       "4                  1                0  \n",
       "\n",
       "[5 rows x 72 columns]"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tw_ohe = pd.get_dummies(df[\"Toebox width\"], prefix=\"toeboxwidth\").astype(int)\n",
    "\n",
    "for col in [\"toeboxwidth_Narrow\", \"toeboxwidth_Medium\", \"toeboxwidth_Wide\"]:\n",
    "    if col not in tw_ohe.columns:\n",
    "        tw_ohe[col] = 0\n",
    "\n",
    "tw_ohe = tw_ohe.rename(columns={\n",
    "    \"toeboxwidth_Narrow\": \"toeboxwidth_narrow\",\n",
    "    \"toeboxwidth_Medium\": \"toeboxwidth_medium\",\n",
    "    \"toeboxwidth_Wide\": \"toeboxwidth_wide\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, tw_ohe[[\"toeboxwidth_narrow\",\"toeboxwidth_medium\",\"toeboxwidth_wide\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "8615c63c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "toeboxwidth_narrow    170\n",
      "toeboxwidth_medium    669\n",
      "toeboxwidth_wide      179\n",
      "dtype: int64\n",
      "Missing toebox width rows: 152\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"toeboxwidth_narrow\",\"toeboxwidth_medium\",\"toeboxwidth_wide\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"toeboxwidth_narrow\",\"toeboxwidth_medium\",\"toeboxwidth_wide\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"toeboxwidth_narrow\",\"toeboxwidth_medium\",\"toeboxwidth_wide\"]].sum())\n",
    "print(\n",
    "    \"Missing toebox width rows:\",\n",
    "    int((df[[\"toeboxwidth_narrow\",\"toeboxwidth_medium\",\"toeboxwidth_wide\"]].sum(axis=1) == 0).sum())\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a0c1581",
   "metadata": {},
   "source": [
    "### Analisis Toebox Width\n",
    "\n",
    "Toebox width menggambarkan lebar ruang di bagian depan sepatu (area jari kaki).\n",
    "Fitur ini memengaruhi kenyamanan jari, risiko lecet, dan rasa sempit/lega saat berlari, terutama pada jarak jauh.\n",
    "\n",
    "Berbeda dengan Width / fit (lebar sepatu secara umum), toebox width fokus ke area jari kaki.\n",
    "\n",
    "Narrow\n",
    "\n",
    "Ruang jari sempit\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "kaki ramping\n",
    "\n",
    "pelari yang suka fit ketat\n",
    "\n",
    "Risiko: tekanan pada jari kaki, potensi lecet\n",
    "\n",
    "Medium\n",
    "\n",
    "Ruang jari standar\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "mayoritas pelari\n",
    "\n",
    "Catatan: ini adalah default di pasaran\n",
    "\n",
    "Wide\n",
    "\n",
    "Ruang jari lebih lega\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "kaki lebar\n",
    "\n",
    "pelari yang sering merasa jari tertekan\n",
    "\n",
    "Trade-off: bisa terasa kurang “locked-in” bagi kaki sempit"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e9b17fa9",
   "metadata": {},
   "source": [
    "# Cleaning Stiffness"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "f11dfa24",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stiffness (4 uniques): \n",
      " ['-', 'Flexible', 'Moderate', 'Stiff']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Stiffness\n",
       "Moderate    530\n",
       "Stiff       510\n",
       "Flexible    114\n",
       "-            16\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Stiffness\"] = (\n",
    "    df[\"Stiffness\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "stiffness_uniques = df[\"Stiffness\"].dropna().unique()\n",
    "# stiffness_uniques.sort()\n",
    "stiffness_uniques = sorted(stiffness_uniques)\n",
    "print(f\"Stiffness ({len(stiffness_uniques)} uniques): \\n\",stiffness_uniques)\n",
    "\n",
    "df[\"Stiffness\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "047339b7",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>breath_warm</th>\n",
       "      <th>width_narrow</th>\n",
       "      <th>width_medium</th>\n",
       "      <th>width_wide</th>\n",
       "      <th>toeboxwidth_narrow</th>\n",
       "      <th>toeboxwidth_medium</th>\n",
       "      <th>toeboxwidth_wide</th>\n",
       "      <th>stiff_flexible</th>\n",
       "      <th>stiff_moderate</th>\n",
       "      <th>stiff_stiff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</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",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</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",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 75 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... breath_warm width_narrow width_medium width_wide  \\\n",
       "0  Heelmid/Forefoot  ...           0            1            0          0   \n",
       "1      Mid/Forefoot  ...           0            1            0          0   \n",
       "2  Heelmid/Forefoot  ...           1            1            0          0   \n",
       "3              Heel  ...           1            1            0          0   \n",
       "4  Heelmid/Forefoot  ...           1            1            0          0   \n",
       "\n",
       "  toeboxwidth_narrow toeboxwidth_medium toeboxwidth_wide stiff_flexible  \\\n",
       "0                  0                  0                0              0   \n",
       "1                  0                  1                0              0   \n",
       "2                  0                  0                0              0   \n",
       "3                  0                  0                0              0   \n",
       "4                  0                  1                0              0   \n",
       "\n",
       "  stiff_moderate stiff_stiff  \n",
       "0              0           1  \n",
       "1              0           1  \n",
       "2              0           1  \n",
       "3              0           1  \n",
       "4              1           0  \n",
       "\n",
       "[5 rows x 75 columns]"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stiff_ohe = pd.get_dummies(df[\"Stiffness\"], prefix=\"stiff\").astype(int)\n",
    "\n",
    "for col in [\"stiff_Flexible\", \"stiff_Moderate\", \"stiff_Stiff\"]:\n",
    "    if col not in stiff_ohe.columns:\n",
    "        stiff_ohe[col] = 0\n",
    "\n",
    "stiff_ohe = stiff_ohe.rename(columns={\n",
    "    \"stiff_Flexible\": \"stiff_flexible\",\n",
    "    \"stiff_Moderate\": \"stiff_moderate\",\n",
    "    \"stiff_Stiff\": \"stiff_stiff\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, stiff_ohe[[\"stiff_flexible\",\"stiff_moderate\",\"stiff_stiff\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "3a78b017",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "stiff_flexible    114\n",
      "stiff_moderate    530\n",
      "stiff_stiff       510\n",
      "dtype: int64\n",
      "Missing stiffness rows: 16\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"stiff_flexible\",\"stiff_moderate\",\"stiff_stiff\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"stiff_flexible\",\"stiff_moderate\",\"stiff_stiff\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"stiff_flexible\",\"stiff_moderate\",\"stiff_stiff\"]].sum())\n",
    "print(\n",
    "    \"Missing stiffness rows:\",\n",
    "    int((df[[\"stiff_flexible\",\"stiff_moderate\",\"stiff_stiff\"]].sum(axis=1) == 0).sum())\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f6bd750",
   "metadata": {},
   "source": [
    "### Analisis Stiffness\n",
    "Stiffness menggambarkan tingkat kekakuan sepatu secara keseluruhan, terutama saat sepatu ditekuk atau diberi beban.\n",
    "Fitur ini memengaruhi fleksibilitas langkah, responsivitas, dan kenyamanan.\n",
    "\n",
    "Berbeda dengan torsional rigidity atau heel counter stiffness, stiffness di sini bersifat global.\n",
    "\n",
    "Flexible\n",
    "\n",
    "Sepatu mudah ditekuk\n",
    "\n",
    "Memberikan rasa:\n",
    "\n",
    "natural\n",
    "\n",
    "bebas\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "easy run\n",
    "\n",
    "pelari yang suka feel santai\n",
    "\n",
    "Trade-off: stabilitas & responsivitas lebih rendah\n",
    "\n",
    "Moderate\n",
    "\n",
    "Kekakuan seimbang\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "daily running\n",
    "\n",
    "penggunaan serbaguna\n",
    "\n",
    "Catatan: ini kategori paling aman & umum\n",
    "\n",
    "Stiff\n",
    "\n",
    "Sepatu kaku dan stabil\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "tempo run\n",
    "\n",
    "sepatu dengan plate\n",
    "\n",
    "lari cepat\n",
    "\n",
    "Trade-off: kurang nyaman untuk pace santai atau jarak jauh"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01d8345b",
   "metadata": {},
   "source": [
    "# Cleaning Torsional rigidity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "03cdb82f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Torsional rigidity (4 uniques): \n",
      " ['-', 'Flexible', 'Moderate', 'Stiff']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Torsional rigidity\n",
       "Stiff       610\n",
       "Moderate    368\n",
       "Flexible    174\n",
       "-            18\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Torsional rigidity\"] = (\n",
    "    df[\"Torsional rigidity\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "torsional_rigidity_uniques = df[\"Torsional rigidity\"].dropna().unique()\n",
    "# torsional_rigidity_uniques.sort()\n",
    "torsional_rigidity_uniques = sorted(torsional_rigidity_uniques)\n",
    "print(f\"Torsional rigidity ({len(torsional_rigidity_uniques)} uniques): \\n\",torsional_rigidity_uniques)\n",
    "\n",
