Winner_Finder.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Example HAWKS vs HEAT prediction for next game\n",
    "#We can fetch team ids for game which we are going to predict \n",
    "#Ex {HAWKS : 101} {HEAT: 112}\n",
    "team1_ID = 101\n",
    "team2_ID = 112 \n",
    "team1_Name = 'Hawks'\n",
    "team2_Name ='Heat'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>tid</th>\n",
       "      <th>tname</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>101</td>\n",
       "      <td>Atlanta Hawks</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>102</td>\n",
       "      <td>Boston Celtics</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>103</td>\n",
       "      <td>Cleveland Cavaliers</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>104</td>\n",
       "      <td>New Orleans Pelicans</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>105</td>\n",
       "      <td>Chicago Bulls</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tid                 tname\n",
       "0  101         Atlanta Hawks\n",
       "1  102        Boston Celtics\n",
       "2  103   Cleveland Cavaliers\n",
       "3  104  New Orleans Pelicans\n",
       "4  105         Chicago Bulls"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "team_data_frame = pd.read_excel('past_record.xlsx',sheet_name='Teams')\n",
    "\n",
    "team_data_frame.head()\n",
    "\n",
    "maindf = pd.read_excel('past_record.xlsx',sheet_name='Schedules')\n",
    "\n",
    "team_data_frame.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Game Played by Hawks : \n",
      "82\n",
      "Total Game win by Hawks : \n",
      "29\n"
     ]
    }
   ],
   "source": [
    "def checkTotalwin(total_df, ID):\n",
    "    \n",
    "    for index, row in total_df.iterrows():\n",
    "        if row['hlstid'] == ID and row['hlsscore'] > row['vlsscore']:\n",
    "            total_df.loc[index, 'winner'] = True   \n",
    "        else:\n",
    "            total_df.loc[index, 'winner'] = False\n",
    "            \n",
    "def checkTotalVisitorWin(total_df, ID):\n",
    "    \n",
    "    for index, row in total_df.iterrows():\n",
    "        if row['vlstid'] == ID and row['hlsscore'] < row['vlsscore']:\n",
    "            total_df.loc[index, 'winner'] = True   \n",
    "\n",
    "            \n",
    "team1_total_df = maindf[(maindf['hlstid'] == team1_ID) | (maindf['vlstid'] == team1_ID)]\n",
    "team1_total_df = team1_total_df.drop_duplicates(subset ='gid') \n",
    "team1TotalGame = len(team1_total_df)\n",
    "\n",
    "checkTotalwin(team1_total_df, team1_ID)\n",
    "checkTotalVisitorWin(team1_total_df, team1_ID)\n",
    "team1_win_df = team1_total_df[team1_total_df['winner'] == True]\n",
    "team1WinTot  = len(team1_win_df)\n",
    "\n",
    "print(\"Total Game Played by \"+team1_Name+\" : \")\n",
    "print(team1TotalGame)\n",
    "print(\"Total Game win by \"+team1_Name+\" : \")\n",
    "print(team1WinTot)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Game Played by Heat : \n",
      "82\n",
      "Total Game win by Heat : \n",
      "39\n"
     ]
    }
   ],
   "source": [
    "team2_total_df = maindf[(maindf['hlstid'] == team2_ID) | (maindf['vlstid'] == team2_ID)]\n",
    "team2_total_df = team2_total_df.drop_duplicates(subset ='gid') \n",
    "team2TotalGame = len(team2_total_df)\n",
    "\n",
    "checkTotalwin(team2_total_df, team2_ID)\n",
    "checkTotalVisitorWin(team2_total_df, team2_ID)\n",
    "team2_win_df = team2_total_df[team2_total_df['winner'] == True]\n",
    "team2WinTot  = len(team2_win_df)\n",
    "\n",
    "print(\"Total Game Played by \"+team2_Name+\" : \")\n",
    "print(team2TotalGame)\n",
    "print(\"Total Game win by \"+team2_Name+\" : \")\n",
    "print(team2WinTot)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True\n"
     ]
    },
    {
     "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>gid</th>\n",
       "      <th>hlsscore</th>\n",
       "      <th>hlstid</th>\n",
       "      <th>vlsscore</th>\n",
       "      <th>vlstid</th>\n",
       "      <th>winner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1009</td>\n",
       "      <td>123</td>\n",
       "      <td>101</td>\n",
       "      <td>118</td>\n",
       "      <td>112</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1021</td>\n",
       "      <td>113</td>\n",
       "      <td>112</td>\n",
       "      <td>115</td>\n",
       "      <td>101</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>1039</td>\n",
       "      <td>106</td>\n",
       "      <td>101</td>\n",
       "      <td>82</td>\n",
       "      <td>112</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>1065</td>\n",
       "      <td>114</td>\n",
       "      <td>112</td>\n",
       "      <td>113</td>\n",
       "      <td>101</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     gid  hlsscore  hlstid  vlsscore  vlstid  winner\n",
       "8   1009       123     101       118     112   False\n",
