goal-prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['data.csv']\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "import os\n",
    "print(os.listdir('../input/'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(30697, 28)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# reading the data\n",
    "\n",
    "data = pd.read_csv('../input/data.csv')\n",
    "data.shape"
   ]
  },
  {
   "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>Unnamed: 0</th>\n",
       "      <th>match_event_id</th>\n",
       "      <th>location_x</th>\n",
       "      <th>location_y</th>\n",
       "      <th>remaining_min</th>\n",
       "      <th>power_of_shot</th>\n",
       "      <th>knockout_match</th>\n",
       "      <th>game_season</th>\n",
       "      <th>remaining_sec</th>\n",
       "      <th>distance_of_shot</th>\n",
       "      <th>is_goal</th>\n",
       "      <th>area_of_shot</th>\n",
       "      <th>shot_basics</th>\n",
       "      <th>range_of_shot</th>\n",
       "      <th>team_name</th>\n",
       "      <th>date_of_game</th>\n",
       "      <th>home/away</th>\n",
       "      <th>shot_id_number</th>\n",
       "      <th>lat/lng</th>\n",
       "      <th>type_of_shot</th>\n",
       "      <th>type_of_combined_shot</th>\n",
       "      <th>match_id</th>\n",
       "      <th>team_id</th>\n",
       "      <th>remaining_min.1</th>\n",
       "      <th>power_of_shot.1</th>\n",
       "      <th>knockout_match.1</th>\n",
       "      <th>remaining_sec.1</th>\n",
       "      <th>distance_of_shot.1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>167.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2000-01</td>\n",
       "      <td>27.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Right Side(R)</td>\n",
       "      <td>Mid Range</td>\n",
       "      <td>16-24 ft.</td>\n",
       "      <td>Manchester United</td>\n",
       "      <td>2000-10-31</td>\n",
       "      <td>MANU @ POR</td>\n",
       "      <td>1.0</td>\n",
       "      <td>45.539131, -122.651648</td>\n",
       "      <td>shot - 30</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20000012</td>\n",
       "      <td>1610612747</td>\n",
       "      <td>10.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>50.608</td>\n",
       "      <td>54.2000</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>-157.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2000-01</td>\n",
       "      <td>22.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Left Side(L)</td>\n",
       "      <td>Mid Range</td>\n",
       "      <td>8-16 ft.</td>\n",
       "      <td>Manchester United</td>\n",
       "      <td>2000-10-31</td>\n",
       "      <td>MANU @ POR</td>\n",
       "      <td>2.0</td>\n",
       "      <td>45.539131, -122.651648</td>\n",
       "      <td>shot - 45</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20000012</td>\n",
       "      <td>1610612747</td>\n",
       "      <td>10.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>28.800</td>\n",
       "      <td>22.0000</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>35.0</td>\n",
       "      <td>-101.0</td>\n",
       "      <td>135.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2000-01</td>\n",
       "      <td>45.0</td>\n",
       "      <td>36.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Left Side Center(LC)</td>\n",
       "      <td>Mid Range</td>\n",
       "      <td>16-24 ft.</td>\n",
       "      <td>Manchester United</td>\n",
       "      <td>2000-10-31</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.0</td>\n",
       "      <td>45.539131, -122.651648</td>\n",
       "      <td>shot - 25</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20000012</td>\n",
       "      <td>1610612747</td>\n",
       "      <td>92.64</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>63.7216</td>\n",
       "      <td>54.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>43.0</td>\n",
       "      <td>138.0</td>\n",
       "      <td>175.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2000-01</td>\n",
       "      <td>52.0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Right Side Center(RC)</td>\n",
       "      <td>Mid Range</td>\n",
       "      <td>16-24 ft.</td>\n",
       "      <td>Manchester United</td>\n",
       "      <td>2000-10-31</td>\n",
       "      <td>MANU @ POR</td>\n",
       "      <td>4.0</td>\n",
       "      <td>45.539131, -122.651648</td>\n",
       "      <td>NaN</td>\n",
       "      <td>shot - 3</td>\n",
       "      <td>20000012</td>\n",
       "      <td>1610612747</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>122.608</td>\n",
       "      <td>52.0000</td>\n",
       "      <td>42.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>155.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2000-01</td>\n",
       "      <td>19.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Center(C)</td>\n",
       "      <td>Goal Area</td>\n",
       "      <td>Less Than 8 ft.</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2000-10-31</td>\n",
       "      <td>MANU @ POR</td>\n",
       "      <td>5.0</td>\n",
