genetic_algorithm_balancing_matchmaking_game_5vs5.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import random\n",
    "\n",
    "# Set random seed for reproducibility\n",
    "np.random.seed(42)\n",
    "\n",
    "# Create the role dictionary\n",
    "role_dict_inverse = {'jungler': 1, 'marksman': 2, 'midlaner': 3, 'explaner': 4, 'roamer': 5}\n",
    "role_dict = {v: k for k, v in role_dict_inverse.items()}\n",
    "\n",
    "# Generate winrate data with specified distribution\n",
    "def generate_winrate_distribution(size):\n",
    "    winrate_data = []\n",
    "    # 15% of data with winrate 30-40\n",
    "    winrate_data.extend(np.random.uniform(30, 40, int(size * 0.15)))\n",
    "    # 60% of data with winrate 40-60\n",
    "    winrate_data.extend(np.random.uniform(40, 60, int(size * 0.60)))\n",
    "    # 20% of data with winrate 60-80\n",
    "    winrate_data.extend(np.random.uniform(60, 80, int(size * 0.20)))\n",
    "    # 5% of data with winrate 80-99\n",
    "    winrate_data.extend(np.random.uniform(80, 99, int(size * 0.05)))\n",
    "    return winrate_data\n",
    "\n",
    "# Generate synthetic data\n",
    "data = {\n",
    "    'id': range(1, 10001),\n",
    "    'tier': np.random.randint(1, 3, 10000),  # 1st Tier-2nd Tier\n",
    "    'total_match': np.random.randint(10, 10000, 10000),\n",
    "    'winrate': generate_winrate_distribution(10000),\n",
    "    'most_pick_role': np.random.randint(1, 6, 10000)  # 1=jungler, 2=marksman, 3=midlaner, 4=explaner, 5=roamer\n",
    "}\n",
    "\n",
    "df = pd.DataFrame(data)\n",
    "df['most_pick_role'] = df['most_pick_role'].map(role_dict)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         id  tier  total_match    winrate most_pick_role\n",
      "0         1     1         3132  38.393709       explaner\n",
      "1         2     2         8177  39.444879        jungler\n",
      "2         3     1         5200  32.729217         roamer\n",
      "3         4     1         4585  31.696611         roamer\n",
      "4         5     1         7737  34.839908       midlaner\n",
      "...     ...   ...          ...        ...            ...\n",
      "9995   9996     2         1336  94.532901         roamer\n",
      "9996   9997     1         6187  89.489781       marksman\n",
      "9997   9998     2         9227  93.787454       marksman\n",
      "9998   9999     2          371  89.598633        jungler\n",
      "9999  10000     1         1228  91.265201       explaner\n",
      "\n",
      "[10000 rows x 5 columns]\n"
     ]
    }
   ],
   "source": [
    "print(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Exploratory Data Analysis (EDA)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsAAAAIjCAYAAAAN/63DAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAyl0lEQVR4nO3df1TUdb7H8df4gxHFGdQEJBAxW5NSS211ykqTJMNaU0/ZLUVTuxpaYJnZGv5oW/Zq+aPSbLeb2A9PmrfMJH8lgtekMrqUuunJTRcLAdNgxFVQmPvHHr7HEX/iwJCf5+OcOaf5fj985/3d7UxPx+98sXk8Ho8AAAAAQzTw9wAAAABAXSKAAQAAYBQCGAAAAEYhgAEAAGAUAhgAAABGIYABAABgFAIYAAAARiGAAQAAYBQCGAAAAEYhgAEYZcaMGbLZbHXyWn369FGfPn2s55mZmbLZbFq5cmWdvP7IkSPVrl27OnmtmiotLdWYMWMUFhYmm82mpKSkyzre/v37ZbPZlJaW5pP5AFyZCGAAv1lpaWmy2WzWo0mTJgoPD1dcXJxeeeUVHT161Cevk5+frxkzZig3N9cnx/Ol+jzbxfjzn/+stLQ0jR8/Xu+8846GDx9ebU3VH1ou9Dj9DxsAcD6N/D0AAFyuWbNmKTo6WidPnlRBQYEyMzOVlJSkuXPnavXq1erSpYu1dtq0aXr22Wcv6fj5+fmaOXOm2rVrpxtvvPGif27Dhg2X9Do1cb7Z/va3v6mysrLWZ7gcGRkZ6tWrl6ZPn37ONYMHD1aHDh2s56WlpRo/frzuv/9+DR482NoeGhqqqKgoHT9+XI0bN67VuQH8thHAAH7zBgwYoB49eljPp06dqoyMDA0cOFD33Xefvv/+ewUGBkqSGjVqpEaNavet71//+peaNm2qgICAWn2dC/