{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# In Memory of Kobe Bryant "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/jpeg": "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\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 1,
     "metadata": {
      "image/jpeg": {
       "width": 780
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.display import Image\n",
    "Image('C:/Users/Public/medium_kobe/kobe_image.jpg', width=780)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Prerequisite"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Public\\medium_kobe\n",
      "Overall data 30697\n",
      "Kobe 8 data 15381\n",
      "Kobe 24 data 15316\n"
     ]
    }
   ],
   "source": [
    "# Set working directory\n",
    "import os\n",
    "os.chdir(\"C:/Users/Public/medium_kobe/\")\n",
    "print(os.getcwd())\n",
    "\n",
    "# Import library\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import time\n",
    "from datetime import date\n",
    "import ipywidgets as widgets\n",
    "from itertools import accumulate\n",
    "from IPython.display import display_html\n",
    "\n",
    "# Preprocess data  \n",
    "kobe_data = pd.read_csv(\"kobe.csv\")\n",
    "data = kobe_data.copy() #copy, to construct whole new dataset\n",
    "# Transform type of shot_type value into numeric\n",
    "data[\"shot_type_value\"] = data[\"shot_type\"].apply(lambda x: 2 if x==\"2PT Field Goal\" else 3) #map\n",
    "data[\"points\"] = data[\"shot_type_value\"] * data[\"shot_made_flag\"] #transform\n",
    "data['game_date'] =pd.to_datetime(data['game_date']) #data time\n",
    "data.sort_values(\"game_date\",inplace=True)\n",
    "data.index =list(range(len(data)))\n",
    "opponent_list = list(np.unique(data.opponent))\n",
    "\n",
    "# The data for the date after Kobe changed his number\n",
    "NBA_season_2006_7_start = date(2006, 10, 31)\n",
    "NBA_season_2006_7_end = date(2007, 4, 19)\n",
    "NBA_season_2006_7_interval = pd.date_range(start=NBA_season_2006_7_start, end=NBA_season_2006_7_end)\n",
    "newdata_index = data[data[\"game_date\"].isin(NBA_season_2006_7_interval)].index[0]\n",
    "kobe_24_data = data.iloc[newdata_index:]\n",
    "kobe_8_data = data.iloc[:newdata_index]\n",
    "print(\"Overall data\", len(data))\n",
    "print(\"Kobe 8 data\", len(kobe_8_data))\n",
    "print(\"Kobe 24 data\", len(kobe_24_data))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. Kobe's performance against any team.\n",
    "\n",
    "## Calculate the average 2 points, 3 points field goal rate, and  gained scores against any team."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def record(opponent):\n",
    "    def Mean_FGR(Input, opponent):\n",
    "        data_1 = Input.copy()\n",
    "        data_1.index = data_1.opponent\n",
    "        data_1_final = data_1.loc[[opponent],[\"shot_type\",\"shot_made_flag\"]].groupby(\"shot_type\").mean()\n",
    "        data_1_final.rename(columns ={\"shot_made_flag\":\"Average_field_goal_rate\"},inplace = True) #Rename colunm\n",
    "        return(data_1_final.style.set_table_attributes(\"style='display:inline'\"))\n",
    "\n",
    "    def mean_scores(Input, opponent):\n",
    "        data_2 = Input.copy()\n",
    "        data_2 = data_2[[\"game_date\", \"opponent\", \"points\"]] #subset\n",
    "        data_2_group = data_2.groupby([\"game_date\",\"opponent\"], as_index=False).sum() #aggregate\n",
    "        data_2_mean = data_2_group.groupby(\"opponent\").mean()\n",
    "        data_2_mean_oppo = data_2_mean[data_2_mean.index == opponent]\n",
    "        return(data_2_mean_oppo.style.set_table_attributes(\"style='display:inline'\"))\n",
    "    print(\"\\x1b[31m Kobe entire career \"\"\\x1b[0m\") \n",
    "    df1_styler = Mean_FGR(data, opponent)\n",
    "    df2_styler = mean_scores(data, opponent)\n",
    "    display_html(df1_styler._repr_html_()+\" \"+ df2_styler._repr_html_(), raw=True)\n",
    "    print(\"\\x1b[31m Kobe 8 period \"\"\\x1b[0m\")   \n",
    "    df1_styler = Mean_FGR(kobe_8_data, opponent)\n",
    "    df2_styler = mean_scores(kobe_8_data, opponent)\n",
    "    display_html(df1_styler._repr_html_()+\" \"+ df2_styler._repr_html_(), raw=True)\n",
    "    print(\"\\x1b[31m Kobe 24 period \"\"\\x1b[0m\")   \n",
    "    df1_styler =Mean_FGR(kobe_24_data, opponent)\n",
    "    df2_styler = mean_scores(kobe_24_data, opponent)\n",