    "df[\"Torsional rigidity\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "34f7fa79",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>width_wide</th>\n",
       "      <th>toeboxwidth_narrow</th>\n",
       "      <th>toeboxwidth_medium</th>\n",
       "      <th>toeboxwidth_wide</th>\n",
       "      <th>stiff_flexible</th>\n",
       "      <th>stiff_moderate</th>\n",
       "      <th>stiff_stiff</th>\n",
       "      <th>torsion_flexible</th>\n",
       "      <th>torsion_moderate</th>\n",
       "      <th>torsion_stiff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</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>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 78 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... width_wide toeboxwidth_narrow toeboxwidth_medium  \\\n",
       "0  Heelmid/Forefoot  ...          0                  0                  0   \n",
       "1      Mid/Forefoot  ...          0                  0                  1   \n",
       "2  Heelmid/Forefoot  ...          0                  0                  0   \n",
       "3              Heel  ...          0                  0                  0   \n",
       "4  Heelmid/Forefoot  ...          0                  0                  1   \n",
       "\n",
       "  toeboxwidth_wide stiff_flexible stiff_moderate stiff_stiff torsion_flexible  \\\n",
       "0                0              0              0           1                0   \n",
       "1                0              0              0           1                0   \n",
       "2                0              0              0           1                1   \n",
       "3                0              0              0           1                1   \n",
       "4                0              0              1           0                1   \n",
       "\n",
       "  torsion_moderate torsion_stiff  \n",
       "0                0             1  \n",
       "1                1             0  \n",
       "2                0             0  \n",
       "3                0             0  \n",
       "4                0             0  \n",
       "\n",
       "[5 rows x 78 columns]"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tors_ohe = pd.get_dummies(df[\"Torsional rigidity\"], prefix=\"torsion\").astype(int)\n",
    "\n",
    "for col in [\"torsion_Flexible\", \"torsion_Moderate\", \"torsion_Stiff\"]:\n",
    "    if col not in tors_ohe.columns:\n",
    "        tors_ohe[col] = 0\n",
    "\n",
    "tors_ohe = tors_ohe.rename(columns={\n",
    "    \"torsion_Flexible\": \"torsion_flexible\",\n",
    "    \"torsion_Moderate\": \"torsion_moderate\",\n",
    "    \"torsion_Stiff\": \"torsion_stiff\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, tors_ohe[[\"torsion_flexible\",\"torsion_moderate\",\"torsion_stiff\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "ef8e64fa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torsion_flexible    174\n",
      "torsion_moderate    368\n",
      "torsion_stiff       610\n",
      "dtype: int64\n",
      "Missing torsional rigidity rows: 18\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"torsion_flexible\",\"torsion_moderate\",\"torsion_stiff\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"torsion_flexible\",\"torsion_moderate\",\"torsion_stiff\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"torsion_flexible\",\"torsion_moderate\",\"torsion_stiff\"]].sum())\n",
    "print(\n",
    "    \"Missing torsional rigidity rows:\",\n",
    "    int((df[[\"torsion_flexible\",\"torsion_moderate\",\"torsion_stiff\"]].sum(axis=1) == 0).sum())\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3236dda7",
   "metadata": {},
   "source": [
    "### Analisis Torsional Rigidity\n",
    "\n",
    "Torsional rigidity menggambarkan seberapa sulit sepatu dipuntir (twist) dari depan ke belakang.\n",
    "Fitur ini berhubungan dengan stabilitas lateral, kontrol kaki, dan dukungan saat mendarat.\n",
    "\n",
    "Berbeda dengan overall stiffness (tekuk depan-belakang), torsional rigidity fokus pada puntiran samping.\n",
    "\n",
    "Flexible\n",
    "\n",
    "Sepatu mudah dipuntir\n",
    "\n",
    "Memberikan feel:\n",
    "\n",
    "natural\n",
    "\n",
    "bebas\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "pelari dengan gait stabil\n",
    "\n",
    "easy run\n",
    "\n",
    "Trade-off: stabilitas lebih rendah\n",
    "\n",
    "Moderate\n",
    "\n",
    "Tingkat puntiran seimbang\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "daily running\n",
    "\n",
    "mayoritas pelari\n",
    "\n",
    "Catatan: kategori paling aman & umum\n",
    "\n",
    "Stiff\n",
    "\n",
    "Sepatu sulit dipuntir\n",
    "\n",
    "Memberikan:\n",
    "\n",
    "stabilitas tinggi\n",
    "\n",
    "kontrol tambahan\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "pelari yang butuh support\n",
    "\n",
    "sepatu berstruktur / plated\n",
    "\n",
    "Trade-off: feel lebih kaku"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8a7b505",
   "metadata": {},
   "source": [
    "# Cleaning Heel counter stiffness"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "b617da2f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Heel counter stiffness (4 uniques): \n",
      " ['-', 'Flexible', 'Moderate', 'Stiff']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Heel counter stiffness\n",
       "Moderate    419\n",
       "Stiff       368\n",
       "Flexible    351\n",
       "-            32\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Heel counter stiffness\"] = (\n",
    "    df[\"Heel counter stiffness\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "heel_counter_stiffness_uniques = df[\"Heel counter stiffness\"].dropna().unique()\n",
    "# heel_counter_stiffness_uniques.sort()\n",
    "heel_counter_stiffness_uniques = sorted(heel_counter_stiffness_uniques)\n",
    "print(f\"Heel counter stiffness ({len(heel_counter_stiffness_uniques)} uniques): \\n\",heel_counter_stiffness_uniques)\n",
    "\n",
    "df[\"Heel counter stiffness\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "f477af46",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>toeboxwidth_wide</th>\n",
       "      <th>stiff_flexible</th>\n",
       "      <th>stiff_moderate</th>\n",
       "      <th>stiff_stiff</th>\n",
       "      <th>torsion_flexible</th>\n",
       "      <th>torsion_moderate</th>\n",
       "      <th>torsion_stiff</th>\n",
       "      <th>heelcounter_flexible</th>\n",
       "      <th>heelcounter_moderate</th>\n",
       "      <th>heelcounter_stiff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 81 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... toeboxwidth_wide stiff_flexible stiff_moderate  \\\n",
       "0  Heelmid/Forefoot  ...                0              0              0   \n",
       "1      Mid/Forefoot  ...                0              0              0   \n",
       "2  Heelmid/Forefoot  ...                0              0              0   \n",
       "3              Heel  ...                0              0              0   \n",
       "4  Heelmid/Forefoot  ...                0              0              1   \n",
       "\n",
       "  stiff_stiff torsion_flexible torsion_moderate torsion_stiff  \\\n",
       "0           1                0                0             1   \n",
       "1           1                0                1             0   \n",
       "2           1                1                0             0   \n",
       "3           1                1                0             0   \n",
       "4           0                1                0             0   \n",
       "\n",
       "  heelcounter_flexible heelcounter_moderate heelcounter_stiff  \n",
       "0                    1                    0                 0  \n",
       "1                    0                    1                 0  \n",
       "2                    1                    0                 0  \n",
       "3                    0                    1                 0  \n",
       "4                    1                    0                 0  \n",
       "\n",
       "[5 rows x 81 columns]"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hc_ohe = pd.get_dummies(df[\"Heel counter stiffness\"], prefix=\"heelcounter\").astype(int)\n",
    "\n",
    "for col in [\"heelcounter_Flexible\", \"heelcounter_Moderate\", \"heelcounter_Stiff\"]:\n",
    "    if col not in hc_ohe.columns:\n",
    "        hc_ohe[col] = 0\n",
    "\n",
    "hc_ohe = hc_ohe.rename(columns={\n",
    "    \"heelcounter_Flexible\": \"heelcounter_flexible\",\n",
    "    \"heelcounter_Moderate\": \"heelcounter_moderate\",\n",
    "    \"heelcounter_Stiff\": \"heelcounter_stiff\"\n",
    "})\n",
    "\n",
    "df = pd.concat([df, hc_ohe[[\"heelcounter_flexible\",\"heelcounter_moderate\",\"heelcounter_stiff\"]]], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "9b91e5e5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "heelcounter_flexible    351\n",
      "heelcounter_moderate    419\n",
      "heelcounter_stiff       368\n",
      "dtype: int64\n",
      "Missing heel counter rows: 32\n"
     ]
    }
   ],
   "source": [
    "# hanya 0 / 1\n",
    "for c in [\"heelcounter_flexible\",\"heelcounter_moderate\",\"heelcounter_stiff\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})\n",
    "\n",
    "# single-label atau missing\n",
    "assert df[[\"heelcounter_flexible\",\"heelcounter_moderate\",\"heelcounter_stiff\"]].sum(axis=1).le(1).all()\n",
    "\n",
    "print(df[[\"heelcounter_flexible\",\"heelcounter_moderate\",\"heelcounter_stiff\"]].sum())\n",