ktRGBRUZFiYmLOu6ZLly5ef4j55ZdfNH78eHXp0kWPPPJItfVNmjTx2XzHjh1Ts2bNfHY8APUDl0AAuCLdeeedev755/XPf/5T7777rrX9bNcAb9y4Ub1791ZwcLCCgoLUsWNHPffcc5L+fd3uzTffLEkaNWqU9dftVdeY9unTRzfccINycnJ0++23q2nTptbPnnkNcJWKigo999xzCgsLU7NmzXTffffpwIEDXmvatWunkSNHVvvZ0495odnOdg3wsWPH9NRTTykyMlJ2u10dO3bUSy+9JI/H47XOZrNpwoQJWrVqlW644QbZ7XZdf/31Wrdu3dn/Bz9DUVGRRo8erdDQUDVp0kRdu3bV0qVLrf1V10Pv27dP6enp1uz79++/qOOfy7muAd69e7eGDh2qli1bqkmTJurRo4dWr17ttabqkpqsrCw9/vjjCgkJUUREhCTp6NGjSkpKUrt27WS32xUSEqK77rpL33zzzWXNC8A/+AQYwBVr+PDheu6557RhwwaNHTv2rGt27dqlgQMHqkuXLpo1a5bsdrv27t2rzz//XJLUqVMnzZo1SykpKXrsscd02223SZJuueUW6xiHDx/WgAEDNGzYMD3yyCMKDQ0971wvvviibDabpkyZoqKiIs2fP1+xsbHKzc21Pqm+GBcz2+k8Ho/uu+8+bd68WaNHj9aNN96o9evXa/Lkyfr55581b948r/Vbt27Vhx9+qMcff1zNmzfXK6+8oiFDhigvL0+tWrU651zHjx9Xnz59tHfvXk2YMEHR0dH64IMPNHLkSBUXF+vJJ59Up06d9M477yg5OVkRERF66qmnJEmtW7e+6PO/WLt27dKtt96qq6++Ws8++6yaNWumFStWaNCgQfqf//kf3X///V7rH3/8cbVu3VopKSk6duyYJGncuHFauXKlJkyYoJiYGB0+fFhbt27V999/r27duvl8ZgC1zAMAv1FLlizxSPJs3779nGucTqfnpptusp5Pnz7dc/pb37x58zySPIcOHTrnMbZv3+6R5FmyZEm1fXfccYdHkmfx4sVn3XfHHXdYzzdv3uyR5Ln66qs9brfb2r5ixQqPJM+CBQusbVFRUZ6EhIQLHvN8syUkJHiioqKs56tWrfJI8vzpT3/yWjd06FCPzWbz7N2719omyRMQEOC17dtvv/VI8rz66qvVXut08+fP90jyvPvuu9a28vJyj8vl8gQFBXmde1RUlCc+Pv68xzvToUOHPJI806dPr7Zv37591f736Nevn6dz586eEydOWNsqKys9t9xyi+faa6+1tlX9+9S7d2/PqVOnvI7rdDo9iYmJlzQngPqLSyAAXNGCgoLOezeI4OBgSdLHH39c4y+M2e12jRo16qLXjxgxQs2bN7eeDx06VG3atNGnn35ao9e/WJ9++qkaNmyoJ554wmv7U089JY/Ho7Vr13ptj42N1TXXXGM979KlixwOh3788ccLvk5YWJgeeugha1vjxo31xBNPqLS0VFlZWT44m4tz5MgRZWRk6IEHHtDRo0f1yy+/6JdfftHhw4cVFxenH374QT///LPXz4wdO1YNGzb02hYcHKwvv/xS+fn5dTY7gNpDAAO4opWWlnrF5pkefPBB3XrrrRozZoxCQ0M1bNgwrVix4pJi+Oqrr76kL7xde+21Xs9tNps6dOhw2de/Xsg///lPhYeHV/vfo1OnTtb+07Vt27baMVq0aKFff/31gq9z7bXXqkED7//EnOt1atPevXvl8Xj0/PPPq3Xr1l6PqjtPFBUVef1MdHR0tePMnj1bO3fuVGRkpH7/+99rxowZF/yDAID6i2uAAVyxfvrpJ5WUlHjdQutMgYGB2rJlizZv3qz09HStW7dOy5cv15133qkNGzZU+yTwXMfwtXP9so6KioqLmskXzvU6njO+MFefVf1B5umnn1ZcXNxZ15z578fZ/v984IEHdNttt+mjjz7Shg0bNGfOHP3Xf/2XPvzwQw0YMMD3gwOoVXwCDOCK9c4770jSOcOnSoMGDdSvXz/NnTtXf//73/Xiiy8qIyNDmzdvlnTuGK2pH374weu5x+PR3r17ve7Y0KJFCxUXF1f72TM/Pb2U2aKiopSfn1/tkpDdu3db+30hKipKP/zwQ7VP0X39Ohejffv2kv59CUZsbOxZH+f7G4LTtWnTRo8//rhWrVqlffv2qVWrVnrxxRdrc3wAtYQABnBFysjI0AsvvKDo6Gg9/PDD51x35MiRatuqfqFEWVmZJFn3gT1bkNbE22+/7RWhK1eu1MGDB70+Sbzmmmv0xRdfqLy83Nq2Zs2aardLu5TZ7rnnHlVUVOi1117z2j5v3jzZbDaffZJ5zz33qKCgQMuXL7e2nTp1Sq+++qqCgoJ0xx13+OR1LkZISIj69OmjN954QwcPHqy2/9ChQxc8RkVFhUpKSqodNzw83Pp3BMBvC5dAAPjNW7t2rXbv3q1Tp06psLBQGRkZ2rhxo6KiorR69erz/mKEWbNmacuWLYqPj1dUVJSKioq0aNEiRUREqHfv3pL+HaPBwcFavHixmjdvrmbNmqlnz55nvVb0YrRs2VK9e/fWqFGjVFhYqPnz56tDhw5et2obM2aMVq5cqbvvvlsPPPCA/vGPf+jdd9/1+lLapc527733qm/fvvrjH/+o/fv3q2vXrtqwYYM+/vhjJSUlVTt2TT322GN64403NHLkSOXk5Khdu3ZauXKlPv/8c82fP/+iP3H1lYULF6p3797q3Lmzxo4dq/bt26uwsFDZ2dn66aef9O233573548ePaqIiAgNHTpUXbt2VVBQkD777DNt375dL7/8ch2dBQBfIoAB/OalpKRIkgICAtSyZUt17txZ8+fP16hRoy4YW/fdd5/279+vt956S7/88ouuuuoq3XHHHZo5c6acTqekf//1+dKlSzV16lSNGzdOp06d0pIlS2ocwM8995y+++47paam6ujRo+rXr58WLVqkpk2bWmvi4uL08ssva+7cuUpKSlKPHj20Zs0a6365VS5ltgYNGmj16tVKSUnR8uXLtWTJErVr105z5sypdtzLERgYqMzMTD377LNaunSp3G63OnbsqCVLlpz1l3vUtpiYGH399deaOXOm0tLSdPjwYYWEhOimm26y/t05n6ZNm+rxxx/Xhg0b9OGHH6qyslIdOnTQokWLNH78+Do4AwC+ZvP8lr7NAAAAAFwmrgEGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhfsAX4TKykrl5+erefPmPv+VqAAAALh8Ho9HR48eVXh4uBo0OP9nvATwRcjPz1dkZKS/xwAAAMAFHDhwQBEREeddQwBfhKrfJHXgwAE5HA4/TwMAAIAzud1uRUZGXtSvWyeAL0LVZQ8Oh4MABgAAqMcu5nJVvgQHAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADCKXwN4xowZstlsXo/rrrvO2n/ixAklJiaqVatWCgoK0pAhQ1RYWOh1jLy8PMXHx6tp06YKCQnR5MmTderUKa81