lahman-analysis.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sqlalchemy\n",
    "sqlalchemy.create_engine('mysql+mysqlconnector://root:secret@localhost:3306/lahmansbaseballdb')\n",
    "%reload_ext sql"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns\n",
    "import scipy.stats\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "%sql mysql+mysqlconnector://root:secret@localhost:3306/lahmansbaseballdb"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Lahman Open-ended analysis questions\n",
    "This is my second post on using the Lahman Baseball Database to practice my SQL and python analysis skills. I used the questions from [github user saifislam1](https://github.com/saifislam1/Lahman-Baseball) as a guide. The first post answered the *Initial Questions* while this post is all about the *Open-ended questions*."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 1: \n",
    "### Analyze all the colleges in the state of Tennessee. Which college has had the most success in the major leagues. Use whatever metric for success you like - number of players, number of games, salaries, world series wins, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * mysql+mysqlconnector://root:***@localhost:3306/lahmansbaseballdb\n",
      "33 rows affected.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table>\n",
       "    <tr>\n",
       "        <th>schoolID</th>\n",
       "        <th>name_full</th>\n",
       "        <th>city</th>\n",
       "        <th>state</th>\n",
       "        <th>totalGS</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tennessee</td>\n",
       "        <td>University of Tennessee</td>\n",
       "        <td>Knoxville</td>\n",
       "        <td>TN</td>\n",
       "        <td>12746</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>vandy</td>\n",
       "        <td>Vanderbilt University</td>\n",
       "        <td>Nashville</td>\n",
       "        <td>TN</td>\n",
       "        <td>4819</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>memphis</td>\n",
       "        <td>University of Memphis</td>\n",
       "        <td>Memphis</td>\n",
       "        <td>TN</td>\n",
       "        <td>2082</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tennst</td>\n",
       "        <td>Tennessee State University</td>\n",
       "        <td>Nashville</td>\n",
       "        <td>TN</td>\n",
       "        <td>1514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>mryvilletn</td>\n",
       "        <td>Maryville College</td>\n",
       "        <td>Maryville</td>\n",
       "        <td>TN</td>\n",
       "        <td>1275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>austinpeay</td>\n",
       "        <td>Austin Peay State University</td>\n",
       "        <td>Clarksville</td>\n",
       "        <td>TN</td>\n",
       "        <td>836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tncolum</td>\n",
       "        <td>Columbia State Community College</td>\n",
       "        <td>Columbia</td>\n",
       "        <td>TN</td>\n",
       "        <td>724</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>mtennst</td>\n",
       "        <td>Middle Tennessee State University</td>\n",
       "        <td>Murfreesboro</td>\n",
       "        <td>TN</td>\n",
       "        <td>674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>milligantn</td>\n",
       "        <td>Milligan College</td>\n",
       "        <td>Milligan College</td>\n",
       "        <td>TN</td>\n",
       "        <td>614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tusculum</td>\n",
       "        <td>Tusculum College</td>\n",
       "        <td>Greenville</td>\n",
       "        <td>TN</td>\n",
       "        <td>614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tncleve</td>\n",
       "        <td>Cleveland State Community College</td>\n",
       "        <td>Cleveland</td>\n",
       "        <td>TN</td>\n",
       "        <td>535</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>uniontn</td>\n",
       "        <td>Union University</td>\n",
       "        <td>Jackson</td>\n",
       "        <td>TN</td>\n",
       "        <td>483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>etennst</td>\n",
       "        <td>East Tennessee State University</td>\n",
       "        <td>Johnson City</td>\n",
       "        <td>TN</td>\n",