       "      <td>45.539131, -122.651648</td>\n",
       "      <td>NaN</td>\n",
       "      <td>shot - 1</td>\n",
       "      <td>20000012</td>\n",
       "      <td>1610612747</td>\n",
       "      <td>42.64</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>19.0000</td>\n",
       "      <td>20.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0         ...          distance_of_shot.1\n",
       "0           0         ...                        38.0\n",
       "1           1         ...                        35.0\n",
       "2           2         ...                        54.4\n",
       "3           3         ...                        42.0\n",
       "4           4         ...                        20.0\n",
       "\n",
       "[5 rows x 28 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Unnamed: 0</th>\n",
       "      <th>match_event_id</th>\n",
       "      <th>location_x</th>\n",
       "      <th>location_y</th>\n",
       "      <th>remaining_min</th>\n",
       "      <th>power_of_shot</th>\n",
       "      <th>knockout_match</th>\n",
       "      <th>remaining_sec</th>\n",
       "      <th>distance_of_shot</th>\n",
       "      <th>is_goal</th>\n",
       "      <th>shot_id_number</th>\n",
       "      <th>match_id</th>\n",
       "      <th>team_id</th>\n",
       "      <th>remaining_min.1</th>\n",
       "      <th>power_of_shot.1</th>\n",
       "      <th>knockout_match.1</th>\n",
       "      <th>remaining_sec.1</th>\n",
       "      <th>distance_of_shot.1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>30697.000000</td>\n",
       "      <td>29134.000000</td>\n",
       "      <td>29236.000000</td>\n",
       "      <td>29157.000000</td>\n",
       "      <td>29135.000000</td>\n",
       "      <td>29211.000000</td>\n",
       "      <td>29180.000000</td>\n",
       "      <td>29103.000000</td>\n",
       "      <td>29130.000000</td>\n",
       "      <td>24429.000000</td>\n",
       "      <td>29134.000000</td>\n",
       "      <td>3.069700e+04</td>\n",
       "      <td>3.069700e+04</td>\n",
       "      <td>29162.000000</td>\n",
       "      <td>29158.000000</td>\n",
       "      <td>29204.000000</td>\n",
       "      <td>29158.000000</td>\n",
       "      <td>29129.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>15348.000000</td>\n",
       "      <td>249.576028</td>\n",
       "      <td>7.383876</td>\n",
       "      <td>91.126933</td>\n",
       "      <td>4.883233</td>\n",
       "      <td>2.519359</td>\n",
       "      <td>0.145956</td>\n",
       "      <td>28.329382</td>\n",
       "      <td>33.448884</td>\n",
       "      <td>0.445331</td>\n",
       "      <td>15368.581039</td>\n",
       "      <td>2.476407e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>18.204615</td>\n",
       "      <td>15.994109</td>\n",
       "      <td>16.599402</td>\n",
       "      <td>39.027303</td>\n",
       "      <td>38.801852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>8861.604943</td>\n",
       "      <td>150.186019</td>\n",
       "      <td>110.263049</td>\n",
       "      <td>87.676395</td>\n",
       "      <td>3.452533</td>\n",
       "      <td>1.153976</td>\n",
       "      <td>0.353068</td>\n",
       "      <td>17.470663</td>\n",
       "      <td>9.369656</td>\n",
       "      <td>0.497013</td>\n",
       "      <td>8866.520772</td>\n",
       "      <td>7.755175e+06</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>29.416973</td>\n",
       "      <td>29.676815</td>\n",
       "      <td>35.172016</td>\n",
       "      <td>29.835284</td>\n",
       "      <td>18.787711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>-250.000000</td>\n",
       "      <td>-44.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000001e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>9.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>7674.000000</td>\n",
       "      <td>111.000000</td>\n",
       "      <td>-68.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7693.250000</td>\n",
       "      <td>2.050008e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>26.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>15348.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>74.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>15378.500000</td>\n",
       "      <td>2.090035e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>36.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>23022.000000</td>\n",
       "      <td>369.000000</td>\n",
       "      <td>95.000000</td>\n",
       "      <td>160.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>23055.750000</td>\n",
       "      <td>2.960047e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>44.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>30696.000000</td>\n",
       "      <td>659.000000</td>\n",
       "      <td>248.000000</td>\n",
       "      <td>791.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>30697.000000</td>\n",
       "      <td>4.990009e+07</td>\n",
       "      <td>1.610613e+09</td>\n",
       "      <td>128.761600</td>\n",
       "      <td>118.360000</td>\n",
       "      <td>141.352320</td>\n",
       "      <td>144.785600</td>\n",