mZmZ6tatm+x2uzp06KC0tLS6OD0AAADUQ37/BPj666/XwYMHrcfWrVutfcnJyfrkk0/0wQcfKCsrS/n5+Ro8eLC1v6KiQvHx8SovL9e2bdu0dOlSpaWlKSUlxVqzb98+xcfHq2/fvsrNzVVSUpLGjBmj9evX1+l5AgAAoH6weTwej79efMaMGVq1apVyc3Or7SspKVHr1q21bNkyDR06VJK0e/duderUSdnZ2erVq5fWrl2rgQMHKj8/X6GhoZKkxYsXa8qUKTp06JACAgI0ZcoUpaena+fOndaxhw0bpuLiYq1bt+6i5nS73XI6nSopKZHD4bj8EwcAAIBPXUqvNaqjmc7phx9+UHh4uJo0aSKXy6XU1FS1bdtWOTk5OnnypGJjY6211113ndq2bWsFcHZ2tjp37mzFryTFxcVp/Pjx2rVrl2666SZlZ2d7HaNqTVJS0jlnKisrU1lZmfXc7Xb77oRroPvkt/36+gBqT86cEf4eAQCM49dLIHr27Km0tDStW7dOr7/+uvbt26fbbrtNR48eVUFBgQICAhQcHOz1M6GhoSooKJAkFRQUeMVv1f6qfedb43a7dfz48bPOlZqaKqfTaT0iIyN9cboAAACoB/z6CfCAAQOsf+7SpYt69uypqKgorVixQoGBgX6ba+rUqZo0aZL13O12E8EA4EP8zRZw5fot/M2W378Ed7rg4GD97ne/0969exUWFqby8nIVFxd7rSksLFRYWJgkKSwsrNpdIaqeX2iNw+E4Z2Tb7XY5HA6vBwAAAK4M9SqAS0tL9Y9//ENt2rRR9+7d1bhxY23atMnav2fPHuXl5cnlckmSXC6XduzYoaKiImvNxo0b5XA4FBMTY605/RhVa6qOAQAAALP4NYCffvppZWVlaf/+/dq2bZvuv/9+NWzYUA899JCcTqdGjx6tSZMmafPmzcrJydGoUaPkcrnUq1cvSVL//v0VExOj4cOH69tvv9X69es1bdo0JSYmym63S5LGjRunH3/8Uc8884x2796tRYsWacWKFUpOTvbnqQMAAMBP/HoN8E8//aSHHnpIhw8fVuvWrdW7d2998cUXat26tSRp3rx5atCggYYMGaKysjLFxcVp0aJF1s83bNhQa9as0fjx4+VyudSsWTMlJCRo1qxZ1pro6Gilp6crOTlZCxYsUEREhN58803FxcXV+fkCAADA//x6H+DfCn/fB5gviwBXrt/Cl0VqA+9rwJXLX+9rl9Jr9eoaYAAAAKC2EcAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKPUmwD+y1/+IpvNpqSkJGvbiRMnlJiYqFatWikoKEhDhgxRYWGh18/l5eUpPj5eTZs2VUhIiCZPnqxTp055rcnMzFS3bt1kt9vVoUMHpaWl1cEZAQAAoD6qFwG8fft2vfHGG+rSpYvX9uTkZH3yySf64IMPlJWVpfz8fA0ePNjaX1FRofj4eJWXl2vbtm1aunSp0tLSlJKSYq3Zt2+f4uPj1bdvX+Xm5iopKUljxozR+vXr6+z8AAAAUH/4PYBLS0v18MMP629/+5tatGhhbS8pKdF///d/a+7cubrzzjvVvXt3LVmyRNu2bdMXX3whSdqwYYP+/ve/691339WNN96oAQMG6IUXXtDChQtVXl4uSVq8eLGio6P18ssvq1OnTpowYYKGDh2qefPm+eV8AQAA4F9+D+DExETFx8crNjbWa3tOTo5Onjzptf26665T27ZtlZ2dLUnKzs5W586dFRoaaq2Ji4uT2+3Wrl27rDVnHjsuLs46xtmUlZXJ7XZ7PQAAAHBlaOTPF3///ff1zTffaPv27dX2FRQUKCAgQMHBwV7bQ0NDVVBQYK05PX6r9lftO98at9ut48ePKzAwsNprp6amaubMmTU+LwAAANRffvsE+MCBA3ryySf13nvvqUmTJv4a46ymTp2qkpIS63HgwAF/jwQAAAAf8VsA5+TkqKioSN26dVOjRo3UqFEjZWVl6ZVXXlGjRo0UGhqq8vJyFRcXe/1cYWGhwsLCJElhYWHV7gpR9fxCaxwOx1k//ZUku90uh8Ph9QAAAMCVwW8B3K9fP+3YsUO5ubnWo0ePHnr44Yetf27cuLE2bdpk/cyePXuUl5cnl8slSXK5XNqxY4eKioqsNRs3bpTD4VBMTIy15vRjVK2pOgYAAADM4rdrgJs3b64bbrjBa1uzZs3UqlUra/vo0aM1adIktWzZUg6HQxMnTpTL5VKvXr0kSf3791dMTIyGDx+u2bNnq6CgQNOmTVNiYqLsdrskady4cXrttdf0zDPP6NFHH1VGRoZWrFih9PT0uj1hAAAA1At+/RLchcybN08NGjTQkCFDVFZWpri4OC1atMja37BhQ61Zs0bjx4+Xy+VSs2bNlJCQoFmzZllroqOjlZ6eruTkZC1YsEARERF68803FRcX549TAgAAgJ/ZPB6Px99D1Hdut1tOp1MlJSV+uR64++S36/w1AdSNnDkj/D2CX/C+Bly5/PW+dim95vf7AAMAAAB1iQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABjFrwH8+uuvq0uXLnI4HHI4HHK5XFq7dq21/8SJE0pMTFSrVq0UFBSkIUOGqLCw0OsYeXl5io+PV9OmTRUSEqLJkyfr1KlTXmsyMzPVrVs32e12dejQQWlpaXVxegAAAKiH/BrAERER+stf/qKcnBx9/fXXuvPOO/WHP/xBu3btkiQlJyfrk08+0QcffKCsrCzl5+dr8ODB1s9XVFQoPj5e5eXl2rZtm5YuXaq0tDSlpKRYa/bt26f4+Hj17dtXubm5SkpK0pgxY7R+/fo6P18AAAD4n83j8Xj8PcTpWrZsqTlz5mjo0KFq3bq1li1bpqFDh0qSdu/erU6dOik7O1u9evXS2rVrNXDgQOXn5ys0NFSStHjxYk2ZMkWHDh1SQECApkyZovT0dO3cudN6jWHDhqm4uFjr1q076wxlZWUqKyuznrvdbkVGRqqkpEQOh6MWz/7suk9+u85fE0DdyJkzwt8j+AXva8CVy1/va263W06n86J6rd5cA1xRUaH3339fx44dk8vlUk5Ojk6ePKnY2FhrzXXXXae2bdsqOztbkpSdna3OnTtb8StJcXFxcrvd1qfI2dnZXseoWlN1jLNJTU2V0+m0HpGRkb48VQAAAPiR3wN4x44dCgoKkt1u17hx4/TRRx8pJiZGBQUFCggIUHBwsNf60NBQFRQUSJIKCgq84rdqf9W+861xu906fvz4WWeaOnWqSkpKrMeBAwd8caoAAACoBxr5e4COHTsqNzdXJSUlWrlypRISEpSVleXXmex2u+x2u19nAAAAQO3wewAHBASoQ4cOkqTu3btr+/btWrBggR588EGVl5eruLjY61PgwsJChYWFSZLCwsL01VdfeR2v6i4Rp685884RhYWFcjgcCgwMrK3TAgAAQD3l90sgzlRZWamysjJ1795djRs31qZNm6x9e/bsUV5enlwulyTJ5XJpx44dKioqstZs3LhRDodDMTEx1prTj1G1puoYAAAAMItfPwGeOnWqBgwYoLZt2+ro0aNatmyZMjMztX79ejmdTo0ePVqTJk1Sy5Yt5XA4NHHiRLlcLvXq1UuS1L9/f8XExGj48OGaPXu2CgoKNG3aNCUmJlqXMIwbN06vvfaannnmGT366KPKyMjQihUrlJ6e7s9TBwAAgJ/4NYCLioo0YsQIHTx4UE6nU126dNH69et11113SZLmzZunBg0aaMiQISorK1NcXJwWLVpk/XzDhg21Zs0ajR8/Xi6XS82aNVNCQoJmzZplrYmOjlZ6erqSk5O1YMECRURE6M0331RcXFydny8AAAD8r97dB7g+upT7ytUG7pcJXLm4DzCAKw33AQYAAADqGQIYAAAARiGAAQAAYBQCGAAAAEYhgAEAAGAUAhgAAABGIYABAABglBoFcPv27XX48OFq24uLi9W+ffvLHgoAAACoLTUK4P3796uioqLa9rKyMv3888+XPRQAAABQWy7pVyGvXr3a+uf169fL6XRazysqKrRp0ya1a9fOZ8MBAAAAvnZJATxo0CBJks1mU0JCgte+xo0bq127dnr55Zd9NhwAAADga5cUwJWVlZKk6Ohobd++XVdddVWtDAUAAADUlksK4Cr79u3z9RwAAABAnahRAEvSpk2btGnTJhUVFVmfDFd56623LnswAAAAoDbUKIBnzpypWbNmqUePHmrTpo1sNpuv5wIAAABqRY0CePHixUpLS9Pw4cN9PQ8AAABQq2p0H+Dy8nLdcsstvp4FAAAAqHU1CuAxY8Zo2bJlvp4FAAAAqHU1ugTixIkT+utf/6rPPvtMXbp0UePGjb32z5071yfDAQAAAL5WowD+7rvvdOONN0qSdu7c6bWPL8QBAACgPqtRAG/evNnXcwAAAAB1okbXAAMAAAC/VTX6BLhv377nvdQhIyOjxgMBAAAAtalGAVx1/W+VkydPKjc3Vzt37lRCQoIv5gIAAABqRY0CeN68eWfdPmPGDJWWll7WQAAAAEBt8uk1wI888ojeeustXx4SAAAA8CmfBnB2draaNGniy0MCAAAAPlWjSyAGDx7s9dzj8ejgwYP6+uuv9fzzz/tkMAAAAKA21CiAnU6n1/MGDRqoY8eOmjVrlvr37++TwQAAAIDaUKMAXrJkia/nAAAAAOpEjQK4Sk5Ojr7//ntJ0vXXX6+bbrrJJ0MBAAAAtaVGAVxUVKRhw4YpMzNTwcHBkqTi4mL17dtX77//vlq3bu3LGQEAAACfqdFdICZOnKijR49q165dOnLkiI4cOaKdO3fK7XbriSee8PWMAAAAgM/U6BPgdevW6bPPPlOnTp2sbTExMVq4cCFfggMAAEC9VqNPgCsrK9W4ceNq2xs3bqzKysrLHgoAAACoLTUK4DvvvFNPPvmk8vPzrW0///yzkpOT1a9fP58NBwAAAPhajQL4tddek9vtVrt27XTNNdfommuuUXR0tNxut1599VVfzwgAAAD4TI2uAY6MjNQ333yjzz77TLt375YkderUSbGxsT4dDgAAAPC1S/oEOCMjQzExMXK73bLZbLrrrrs0ceJETZw4UTfffLOuv/56/e///m9tzQoAAABctksK4Pnz52vs2LFyOBzV9jmdTv3nf/6n5s6d67PhAAAAAF+7pAD+9ttvdffdd59zf//+/ZWTk3PZQwEAAAC15ZICuLCw8Ky3P6vSqFEjHTp06LKHAgAAAGrLJQXw1VdfrZ07d55z/3fffac2bdpc9lAAAABAbbmkAL7nnnv0/PPP68SJE9X2HT9+XNOnT9fAgQN9NhwAAADga5d0G7Rp06bpww8/1O9+9ztNmDBBHTt2lCTt3r1bCxcuVEVFhf74xz/WyqAAAACAL1xSAIeGhmrbtm0aP368pk6dKo/HI0my2WyKi4vTwoULFRoaWiuDAgAAAL5wyb8IIyoqSp9++ql+/fVX7d27Vx6PR9dee61atGhRG/MBAAAAPlWj3wQnSS1atNDNN9/sy1kAAACAWndJX4IDAAAAfusIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYxa8BnJqaqptvvlnNmzdXSEiIBg0apD179nitOXHihBITE9WqVSsFBQVpyJAhKiws9FqTl5en+Ph4NW3aVCEhIZo8ebJOnTrltSYzM1PdunWT3W5Xhw4dlJaWVtunBwAAgHrIrwGclZWlxMREffHFF9q4caNOnjyp/v3769ixY9aa5ORkffLJJ/rggw+UlZWl/Px8DR482NpfUVGh+Ph4lZeXa9u2bVq6dKnS0tKUkpJirdm3b5/i4+PVt29f5ebmKikpSWPGjNH69evr9HwBAADgfzaPx+Px9xBVDh06pJCQEGVlZen2229XSUmJWrdurWXLlmno0KGSpN27d6tTp07Kzs5Wr169tHbtWg0cOFD5+fkKDQ2VJC1evFhTpkzRoUOHFBAQoClTpig9PV07d+60XmvYsGEqLi7WunXrLjiX2+2W0+lUSUmJHA5H7Zz8eXSf/HadvyaAupEzZ4S/R/AL3teAK5e/3tcupdfq1TXAJSUlkqSWLVtKknJycnTy5EnFxsZaa6677jq1bdtW2dnZkqTs7Gx17tzZil9JiouLk9vt1q5du6w1px+jak3VMc5UVlYmt9vt9QAAAMCVod4EcGVlpZKSknTrrbfqhhtukCQVFBQoICBAwcHBXmtDQ0NVUFBgrTk9fqv2V+073xq3263jx49XmyU1NVVOp9N6REZG+uQcAQAA4H/1JoATExO1c+dOvf/++/4eRVOnTlVJSYn1OHDggL9HAgAAgI808vcAkjRhwgStWbNGW7ZsUUREhLU9LCxM5eXlKi4u9voUuLCwUGFhYdaar776yut4VXeJOH3NmXeOKCwslMPhUGBgYLV57Ha77Ha7T84NAAAA9YtfPwH2eDyaMGGCPvroI2VkZCg6Otprf/fu3dW4cWNt2rTJ2rZnzx7l5eXJ5XJJklwul3bs2KGioiJrzcaNG+VwOBQTE2OtOf0YVWuqjgEAAABz+PUT4MTERC1btkwff/yxmjdvbl2z63Q6FRgYKKfTqdGjR2vSpElq2bKlHA6HJk6cKJfLpV69ekmS+vfvr5iYGA0fPlyzZ89WQUGBpk2bpsTEROtT3HHjxum1117TM888o0cffVQZGRlasWKF0tPT/XbuAAAA8A+/fgL8+uuvq6SkRH369FGbNm2sx/Lly6018+bN08CBAzVkyBDdfvvtCgsL04cffmjtb9iwodasWaOGDRvK5XLpkUce0YgRIzRr1ixrTXR0tNLT07Vx40Z17dpVL7/8st58803FxcXV6fkCAADA//z6CfDF3IK4SZMmWrhwoRYuXHjONVFRUfr000/Pe5w+ffro//7v/y55RgAAAFxZ6s1dIAAAAIC6QAADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIxCAAMAAMAoBDAAAACMQgADAADAKAQwAAAAjEIAAwAAwCgEMAAAAIzi1wDesmWL7r33XoWHh8tms2nVqlVe+z0ej1JSUtSmTRsFBgYqNjZWP/zwg9eaI0eO6OGHH5bD4VBwcLBGjx6t0tJSrzXfffedbrvtNjVp0kSRkZGaPXt2bZ8aAAAA6im/BvCxY8fUtWtXLVy48Kz7Z8+erVdeeUWLFy/Wl19+qWbNmikuLk4nTpyw1jz88MPatWuXNm7cqDVr1mjLli167LHHrP1ut1v9+/dXVFSUcnJyNGfOHM2YMUN//etfa/38AAAAUP808ueLDxgwQAMGDDjrPo/Ho/nz52vatGn6wx/+IEl6++23FRoaqlWrVmnYsGH6/vvvtW7dOm3fvl09evSQJL366qu655579NJLLyk8PFzvvfeeysvL9dZbbykgIEDXX3+9cnNzNXfuXK9QBgAAgBnq7TXA+/btU0FBgWJjY61tTqdTPXv2VHZ2tiQpOztbwcHBVvxKUmxsrBo0aKAvv/zSWnP77bcrICDAWhMXF6c9e/bo119/Petrl5WVye12ez0AAABwZai3AVxQUCBJCg0N9doeGhpq7SsoKFBISIjX/kaNGqlly5Zea852jNNf40ypqalyOp3WIzIy8vJPCAAAAPVCvQ1gf5o6dapKSkqsx4EDB/w9EgAAAHyk3gZwWFiYJKmwsNBre2FhobUvLCxMRUVFXvtPnTqlI0eOeK052zFOf40z2e12ORwOrwcAAACuDPU2gKOjoxUWFqZNmzZZ29xut7788ku5XC5JksvlUnFxsXJycqw1GRkZqqysVM+ePa01W7Zs0cmTJ601GzduVMeOHdWiRYs6OhsAAADUF34N4NLSUuXm5io3N1fSv7/4lpubq7y8PNlsNiUlJelPf/qTVq9erR07dmjEiBEKDw/XoEGDJEmdOnXS3XffrbFjx+qrr77S559/rgkTJmjYsGEKDw+XJP3Hf/yHAgICNHr0aO3atUvLly/XggULNGnSJD+dNQAAAPzJr7dB+/rrr9W3b1/reVWUJiQkKC0tTc8884yOHTumxx57TMXFxerdu7fWrVunJk2aWD/z3nvvacKECerXr58aNGigIUOG6JVXXrH2O51ObdiwQYmJierevbuuuuoqpaSkcAs0AAAAQ9k8Ho/H30PUd263W06nUyUlJX65Hrj75Lfr/DUB1I2cOSP8PYJf8L4GXLn89b52Kb1Wb68BBgAAAGoDAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMAoBDAAAAKMQwAAAADAKAQwAAACjEMAAAAAwCgEMAAAAoxDAAAAAMIpRAbxw4UK1a9dOTZo0Uc+ePfXVV1/5eyQAAADUMWMCePny5Zo0aZKmT5+ub775Rl27dlVcXJyKior8PRoAAADqkDEBPHfuXI0dO1ajRo1STEyMFi9erKZNm+qtt97y92gAAACoQ438PUBdKC8vV05OjqZOnWpta9CggWJjY5WdnV1tfVlZmcrKyqznJSUlkiS32137w55FRdlxv7wugNrnr/cVf+N9Dbhy+et9rep1PR7PBdcaEcC//PKLKioqFBoa6rU9NDRUu3fvrrY+NTVVM2fOrLY9MjKy1mYEYCbnq+P8PQIA+JS/39eOHj0qp9N53jVGBPClmjp1qiZNmmQ9r6ys1JEjR9SqVSvZbDY/ToYrndvtVmRkpA4cOCCHw+HvcQDgsvG+hrri8Xh09OhRhYeHX3CtEQF81VVXqWHDhiosLPTaXlhYqLCwsGrr7Xa77Ha717bg4ODaHBHw4nA4+A8FgCsK72uoCxf65LeKEV+CCwgIUPfu3bVp0yZrW2VlpTZt2iSXy+XHyQAAAFDXjPgEWJImTZqkhIQE9ejRQ7///e81f/58HTt2TKNGjfL3aAAAAKhDxgTwgw8+qEOHDiklJUUFBQW68cYbtW7dumpfjAP8yW63a/r06dUuwQGA3yre11Af2TwXc68IAAAA4AphxDXAAAAAQBUCGAAAAEYhgAEAAGAUAhgAAABGIYCBemLLli269957FR4eLpvNplWrVvl7JACosdTUVN18881q3ry5QkJCNGjQIO3Zs8ffYwGSCGCg3jh27Ji6du2qhQsX+nsUALhsWVlZSkxM1BdffKGNGzfq5MmT6t+/v44dO+bv0QBugwbURzabTR999JEGDRrk71EAwCcOHTqkkJAQZWVl6fbbb/f3ODAcnwADAIBaV1JSIklq2bKlnycBCGAAAFDLKisrlZSUpFtvvVU33HCDv8cBzPlVyAAAwD8SExO1c+dObd261d+jAJIIYAAAUIsmTJigNWvWaMuWLYqIiPD3OIAkAhgAANQCj8ejiRMn6qOPPlJmZqaio6P9PRJgIYCBeqK0tFR79+61nu/bt0+5ublq2bKl2rZt68fJAODSJSYmatmyZfr444/VvHlzFRQUSJKcTqcCAwP9PB1Mx23QgHoiMzNTffv2rbY9ISFBaWlpdT8QAFwGm8121u1LlizRyJEj63YY4AwEMAAAAIzCbdAAAABgFAIYAAAARiGAAQAAYBQCGAAAAEYhgAEAAGAUAhgAAABGIYABAABgFAIYAAAARiGAAcAQI0eO1KBBg/w9BgD4XSN/DwAAuHzn+rWzVaZPn64FCxaIX/4JAAQwAFwRDh48aP3z8uXLlZKSoj179ljbgoKCFBQUdFmv4fF4VFFRoUaN+E8HgN82LoEAgCtAWFiY9XA6nbLZbF7bgoKCql0CUVlZqdTUVEVHRyswMFBdu3bVypUrrf2ZmZmy2Wxau3atunfvLrvdrq1bt/rh7ADAt/hjPAAYKjU1Ve+++64WL16sa6+9Vlu2bNEjjzyi1q1b64477rDWPfvss3rppZfUvn17tWjRwo8TA4BvEMAAYKCysjL9+c9/1meffSaXyyVJat++vbZu3ao33njDK4BnzZqlu+66y1+jAoDPEcAAYKC9e/fqX//6V7WwLS8v10033eS1rUePHnU5GgDUOgIYAAxUWloqSUpPT9fVV1/ttc9ut3s9b9asWZ3NBQB1gQAGAAPFxMTIbrcrLy/P63IHADABAQwABmrevLmefvppJScnq7KyUr1791ZJSYk+//xzORwOJSQk+HtEAKg1BDAAGOqFF15Q69atlZqaqh9//FHBwcHq1q2bnnvuOX+PBgC1yubh1wIBAADAIPwiDAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGIUABgAAgFEIYAAAABiFAAYAAIBRCGAAAAAYhQAGAACAUQhgAAAAGOX/AbxoiywtFJLSAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Visualize tier distribution\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.countplot(data=df, x='tier')\n",
    "plt.title('Distribution of Tiers')\n",
    "plt.xlabel('Tier')\n",
    "plt.ylabel('Count')\n",
    "plt.show()\n",