    "    display_html(df1_styler._repr_html_()+\" \"+ df2_styler._repr_html_(), raw=True)   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1693f6c976ba42cd8f5092f0c0faf805",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(Dropdown(description='Opponent', index=10, options=('ATL', 'BKN', 'BOS', 'CHA', 'CHI', '…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "widgets.interact(record, \n",
    "    opponent = widgets.Dropdown(value = \"HOU\", description = \"Opponent\", options = opponent_list));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Toughest Teams Kobe Has Competed against In His Career\n",
    "## Find the 5 teams making Kobe get the lowest average scores in whole career."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": false
   },
   "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>points</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>opponent</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>VAN</th>\n",
       "      <td>11.166667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BKN</th>\n",
       "      <td>12.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>IND</th>\n",
       "      <td>14.025641</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>UTA</th>\n",
       "      <td>14.142857</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NJN</th>\n",
       "      <td>14.178571</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             points\n",
       "opponent           \n",
       "VAN       11.166667\n",
       "BKN       12.666667\n",
       "IND       14.025641\n",
       "UTA       14.142857\n",
       "NJN       14.178571"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(2) OK\n",
    "data_2 = data.copy()\n",
    "data_2 = data_2[[\"game_date\", \"opponent\", \"points\"]] #subset\n",
    "data_2_group = data_2.groupby([\"game_date\",\"opponent\"], as_index=False).sum() #aggregate\n",
    "data_2_group.groupby(\"opponent\").mean().sort_values(\"points\").head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Kobe's clutch moments in NBA playoff.\n",
    "## Find the games in which Kobe got the highest scores during the last 3 minutes in the playoff."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "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></th>\n",
       "      <th>points</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>game_date</th>\n",
       "      <th>matchup</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000-06-02</th>\n",
       "      <th>LAL @ POR</th>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002-05-12</th>\n",
       "      <th>LAL @ SAS</th>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-04-30</th>\n",
       "      <th>LAL @ SAC</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-06-08</th>\n",
       "      <th>LAL @ BOS</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2002-06-07</th>\n",
       "      <th>LAL vs. NJN</th>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        points\n",
       "game_date  matchup            \n",
       "2000-06-02 LAL @ POR         9\n",
       "2002-05-12 LAL @ SAS         8\n",
       "2000-04-30 LAL @ SAC         7\n",
       "2008-06-08 LAL @ BOS         7\n",
       "2002-06-07 LAL vs. NJN       6"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(3)OK\n",
    "data_3 = data.copy() #copy\n",
    "data_3 = data_3[[\"playoffs\", \"game_date\",\"matchup\", \"period\", \"minutes_remaining\", \"points\"]] #subset\n",
    "data_3_playoffs = data_3[(data_3.playoffs==1) & (data_3.period==4)& (data_3.minutes_remaining<=2)  ]\n",
    "data_3_playoffs = data_3_playoffs.drop([\"playoffs\", \"period\", \"minutes_remaining\"],axis = 1)\n",
    "data_3_playoffs.groupby([\"game_date\",\"matchup\"]).sum().sort_values(\"points\",ascending = False).head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Is Kobe the best closer?\n",
    "## List the Jump-shot  Field Goal Percentage of Kobe in the last one minute in every season playoff."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow0_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow1_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow2_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow3_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow4_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow5_col1 {\n",
       "            color:  red;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow6_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow7_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow9_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow10_col1 {\n",