    "print(\n",
    "    \"Missing heel counter rows:\",\n",
    "    int((df[[\"heelcounter_flexible\",\"heelcounter_moderate\",\"heelcounter_stiff\"]].sum(axis=1) == 0).sum())\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0528c1ca",
   "metadata": {},
   "source": [
    "### Analisis Heel Counter Stiffness\n",
    "\n",
    "Heel counter stiffness menggambarkan tingkat kekakuan struktur di bagian tumit belakang sepatu (heel counter), yang berfungsi menjaga tumit tetap stabil dan terkunci saat berlari.\n",
    "\n",
    "Fitur ini berpengaruh pada stabilitas tumit, kontrol kaki, dan rasa aman saat mendarat, terutama untuk pelari heel strike atau yang membutuhkan support tambahan.\n",
    "\n",
    "Flexible\n",
    "\n",
    "Heel counter mudah ditekan\n",
    "\n",
    "Memberikan rasa:\n",
    "\n",
    "lebih nyaman\n",
    "\n",
    "lebih natural\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "pelari dengan gait stabil\n",
    "\n",
    "sepatu santai / fleksibel\n",
    "\n",
    "Trade-off: stabilitas tumit lebih rendah\n",
    "\n",
    "Moderate\n",
    "\n",
    "Kekakuan seimbang\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "daily running\n",
    "\n",
    "mayoritas pelari\n",
    "\n",
    "Catatan: ini kategori paling aman & umum\n",
    "\n",
    "Stiff\n",
    "\n",
    "Heel counter kaku dan kokoh\n",
    "\n",
    "Memberikan:\n",
    "\n",
    "stabilitas tumit tinggi\n",
    "\n",
    "rasa “locked-in”\n",
    "\n",
    "Cocok untuk:\n",
    "\n",
    "pelari yang butuh support\n",
    "\n",
    "sepatu berstruktur / plated\n",
    "\n",
    "Trade-off: bisa terasa kurang nyaman bagi sebagian orang"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "515d8b22",
   "metadata": {},
   "source": [
    "# Cleaning Widths available"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "3b3f7bec",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Widths available (11 uniques): \n",
      " ['Narrow Normal Wide X-Wide', 'Narrownormal', 'Narrownormalwide', 'Narrownormalwidex-Wide', 'Narrownormalx-Wide', 'Normal', 'Normal Wide', 'Normal Wide X-Wide', 'Normalwide', 'Normalwidex-Wide', 'Normalx-Wide']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Widths available\n",
       "Normal                       537\n",
       "Normalwide                   353\n",
       "Normalwidex-Wide             166\n",
       "Narrownormalwidex-Wide        68\n",
       "Narrownormal                  19\n",
       "Normalx-Wide                  18\n",
       "Narrownormalwide               4\n",
       "Normal Wide X-Wide             2\n",
       "Narrow Normal Wide X-Wide      1\n",
       "Normal Wide                    1\n",
       "Narrownormalx-Wide             1\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Widths available\"] = (\n",
    "    df[\"Widths available\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "widths_available_uniques = df[\"Widths available\"].dropna().unique()\n",
    "# widths_available_uniques.sort()\n",
    "widths_available_uniques = sorted(widths_available_uniques)\n",
    "print(f\"Widths available ({len(widths_available_uniques)} uniques): \\n\",widths_available_uniques)\n",
    "\n",
    "df[\"Widths available\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "23a2a180",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "UNMAPPED Widths available values:\n",
      " Series([], Name: count, dtype: int64)\n"
     ]
    }
   ],
   "source": [
    "wa_map = {\n",
    "    \"Normal\": \"Normal\",\n",
    "    \"Normalwide\": \"Normal|Wide\",\n",
    "    \"Normalwidex-Wide\": \"Normal|Wide|X-Wide\",\n",
    "    \"Narrownormalwidex-Wide\": \"Narrow|Normal|Wide|X-Wide\",\n",
    "    \"Normalx-Wide\": \"Normal|X-Wide\",\n",
    "    \"Narrownormal\": \"Narrow|Normal\",\n",
    "    \"Narrownormalwide\": \"Narrow|Normal|Wide\",\n",
    "    \"Normal Wide X-Wide\": \"Normal|Wide|X-Wide\",\n",
    "    \"Narrow Normal Wide X-Wide\": \"Narrow|Normal|Wide|X-Wide\",\n",
    "    \"Normal Wide\": \"Normal|Wide\",\n",
    "    \"Narrownormalx-Wide\": \"Narrow|Normal|X-Wide\",\n",
    "}\n",
    "\n",
    "df[\"widthavail_norm\"] = df[\"Widths available\"].map(wa_map)\n",
    "\n",
    "unmapped = df[df[\"widthavail_norm\"].isna()][\"Widths available\"].value_counts()\n",
    "print(\"UNMAPPED Widths available values:\\n\", unmapped)\n",
    "assert df[\"widthavail_norm\"].notna().all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "211dba05",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Widths available - norm: (8) uniques\n",
      " <StringArray>\n",
      "[              'Normal|Wide',                    'Normal',\n",
      " 'Narrow|Normal|Wide|X-Wide',             'Normal|X-Wide',\n",
      "        'Narrow|Normal|Wide',        'Normal|Wide|X-Wide',\n",
      "             'Narrow|Normal',      'Narrow|Normal|X-Wide']\n",
      "Length: 8, dtype: str\n",
      "widthavail_norm\n",
      "Normal                       537\n",
      "Normal|Wide                  354\n",
      "Normal|Wide|X-Wide           168\n",
      "Narrow|Normal|Wide|X-Wide     69\n",
      "Narrow|Normal                 19\n",
      "Normal|X-Wide                 18\n",
      "Narrow|Normal|Wide             4\n",
      "Narrow|Normal|X-Wide           1\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "wa_norm_unique = df[\"widthavail_norm\"].dropna().unique()\n",
    "print(f'Widths available - norm: ({len(wa_norm_unique)}) uniques\\n', wa_norm_unique)\n",
    "\n",
    "print(df[\"widthavail_norm\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "b63b2f3e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"widthavail_list\"] = df[\"widthavail_norm\"].str.split(\"|\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "17dee763",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>torsion_stiff</th>\n",
       "      <th>heelcounter_flexible</th>\n",
       "      <th>heelcounter_moderate</th>\n",
       "      <th>heelcounter_stiff</th>\n",
       "      <th>widthavail_norm</th>\n",
       "      <th>widthavail_list</th>\n",
       "      <th>widthavail_narrow</th>\n",
       "      <th>widthavail_normal</th>\n",
       "      <th>widthavail_wide</th>\n",
       "      <th>widthavail_xwide</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Normal|Wide</td>\n",
       "      <td>[Normal, Wide]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Normal</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Normal</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Normal</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Normal</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 87 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... torsion_stiff heelcounter_flexible  \\\n",
       "0  Heelmid/Forefoot  ...             1                    1   \n",
       "1      Mid/Forefoot  ...             0                    0   \n",
       "2  Heelmid/Forefoot  ...             0                    1   \n",
       "3              Heel  ...             0                    0   \n",
       "4  Heelmid/Forefoot  ...             0                    1   \n",
       "\n",
       "  heelcounter_moderate heelcounter_stiff widthavail_norm widthavail_list  \\\n",
       "0                    0                 0     Normal|Wide  [Normal, Wide]   \n",
       "1                    1                 0          Normal        [Normal]   \n",
       "2                    0                 0          Normal        [Normal]   \n",
       "3                    1                 0          Normal        [Normal]   \n",
       "4                    0                 0          Normal        [Normal]   \n",
       "\n",
       "  widthavail_narrow widthavail_normal widthavail_wide widthavail_xwide  \n",
       "0                 0                 1               1                0  \n",
       "1                 0                 1               0                0  \n",
       "2                 0                 1               0                0  \n",
       "3                 0                 1               0                0  \n",
       "4                 0                 1               0                0  \n",
       "\n",
       "[5 rows x 87 columns]"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wa_exploded = df[\"widthavail_list\"].explode()\n",
    "\n",
    "wa_ohe = (\n",
    "    pd.crosstab(wa_exploded.index, wa_exploded)\n",
    "    .reindex(df.index, fill_value=0)\n",
    ")\n",
    "\n",
    "wa_ohe = wa_ohe.rename(columns={\n",
    "    \"Narrow\": \"widthavail_narrow\",\n",
    "    \"Normal\": \"widthavail_normal\",\n",
    "    \"Wide\": \"widthavail_wide\",\n",
    "    \"X-Wide\": \"widthavail_xwide\"\n",
    "})\n",
    "\n",
    "for col in [\"widthavail_narrow\", \"widthavail_normal\", \"widthavail_wide\", \"widthavail_xwide\"]:\n",
    "    if col not in wa_ohe.columns:\n",
    "        wa_ohe[col] = 0\n",
    "\n",
    "wa_ohe = wa_ohe[[\"widthavail_narrow\",\"widthavail_normal\",\"widthavail_wide\",\"widthavail_xwide\"]]\n",
    "\n",
    "df = pd.concat([df, wa_ohe], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "8ba40a97",
   "metadata": {},
   "outputs": [],
   "source": [
    "for c in [\"widthavail_narrow\",\"widthavail_normal\",\"widthavail_wide\",\"widthavail_xwide\"]:\n",
    "    assert set(df[c].unique()).issubset({0, 1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "0d75845f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "narrow sum: 93\n",
      "normal sum: 1170\n",
      "wide sum: 595\n",