    "\n",
    "# Visualize total match distribution\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.histplot(data=df, x='total_match', bins=30, kde=True)\n",
    "plt.title('Distribution of Total Matches')\n",
    "plt.xlabel('Total Matches')\n",
    "plt.ylabel('Frequency')\n",
    "plt.show()\n",
    "\n",
    "# Visualize winrate distribution\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.histplot(data=df, x='winrate', bins=30, kde=True)\n",
    "plt.title('Distribution of Winrates')\n",
    "plt.xlabel('Winrate')\n",
    "plt.ylabel('Frequency')\n",
    "plt.show()\n",
    "\n",
    "# Visualize most picked role distribution\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.countplot(data=df, x='most_pick_role')\n",
    "plt.title('Distribution of Most Picked Roles')\n",
    "plt.xlabel('Role')\n",
    "plt.ylabel('Count')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Genetic Algorithm Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Standardize the features\n",
    "scaler = StandardScaler()\n",
    "df[['tier', 'total_match', 'winrate']] = scaler.fit_transform(df[['tier', 'total_match', 'winrate']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\Program Files\\Python312\\Lib\\site-packages\\deap\\creator.py:185: RuntimeWarning: A class named 'FitnessMax' has already been created and it will be overwritten. Consider deleting previous creation of that class or rename it.\n",
      "  warnings.warn(\"A class named '{0}' has already been created and it \"\n",
      "d:\\Program Files\\Python312\\Lib\\site-packages\\deap\\creator.py:185: RuntimeWarning: A class named 'Individual' has already been created and it will be overwritten. Consider deleting previous creation of that class or rename it.\n",
      "  warnings.warn(\"A class named '{0}' has already been created and it \"\n"
     ]
    }
   ],
   "source": [
    "from deap import base, creator, tools, algorithms\n",
    "\n",
    "# Function to evaluate the fitness of a team\n",
    "def evaluate_team(team):\n",
    "    roles = [role_dict_inverse[role] for _, role in team]\n",
    "    if len(set(roles)) != len(roles):  # Ensure all roles are unique in the team\n",
    "        return 0,\n",
    "    return sum(df.loc[df['id'].isin([player_id for player_id, _ in team]), 'winrate']),\n",
    "\n",
    "# Create classes for the genetic algorithm\n",
    "creator.create(\"FitnessMax\", base.Fitness, weights=(1.0,))\n",
    "creator.create(\"Individual\", list, fitness=creator.FitnessMax)\n",
    "\n",
    "# Initialize toolbox\n",
    "toolbox = base.Toolbox()\n",
    "toolbox.register(\"attr_player\", random.randint, 1, len(df))\n",
    "toolbox.register(\"individual\", tools.initRepeat, creator.Individual, toolbox.attr_player, 5)\n",
    "toolbox.register(\"team\", tools.initRepeat, list, toolbox.individual, 2)\n",
    "\n",
    "def init_team():\n",
    "    team = []\n",
    "    while len(team) < 5:\n",
    "        player = random.randint(1, len(df))\n",
    "        if player not in [p[0] for p in team] and df.loc[df['id'] == player, 'most_pick_role'].values[0] not in [p[1] for p in team]:\n",
    "            team.append((player, df.loc[df['id'] == player, 'most_pick_role'].values[0]))\n",
    "    return creator.Individual(team)\n",
    "\n",
    "toolbox.register(\"individual\", init_team)\n",
    "toolbox.register(\"population\", tools.initRepeat, list, toolbox.individual)\n",
    "\n",
    "toolbox.register(\"mate\", tools.cxTwoPoint)\n",
    "toolbox.register(\"mutate\", tools.mutShuffleIndexes, indpb=0.05)\n",
