{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "9d832900",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "\n",
    "pd.set_option('display.max_rows', 10000)\n",
    "pd.set_option('display.max_columns', 10000)\n",
    "\n",
    "file_path = 'games.csv'\n",
    "\n",
    "data = pd.read_csv(file_path)   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "84d9af06",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Qd1', 'Qc2', 'Qc3', 'Qb3', 'Qb7+', 'Qxd7#']\n",
      "['Qd1', 'Qxd4', 'Qd1', 'Qa4', 'Qh4', 'Qxg5', 'Qg3', 'Qxg6']\n",
      "Square names from list1: ['d1', 'c2', 'c3', 'b3', 'b7', 'd7']\n",
      "Square names from list2: ['d1', 'd4', 'd1', 'a4', 'h4', 'g5', 'g3', 'g6']\n"
     ]
    }
   ],
   "source": [
    "import re\n",
    "\n",
    "def extract_square_names(moves_list):\n",
    "    square_names = []\n",
    "\n",
    "    for move in moves_list:\n",
    "        # Use a regular expression to match the chess square name\n",
    "        match = re.search(r'[a-h][1-8]', move)\n",
    "        if match:\n",
    "            square_names.append(match.group())\n",
    "\n",
    "    return square_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "1f11b18c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Qd1', 'Qxd4', 'Qd1', 'Qa4', 'Qh4', 'Qxg5', 'Qg3', 'Qxg6']\n",
      "White queen moves: ['d1', 'd4', 'd1', 'a4', 'h4', 'g5', 'g3', 'g6']\n",
      "['Qd8', 'Qe7', 'Qc7', 'Qg7', 'Qxg6']\n",
      "Black queen moves: ['d8', 'e7', 'c7', 'g7', 'g6']\n"
     ]
    }
   ],
   "source": [
    "opening_number_of_games = data['opening_name'].value_counts()\n",
    "opening_number_of_games.head(10)\n",
    "# openings = ['Sicilian Defense', 'Old Benoni Defense', \"Queen's Pawn Game: Mason Attack\"]\n",
    "\n",
    "old_benoni_games = data[data['opening_name'].str.contains('Old Benoni Defense', case = False)]\n",
    "old_benoni_count = len(old_benoni_games)\n",
    "\n",
    "for text in old_benoni_games.head(1)['moves']:\n",
    "    moves = text.split()\n",
    "    white_queen_moves = ['Qd1']\n",
    "    black_queen_moves = ['Qd8']\n",
    "    for idx, move in enumerate(moves):\n",
    "        if move.startswith(\"Q\"):\n",
    "            if idx % 2 == 0:\n",
    "                white_queen_moves.append(move)\n",
    "            if idx % 2 == 1:\n",
    "                black_queen_moves.append(move)\n",
    "#     print(f'White queen moves: {white_queen_moves}')\n",
    "#     print(f'Black queen moves: {black_queen_moves}')\n",
    "    print(f'White queen moves: {extract_square_names(white_queen_moves)}')\n",
    "    print(f'Black queen moves: {extract_square_names(black_queen_moves)}')\n",
    "# list1 = ['Qd1', 'Qc2', 'Qc3', 'Qb3', 'Qb7+', 'Qxd7#']\n",
    "# list2 = ['Qd1', 'Qxd4', 'Qd1', 'Qa4', 'Qh4', 'Qxg5', 'Qg3', 'Qxg6']\n",
    "# print(white_queen_moves)\n",
    "# print(list1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e0e4858a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "opening_name\n",
      "Alekhine Defense: Exchange Variation                 9.0\n",
      "Anderssen Opening                                    1.0\n",
      "Benko Gambit Accepted |  Fully Accepted Variation    9.0\n",
      "Benko Gambit Declined |  Quiet Line                  7.0\n",
      "Benoni Defense: Benoni-Indian Defense                4.0\n",
      "                                                    ... \n",
      "Trompowsky Attack                                    3.0\n",
      "Van Geet Opening: Dunst-Perrenet Gambit              5.0\n",
      "Vienna Game #2                                       6.0\n",
      "Vienna Game: Vienna Gambit |  Main Line              6.0\n",
      "Yusupov-Rubinstein System                            5.0\n",
      "Name: opening_ply, Length: 112, dtype: float64\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/lm/cbc3n48n4x94zd3vf6zbbly40000gn/T/ipykernel_2729/977498901.py:12: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  filtered_data = data[data['white_rating'] > 2200][data['black_rating'] > 2200]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# Filtrowanie danych dla elo > 2200\n",
    "filtered_data = data[data['white_rating'] > 2200][data['black_rating'] > 2200]\n",
    "\n",
    "# Oblicz średnią opening_ply dla każdej unikalnej wartości w kolumnie 'opening'\n",
    "average_opening_ply = filtered_data.groupby('opening_name')['opening_ply'].mean()\n",
    "\n",
    "# Wyświetl średnie opening_ply dla każdej opening, dla elo > 2200\n",
    "print(average_opening_ply)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}