      "xwide sum: 256\n",
      "   Widths available widthavail_norm  widthavail_normal  widthavail_wide  \\\n",
      "0        Normalwide     Normal|Wide                  1                1   \n",
      "7        Normalwide     Normal|Wide                  1                1   \n",
      "10       Normalwide     Normal|Wide                  1                1   \n",
      "11       Normalwide     Normal|Wide                  1                1   \n",
      "12       Normalwide     Normal|Wide                  1                1   \n",
      "13       Normalwide     Normal|Wide                  1                1   \n",
      "14       Normalwide     Normal|Wide                  1                1   \n",
      "15       Normalwide     Normal|Wide                  1                1   \n",
      "16       Normalwide     Normal|Wide                  1                1   \n",
      "17       Normalwide     Normal|Wide                  1                1   \n",
      "\n",
      "    widthavail_xwide  widthavail_narrow  \n",
      "0                  0                  0  \n",
      "7                  0                  0  \n",
      "10                 0                  0  \n",
      "11                 0                  0  \n",
      "12                 0                  0  \n",
      "13                 0                  0  \n",
      "14                 0                  0  \n",
      "15                 0                  0  \n",
      "16                 0                  0  \n",
      "17                 0                  0  \n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"narrow sum:\", int(df[\"widthavail_narrow\"].sum()))\n",
    "print(\"normal sum:\", int(df[\"widthavail_normal\"].sum()))\n",
    "print(\"wide sum:\", int(df[\"widthavail_wide\"].sum()))\n",
    "print(\"xwide sum:\", int(df[\"widthavail_xwide\"].sum()))\n",
    "\n",
    "print(df[df[\"Widths available\"].isin([\"Normalwide\",\"Normalwidex-Wide\"])][\n",
    "    [\"Widths available\",\"widthavail_norm\",\"widthavail_normal\",\"widthavail_wide\",\"widthavail_xwide\",\"widthavail_narrow\"]\n",
    "].head(10))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a93dbbd",
   "metadata": {},
   "source": [
    "### Analisis Widths Available\n",
    "\n",
    "Widths available menjelaskan opsi lebar yang tersedia untuk model sepatu tersebut (bukan “fit feel”), misalnya hanya Normal, atau tersedia juga Wide dan X-Wide.\n",
    "\n",
    "Berbeda dengan Width / fit yang menggambarkan rasa lebar sepatu secara umum, Widths available itu varian produk yang dijual.\n",
    "\n",
    "Kategori yang relevan\n",
    "\n",
    "Narrow: opsi lebar sempit tersedia\n",
    "\n",
    "Normal: opsi standar tersedia\n",
    "\n",
    "Wide: opsi lebar tersedia\n",
    "\n",
    "X-Wide: opsi ekstra lebar tersedia"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c875704",
   "metadata": {},
   "source": [
    "# Cleaning Season"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "cde921aa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Season (4 uniques): \n",
      " ['-', 'All Seasons', 'Summerall Seasons', 'Winter']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Season\n",
       "All Seasons          741\n",
       "Summerall Seasons    347\n",
       "-                     63\n",
       "Winter                19\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Season\"] = (\n",
    "    df[\"Season\"]\n",
    "    .astype(str)\n",
    "    .str.strip()\n",
    "    .str.replace(r\"\\s+\", \" \", regex=True)\n",
    "    .str.title()\n",
    ")\n",
    "\n",
    "season_uniques = df[\"Season\"].dropna().unique()\n",
    "# season_uniques.sort()\n",
    "season_uniques = sorted(season_uniques)\n",
    "print(f\"Season ({len(season_uniques)} uniques): \\n\",season_uniques)\n",
    "\n",
    "df[\"Season\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "0e512dee",
   "metadata": {},
   "outputs": [],
   "source": [
    "season_map = {\n",
    "    \"All Seasons\": \"All\",\n",
    "    \"Summerall Seasons\": \"Summer|All\",\n",
    "    \"Winter\": \"Winter\",\n",
    "    \"-\": pd.NA,\n",
    "}\n",
    "\n",
    "df[\"season_norm\"] = df[\"Season\"].map(season_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "5652f560",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "UNMAPPED Season values (should be empty):\n",
      " Series([], Name: count, dtype: int64)\n"
     ]
    }
   ],
   "source": [
    "unmapped = df[df[\"season_norm\"].isna() & df[\"Season\"].ne(\"-\")][\"Season\"].value_counts()\n",
    "print(\"UNMAPPED Season values (should be empty):\\n\", unmapped)\n",
    "assert unmapped.empty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "5ec9108f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Season - norm: (4) uniques\n",
      " <StringArray>\n",
      "[nan, 'Summer|All', 'All', 'Winter']\n",
      "Length: 4, dtype: str\n",
      "season_norm\n",
      "All           741\n",
      "Summer|All    347\n",
      "Winter         19\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "season_norm_unique = df[\"season_norm\"].unique()\n",
    "print(f'Season - norm: ({len(season_norm_unique)}) uniques\\n', season_norm_unique)\n",
    "print(df[\"season_norm\"].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "1face7ad",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>widthavail_list</th>\n",
       "      <th>widthavail_narrow</th>\n",
       "      <th>widthavail_normal</th>\n",
       "      <th>widthavail_wide</th>\n",
       "      <th>widthavail_xwide</th>\n",
       "      <th>season_norm</th>\n",
       "      <th>season_list</th>\n",
       "      <th>season_all</th>\n",
       "      <th>season_summer</th>\n",
       "      <th>season_winter</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Normal, Wide]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Summer|All</td>\n",
       "      <td>[Summer, All]</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Normal]</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 92 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... widthavail_list widthavail_narrow widthavail_normal  \\\n",
       "0  Heelmid/Forefoot  ...  [Normal, Wide]                 0                 1   \n",
       "1      Mid/Forefoot  ...        [Normal]                 0                 1   \n",
       "2  Heelmid/Forefoot  ...        [Normal]                 0                 1   \n",
       "3              Heel  ...        [Normal]                 0                 1   \n",
       "4  Heelmid/Forefoot  ...        [Normal]                 0                 1   \n",
       "\n",
       "  widthavail_wide widthavail_xwide season_norm    season_list season_all  \\\n",
       "0               1                0         NaN            NaN          0   \n",
       "1               0                0  Summer|All  [Summer, All]          1   \n",
       "2               0                0         All          [All]          1   \n",
       "3               0                0         All          [All]          1   \n",
       "4               0                0         All          [All]          1   \n",
       "\n",
       "  season_summer season_winter  \n",
       "0             0             0  \n",
       "1             1             0  \n",
       "2             0             0  \n",
       "3             0             0  \n",
       "4             0             0  \n",
       "\n",
       "[5 rows x 92 columns]"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"season_list\"] = df[\"season_norm\"].str.split(\"|\")\n",
    "\n",
    "season_exploded = df[\"season_list\"].explode()\n",
    "\n",
    "season_ohe = (\n",
    "    pd.crosstab(season_exploded.index, season_exploded)\n",
    "    .reindex(df.index, fill_value=0)\n",
    ")\n",
    "\n",
    "season_ohe = season_ohe.rename(columns={\n",
    "    \"All\": \"season_all\",\n",
    "    \"Summer\": \"season_summer\",\n",
    "    \"Winter\": \"season_winter\"\n",
    "})\n",
    "\n",
    "for col in [\"season_all\",\"season_summer\",\"season_winter\"]:\n",
    "    if col not in season_ohe.columns:\n",
    "        season_ohe[col] = 0\n",
    "\n",
    "season_ohe = season_ohe[[\"season_all\",\"season_summer\",\"season_winter\"]]\n",
    "\n",
    "df = pd.concat([df, season_ohe], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a18946b6",
   "metadata": {},
   "source": [
    "jujur janggal temen temen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "c1515be9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows: 1170\n",
      "all seasons sum: 1088\n",
      "summer sum: 347\n",
      "winter sum: 19\n"
     ]
    }
   ],
   "source": [
    "print(\"Rows:\", len(df))\n",
    "print(\"all seasons sum:\", int(df[\"season_all\"].sum()))\n",
    "print(\"summer sum:\", int(df[\"season_summer\"].sum()))\n",
    "print(\"winter sum:\", int(df[\"season_winter\"].sum()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "80f95641",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               Season season_norm  season_all  season_summer  season_winter\n",
      "1   Summerall Seasons  Summer|All           1              1              0\n",
      "7   Summerall Seasons  Summer|All           1              1              0\n",
      "9   Summerall Seasons  Summer|All           1              1              0\n",
      "10  Summerall Seasons  Summer|All           1              1              0\n",
      "11  Summerall Seasons  Summer|All           1              1              0\n"
     ]
    }