       "            color:  red;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow11_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow12_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow13_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow14_col1 {\n",
       "            color:  black;\n",
       "        }    #T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow15_col1 {\n",
       "            color:  black;\n",
       "        }</style><table id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334c\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >season</th>        <th class=\"col_heading level0 col1\" >shot_made_flag</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow0_col0\" class=\"data row0 col0\" >1996-97</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow0_col1\" class=\"data row0 col1\" >0.4</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow1_col0\" class=\"data row1 col0\" >1997-98</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow1_col1\" class=\"data row1 col1\" >0</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow2_col0\" class=\"data row2 col0\" >1998-99</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow2_col1\" class=\"data row2 col1\" >0.142857</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow3_col0\" class=\"data row3 col0\" >1999-00</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow3_col1\" class=\"data row3 col1\" >0.1</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row4\" class=\"row_heading level0 row4\" >8</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow4_col0\" class=\"data row4 col0\" >Jan-00</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow4_col1\" class=\"data row4 col1\" >0</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row5\" class=\"row_heading level0 row5\" >7</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow5_col0\" class=\"data row5 col0\" >Feb-01</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow5_col1\" class=\"data row5 col1\" >0.5</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row6\" class=\"row_heading level0 row6\" >11</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow6_col0\" class=\"data row6 col0\" >Mar-02</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow6_col1\" class=\"data row6 col1\" >0.333333</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row7\" class=\"row_heading level0 row7\" >4</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow7_col0\" class=\"data row7 col0\" >Apr-03</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow7_col1\" class=\"data row7 col1\" >0.166667</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row8\" class=\"row_heading level0 row8\" >18</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow8_col0\" class=\"data row8 col0\" >May-04</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow8_col1\" class=\"data row8 col1\" >No shooting record</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row9\" class=\"row_heading level0 row9\" >10</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow9_col0\" class=\"data row9 col0\" >Jun-05</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow9_col1\" class=\"data row9 col1\" >0</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row10\" class=\"row_heading level0 row10\" >9</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow10_col0\" class=\"data row10 col0\" >Jul-06</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow10_col1\" class=\"data row10 col1\" >0.5</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row11\" class=\"row_heading level0 row11\" >5</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow11_col0\" class=\"data row11 col0\" >Aug-07</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow11_col1\" class=\"data row11 col1\" >0</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row12\" class=\"row_heading level0 row12\" >14</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow12_col0\" class=\"data row12 col0\" >Sep-08</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow12_col1\" class=\"data row12 col1\" >0.142857</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow13_col0\" class=\"data row13 col0\" >Oct-09</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow13_col1\" class=\"data row13 col1\" >0.333333</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row14\" class=\"row_heading level0 row14\" >12</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow14_col0\" class=\"data row14 