       "      <td>115.728000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Unnamed: 0         ...          distance_of_shot.1\n",
       "count  30697.000000         ...                29129.000000\n",
       "mean   15348.000000         ...                   38.801852\n",
       "std     8861.604943         ...                   18.787711\n",
       "min        0.000000         ...                    9.400000\n",
       "25%     7674.000000         ...                   26.000000\n",
       "50%    15348.000000         ...                   36.000000\n",
       "75%    23022.000000         ...                   44.000000\n",
       "max    30696.000000         ...                  115.728000\n",
       "\n",
       "[8 rows x 18 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Unnamed: 0                   0\n",
       "match_event_id            1563\n",
       "location_x                1461\n",
       "location_y                1540\n",
       "remaining_min             1562\n",
       "power_of_shot             1486\n",
       "knockout_match            1517\n",
       "game_season               5862\n",
       "remaining_sec             1594\n",
       "distance_of_shot          1567\n",
       "is_goal                   6268\n",
       "area_of_shot              1502\n",
       "shot_basics               1575\n",
       "range_of_shot             1564\n",
       "team_name                 1535\n",
       "date_of_game              1550\n",
       "home/away                 1497\n",
       "shot_id_number            1563\n",
       "lat/lng                   1565\n",
       "type_of_shot             15280\n",
       "type_of_combined_shot    15417\n",
       "match_id                     0\n",
       "team_id                      0\n",
       "remaining_min.1           1535\n",
       "power_of_shot.1           1539\n",
       "knockout_match.1          1493\n",
       "remaining_sec.1           1539\n",
       "distance_of_shot.1        1568\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Unnamed: 0                  0\n",
       "match_event_id              0\n",
       "location_x                  0\n",
       "location_y                  0\n",
       "remaining_min               0\n",
       "power_of_shot               0\n",
       "knockout_match              0\n",
       "game_season                 0\n",
       "remaining_sec               0\n",
       "distance_of_shot            0\n",
       "is_goal                  6268\n",
       "area_of_shot                0\n",
       "shot_basics                 0\n",
       "range_of_shot               0\n",
       "team_name                   0\n",
       "date_of_game                0\n",
       "home/away                   0\n",
       "shot_id_number              0\n",
       "lat/lng                     0\n",
       "type_of_shot                0\n",
       "type_of_combined_shot       0\n",
       "match_id                    0\n",
       "team_id                     0\n",
       "remaining_min.1             0\n",
       "power_of_shot.1             0\n",
       "knockout_match.1            0\n",
       "remaining_sec.1             0\n",
       "distance_of_shot.1          0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# filling the missing values\n",
    "\n",
    "data['match_event_id'].fillna(data['match_event_id'].mean(), inplace = True)\n",
    "data['location_x'].fillna(data['location_x'].mean(), inplace = True)\n",
    "data['location_y'].fillna(data['location_y'].mean(), inplace = True)\n",
    "data['remaining_min'].fillna(data['remaining_min'].mean(), inplace = True)\n",
    "data['power_of_shot'].fillna(data['power_of_shot'].mean(), inplace = True)\n",
    "data['knockout_match'].fillna(data['knockout_match'].mean(), inplace = True)\n",
    "data['game_season'].fillna(data['game_season'].mode()[0], inplace = True)\n",
    "data['remaining_sec'].fillna(data['remaining_sec'].mean(), inplace = True)\n",
    "data['distance_of_shot'].fillna(data['distance_of_shot'].mean(), inplace = True)\n",
    "data['area_of_shot'].fillna(data['area_of_shot'].mode()[0], inplace = True)\n",
    "data['shot_basics'].fillna(data['shot_basics'].mode()[0], inplace = True)\n",
    "data['range_of_shot'].fillna(data['range_of_shot'].mode()[0], inplace = True)\n",
    "data['team_name'].fillna(data['team_name'].mode()[0], inplace = True)\n",
    "data['date_of_game'].fillna(data['date_of_game'].mode()[0], inplace = True)\n",
    "data['home/away'].fillna(data['home/away'].mode()[0], inplace = True)\n",
    "data['shot_id_number'].interpolate(method = 'linear', inplace = True)\n",
    "data['type_of_shot'].fillna(data['type_of_shot'].mode()[0], inplace = True)\n",
    "data['type_of_combined_shot'].fillna(data['type_of_combined_shot'].mode()[0], inplace = True)\n",
    "data['remaining_min.1'].fillna(data['remaining_min.1'].mean(), inplace = True)\n",
    "data['power_of_shot.1'].fillna(data['power_of_shot.1'].mean(), inplace = True)\n",
    "data['knockout_match.1'].fillna(data['knockout_match.1'].mean(), inplace = True)\n",
    "data['remaining_sec.1'].fillna(data['remaining_sec.1'].mean(), inplace = True)\n",