   ],
   "source": [
    "print(df[df[\"Season\"]==\"Summerall Seasons\"][\n",
    "    [\"Season\",\"season_norm\",\"season_all\",\"season_summer\",\"season_winter\"]\n",
    "].head())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e8a94b15",
   "metadata": {},
   "source": [
    "# Split Weight lab Weight brand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "cf9c609f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.int64(0)"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cek \"-\" dan null\n",
    "mask_missing = (\n",
    "    df[\"Weight lab Weight brand\"].isna() |\n",
    "    (df[\"Weight lab Weight brand\"].astype(str).str.strip() == \"-\")\n",
    ")\n",
    "mask_missing.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "0ff4d1f0",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>widthavail_xwide</th>\n",
       "      <th>season_norm</th>\n",
       "      <th>season_list</th>\n",
       "      <th>season_all</th>\n",
       "      <th>season_summer</th>\n",
       "      <th>season_winter</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>Summer|All</td>\n",
       "      <td>[Summer, All]</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>All</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 96 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... widthavail_xwide season_norm    season_list  \\\n",
       "0  Heelmid/Forefoot  ...                0         NaN            NaN   \n",
       "1      Mid/Forefoot  ...                0  Summer|All  [Summer, All]   \n",
       "2  Heelmid/Forefoot  ...                0         All          [All]   \n",
       "3              Heel  ...                0         All          [All]   \n",
       "4  Heelmid/Forefoot  ...                0         All          [All]   \n",
       "\n",
       "  season_all season_summer season_winter weight_lab_oz weight_lab_g  \\\n",
       "0          0             0             0           7.9          225   \n",
       "1          1             1             0          10.7          304   \n",
       "2          1             0             0          11.9          336   \n",
       "3          1             0             0          12.6          356   \n",
       "4          1             0             0          12.3          348   \n",
       "\n",
       "  weight_brand_oz weight_brand_g  \n",
       "0             8.1          230.0  \n",
       "1            10.9          309.0  \n",
       "2            11.5          327.0  \n",
       "3            12.4          352.0  \n",
       "4            12.2          345.0  \n",
       "\n",
       "[5 rows x 96 columns]"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ambil angka pakai regex\n",
    "weight = df[\"Weight lab Weight brand\"].str.findall(r\"[\\d.]+\")\n",
    "\n",
    "# Ubah jadi 4 kolom\n",
    "df[[\"weight_lab_oz\", \"weight_lab_g\", \"weight_brand_oz\", \"weight_brand_g\"]] = (\n",
    "    pd.DataFrame(weight.tolist(), index=df.index)\n",
    ")\n",
    "\n",
    "# ubah ke numeric\n",
    "for col in [\"weight_lab_oz\", \"weight_lab_g\", \"weight_brand_oz\", \"weight_brand_g\"]:\n",
    "    df[col] = pd.to_numeric(df[col], errors=\"coerce\")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac8090cb",
   "metadata": {},
   "source": [
    "# Split Drop lab Drop Brand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "07739c09",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.int64(0)"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cek \"-\" dan null\n",
    "mask_missing = (\n",
    "    df[\"Drop lab Drop brand\"].isna() |\n",
    "    (df[\"Drop lab Drop brand\"].astype(str).str.strip() == \"-\")\n",
    ")\n",
    "mask_missing.sum()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "3b2af74a",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>season_list</th>\n",
       "      <th>season_all</th>\n",
       "      <th>season_summer</th>\n",
       "      <th>season_winter</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[Summer, All]</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>[All]</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 98 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ...    season_list season_all season_summer  \\\n",
       "0  Heelmid/Forefoot  ...            NaN          0             0   \n",
       "1      Mid/Forefoot  ...  [Summer, All]          1             1   \n",
       "2  Heelmid/Forefoot  ...          [All]          1             0   \n",
       "3              Heel  ...          [All]          1             0   \n",
       "4  Heelmid/Forefoot  ...          [All]          1             0   \n",
       "\n",
       "  season_winter weight_lab_oz weight_lab_g weight_brand_oz weight_brand_g  \\\n",
       "0             0           7.9          225             8.1          230.0   \n",
       "1             0          10.7          304            10.9          309.0   \n",
       "2             0          11.9          336            11.5          327.0   \n",
       "3             0          12.6          356            12.4          352.0   \n",
       "4             0          12.3          348            12.2          345.0   \n",
       "\n",
       "  drop_lab_mm drop_brand_mm  \n",
       "0         9.4          10.0  \n",
       "1         7.7           8.0  \n",
       "2         8.9          10.0  \n",
       "3        10.6          11.0  \n",
       "4         9.9          10.0  \n",
       "\n",
       "[5 rows x 98 columns]"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ambil angka pakai regex\n",
    "drop = df[\"Drop lab Drop brand\"].str.findall(r\"[\\d.]+\")\n",
    "\n",
    "# Ubah jadi 2 kolom\n",
    "df[[\"drop_lab_mm\", \"drop_brand_mm\"]] = (\n",
    "    pd.DataFrame(drop.tolist(), index=df.index)\n",
    ")\n",
    "\n",
    "# ubah ke numeric\n",
    "for col in [\"drop_lab_mm\", \"drop_brand_mm\"]:\n",
    "    df[col] = pd.to_numeric(df[col], errors=\"coerce\")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "4e164df8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = df.drop(labels=\"drop_brand\", axis=1)\n",
    "# df = df.drop(labels=\"drop_lab\", axis=1)\n",
    "# df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bda80a11",
   "metadata": {},
   "source": [
    "# Split Heel lab dan Heel brand"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "27cb847d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.int64(0)"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cek \"-\" dan null\n",
    "mask_missing = (\n",
    "    df[\"Heel lab Heel brand\"].isna() |\n",
    "    (df[\"Heel lab Heel brand\"].astype(str).str.strip() == \"-\")\n",
    ")\n",
    "mask_missing.sum()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "dacdb07a",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>season_summer</th>\n",
       "      <th>season_winter</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "      <th>heel_lab_mm</th>\n",
       "      <th>heel_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.4</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.3</td>\n",
       "      <td>32.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>33.3</td>\n",
       "      <td>32.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>31.8</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.6</td>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 100 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... season_summer season_winter weight_lab_oz  \\\n",
       "0  Heelmid/Forefoot  ...             0             0           7.9   \n",
       "1      Mid/Forefoot  ...             1             0          10.7   \n",
       "2  Heelmid/Forefoot  ...             0             0          11.9   \n",
       "3              Heel  ...             0             0          12.6   \n",
       "4  Heelmid/Forefoot  ...             0             0          12.3   \n",
       "\n",
       "  weight_lab_g weight_brand_oz weight_brand_g drop_lab_mm drop_brand_mm  \\\n",
       "0          225             8.1          230.0         9.4          10.0   \n",
       "1          304            10.9          309.0         7.7           8.0   \n",
       "2          336            11.5          327.0         8.9          10.0   \n",
       "3          356            12.4          352.0        10.6          11.0   \n",
       "4          348            12.2          345.0         9.9          10.0   \n",
       "\n",
       "  heel_lab_mm heel_brand_mm  \n",
       "0        32.4          36.0  \n",
       "1        34.3          32.5  \n",
       "2        33.3          32.5  \n",
       "3        31.8          32.0  \n",
       "4        32.6          34.0  \n",
       "\n",
       "[5 rows x 100 columns]"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ambil angka pakai regex\n",
    "Heel = df[\"Heel lab Heel brand\"].str.findall(r\"[\\d.]+\")\n",
    "\n",
    "# Ubah jadi 2 kolom\n",
    "df[[\"heel_lab_mm\", \"heel_brand_mm\"]] = (\n",
    "    pd.DataFrame(Heel.tolist(), index=df.index)\n",
    ")\n",
    "\n",
    "# ubah ke numeric\n",
    "for col in [\"heel_lab_mm\", \"heel_brand_mm\"]:\n",
    "    df[col] = pd.to_numeric(df[col], errors=\"coerce\")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5facbd7",
   "metadata": {},
   "source": [
    "# Split Forefoot lab dan Forefoot brand\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "0fca0f24",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.int64(0)"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cek \"-\" dan null\n",