col0\" >Nov-10</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow14_col1\" class=\"data row14 col1\" >0</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row15\" class=\"row_heading level0 row15\" >6</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow15_col0\" class=\"data row15 col0\" >Dec-11</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow15_col1\" class=\"data row15 col1\" >0.0909091</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row16\" class=\"row_heading level0 row16\" >17</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow16_col0\" class=\"data row16 col0\" >2012-13</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow16_col1\" class=\"data row16 col1\" >No shooting record</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row17\" class=\"row_heading level0 row17\" >15</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow17_col0\" class=\"data row17 col0\" >2013-14</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow17_col1\" class=\"data row17 col1\" >No shooting record</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row18\" class=\"row_heading level0 row18\" >19</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow18_col0\" class=\"data row18 col0\" >2014-15</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow18_col1\" class=\"data row18 col1\" >No shooting record</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334clevel0_row19\" class=\"row_heading level0 row19\" >16</th>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow19_col0\" class=\"data row19 col0\" >2015-16</td>\n",
       "                        <td id=\"T_afbfb824_5f86_11ea_b8df_eebc1bc1334crow19_col1\" class=\"data row19 col1\" >No shooting record</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x23954eeeac8>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(4)OK\n",
    "def color_negative_red(val):\n",
    "    \"\"\"\n",
    "    Takes a scalar and returns a string with\n",
    "    the css property `'color: red'` for negative\n",
    "    strings, black otherwise.\n",
    "    \"\"\"\n",
    "    if isinstance(val, float):\n",
    "        color = 'red' if val >= 0.5 else 'black'\n",
    "        return 'color: %s' % color\n",
    "    else:\n",
    "        return val\n",
    "\n",
    "data_4 = kobe_data.copy() #copy\n",
    "data_4 = data_4[[\"playoffs\", \"season\", \"action_type\", \"shot_made_flag\", \"period\", \"minutes_remaining\"]] #subset\n",
    "data_4_select = data_4[(data_4.playoffs==1) & (data_4.period==4)& (data_4.minutes_remaining<1)& (data_4.action_type ==\"Jump Shot\") ]\n",
    "data_4_select = data_4_select.drop([\"playoffs\", \"period\", \"minutes_remaining\", \"action_type\"],axis = 1)\n",
    "data_4_select = data_4_select.groupby([\"season\"], as_index=False).mean()\n",
    "for i in list(set(data.season) - set(data_4_select.season)):\n",
    "    data_4_select=data_4_select.append({'season' : i , 'shot_made_flag' : \"No shooting record\"} , ignore_index=True)\n",
    "index = {'1996-97':1,'1997-98':2,'1998-99':3,'1999-00':4,'Jan-00':5, 'Feb-01':6, 'Mar-02':7, 'Apr-03':8, 'May-04':9, 'Jun-05':10,\n",
    "     'Jul-06':11, 'Aug-07':12, 'Sep-08':13, 'Oct-09':14, 'Nov-10':15, 'Dec-11':16,\n",
    "       '2012-13':17, '2013-14':18, '2014-15':19, '2015-16':20}\n",
    "data_4_select[\"order\"] = data_4_select.season.map(index)\n",
    "data_4_final = data_4_select.sort_values(\"order\");del data_4_final[\"order\"]\n",
    "data_4_final = data_4_final.style.applymap(color_negative_red)\n",
    "data_4_final"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 5. Kobe's \"hot hand\" performance\n",
    "## List the longest consecutive games which Kobe got at least 33% FGP."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>length</th>\n",
       "      <th>Starting_date</th>\n",
       "      <th>Ending_date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>19</td>\n",
       "      <td>2000-02-01</td>\n",
       "      <td>2000-03-12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>19</td>\n",
       "      <td>2001-06-15</td>\n",
       "      <td>2001-12-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>89</th>\n",
       "      <td>16</td>\n",
       "      <td>2002-01-14</td>\n",
       "      <td>2002-02-17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>14</td>\n",
       "      <td>2004-01-02</td>\n",
       "      <td>2004-02-25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     length Starting_date Ending_date\n",
       "60       19    2000-02-01  2000-03-12\n",