    "data['distance_of_shot.1'].fillna(data['distance_of_shot.1'].mean(), inplace = True)\n",
    "data['lat/lng'].fillna(data['lat/lng'].mode()[0], inplace = True)\n",
    "\n",
    "data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.rcParams['figure.figsize'] = (15, 15)\n",
    "sns.heatmap(data.corr(), annot = True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['location_x', 'location_y', 'remaining_min', 'power_of_shot',\n",
       "       'knockout_match', 'game_season', 'remaining_sec', 'distance_of_shot',\n",
       "       'is_goal', 'area_of_shot', 'shot_basics', 'range_of_shot', 'team_name',\n",
       "       'date_of_game', 'shot_id_number', 'lat/lng', 'type_of_shot',\n",
       "       'type_of_combined_shot', 'remaining_min.1', 'power_of_shot.1',\n",
       "       'knockout_match.1', 'remaining_sec.1', 'distance_of_shot.1'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's delete some unnecassary columns\n",
    "\n",
    "data = data.drop(['Unnamed: 0', 'team_id', 'match_id','match_event_id', 'home/away'], axis = 1)\n",
    "data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type_of_combined_shot</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>shot - 0</th>\n",
       "      <td>0.737705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 1</th>\n",
       "      <td>0.927660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 2</th>\n",
       "      <td>0.560606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 3</th>\n",
       "      <td>0.422079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 4</th>\n",
       "      <td>0.566463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 5</th>\n",
       "      <td>0.347222</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        is_goal\n",
       "                           mean\n",
       "type_of_combined_shot          \n",
       "shot - 0               0.737705\n",
       "shot - 1               0.927660\n",
       "shot - 2               0.560606\n",
       "shot - 3               0.422079\n",
       "shot - 4               0.566463\n",
       "shot - 5               0.347222"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[['is_goal', 'type_of_combined_shot']].groupby(['type_of_combined_shot']).agg(['mean'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.42    27102\n",
       "0.56     3345\n",
       "0.34       90\n",
       "0.92       82\n",
       "0.73       78\n",
       "Name: type_of_combined_shot, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# target encoding for combined shot\n",
    "\n",
    "data['type_of_combined_shot'].replace(('shot - 0', 'shot - 2', 'shot - 1', 'shot - 3',\n",
    "                                      'shot - 4', 'shot - 5'), (0.73, 0.92, 0.56, 0.42, 0.56, 0.34), inplace = True)\n",
    "\n",
    "data['type_of_combined_shot'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type_of_shot</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>shot - 0</th>\n",
       "      <td>0.431579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 1</th>\n",
       "      <td>0.502924</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 10</th>\n",
       "      <td>0.405882</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 11</th>\n",
       "      <td>0.387387</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 12</th>\n",
       "      <td>0.667808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 13</th>\n",
       "      <td>0.280000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 14</th>\n",
       "      <td>0.313559</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 15</th>\n",
       "      <td>0.527076</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 16</th>\n",
       "      <td>0.433566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 17</th>\n",
       "      <td>0.578431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 18</th>\n",
       "      <td>0.414474</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 19</th>\n",
       "      <td>0.427536</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 2</th>\n",
       "      <td>0.330769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 20</th>\n",
       "      <td>0.341270</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 21</th>\n",
       "      <td>0.390625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 22</th>\n",
       "      <td>0.343511</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 23</th>\n",
       "      <td>0.300813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 24</th>\n",
       "      <td>0.460993</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 25</th>\n",
       "      <td>0.267241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 26</th>\n",
       "      <td>0.426752</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 27</th>\n",
       "      <td>0.426829</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 28</th>\n",
       "      <td>0.303571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 29</th>\n",
       "      <td>0.359155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 3</th>\n",
       "      <td>0.375000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 30</th>\n",