       "        <td>460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>carsnewm</td>\n",
       "        <td>Carson-Newman College</td>\n",
       "        <td>Jefferson City</td>\n",
       "        <td>TN</td>\n",
       "        <td>371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>uofsouth</td>\n",
       "        <td>University of the South</td>\n",
       "        <td>Sewanee</td>\n",
       "        <td>TN</td>\n",
       "        <td>370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>rhodestn</td>\n",
       "        <td>Rhodes College</td>\n",
       "        <td>Memphis</td>\n",
       "        <td>TN</td>\n",
       "        <td>363</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnwesleyan</td>\n",
       "        <td>Tennessee Wesleyan College</td>\n",
       "        <td>Athens</td>\n",
       "        <td>TN</td>\n",
       "        <td>339</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnswten</td>\n",
       "        <td>Southwest Tennessee Community College</td>\n",
       "        <td>Memphis</td>\n",
       "        <td>TN</td>\n",
       "        <td>306</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>lanecol</td>\n",
       "        <td>Lane College</td>\n",
       "        <td>Jackson</td>\n",
       "        <td>TN</td>\n",
       "        <td>305</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnjacks</td>\n",
       "        <td>Jackson State Community College</td>\n",
       "        <td>Jackson</td>\n",
       "        <td>TN</td>\n",
       "        <td>295</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnkingc</td>\n",
       "        <td>King College</td>\n",
       "        <td>Bristol</td>\n",
       "        <td>TN</td>\n",
       "        <td>220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tntenme</td>\n",
       "        <td>University of Tennessee Health Science Center</td>\n",
       "        <td>Memphis</td>\n",
       "        <td>TN</td>\n",
       "        <td>188</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>freedhrdmn</td>\n",
       "        <td>Freed-Hardeman University</td>\n",
       "        <td>Henderson</td>\n",
       "        <td>TN</td>\n",
       "        <td>162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnmotlo</td>\n",
       "        <td>Motlow State Community College</td>\n",
       "        <td>Lynchburg</td>\n",
       "        <td>TN</td>\n",
       "        <td>69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>cumbrlndtn</td>\n",
       "        <td>Cumberland University</td>\n",
       "        <td>Lebanon</td>\n",
       "        <td>TN</td>\n",
       "        <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>lemoynowen</td>\n",
       "        <td>LeMoyne-Owen College</td>\n",
       "        <td>Memphis</td>\n",
       "        <td>TN</td>\n",
       "        <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>belmont</td>\n",
       "        <td>Belmont University</td>\n",
       "        <td>Nashville</td>\n",
       "        <td>TN</td>\n",
       "        <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>lipscomb</td>\n",
       "        <td>Lipscomb University</td>\n",
       "        <td>Nashville</td>\n",
       "        <td>TN</td>\n",
       "        <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>lincolnmem</td>\n",
       "        <td>Lincoln Memorial University</td>\n",
       "        <td>Harrogate</td>\n",
       "        <td>TN</td>\n",
       "        <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnchatt</td>\n",
       "        <td>Chattanooga State Technical Community College</td>\n",
       "        <td>Chattanooga</td>\n",
       "        <td>TN</td>\n",
       "        <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tnhiwas</td>\n",
       "        <td>Hiwassee College</td>\n",
       "        <td>Madisonville</td>\n",
       "        <td>TN</td>\n",
       "        <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>lambuthtn</td>\n",
       "        <td>Lambuth University</td>\n",
       "        <td>Jackson</td>\n",
       "        <td>TN</td>\n",
       "        <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td>tntech</td>\n",
       "        <td>Tennessee Technological University</td>\n",
       "        <td>Cookeville</td>\n",
       "        <td>TN</td>\n",
       "        <td>0</td>\n",
       "    </tr>\n",
       "</table>"
      ],