    "toolbox.register(\"select\", tools.selTournament, tournsize=3)\n",
    "toolbox.register(\"evaluate\", evaluate_team)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Genetic Algorithm Execution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gen 0: Best fitness: 4.727708792858232\n",
      "Gen 1: Best fitness: 4.727708792858232\n",
      "Gen 2: Best fitness: 5.629688910411083\n",
      "Gen 3: Best fitness: 5.454738769566533\n",
      "Gen 4: Best fitness: 5.7239503067004955\n",
      "Gen 5: Best fitness: 6.96536855634021\n",
      "Gen 6: Best fitness: 7.226316435920787\n",
      "Gen 7: Best fitness: 7.665514177885483\n",
      "Gen 8: Best fitness: 7.665514177885483\n",
      "Gen 9: Best fitness: 8.032408392374236\n",
      "Gen 10: Best fitness: 8.032408392374236\n",
      "Gen 11: Best fitness: 8.032408392374236\n",
      "Gen 12: Best fitness: 8.032408392374236\n",
      "Gen 13: Best fitness: 8.032408392374236\n",
      "Gen 14: Best fitness: 8.032408392374236\n",
      "Gen 15: Best fitness: 9.504840631268133\n",
      "Gen 16: Best fitness: 9.504840631268133\n",
      "Gen 17: Best fitness: 9.504840631268133\n",
      "Gen 18: Best fitness: 9.504840631268133\n",
      "Gen 19: Best fitness: 9.504840631268133\n",
      "Gen 20: Best fitness: 9.504840631268133\n",
      "Gen 21: Best fitness: 9.504840631268133\n",
      "Gen 22: Best fitness: 9.504840631268133\n",
      "Gen 23: Best fitness: 9.504840631268133\n",
      "Gen 24: Best fitness: 9.504840631268133\n",
      "Gen 25: Best fitness: 9.504840631268133\n",
      "Gen 26: Best fitness: 9.504840631268133\n",
      "Gen 27: Best fitness: 9.504840631268133\n",
      "Gen 28: Best fitness: 10.068719468297354\n",
      "Gen 29: Best fitness: 10.068719468297354\n",
      "Gen 30: Best fitness: 10.068719468297354\n",
      "Gen 31: Best fitness: 10.068719468297354\n",
      "Gen 32: Best fitness: 10.068719468297354\n",
      "Gen 33: Best fitness: 10.068719468297354\n",
      "Gen 34: Best fitness: 10.068719468297354\n",
      "Gen 35: Best fitness: 10.068719468297354\n",
      "Gen 36: Best fitness: 10.068719468297354\n",
      "Gen 37: Best fitness: 10.068719468297354\n",
      "Gen 38: Best fitness: 10.068719468297354\n",
      "Gen 39: Best fitness: 10.068719468297354\n",
      "Gen 40: Best fitness: 10.068719468297354\n",
      "Gen 41: Best fitness: 10.068719468297354\n",
      "Gen 42: Best fitness: 10.068719468297354\n",
      "Gen 43: Best fitness: 10.068719468297354\n",
      "Gen 44: Best fitness: 10.068719468297354\n",
      "Gen 45: Best fitness: 10.068719468297354\n",
      "Gen 46: Best fitness: 10.068719468297354\n",
      "Gen 47: Best fitness: 10.068719468297354\n",
      "Gen 48: Best fitness: 10.068719468297354\n",
      "Gen 49: Best fitness: 10.068719468297354\n"
     ]
    }
   ],
   "source": [
    "# Parameters for the genetic algorithm\n",
    "population = toolbox.population(n=300)\n",
    "NGEN = 50\n",
    "CXPB, MUTPB = 0.5, 0.2\n",
    "\n",
    "# Run the genetic algorithm\n",
    "for gen in range(NGEN):\n",
    "    offspring = algorithms.varAnd(population, toolbox, cxpb=CXPB, mutpb=MUTPB)\n",
    "    fits = map(toolbox.evaluate, offspring)\n",
    "    \n",
    "    for fit, ind in zip(fits, offspring):\n",
    "        ind.fitness.values = fit\n",
    "\n",
    "    population = toolbox.select(offspring, k=len(population))\n",
    "    best_ind = tools.selBest(population, 1)[0]\n",
    "    print(f\"Gen {gen}: Best fitness: {best_ind.fitness.values[0]}\")\n",
    "\n",