    "mask_missing = (\n",
    "    df[\"Forefoot lab Forefoot brand\"].isna() |\n",
    "    (df[\"Forefoot lab Forefoot brand\"].astype(str).str.strip() == \"-\")\n",
    ")\n",
    "mask_missing.sum()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "dcd7f1b6",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "      <th>heel_lab_mm</th>\n",
       "      <th>heel_brand_mm</th>\n",
       "      <th>forefoot_lab_mm</th>\n",
       "      <th>forefoot_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87\\n Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.4</td>\n",
       "      <td>36.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>26.6</td>\n",
       "      <td>24.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>33.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>24.4</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90\\n Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>31.8</td>\n",
       "      <td>32.0</td>\n",
       "      <td>21.2</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88\\n Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.6</td>\n",
       "      <td>34.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 102 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9    87\\n Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6   90\\n Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2   90\\n Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3    88\\n Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... weight_lab_oz weight_lab_g weight_brand_oz  \\\n",
       "0  Heelmid/Forefoot  ...           7.9          225             8.1   \n",
       "1      Mid/Forefoot  ...          10.7          304            10.9   \n",
       "2  Heelmid/Forefoot  ...          11.9          336            11.5   \n",
       "3              Heel  ...          12.6          356            12.4   \n",
       "4  Heelmid/Forefoot  ...          12.3          348            12.2   \n",
       "\n",
       "  weight_brand_g drop_lab_mm drop_brand_mm heel_lab_mm heel_brand_mm  \\\n",
       "0          230.0         9.4          10.0        32.4          36.0   \n",
       "1          309.0         7.7           8.0        34.3          32.5   \n",
       "2          327.0         8.9          10.0        33.3          32.5   \n",
       "3          352.0        10.6          11.0        31.8          32.0   \n",
       "4          345.0         9.9          10.0        32.6          34.0   \n",
       "\n",
       "  forefoot_lab_mm forefoot_brand_mm  \n",
       "0            23.0              26.0  \n",
       "1            26.6              24.5  \n",
       "2            24.4              22.5  \n",
       "3            21.2              21.0  \n",
       "4            22.7              24.0  \n",
       "\n",
       "[5 rows x 102 columns]"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ambil angka pakai regex\n",
    "forefoot = df[\"Forefoot lab Forefoot brand\"].str.findall(r\"[\\d.]+\")\n",
    "\n",
    "# Ubah jadi 2 kolom\n",
    "df[[\"forefoot_lab_mm\", \"forefoot_brand_mm\"]] = (\n",
    "    pd.DataFrame(forefoot.tolist(), index=df.index)\n",
    ")\n",
    "\n",
    "# ubah ke numeric\n",
    "for col in [\"forefoot_lab_mm\", \"forefoot_brand_mm\"]:\n",
    "    df[col] = pd.to_numeric(df[col], errors=\"coerce\")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "7ccecc50",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Audience score\"] = (\n",
    "    df[\"Audience score\"]\n",
    "    .astype(str)\n",
    "    .str.replace(\"\\n\", \" - \", regex=False)\n",
    "    .str.strip()\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "19dd690d",
   "metadata": {},
   "source": [
    "# Remove duplicates"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4f09526",
   "metadata": {},
   "source": [
    "cuma ada 433 shoes road"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "7559acf1",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adistar 3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adistar 3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adistar 3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>Adistar 3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudflyer 5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudflyer 5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudgo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>169</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudmonster 2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>On</td>\n",
       "      <td>Cloudmonster 2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Brand            Name\n",
       "5    Adidas         4DFWD 3\n",
       "11   Adidas       Adistar 3\n",
       "12   Adidas       Adistar 3\n",
       "13   Adidas       Adistar 3\n",
       "14   Adidas       Adistar 3\n",
       "..      ...             ...\n",
       "163      On    Cloudflyer 5\n",
       "164      On    Cloudflyer 5\n",
       "166      On         Cloudgo\n",
       "169      On  Cloudmonster 2\n",
       "170      On  Cloudmonster 2\n",
       "\n",
       "[100 rows x 2 columns]"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dup_mask = df.duplicated(subset=[\"Brand\", \"Name\"], keep=\"first\")\n",
    "# print(len(dup_mask))\n",
    "df.loc[dup_mask, [\"Brand\", \"Name\"]].head(100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "4e91ab51",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before: 1170\n",
      "After : 434\n"
     ]
    }
   ],
   "source": [
    "# sebelum hapus\n",
    "print(\"Before:\", len(df))\n",
    "\n",
    "#hapus\n",
    "df = df.drop_duplicates(subset=[\"Brand\", \"Name\"], keep=\"first\").reset_index(drop=True)\n",
    "\n",
    "print(\"After :\", len(df))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "783d9c01",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Brand, Name]\n",
       "Index: []"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dup_mask = df.duplicated(subset=[\"Brand\", \"Name\"], keep=\"first\")\n",
    "df.loc[dup_mask, [\"Brand\", \"Name\"]].head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1873def0",
   "metadata": {},
   "source": [
    "udah ga ada duplicate, sisa 433 sepatu"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a094cf88",
   "metadata": {},
   "source": [
    "# Done cleaned"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "079b45bd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.DataFrame'>\n",
      "RangeIndex: 434 entries, 0 to 433\n",
      "Columns: 102 entries, Brand to forefoot_brand_mm\n",
      "dtypes: float64(9), int64(55), object(4), str(34)\n",
      "memory usage: 346.0+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "813168be",
   "metadata": {},
   "source": [
    "kenapa ada int ya"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "82f15329",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "      <th>heel_lab_mm</th>\n",
       "      <th>heel_brand_mm</th>\n",
       "      <th>forefoot_lab_mm</th>\n",
       "      <th>forefoot_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87 -&nbsp;&nbsp;Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.4</td>\n",
       "      <td>36.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>26.6</td>\n",
       "      <td>24.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>33.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>24.4</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>31.8</td>\n",
       "      <td>32.0</td>\n",
       "      <td>21.2</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88 -&nbsp;&nbsp;Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.6</td>\n",
       "      <td>34.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 102 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name Audience score Price                Pace Arch support  \\\n",
       "0  Brooks     Launch 9   87 -  Great!  $110  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6  90 -  Superb!  $150       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD  90 -  Superb!  $200       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2  90 -  Superb!  $200       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3   88 -  Great!  $200       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern  ... weight_lab_oz weight_lab_g weight_brand_oz  \\\n",
       "0  Heelmid/Forefoot  ...           7.9          225             8.1   \n",
       "1      Mid/Forefoot  ...          10.7          304            10.9   \n",
       "2  Heelmid/Forefoot  ...          11.9          336            11.5   \n",
       "3              Heel  ...          12.6          356            12.4   \n",
       "4  Heelmid/Forefoot  ...          12.3          348            12.2   \n",
       "\n",
       "  weight_brand_g drop_lab_mm drop_brand_mm heel_lab_mm heel_brand_mm  \\\n",
       "0          230.0         9.4          10.0        32.4          36.0   \n",
       "1          309.0         7.7           8.0        34.3          32.5   \n",
       "2          327.0         8.9          10.0        33.3          32.5   \n",
       "3          352.0        10.6          11.0        31.8          32.0   \n",
       "4          345.0         9.9          10.0        32.6          34.0   \n",
       "\n",
       "  forefoot_lab_mm forefoot_brand_mm  \n",
       "0            23.0              26.0  \n",
       "1            26.6              24.5  \n",
       "2            24.4              22.5  \n",
       "3            21.2              21.0  \n",