       "      <td>0.275000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 31</th>\n",
       "      <td>0.468927</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 32</th>\n",
       "      <td>0.690763</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 33</th>\n",
       "      <td>0.362745</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 34</th>\n",
       "      <td>0.275510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 35</th>\n",
       "      <td>0.361111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 36</th>\n",
       "      <td>0.312860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 37</th>\n",
       "      <td>0.297297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 38</th>\n",
       "      <td>0.514395</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 39</th>\n",
       "      <td>0.440102</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 4</th>\n",
       "      <td>0.690286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 40</th>\n",
       "      <td>0.359649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 41</th>\n",
       "      <td>0.345133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 42</th>\n",
       "      <td>0.311475</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 43</th>\n",
       "      <td>0.490566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 44</th>\n",
       "      <td>0.677618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 45</th>\n",
       "      <td>0.311475</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 46</th>\n",
       "      <td>0.501859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 47</th>\n",
       "      <td>0.329787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 48</th>\n",
       "      <td>0.419847</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 49</th>\n",
       "      <td>0.316940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 5</th>\n",
       "      <td>0.348485</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 50</th>\n",
       "      <td>0.264463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 51</th>\n",
       "      <td>0.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 52</th>\n",
       "      <td>0.577617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 53</th>\n",
       "      <td>0.325581</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 54</th>\n",
       "      <td>0.435484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 55</th>\n",
       "      <td>0.411392</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 56</th>\n",
       "      <td>0.576419</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 6</th>\n",
       "      <td>0.316667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 7</th>\n",
       "      <td>0.281553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 8</th>\n",
       "      <td>0.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot - 9</th>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               is_goal\n",
       "                  mean\n",
       "type_of_shot          \n",
       "shot - 0      0.431579\n",
       "shot - 1      0.502924\n",
       "shot - 10     0.405882\n",
       "shot - 11     0.387387\n",
       "shot - 12     0.667808\n",
       "shot - 13     0.280000\n",
       "shot - 14     0.313559\n",
       "shot - 15     0.527076\n",
       "shot - 16     0.433566\n",
       "shot - 17     0.578431\n",
       "shot - 18     0.414474\n",
       "shot - 19     0.427536\n",
       "shot - 2      0.330769\n",
       "shot - 20     0.341270\n",
       "shot - 21     0.390625\n",
       "shot - 22     0.343511\n",
       "shot - 23     0.300813\n",
       "shot - 24     0.460993\n",
       "shot - 25     0.267241\n",
       "shot - 26     0.426752\n",
       "shot - 27     0.426829\n",
       "shot - 28     0.303571\n",
       "shot - 29     0.359155\n",
       "shot - 3      0.375000\n",
       "shot - 30     0.275000\n",
       "shot - 31     0.468927\n",
       "shot - 32     0.690763\n",
       "shot - 33     0.362745\n",
       "shot - 34     0.275510\n",
       "shot - 35     0.361111\n",
       "shot - 36     0.312860\n",
       "shot - 37     0.297297\n",
       "shot - 38     0.514395\n",
       "shot - 39     0.440102\n",
       "shot - 4      0.690286\n",
       "shot - 40     0.359649\n",
       "shot - 41     0.345133\n",
       "shot - 42     0.311475\n",
       "shot - 43     0.490566\n",
       "shot - 44     0.677618\n",
       "shot - 45     0.311475\n",
       "shot - 46     0.501859\n",
       "shot - 47     0.329787\n",
       "shot - 48     0.419847\n",
       "shot - 49     0.316940\n",
       "shot - 5      0.348485\n",
       "shot - 50     0.264463\n",
       "shot - 51     0.250000\n",
       "shot - 52     0.577617\n",
       "shot - 53     0.325581\n",
       "shot - 54     0.435484\n",
       "shot - 55     0.411392\n",
       "shot - 56     0.576419\n",
       "shot - 6      0.316667\n",
       "shot - 7      0.281553\n",
       "shot - 8      0.500000\n",
       "shot - 9      0.333333"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[['is_goal', 'type_of_shot']].groupby(['type_of_shot']).agg(['mean'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.44    16725\n",