    "# Extract the best individual (team) and ensure no duplicate members for the second team\n",
    "best_team = tools.selBest(population, 1)[0]\n",
    "\n",
    "# Function to ensure no duplicate players in second team\n",
    "def create_second_team(exclude_players):\n",
    "    while True:\n",
    "        team = []\n",
    "        while len(team) < 5:\n",
    "            player = random.randint(1, len(df))\n",
    "            if player not in exclude_players and player not in [p[0] for p in team] and df.loc[df['id'] == player, 'most_pick_role'].values[0] not in [p[1] for p in team]:\n",
    "                team.append((player, df.loc[df['id'] == player, 'most_pick_role'].values[0]))\n",
    "        if len(set([p[1] for p in team])) == 5:  # Ensure all roles are unique\n",
    "            return creator.Individual(team)\n",
    "\n",
    "# Exclude players in the best_team to create the second team\n",
    "exclude_players = [player_id for player_id, _ in best_team]\n",
    "team2 = create_second_team(exclude_players)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Display Teams"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Team 1: [(9393, 'marksman'), (9711, 'explaner'), (9881, 'roamer'), (9776, 'jungler'), (9294, 'midlaner')]\n",
      "Team 2: [(6063, 'midlaner'), (9885, 'jungler'), (4678, 'explaner'), (745, 'roamer'), (9124, 'marksman')]\n"
     ]
    }
   ],
   "source": [
    "# Display teams with proper role mapping\n",
    "def display_team(team):\n",
    "    return [(player_id, role_dict[role_dict_inverse[role]]) for player_id, role in team]\n",
    "\n",
    "print(\"Team 1:\", display_team(best_team))\n",
    "print(\"Team 2:\", display_team(team2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Section: Evaluates the balance between the two teams based on the difference in average winrates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Team Balance Evaluation:\n",
      "Both teams are balanced. Score difference: 1.61 with a threshold of 3\n"
     ]
    }
   ],
   "source": [
    "threshold = 3  # Threshold for the difference in winrates\n",
    "\n",
    "def evaluate_balance(team1, team2):\n",
    "    # Extract roles for each team\n",
    "    roles_team1 = [role for _, role in team1]\n",
    "    roles_team2 = [role for _, role in team2]\n",
    "    # Check if each team has all roles covered\n",
    "    unique_roles = set(roles_team1 + roles_team2)\n",
    "    if len(unique_roles) != 5:\n",
    "        return \"Teams are unbalanced as not all roles are represented.\"\n",
    "\n",
    "    # Calculate average winrate for each team\n",
    "    avg_score_team1 = sum(df.loc[df['id'].isin([player_id for player_id, _ in team1]), 'winrate']) / 5\n",
    "    avg_score_team2 = sum(df.loc[df['id'].isin([player_id for player_id, _ in team2]), 'winrate']) / 5\n",
    "    \n",
    "    # Calculate the absolute difference in average winrates between the two teams\n",
    "    diff = abs(avg_score_team1 - avg_score_team2)\n",
    "    \n",
    "    # Check if the difference is within the threshold\n",
    "    if diff <= threshold:  # Threshold for the difference in winrates\n",
    "        return f\"Both teams are balanced. Score difference: {diff:.2f}\"\n",
    "    else:\n",
    "        return f\"Both teams are unbalanced. Score difference: {diff:.2f}\"\n",
    "\n",
    "evaluation = evaluate_balance(best_team, team2)\n",
    "print(\"Team Balance Evaluation:\")\n",
    "print(f\"{evaluation} with a threshold of {threshold}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}