       "4            22.7              24.0  \n",
       "\n",
       "[5 rows x 102 columns]"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "2832aee5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "           Weight lab Weight brand  weight_lab_oz  weight_lab_g  \\\n",
      "0      7.9 oz / 225g 8.1 oz / 230g            7.9           225   \n",
      "1    10.7 oz / 304g 10.9 oz / 309g           10.7           304   \n",
      "2    11.9 oz / 336g 11.5 oz / 327g           11.9           336   \n",
      "3    12.6 oz / 356g 12.4 oz / 352g           12.6           356   \n",
      "4    12.3 oz / 348g 12.2 oz / 345g           12.3           348   \n",
      "..                             ...            ...           ...   \n",
      "429   9.8 oz / 279g 10.1 oz / 286g            9.8           279   \n",
      "430    8.7 oz / 248g 8.6 oz / 244g            8.7           248   \n",
      "431   10.3 oz / 291g 9.7 oz / 274g           10.3           291   \n",
      "432        6 oz / 171g 6 oz / 171g            6.0           171   \n",
      "433    6.9 oz / 196g 6.9 oz / 196g            6.9           196   \n",
      "\n",
      "     weight_brand_oz  weight_brand_g  \n",
      "0                8.1           230.0  \n",
      "1               10.9           309.0  \n",
      "2               11.5           327.0  \n",
      "3               12.4           352.0  \n",
      "4               12.2           345.0  \n",
      "..               ...             ...  \n",
      "429             10.1           286.0  \n",
      "430              8.6           244.0  \n",
      "431              9.7           274.0  \n",
      "432              6.0           171.0  \n",
      "433              6.9           196.0  \n",
      "\n",
      "[434 rows x 5 columns]\n"
     ]
    }
   ],
   "source": [
    "print(df[['Weight lab Weight brand', 'weight_lab_oz', 'weight_lab_g', 'weight_brand_oz',\t'weight_brand_g']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "9266754f",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Audience score</th>\n",
       "      <th>Price</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>...</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "      <th>heel_lab_mm</th>\n",
       "      <th>heel_brand_mm</th>\n",
       "      <th>forefoot_lab_mm</th>\n",
       "      <th>forefoot_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>87 -&nbsp;&nbsp;Great!</td>\n",
       "      <td>$110</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.4</td>\n",
       "      <td>36.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$150</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>26.6</td>\n",
       "      <td>24.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>33.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>24.4</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>90 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>31.8</td>\n",
       "      <td>32.0</td>\n",
       "      <td>21.2</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>88 -&nbsp;&nbsp;Great!</td>\n",
       "      <td>$200</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.6</td>\n",
       "      <td>34.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>24.0</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",
       "      <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>428</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 4</td>\n",
       "      <td>86 -&nbsp;&nbsp;Good!</td>\n",
       "      <td>$160</td>\n",
       "      <td>Tempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>9.6 oz / 271g 8.8 oz / 249g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.1 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>9.6</td>\n",
       "      <td>271</td>\n",
       "      <td>8.8</td>\n",
       "      <td>249.0</td>\n",
       "      <td>7.1</td>\n",
       "      <td>8.0</td>\n",
       "      <td>38.4</td>\n",
       "      <td>36.0</td>\n",
       "      <td>31.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>429</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 5</td>\n",
       "      <td>80 -&nbsp;&nbsp;Good!</td>\n",
       "      <td>$160</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>9.8 oz / 279g 10.1 oz / 286g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.5 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>9.8</td>\n",
       "      <td>279</td>\n",
       "      <td>10.1</td>\n",
       "      <td>286.0</td>\n",
       "      <td>7.5</td>\n",
       "      <td>8.0</td>\n",
       "      <td>36.9</td>\n",
       "      <td>41.0</td>\n",
       "      <td>29.4</td>\n",
       "      <td>33.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>430</th>\n",
       "      <td>Nike</td>\n",
       "      <td>Zoom Fly 6</td>\n",
       "      <td>92 -&nbsp;&nbsp;Superb!</td>\n",
       "      <td>$170</td>\n",
       "      <td>Competitiontempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>8.7 oz / 248g 8.6 oz / 244g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.6 mm 8.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>8.7</td>\n",
       "      <td>248</td>\n",
       "      <td>8.6</td>\n",
       "      <td>244.0</td>\n",
       "      <td>9.6</td>\n",
       "      <td>8.0</td>\n",
       "      <td>39.7</td>\n",
       "      <td>40.0</td>\n",
       "      <td>30.1</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>431</th>\n",
       "      <td>Nike</td>\n",
       "      <td>ZoomX Invincible Run Flyknit 2</td>\n",
       "      <td>86 -&nbsp;&nbsp;Good!</td>\n",
       "      <td>$180</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.3 oz / 291g 9.7 oz / 274g</td>\n",
       "      <td>0</td>\n",
       "      <td>12.0 mm 9.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>...</td>\n",
       "      <td>10.3</td>\n",
       "      <td>291</td>\n",
       "      <td>9.7</td>\n",
       "      <td>274.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>35.5</td>\n",
       "      <td>37.0</td>\n",
       "      <td>23.5</td>\n",
       "      <td>28.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>432</th>\n",
       "      <td>Nike</td>\n",
       "      <td>ZoomX Streakfly</td>\n",
       "      <td>87 -&nbsp;&nbsp;Great!</td>\n",
       "      <td>$160</td>\n",
       "      <td>Tempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>6 oz / 171g 6 oz / 171g</td>\n",
       "      <td>1</td>\n",
       "      <td>6.3 mm 6.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>171</td>\n",
       "      <td>6.0</td>\n",
       "      <td>171.0</td>\n",
       "      <td>6.3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>31.7</td>\n",
       "      <td>32.0</td>\n",
       "      <td>25.4</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>433 rows × 102 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Brand                            Name Audience score Price  \\\n",
       "0    Brooks                        Launch 9   87 -  Great!  $110   \n",
       "1    Brooks                      Levitate 6  90 -  Superb!  $150   \n",
       "2    Adidas                           4DFWD  90 -  Superb!  $200   \n",
       "3    Adidas                         4DFWD 2  90 -  Superb!  $200   \n",
       "4    Adidas                         4DFWD 3   88 -  Great!  $200   \n",
       "..      ...                             ...            ...   ...   \n",
       "428    Nike                      Zoom Fly 4    86 -  Good!  $160   \n",
       "429    Nike                      Zoom Fly 5    80 -  Good!  $160   \n",
       "430    Nike                      Zoom Fly 6  92 -  Superb!  $170   \n",
       "431    Nike  ZoomX Invincible Run Flyknit 2    86 -  Good!  $180   \n",
       "432    Nike                 ZoomX Streakfly   87 -  Great!  $160   \n",
       "\n",
       "                   Pace Arch support        Weight lab Weight brand  \\\n",
       "0    Daily Runningtempo      Neutral    7.9 oz / 225g 8.1 oz / 230g   \n",
       "1         Daily Running      Neutral  10.7 oz / 304g 10.9 oz / 309g   \n",
       "2         Daily Running      Neutral  11.9 oz / 336g 11.5 oz / 327g   \n",
       "3         Daily Running      Neutral  12.6 oz / 356g 12.4 oz / 352g   \n",
       "4         Daily Running      Neutral  12.3 oz / 348g 12.2 oz / 345g   \n",
       "..                  ...          ...                            ...   \n",
       "428               Tempo      Neutral    9.6 oz / 271g 8.8 oz / 249g   \n",
       "429  Daily Runningtempo      Neutral   9.8 oz / 279g 10.1 oz / 286g   \n",
       "430    Competitiontempo      Neutral    8.7 oz / 248g 8.6 oz / 244g   \n",
       "431       Daily Running      Neutral   10.3 oz / 291g 9.7 oz / 274g   \n",
       "432               Tempo      Neutral        6 oz / 171g 6 oz / 171g   \n",
       "\n",
       "     Lightweight Drop lab Drop brand    Strike pattern  ... weight_lab_oz  \\\n",
       "0              1      9.4 mm 10.0 mm  Heelmid/Forefoot  ...           7.9   \n",
       "1              0       7.7 mm 8.0 mm      Mid/Forefoot  ...          10.7   \n",
       "2              0      8.9 mm 10.0 mm  Heelmid/Forefoot  ...          11.9   \n",
       "3              0     10.6 mm 11.0 mm              Heel  ...          12.6   \n",
       "4              0      9.9 mm 10.0 mm  Heelmid/Forefoot  ...          12.3   \n",
       "..           ...                 ...               ...  ...           ...   \n",
       "428            0       7.1 mm 8.0 mm      Mid/Forefoot  ...           9.6   \n",