       "0.31     2118\n",
       "0.69     1432\n",
       "0.57     1010\n",
       "0.52      701\n",
       "0.50      685\n",
       "0.51      676\n",
       "0.34      645\n",
       "0.67      609\n",
       "0.42      565\n",
       "0.41      544\n",
       "0.43      460\n",
       "0.49      400\n",
       "0.46      397\n",
       "0.66      361\n",
       "0.33      334\n",
       "0.35      325\n",
       "0.30      296\n",
       "0.27      287\n",
       "0.28      286\n",
       "0.26      283\n",
       "0.32      276\n",
       "0.36      272\n",
       "0.40      197\n",
       "0.25      196\n",
       "0.39      165\n",
       "0.37      165\n",
       "0.29      150\n",
       "0.38      137\n",
       "Name: type_of_shot, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# target encoding for type of shot\n",
    "\n",
    "data['type_of_shot'].replace(('shot - 0', 'shot - 1','shot - 10', 'shot - 11', 'shot - 12', 'shot - 13','shot - 14',\n",
    "                              'shot - 15', 'shot - 16', 'shot - 17','shot - 18','shot - 19','shot - 2', 'shot - 20',\n",
    "                             'shot - 21', 'shot - 22', 'shot - 23','shot - 24', 'shot - 25', 'shot - 26','shot - 27', \n",
    "                              'shot - 28', 'shot - 29','shot - 3','shot - 30', 'shot - 31', 'shot - 32','shot - 33', 'shot - 34',\n",
    "                              'shot - 35','shot - 36','shot - 37','shot - 38', 'shot - 39','shot - 4', 'shot - 40','shot - 41', 'shot - 42',\n",
    "                              'shot - 43', 'shot - 44', 'shot - 45','shot - 46','shot - 47','shot - 48', 'shot - 49','shot - 5',\n",
    "                              'shot - 50','shot - 51','shot - 52','shot - 53', 'shot - 54', 'shot - 55', 'shot - 56', 'shot - 6','shot - 7','shot - 8',\n",
    "                             'shot - 9'), (0.43, 0.5, 0.4, 0.38, 0.66, 0.28, 0.31, 0.52, 0.43, 0.57, 0.41, 0.42, 0.33, 0.34,\n",
    "                                          0.39, 0.34,0.30, 0.46, 0.26, 0.42, 0.42, 0.30, 0.35, 0.37, 0.27, 0.46, 0.69, 0.36,\n",
    "                                          0.27, 0.36, 0.31, 0.29, 0.51, 0.44, 0.69, 0.35, 0.34, 0.31, 0.49, 0.67, 0.31, \n",
    "                                          0.50, 0.32, 0.41, 0.31, 0.34, 0.26, 0.25, 0.57, 0.32, 0.43, 0.41, 0.57, 0.31, 0.28,\n",
    "                                          0.50, 0.33), inplace = True)\n",
    "\n",
    "data['type_of_shot'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    14182\n",
       "3    10497\n",
       "1     5937\n",
       "0       81\n",
       "Name: range_of_shot, dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's target encode the range of shot\n",
    "\n",
    "data['range_of_shot'].replace(('16-24 ft.', '24+ ft.', '8-16 ft.',\n",
    "                            'Back Court Shot', 'Less Than 8 ft.'), (2, 1, 2, 0, 3), inplace = True)\n",
    "\n",
    "data['range_of_shot'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shot_basics</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Goal Area</th>\n",
       "      <td>0.618073</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Goal Line</th>\n",
       "      <td>0.453485</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Left Corner</th>\n",
       "      <td>0.365741</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mid Ground Line</th>\n",
       "      <td>0.017544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mid Range</th>\n",
       "      <td>0.408133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Penalty Spot</th>\n",
       "      <td>0.334040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Right Corner</th>\n",
       "      <td>0.334437</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  is_goal\n",
       "                     mean\n",
       "shot_basics              \n",
       "Goal Area        0.618073\n",
       "Goal Line        0.453485\n",
       "Left Corner      0.365741\n",
       "Mid Ground Line  0.017544\n",
       "Mid Range        0.408133\n",
       "Penalty Spot     0.334040\n",
       "Right Corner     0.334437"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[['is_goal', 'shot_basics']].groupby(['shot_basics']).agg(['mean'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.25    13530\n",
       "0.50     6787\n",
       "0.30     5321\n",
       "0.44     4357\n",
       "0.00      434\n",
       "0.75      268\n",
       "Name: shot_basics, dtype: int64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's target encode the area of shot \n",
    "\n",
    "data['shot_basics'].replace(('Goal Area', 'Goal Line', 'Left Corner', 'Mid Ground Line',\n",
    "                            'Mid Range', 'Penalty Spot', 'Right Corner'), (0.5, 0.44, 0.75, 0, 0.25, 0.3, 0), inplace = True)\n",
    "\n",
    "data['shot_basics'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>area_of_shot</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Center(C)</th>\n",
       "      <td>0.517915</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Left Side Center(LC)</th>\n",