      "text/plain": [
       "[('tennessee', 'University of Tennessee', 'Knoxville', 'TN', Decimal('12746')),\n",
       " ('vandy', 'Vanderbilt University', 'Nashville', 'TN', Decimal('4819')),\n",
       " ('memphis', 'University of Memphis', 'Memphis', 'TN', Decimal('2082')),\n",
       " ('tennst', 'Tennessee State University', 'Nashville', 'TN', Decimal('1514')),\n",
       " ('mryvilletn', 'Maryville College', 'Maryville', 'TN', Decimal('1275')),\n",
       " ('austinpeay', 'Austin Peay State University', 'Clarksville', 'TN', Decimal('836')),\n",
       " ('tncolum', 'Columbia State Community College', 'Columbia', 'TN', Decimal('724')),\n",
       " ('mtennst', 'Middle Tennessee State University', 'Murfreesboro', 'TN', Decimal('674')),\n",
       " ('milligantn', 'Milligan College', 'Milligan College', 'TN', Decimal('614')),\n",
       " ('tusculum', 'Tusculum College', 'Greenville', 'TN', Decimal('614')),\n",
       " ('tncleve', 'Cleveland State Community College', 'Cleveland', 'TN', Decimal('535')),\n",
       " ('uniontn', 'Union University', 'Jackson', 'TN', Decimal('483')),\n",
       " ('etennst', 'East Tennessee State University', 'Johnson City', 'TN', Decimal('460')),\n",
       " ('carsnewm', 'Carson-Newman College', 'Jefferson City', 'TN', Decimal('371')),\n",
       " ('uofsouth', 'University of the South', 'Sewanee', 'TN', Decimal('370')),\n",
       " ('rhodestn', 'Rhodes College', 'Memphis', 'TN', Decimal('363')),\n",
       " ('tnwesleyan', 'Tennessee Wesleyan College', 'Athens', 'TN', Decimal('339')),\n",
       " ('tnswten', 'Southwest Tennessee Community College', 'Memphis', 'TN', Decimal('306')),\n",
       " ('lanecol', 'Lane College', 'Jackson', 'TN', Decimal('305')),\n",
       " ('tnjacks', 'Jackson State Community College', 'Jackson', 'TN', Decimal('295')),\n",
       " ('tnkingc', 'King College', 'Bristol', 'TN', Decimal('220')),\n",
       " ('tntenme', 'University of Tennessee Health Science Center', 'Memphis', 'TN', Decimal('188')),\n",
       " ('freedhrdmn', 'Freed-Hardeman University', 'Henderson', 'TN', Decimal('162')),\n",
       " ('tnmotlo', 'Motlow State Community College', 'Lynchburg', 'TN', Decimal('69')),\n",
       " ('cumbrlndtn', 'Cumberland University', 'Lebanon', 'TN', Decimal('44')),\n",
       " ('lemoynowen', 'LeMoyne-Owen College', 'Memphis', 'TN', Decimal('31')),\n",
       " ('belmont', 'Belmont University', 'Nashville', 'TN', Decimal('30')),\n",
       " ('lipscomb', 'Lipscomb University', 'Nashville', 'TN', Decimal('21')),\n",
       " ('lincolnmem', 'Lincoln Memorial University', 'Harrogate', 'TN', Decimal('19')),\n",
       " ('tnchatt', 'Chattanooga State Technical Community College', 'Chattanooga', 'TN', Decimal('11')),\n",
       " ('tnhiwas', 'Hiwassee College', 'Madisonville', 'TN', Decimal('2')),\n",
       " ('lambuthtn', 'Lambuth University', 'Jackson', 'TN', Decimal('0')),\n",
       " ('tntech', 'Tennessee Technological University', 'Cookeville', 'TN', Decimal('0'))]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%sql\n",
    "with TN_colleges as (SELECT \n",
    "    c.playerID, max(c.yearID) 'gradYear',  s.schoolID, s.name_full, s.city, s.state\n",
    "\tFROM\n",
    "\t\tcollegeplaying c\n",
    "\tINNER JOIN\n",
    "\t\tschools s ON s.schoolID = c.schoolID\n",
    "\tWHERE\n",
    "\t\ts.state = 'TN'\n",
    "\tgroup by c.playerID, s.schoolID, s.name_full, s.city, s.state\n",
    "    ),\n",
    " tn_games as (\n",
    "\tSELECT \n",
    "\t\ttn.*, SUM(apps.GS) 'GS'\n",
    "\tFROM\n",
    "\t\tTN_colleges tn\n",
    "\tINNER JOIN\n",
    "\t\tappearances apps ON tn.playerID = apps.playerID\n",
    "\tGROUP BY tn.playerID , tn.gradYear , tn.schoolID , tn.name_full , tn.city , tn.state\n",
    "        )\n",
    "SELECT \n",
    "    tng.schoolID,\n",
    "    tng.name_full,\n",
    "    tng.city,\n",
    "    tng.state,\n",
    "    SUM(tng.GS) as 'totalGS'\n",
    "\tFROM\n",
    "\t\ttn_games tng\n",
    "\tGROUP BY tng.schoolID , tng.name_full , tng.city , tng.state\n",
    "\tORDER BY totalGS desc        \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I chose to use total games started as my measure for success. WHy? Career games accounts for longevity, and the more successful players will play in more games. Games started, opposed to games played, measures the skill of each player. Combining the longevity of total games and the skill required to stay in the starting lineup offer a good metric of Major League success."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "# Question 2\n",