       "429            0       7.5 mm 8.0 mm      Mid/Forefoot  ...           9.8   \n",
       "430            1       9.6 mm 8.0 mm  Heelmid/Forefoot  ...           8.7   \n",
       "431            0      12.0 mm 9.0 mm              Heel  ...          10.3   \n",
       "432            1       6.3 mm 6.0 mm      Mid/Forefoot  ...           6.0   \n",
       "\n",
       "    weight_lab_g weight_brand_oz weight_brand_g drop_lab_mm drop_brand_mm  \\\n",
       "0            225             8.1          230.0         9.4          10.0   \n",
       "1            304            10.9          309.0         7.7           8.0   \n",
       "2            336            11.5          327.0         8.9          10.0   \n",
       "3            356            12.4          352.0        10.6          11.0   \n",
       "4            348            12.2          345.0         9.9          10.0   \n",
       "..           ...             ...            ...         ...           ...   \n",
       "428          271             8.8          249.0         7.1           8.0   \n",
       "429          279            10.1          286.0         7.5           8.0   \n",
       "430          248             8.6          244.0         9.6           8.0   \n",
       "431          291             9.7          274.0        12.0           9.0   \n",
       "432          171             6.0          171.0         6.3           6.0   \n",
       "\n",
       "    heel_lab_mm heel_brand_mm forefoot_lab_mm forefoot_brand_mm  \n",
       "0          32.4          36.0            23.0              26.0  \n",
       "1          34.3          32.5            26.6              24.5  \n",
       "2          33.3          32.5            24.4              22.5  \n",
       "3          31.8          32.0            21.2              21.0  \n",
       "4          32.6          34.0            22.7              24.0  \n",
       "..          ...           ...             ...               ...  \n",
       "428        38.4          36.0            31.3               NaN  \n",
       "429        36.9          41.0            29.4              33.0  \n",
       "430        39.7          40.0            30.1              32.0  \n",
       "431        35.5          37.0            23.5              28.0  \n",
       "432        31.7          32.0            25.4              26.0  \n",
       "\n",
       "[433 rows x 102 columns]"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(433)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "6a9ceda0",
   "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>Brand</th>\n",
       "      <th>Name</th>\n",
       "      <th>Pace</th>\n",
       "      <th>Arch support</th>\n",
       "      <th>Weight lab Weight brand</th>\n",
       "      <th>Lightweight</th>\n",
       "      <th>Drop lab Drop brand</th>\n",
       "      <th>Strike pattern</th>\n",
       "      <th>Size</th>\n",
       "      <th>Midsole softness</th>\n",
       "      <th>...</th>\n",
       "      <th>weight_lab_oz</th>\n",
       "      <th>weight_lab_g</th>\n",
       "      <th>weight_brand_oz</th>\n",
       "      <th>weight_brand_g</th>\n",
       "      <th>drop_lab_mm</th>\n",
       "      <th>drop_brand_mm</th>\n",
       "      <th>heel_lab_mm</th>\n",
       "      <th>heel_brand_mm</th>\n",
       "      <th>forefoot_lab_mm</th>\n",
       "      <th>forefoot_brand_mm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Launch 9</td>\n",
       "      <td>Daily Runningtempo</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>7.9 oz / 225g 8.1 oz / 230g</td>\n",
       "      <td>1</td>\n",
       "      <td>9.4 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>True To Size</td>\n",
       "      <td>Balanced</td>\n",
       "      <td>...</td>\n",
       "      <td>7.9</td>\n",
       "      <td>225</td>\n",
       "      <td>8.1</td>\n",
       "      <td>230.0</td>\n",
       "      <td>9.4</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.4</td>\n",
       "      <td>36.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brooks</td>\n",
       "      <td>Levitate 6</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>10.7 oz / 304g 10.9 oz / 309g</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7 mm 8.0 mm</td>\n",
       "      <td>Mid/Forefoot</td>\n",
       "      <td>True To Size</td>\n",
       "      <td>Soft</td>\n",
       "      <td>...</td>\n",
       "      <td>10.7</td>\n",
       "      <td>304</td>\n",
       "      <td>10.9</td>\n",
       "      <td>309.0</td>\n",
       "      <td>7.7</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>26.6</td>\n",
       "      <td>24.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>11.9 oz / 336g 11.5 oz / 327g</td>\n",
       "      <td>0</td>\n",
       "      <td>8.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>True To Size</td>\n",
       "      <td>Firm</td>\n",
       "      <td>...</td>\n",
       "      <td>11.9</td>\n",
       "      <td>336</td>\n",
       "      <td>11.5</td>\n",
       "      <td>327.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>33.3</td>\n",
       "      <td>32.5</td>\n",
       "      <td>24.4</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 2</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.6 oz / 356g 12.4 oz / 352g</td>\n",
       "      <td>0</td>\n",
       "      <td>10.6 mm 11.0 mm</td>\n",
       "      <td>Heel</td>\n",
       "      <td>Slightly Small</td>\n",
       "      <td>Firm</td>\n",
       "      <td>...</td>\n",
       "      <td>12.6</td>\n",
       "      <td>356</td>\n",
       "      <td>12.4</td>\n",
       "      <td>352.0</td>\n",
       "      <td>10.6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>31.8</td>\n",
       "      <td>32.0</td>\n",
       "      <td>21.2</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adidas</td>\n",
       "      <td>4DFWD 3</td>\n",
       "      <td>Daily Running</td>\n",
       "      <td>Neutral</td>\n",
       "      <td>12.3 oz / 348g 12.2 oz / 345g</td>\n",
       "      <td>0</td>\n",
       "      <td>9.9 mm 10.0 mm</td>\n",
       "      <td>Heelmid/Forefoot</td>\n",
       "      <td>True To Size</td>\n",
       "      <td>Firm</td>\n",
       "      <td>...</td>\n",
       "      <td>12.3</td>\n",
       "      <td>348</td>\n",
       "      <td>12.2</td>\n",
       "      <td>345.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>10.0</td>\n",
       "      <td>32.6</td>\n",
       "      <td>34.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 100 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Brand         Name                Pace Arch support  \\\n",
       "0  Brooks     Launch 9  Daily Runningtempo      Neutral   \n",
       "1  Brooks   Levitate 6       Daily Running      Neutral   \n",
       "2  Adidas        4DFWD       Daily Running      Neutral   \n",
       "3  Adidas      4DFWD 2       Daily Running      Neutral   \n",
       "4  Adidas      4DFWD 3       Daily Running      Neutral   \n",
       "\n",
       "         Weight lab Weight brand  Lightweight Drop lab Drop brand  \\\n",
       "0    7.9 oz / 225g 8.1 oz / 230g            1      9.4 mm 10.0 mm   \n",
       "1  10.7 oz / 304g 10.9 oz / 309g            0       7.7 mm 8.0 mm   \n",
       "2  11.9 oz / 336g 11.5 oz / 327g            0      8.9 mm 10.0 mm   \n",
       "3  12.6 oz / 356g 12.4 oz / 352g            0     10.6 mm 11.0 mm   \n",
       "4  12.3 oz / 348g 12.2 oz / 345g            0      9.9 mm 10.0 mm   \n",
       "\n",
       "     Strike pattern            Size Midsole softness  ... weight_lab_oz  \\\n",
       "0  Heelmid/Forefoot    True To Size         Balanced  ...           7.9   \n",
       "1      Mid/Forefoot    True To Size             Soft  ...          10.7   \n",
       "2  Heelmid/Forefoot    True To Size             Firm  ...          11.9   \n",
       "3              Heel  Slightly Small             Firm  ...          12.6   \n",
       "4  Heelmid/Forefoot    True To Size             Firm  ...          12.3   \n",
       "\n",
       "  weight_lab_g weight_brand_oz weight_brand_g drop_lab_mm drop_brand_mm  \\\n",
       "0          225             8.1          230.0         9.4          10.0   \n",
       "1          304            10.9          309.0         7.7           8.0   \n",
       "2          336            11.5          327.0         8.9          10.0   \n",
       "3          356            12.4          352.0        10.6          11.0   \n",
       "4          348            12.2          345.0         9.9          10.0   \n",
       "\n",
       "  heel_lab_mm heel_brand_mm forefoot_lab_mm forefoot_brand_mm  \n",
       "0        32.4          36.0            23.0              26.0  \n",
       "1        34.3          32.5            26.6              24.5  \n",
       "2        33.3          32.5            24.4              22.5  \n",
       "3        31.8          32.0            21.2              21.0  \n",
       "4        32.6          34.0            22.7              24.0  \n",
       "\n",
       "[5 rows x 100 columns]"
      ]
     },
     "execution_count": 138,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop(columns=[\"Audience score\", \"Price\"], inplace=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "id": "154d8336",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('../../data/road_dataset.csv', index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "env",
   "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": "3.13.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}