       "      <td>0.363576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Left Side(L)</th>\n",
       "      <td>0.392556</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mid Ground(MG)</th>\n",
       "      <td>0.014085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Right Side Center(RC)</th>\n",
       "      <td>0.382743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Right Side(R)</th>\n",
       "      <td>0.396975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        is_goal\n",
       "                           mean\n",
       "area_of_shot                   \n",
       "Center(C)              0.517915\n",
       "Left Side Center(LC)   0.363576\n",
       "Left Side(L)           0.392556\n",
       "Mid Ground(MG)         0.014085\n",
       "Right Side Center(RC)  0.382743\n",
       "Right Side(R)          0.396975"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[['is_goal', 'area_of_shot']].groupby(['area_of_shot']).agg(['mean'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.44    14263\n",
       "0.25     4562\n",
       "0.15     4370\n",
       "0.30     3848\n",
       "0.35     3573\n",
       "0.00       81\n",
       "Name: area_of_shot, dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's target encode the area of shot \n",
    "\n",
    "data['area_of_shot'].replace(('Center(C)', 'Left Side Center(LC)', 'Left Side(L)',\n",
    "                             'Mid Ground(MG)', 'Right Side Center(RC)', 'Right Side(R)'), (0.44, 0.3, 0.35, 0, 0.25, 0.15), \n",
    "                             inplace = True)\n",
    "\n",
    "data['area_of_shot'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>game_season</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1996-97</th>\n",
       "      <td>0.422680</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997-98</th>\n",
       "      <td>0.424242</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998-99</th>\n",
       "      <td>0.467797</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1999-00</th>\n",
       "      <td>0.453629</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01</th>\n",
       "      <td>0.466946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2001-02</th>\n",
       "      <td>0.470992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002-03</th>\n",
       "      <td>0.437369</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2003-04</th>\n",
       "      <td>0.439351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2004-05</th>\n",
       "      <td>0.439724</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2005-06</th>\n",
       "      <td>0.449902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2006-07</th>\n",
       "      <td>0.459043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2007-08</th>\n",
       "      <td>0.459016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-09</th>\n",
       "      <td>0.462571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2009-10</th>\n",
       "      <td>0.453421</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-11</th>\n",
       "      <td>0.438855</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2011-12</th>\n",
       "      <td>0.414456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-13</th>\n",
       "      <td>0.452107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013-14</th>\n",
       "      <td>0.377778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014-15</th>\n",
       "      <td>0.364979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015-16</th>\n",
       "      <td>0.357143</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              is_goal\n",
       "                 mean\n",
       "game_season          \n",
       "1996-97      0.422680\n",
       "1997-98      0.424242\n",
       "1998-99      0.467797\n",
       "1999-00      0.453629\n",
       "2000-01      0.466946\n",
       "2001-02      0.470992\n",
       "2002-03      0.437369\n",
       "2003-04      0.439351\n",
       "2004-05      0.439724\n",
       "2005-06      0.449902\n",
       "2006-07      0.459043\n",
       "2007-08      0.459016\n",
       "2008-09      0.462571\n",
       "2009-10      0.453421\n",
       "2010-11      0.438855\n",
       "2011-12      0.414456\n",
       "2012-13      0.452107\n",
       "2013-14      0.377778\n",
       "2014-15      0.364979\n",
       "2015-16      0.357143"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[['game_season', 'is_goal']].groupby(['game_season']).agg(['mean'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# let;s target encode the data using the above values\n",
    "\n",
    "data['game_season'].replace(('1996-97','1997-98','1998-99','1999-00','2000-01','2001-02','2002-03',\n",
    "'2003-04','2004-05','2005-06','2006-07','2007-08','2008-09','2009-10','2010-11','2011-12','2012-13','2013-14',\n",
    "'2014-15','2015-16'), (0.422680,0.424242,0.467797,0.453629,0.466946,0.470992,0.437369,0.439351,0.439724,0.449902,0.459043,0.459016,\n",
    "0.462571,0.453421,0.438855,0.414456,0.452107,0.377778,0.364979,0.357143), inplace = True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.449902    7773\n",
       "0.437369    1823\n",