    "## Is there any correlation between number of wins and team salary? Use data from 2000 and later to answer this question. As you do this analysis, keep in mind that salaries across the whole league tend to increase together, so you may want to look on a year-by-year basis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * mysql+mysqlconnector://root:***@localhost:3306/lahmansbaseballdb\n",
      "480 rows affected.\n",
      "Returning data to local variable salaries\n"
     ]
    }
   ],
   "source": [
    "%%sql salaries <<\n",
    "with teamSalaries as(\n",
    "\tSELECT \n",
    "        SUM(s2.salary) AS 'totalSalary', s2.team_ID, s2.yearID\n",
    "    FROM\n",
    "        salaries s2\n",
    "\twhere s2.yearID > 2000\n",
    "    GROUP BY yearID , team_ID\n",
    ")\n",
    "SELECT DISTINCT\n",
    "    s.yearID, s.teamID, ts.totalSalary, t.W, ts.totalSalary / ts3.yearlyMaxSalary 'percentOfYearlyMaxSalary'\n",
    "FROM\n",
    "    salaries s\n",
    "        INNER JOIn teamSalaries ts on ts.team_ID = s.team_ID\n",
    "\tINNER JOIN\n",
    "    teams t ON t.teamID = s.teamID\n",
    "        AND t.yearID = s.yearID\n",
    "\t\tINNER JOIN\n",
    "    (SELECT \n",
    "        MAX(ts2.totalSalary) 'yearlyMaxSalary', ts2.yearID\n",
    "    FROM\n",
    "        teamSalaries ts2\n",
    "    GROUP BY ts2.yearID) ts3 ON ts3.yearID = s.yearID\n",
    "WHERE\n",
    "    s.yearID >= 2000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "salaries = salaries.DataFrame()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.3774760484994343  p-value: 1.0573378846530879e-17\n"
     ]
    }
   ],
   "source": [
    "# salaries.head()\n",
    "r, pval = scipy.stats.pearsonr(salaries['W'], salaries['percentOfYearlyMaxSalary'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see from the output above, there is some correlation but not a whole lot. The p-value suggests their is evidence to reject the null hypothesis. However, the r coefficient shows that only about 37% of the variance in wins can be attributed to a team's salary. Thanks to teams like the \"Moneyball\" Athletics or, more recently, the Tampa Bay Rays, we cannot completely correlate salary with wins."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='percentOfYearlyMaxSalary', ylabel='W'>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(data = salaries, x=\"percentOfYearlyMaxSalary\", y=\"W\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 3\n",
    "## In this question, you will explore the connection between number of wins and attendance.\n",
    "- Does there appear to be any correlation between attendance at home games and number of wins?\n",
    "- Do teams that win the world series see a boost in attendance the following year?\n",
    "- What about teams that made the playoffs? Making the playoffs means either being a division winner or a wild card winner."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * mysql+mysqlconnector://root:***@localhost:3306/lahmansbaseballdb\n",
      "1086 rows affected.\n",
      "Returning data to local variable q3\n"
     ]
    }
   ],
   "source": [
    "%%sql q3 <<\n",
    "SELECT \n",
    "    yearID,\n",
    "    teamID,\n",
    "    W,\n",
    "    HR,\n",
    "    R ,\n",
    "    park,\n",
    "    attendance,\n",
    "    CASE\n",
    "\t\tWHEN DivWin = 'Y' or WCWin = 'Y' THEN 'Y'\n",
    "\t\tELSE \"N\"\n",
    "\tEND 'madePlayoffs',\n",
    "    WSWin\n",
    "FROM\n",
    "    teams\n",
    "WHERE\n",
    "    yearID > 1981;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "q3 = q3.DataFrame()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.49079324131097524  p-value: 6.622909317268558e-67\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='W', ylabel='attendance'>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "r, pval = scipy.stats.pearsonr(q3['W'], q3['attendance'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n",
    "sns.scatterplot(data = q3, x=\"W\", y=\"attendance\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see from the plot above and the r and p-values, there is some correlation between attendance and wins. \n",
    "\n",