       "85       19    2001-06-15  2001-12-07\n",
       "89       16    2002-01-14  2002-02-17\n",
       "131      14    2004-01-02  2004-02-25"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(5)OK\n",
    "def continuous_split(series): \n",
    "    total_time = iteration = len(series)-1\n",
    "    split = [[],[],[]]\n",
    "    while iteration >0:\n",
    "        if series[total_time-iteration]==0:\n",
    "            iteration -=1\n",
    "        else:\n",
    "            times = 0\n",
    "            begin = total_time-iteration\n",
    "            while (series[total_time-iteration] ==1) and (iteration>0):\n",
    "                times +=1\n",
    "                iteration -=1\n",
    "            end = total_time-iteration-1\n",
    "            split[0].append(times)\n",
    "            split[1].append(begin)\n",
    "            split[2].append(end)\n",
    "    return split\n",
    "data_5 = data.copy()\n",
    "data_5 = data_5[[\"shot_made_flag\", \"game_date\"]]\n",
    "data_5_group = data_5.groupby(\"game_date\").mean()\n",
    "data_5_group.rename(columns ={\"shot_made_flag\":\"Average_field_goal_rate\"},inplace = True) #Rename colunm\n",
    "data_5_group[\"target\"] = data_5_group.Average_field_goal_rate.apply(lambda x: 1 if x>=0.33 else 0) \n",
    "index = continuous_split(data_5_group[\"target\"])\n",
    "d = {'length': index[0], 'begin': index[1], 'end' : index[2]}\n",
    "df = pd.DataFrame(d)\n",
    "df_result = df.sort_values(\"length\",ascending = False).head(4)\n",
    "df_result[\"Starting_date\"] = df_result[\"begin\"].apply(lambda x: data_5_group.index[x])\n",
    "df_result[\"Ending_date\"] = df_result[\"end\"].apply(lambda x: data_5_group.index[x])\n",
    "del df_result[\"begin\"];del df_result[\"end\"]\n",
    "df_result\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 6. Kobe's worst status in the games.\n",
    "## List the games which Kobe got the lowest FGP and gained more scores in the first half than the second one."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": false
   },
   "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>opponent</th>\n",
       "      <th>Average_field_goal_rate</th>\n",
       "      <th>points</th>\n",
       "      <th>FH</th>\n",
       "      <th>SH</th>\n",
       "      <th>Points_spread</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>game_date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2003-12-21</th>\n",
       "      <td>PHX</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016-04-05</th>\n",
       "      <td>LAC</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015-11-24</th>\n",
       "      <td>GSW</td>\n",
       "      <td>0.071429</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           opponent  Average_field_goal_rate  points   FH   SH  Points_spread\n",
       "game_date                                                                    \n",
       "2003-12-21      PHX                 0.083333       2  2.0  0.0            2.0\n",
       "2016-04-05      LAC                 0.083333       2  2.0  0.0            2.0\n",
       "2015-11-24      GSW                 0.071429       3  3.0  0.0            3.0"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(6) OK\n",
    "#Collect opponent, Average_field_goal_rate, points columns\n",
    "fg_data = data.copy() #copy\n",
    "fg_data = fg_data[[\"game_date\", \"shot_made_flag\", \"opponent\"]] #subset\n",
    "fg_data_group = fg_data.groupby([\"game_date\",\"opponent\"]).mean() #aggregate\n",
    "fg_data_group = fg_data_group.reset_index(level=\"opponent\") #reset index\n",
    "fg_data_group.rename(columns ={\"shot_made_flag\":\"Average_field_goal_rate\"},inplace = True) #Rename colunm\n",
    "data_p = data.copy() #copy\n",
    "data_p = data_p[[\"game_date\", \"points\"]] #subset\n",
    "data_p_group = data_p.groupby([\"game_date\"]).sum() #aggregate\n",
    "data_O_A_P = pd.concat([fg_data_group,data_p_group],axis = 1) #combine\n",
    "\n",
    "#Collect FH:First half scores, SH:Second half scores, Points_spread:FH and  SH spread\n",
    "data_6 = data.copy() #copy\n",
    "data_6 = data.loc[:,[\"game_date\",\"period\", \"points\"]] #subset\n",
    "data_6.period = data_6.period.astype(\"str\") #corerce\n",
    "quarter = {'1':'FH','2':'FH', '3':'SH', '4':'SH', '5':'OT1','6':'OT2', '7':'OT3'} #index (map)\n",
    "data_6['quarter'] = data_6.period.map(quarter) #map\n",