       "0.462571    1810\n",
       "0.459016    1733\n",
       "0.453421    1665\n",
       "0.470992    1632\n",
       "0.459043    1537\n",
       "0.466946    1488\n",
       "0.438855    1462\n",
       "0.439351    1329\n",
       "0.414456    1326\n",
       "0.452107    1296\n",
       "0.453629    1264\n",
       "0.439724    1074\n",
       "0.357143     893\n",
       "0.424242     804\n",
       "0.467797     752\n",
       "0.364979     594\n",
       "0.422680     381\n",
       "0.377778      61\n",
       "Name: game_season, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['game_season'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['location_x', 'location_y', 'remaining_min', 'power_of_shot',\n",
       "       'knockout_match', 'game_season', 'remaining_sec', 'distance_of_shot',\n",
       "       'is_goal', 'area_of_shot', 'shot_basics', 'range_of_shot',\n",
       "       'shot_id_number', 'type_of_shot', 'type_of_combined_shot',\n",
       "       'remaining_min.1', 'power_of_shot.1', 'knockout_match.1',\n",
       "       'remaining_sec.1', 'distance_of_shot.1'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's delete some unnecassary columns\n",
    "\n",
    "data = data.drop(['team_name', 'date_of_game', 'lat/lng'], axis = 1)\n",
    "\n",
    "data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6268, 19)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train = data.dropna()\n",
    "test = data[data['is_goal'].isna() == True]\n",
    "\n",
    "test = test.drop(['is_goal'], axis = 1)\n",
    "test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(24429, 19)\n",
      "(24429,)\n",
      "(6268, 19)\n"
     ]
    }
   ],
   "source": [
    "y_train = train['is_goal']\n",
    "x_train = train.drop(['is_goal'], axis = 1)\n",
    "x_test = test\n",
    "\n",
    "print(x_train.shape)\n",
    "print(y_train.shape)\n",
    "print(x_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(19543, 19)\n",
      "(4886, 19)\n",
      "(19543,)\n",
      "(4886,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x_train, x_valid, y_train, y_valid = train_test_split(x_train, y_train, test_size = 0.2, random_state = 0)\n",
    "\n",
    "print(x_train.shape)\n",
    "print(x_valid.shape)\n",
    "print(y_train.shape)\n",
    "print(y_valid.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# standardization\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "sc = StandardScaler()\n",
    "\n",
    "x_train = sc.fit_transform(x_train)\n",
    "x_valid = sc.transform(x_valid)\n",
    "x_test = sc.fit_transform(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dimensionality reduction\n",
    "\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "pca = PCA(n_components = 15)\n",
    "x_train = pca.fit_transform(x_train)\n",
    "x_valid = pca.transform(x_valid)\n",
    "x_test = pca.transform(x_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "model = RandomForestClassifier(n_estimators = 1500, min_samples_split = 2, max_depth = 10, min_samples_leaf = 5)\n",
    "model.fit(x_train, y_train)\n",
    "\n",
    "y_pred = model.predict_proba(x_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "from lightgbm import LGBMClassifier\n",
    "\n",
    "lightgbm = LGBMClassifier(num_leaves=5,\n",
    "                         learning_rate=0.01, \n",
    "                        n_estimators=5000,\n",
    "                        max_bin=300, \n",
    "                        bagging_fraction=0.75,\n",
    "                        bagging_freq=5, \n",
    "                        bagging_seed=7,\n",
    "                        feature_fraction=0.2,\n",
    "                        feature_fraction_seed=7,\n",
    "                        verbose=-1,\n",
    "                                       )\n",
    "lightgbm.fit(x_train, y_train)\n",
    "y_pred = lightgbm.predict_proba(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>shot_id_number</th>\n",
       "      <th>is_goal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.604824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>0.529539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17.0</td>\n",
       "      <td>0.437914</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20.0</td>\n",
       "      <td>0.229235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>22.0</td>\n",
       "      <td>0.576284</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    shot_id_number   is_goal\n",
       "0              1.0  0.604824\n",
       "7              8.0  0.529539\n",
       "16            17.0  0.437914\n",
       "19            20.0  0.229235\n",
       "21            22.0  0.576284"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission = pd.DataFrame({'shot_id_number': test['shot_id_number'],'is_goal': y_pred[:,0]})\n",
    "\n",
    "#Visualize the first 5 rows\n",
    "submission.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Convert DataFrame to a csv file that can be uploaded\n",
    "#This is saved in the same directory as your notebook\n",
    "filename = 'submission.csv'\n",
    "\n",
    "submission.to_csv(filename,index=False)"
   ]
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}