    "Below I calculate the change in attendance (`attendanceDelta`) from the previous year. I add in dummy variables for `madePlayoffsLastYear`, `isDefendingChamps`, and `hasNewPark`. These dummy variables allow me to check for correlation between the previous year's success or whether or not a team built a new stadium. **Spoiler Alert** non of these metric matter."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "q3['prevAttendance'] = q3.sort_values('yearID').groupby('teamID')['attendance'].shift()\n",
    "q3['attendanceDelta'] = q3['attendance'] / q3['prevAttendance']\n",
    "q3['madePlayoffsLastYear'] = q3.sort_values('yearID').groupby('teamID')['madePlayoffs'].shift()\n",
    "q3['madePlayoffsLastYear'] = np.where(q3['madePlayoffsLastYear'] == 'Y', 1, 0)\n",
    "q3['isDefendingChamps'] = q3.sort_values('yearID').groupby('teamID')['WSWin'].shift()\n",
    "q3['isDefendingChamps'] = np.where(q3['isDefendingChamps'] == 'Y', 1, 0)\n",
    "q3['prevPark'] = q3.sort_values('yearID').groupby('teamID')['park'].shift()\n",
    "q3['hasNewPark'] = np.where(q3['park'] != q3['prevPark'], 1, 0)\n",
    "# q3.sort_values(['teamID', 'yearID']).head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.009102894852290157  p-value: 0.7712039512419646\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='madePlayoffsLastYear', ylabel='attendanceDelta'>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "q3 = q3.dropna()\n",
    "r, pval = scipy.stats.pearsonr(q3['madePlayoffsLastYear'], q3['attendanceDelta'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n",
    "sns.boxplot(data = q3,x= \"madePlayoffsLastYear\", y=\"attendanceDelta\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.04269484658468008  p-value: 0.17240380346516374\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='isDefendingChamps', ylabel='attendanceDelta'>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "r, pval = scipy.stats.pearsonr(q3['isDefendingChamps'], q3['attendanceDelta'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n",
    "sns.boxplot(data = q3,x= \"isDefendingChamps\", y=\"attendanceDelta\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.08946904379621956  p-value: 0.004185161900185291\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='hasNewPark', ylabel='attendanceDelta'>"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "r, pval = scipy.stats.pearsonr(q3['hasNewPark'], q3['attendanceDelta'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n",
    "sns.boxplot(data = q3,x= \"hasNewPark\", y=\"attendanceDelta\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see from the r values and p-values, previous year's success doesn't matter all that much in terms of attendance. The boxplots show that while some teams might receive a bump in attendance, the median attendance between years doesn't change all that much.\n",
    "\n",
    "So what does move the attendance needle? Offense. Hit more home runs or simply score more at home and you could see a bump in attendance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.3211656984708274  p-value: 5.637430245287712e-26\n"
     ]
    }
   ],
   "source": [
    "r, pval = scipy.stats.pearsonr(q3['HR'], q3['attendance'])\n",
    "print('pearson r:',r, ' p-value:',pval)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pearson r: 0.35322536152353284  p-value: 1.996126744868917e-31\n"
     ]
    }
   ],
   "source": [
    "r, pval = scipy.stats.pearsonr(q3['R'], q3['attendance'])\n",
    "print('pearson r:',r, ' p-value:',pval)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Question 4\n",
    "## It is thought that since left-handed pitchers are more rare, causing batters to face them less often, that they are more effective. Investigate this claim and present evidence to either support or dispute this claim. First, determine just how rare left-handed pitchers are compared with right-handed pitchers. Are left-handed pitchers more likely to win the Cy Young Award? Are they more likely to make it into the hall of fame?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * mysql+mysqlconnector://root:***@localhost:3306/lahmansbaseballdb\n",
      "2975 rows affected.\n",
      "Returning data to local variable q4\n"
     ]
    }
   ],
   "source": [
    "%%sql q4 <<\n",
    "SELECT \n",
    "    CONCAT(p.nameFirst, ' ', p.nameLast) 'nameFull',\n",
    "    p.throws,\n",
    "    ROUND(SUM(pt.IPOuts / 3), 1) 'CareerIP',\n",
    "    SUM(pt.W) / SUM(pt.G) 'CareerWin%',\n",