    "data_6_part = data_6[data_6.quarter.isin([\"FH\",\"SH\"])] #index(mask)\n",
    "del data_6_part[\"period\"] # remove column\n",
    "x = data_6_part.groupby([\"game_date\", \"quarter\"]).sum() #aggregate\n",
    "data_6_final = x.unstack(level = -1) #flatten\n",
    "data_6_final= data_6_final.fillna(0) #fill NaN\n",
    "data_6_final.columns = data_6_final.columns.droplevel(0) #Remove Hierachy\n",
    "data_6_final = data_6_final.rename_axis(None, axis=1) #Remove Hierachy\n",
    "data_6_final[\"Points_spread\"]  = data_6_final.FH -data_6_final.SH\n",
    "data_6_final = pd.concat([data_O_A_P, data_6_final] ,axis = 1)\n",
    "data_6_final = data_6_final[data_6_final.Points_spread > 0]\n",
    "data_6_final.sort_values(\"Average_field_goal_rate\",ascending = False).tail(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 7. Is Kobe a persistent bricklayer?\n",
    "## List  the maximum of Kobe's continuous missing shot in one game."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>game_date</th>\n",
       "      <th>game_id</th>\n",
       "      <th>opponent</th>\n",
       "      <th>points</th>\n",
       "      <th>Continuous_missing_shot</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1221</th>\n",
       "      <td>2010/4/2</td>\n",
       "      <td>20901131</td>\n",
       "      <td>UTA</td>\n",
       "      <td>8</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1506</th>\n",
       "      <td>2015/12/1</td>\n",
       "      <td>21500263</td>\n",
       "      <td>PHI</td>\n",
       "      <td>10</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1381</th>\n",
       "      <td>2012/3/31</td>\n",
       "      <td>21100769</td>\n",
       "      <td>NOH</td>\n",
       "      <td>7</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>579</th>\n",
       "      <td>2003/3/12</td>\n",
       "      <td>20200925</td>\n",
       "      <td>DET</td>\n",
       "      <td>12</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>710</th>\n",
       "      <td>2005/11/18</td>\n",
       "      <td>20500130</td>\n",
       "      <td>LAC</td>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       game_date   game_id opponent  points  Continuous_missing_shot\n",
       "1221    2010/4/2  20901131      UTA       8                       16\n",
       "1506   2015/12/1  21500263      PHI      10                       16\n",
       "1381   2012/3/31  21100769      NOH       7                       15\n",
       "579    2003/3/12  20200925      DET      12                       15\n",
       "710   2005/11/18  20500130      LAC      14                       14"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#(7)\n",
    "#Part 1\n",
    "data = kobe_data.copy() #copy, to construct scores dataset\n",
    "data[\"shot_type_value\"] = data[\"shot_type\"].apply(lambda x: 2 if x==\"2PT Field Goal\" else 3) #map\n",
    "data[\"points\"] = data[\"shot_type_value\"] * data[\"shot_made_flag\"] #transform\n",
    "data_7 = data\n",
    "data_7 = data_7.loc[:,[\"game_date\", \"game_id\", \"opponent\",\"shot_made_flag\", \"points\"]]\n",
    "data_7_group = data_7.groupby([\"game_date\", \"game_id\", \"opponent\"],as_index = False).points.sum()\n",
    "shot_made_flag_interval = []\n",
    "for idx, value in data_7.groupby([\"game_date\", \"game_id\", \"opponent\"]):\n",
    "    series = value[\"shot_made_flag\"]\n",
    "    series = pd.Series(series)\n",
    "    series.index = list(range(len(series)))\n",
    "    shot_made_flag_interval.append(pd.Series(series))\n",
    "#Part2\n",
    "max_continuity_miss = []\n",
    "for sub in shot_made_flag_interval:\n",
    "    series = sub\n",
    "    total_time = iteration = len(series)-1\n",
    "    split = []\n",
    "    while iteration >=0:\n",
    "        if series[total_time-iteration]==1:\n",
    "            iteration -=1\n",
    "        else:\n",
    "            times = 0\n",
    "            while (iteration >= 0) and (series[total_time-iteration] ==0):\n",
    "                times +=1\n",
    "                iteration -=1\n",
    "            split.append(times)\n",
    "    if len(split)==0:\n",
    "        result =0\n",
    "    else:\n",
    "        result = max(split)\n",
    "    max_continuity_miss.append(result)\n",
    "\n",
    "data_7_group.loc[:,\"Continuous_missing_shot\"] = max_continuity_miss\n",
    "data_final = data_7_group.sort_values(\"Continuous_missing_shot\", ascending = False)\n",
    "data_final.head(5)"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}