       "20  1021       113     112       115     101    True\n",
       "38  1039       106     101        82     112   False\n",
       "64  1065       114     112       113     101   False"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "isHomeFirst = False\n",
    "isVisitorFirst = False\n",
    "\n",
    "def checkvswin(total_df, ID):\n",
    "    \n",
    "    for index, row in total_df.iterrows():\n",
    "        if (row['hlstid'] == ID and row['hlsscore'] > row['vlsscore']):\n",
    "            total_df.loc[index, 'winner'] = True   \n",
    "        else:\n",
    "            total_df.loc[index, 'winner'] = False\n",
    "            \n",
    "def checkvsVisitorWin(total_df, ID):\n",
    "    \n",
    "    for index, row in total_df.iterrows():\n",
    "        if (row['vlstid'] == ID and row['vlsscore'] > row['hlsscore']):\n",
    "            total_df.loc[index, 'winner'] = True\n",
    "        else:\n",
    "            total_df.loc[index, 'winner'] = False\n",
    "            \n",
    "def isFirstORSecond(vs_win_df, team1_ID):\n",
    "        global isHomeFirst\n",
    "        global isVisitorFirst\n",
    "        if (vs_win_df['hlstid'].iloc[0] == team1_ID and vs_win_df['hlsscore'].iloc[0] > vs_win_df['vlsscore'].iloc[0] and not vs_win_df['winner'].iloc[0]):\n",
    "            isHomeFirst = True\n",
    "            isVisitorFirst = False\n",
    "            print(isHomeFirst)\n",
    "        elif vs_win_df['vlsscore'].iloc[0] > vs_win_df['hlsscore'].iloc[0] and not vs_win_df['winner'].iloc[0]:\n",
    "            isVisitorFirst = True\n",
    "            isHomeFirst = False\n",
    "            print(isVisitorFirst)\n",
    "            \n",
    "total_vs_df = maindf[(maindf['hlstid'] == team1_ID) | (maindf['vlstid'] == team1_ID)]\n",
    "total_vs_df = total_vs_df[(total_vs_df['hlstid'] == team2_ID) | (total_vs_df['vlstid'] == team2_ID)]\n",
    "total_vs_df = total_vs_df.drop_duplicates(subset ='gid') \n",
    "\n",
    "totalVsGame = len(total_vs_df)\n",
    "\n",
    "checkvswin(total_vs_df, team1_ID)\n",
    "checkvsVisitorWin(total_vs_df, team1_ID)\n",
    "vs_win_df = total_vs_df[total_vs_df['winner'] == False]\n",
    "vsWinTot = len(vs_win_df)\n",
    "isFirstORSecond(vs_win_df, team1_ID)\n",
    "\n",
    "total_vs_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "percent = 100\n",
    "tot_team1_percent = percent/team1TotalGame\n",
    "tot_team1_percent = tot_team1_percent * team1WinTot\n",
    "\n",
    "tot_team2_percent = percent/team2TotalGame\n",
    "tot_team2_percent = tot_team2_percent *  team2WinTot\n",
    "\n",
    "total_dict = {'Team':[team1_Name, team2_Name], 'Percent':[tot_team1_percent, tot_team2_percent]}\n",
    "    \n",
    "total_predict_df = pd.DataFrame(total_dict)\n",
    "\n",
    "tot_vs_percent = percent/totalVsGame\n",
    "tot_vs_team1_percent = tot_vs_percent * vsWinTot\n",
    "tot_vs_team2_percent = percent - tot_vs_team1_percent\n",
    "\n",
    "vs_dict = {}\n",
    "\n",
    "if(isHomeFirst and not isVisitorFirst):\n",
    "    vs_dict = {'Team':[team1_Name, team2_Name], 'Percent':[tot_vs_team1_percent, tot_vs_team2_percent]}\n",
    "else:\n",
    "    vs_dict = {'Team':[team1_Name, team2_Name], 'Percent':[tot_vs_team2_percent, tot_vs_team1_percent]}\n",
    "\n",
    "vs_predict_df = pd.DataFrame(vs_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "***** Overall Prediction *****\n",
      "------------------------------\n"
     ]
    },
    {
     "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>Team</th>\n",
       "      <th>Percent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hawks</td>\n",
       "      <td>35.365854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Heat</td>\n",
       "      <td>47.560976</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Team    Percent\n",
       "0  Hawks  35.365854\n",
       "1   Heat  47.560976"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "print('***** Overall Prediction *****')\n",
    "print('------------------------------')\n",
    "sns.barplot(total_predict_df['Team'],total_predict_df['Percent'])\n",
    "total_predict_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "***** As Opponent Prediction *****\n",
      "----------------------------------\n"
     ]
    },
    {
     "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>Team</th>\n",
       "      <th>Percent</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hawks</td>\n",
       "      <td>75.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Heat</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Team  Percent\n",
       "0  Hawks     75.0\n",
       "1   Heat     25.0"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "print('***** As Opponent Prediction *****')\n",
    "print('----------------------------------')\n",
    "sns.barplot(vs_predict_df['Team'],vs_predict_df['Percent'])\n",
    "vs_predict_df.head()"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}