    "    SUM(pt.SV)/ (SUM(pt.SV) + SUM(pt.L) ) 'CareerSV%',\n",
    "    ROUND(27 * SUM(pt.ER) / (SUM(pt.IPOuts)), 2) 'CareerERA',\n",
    "    SUM(pt.H) / (SUM(pt.BFP) - SUM(IFNULL(pt.BB, 0)) - SUM(IFNULL(pt.IBB, 0)) - SUM(IFNULL(pt.HBP, 0))) 'CareerBAOpp',\n",
    "    SUM(pt.SO) / SUM(pt.BFP) 'CareerSO%',\n",
    "    cy.CyYoungCount,\n",
    "    asg.CareerAllStarGames,\n",
    "    hof.inducted\n",
    "FROM\n",
    "    pitching pt\n",
    "INNER JOIN   people p ON p.playerID = pt.playerID\n",
    "LEFT JOIN (SELECT playerID, COUNT(gameID) 'CareerAllStarGames' FROM allstarfull GROUP BY playerID) asg ON asg.playerID = p.playerID \n",
    "LEFT JOIN (SELECT playerID, yearID, ROW_NUMBER() OVER(PARTITION BY playerID ORDER BY yearID desc) as rn, inducted from halloffame) hof ON hof.playerID = p.playerID AND hof.rn = 1\n",
    "LEFT JOIN  (SELECT playerID, COUNT(yearID) 'CyYoungCount' from awardsplayers where awardID = 'Cy Young Award' GROUP BY playerID) cy ON p.playerID = cy.playerID \n",
    "WHERE p.throws IS NOT NULL\n",
    "\tAND pt.yearID > 1980\n",
    "GROUP BY nameFull , p.throws,  asg.CareerAllStarGames,hof.inducted, cy.CyYoungCount\n",
    "HAVING SUM(pt.IPOuts / 3) > 50;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "q4 = q4.DataFrame()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's create some dummy variables for handedness, Hall of Fame (hof), All Star apperances, and Cy Young awards."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>nameFull</th>\n",
       "      <th>throws</th>\n",
       "      <th>CareerIP</th>\n",
       "      <th>CareerWin%</th>\n",
       "      <th>CareerSV%</th>\n",
       "      <th>CareerERA</th>\n",
       "      <th>CareerBAOpp</th>\n",
       "      <th>CareerSO%</th>\n",
       "      <th>CyYoungCount</th>\n",
       "      <th>CareerAllStarGames</th>\n",
       "      <th>inducted</th>\n",
       "      <th>throwsLeft</th>\n",
       "      <th>hof</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Don Aase</td>\n",
       "      <td>R</td>\n",
       "      <td>478.0</td>\n",
       "      <td>0.0973</td>\n",
       "      <td>0.7429</td>\n",
       "      <td>3.35</td>\n",
       "      <td>0.2399</td>\n",
       "      <td>0.1640</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>None</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Glenn Abbott</td>\n",
       "      <td>R</td>\n",
       "      <td>303.3</td>\n",
       "      <td>0.2500</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>4.09</td>\n",
       "      <td>0.2775</td>\n",
       "      <td>0.0721</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>None</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Juan Agosto</td>\n",
       "      <td>L</td>\n",
       "      <td>626.3</td>\n",
       "      <td>0.0737</td>\n",
       "      <td>0.4677</td>\n",
       "      <td>4.01</td>\n",
       "      <td>0.2676</td>\n",
       "      <td>0.1132</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>None</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Doyle Alexander</td>\n",
       "      <td>R</td>\n",
       "      <td>1772.7</td>\n",
       "      <td>0.3698</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>3.81</td>\n",
       "      <td>0.2640</td>\n",
       "      <td>0.1230</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>N</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Neil Allen</td>\n",
       "      <td>R</td>\n",
       "      <td>792.0</td>\n",
       "      <td>0.1385</td>\n",
       "      <td>0.4737</td>\n",
       "      <td>3.94</td>\n",
       "      <td>0.2638</td>\n",
       "      <td>0.1370</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>None</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          nameFull throws CareerIP CareerWin% CareerSV% CareerERA CareerBAOpp  \\\n",
       "0         Don Aase      R    478.0     0.0973    0.7429      3.35      0.2399   \n",
       "1     Glenn Abbott      R    303.3     0.2500    0.0000      4.09      0.2775   \n",
       "2      Juan Agosto      L    626.3     0.0737    0.4677      4.01      0.2676   \n",
       "3  Doyle Alexander      R   1772.7     0.3698    0.0000      3.81      0.2640   \n",
       "4       Neil Allen      R    792.0     0.1385    0.4737      3.94      0.2638   \n",
       "\n",
       "  CareerSO%  CyYoungCount  CareerAllStarGames inducted  throwsLeft  hof  \n",
       "0    0.1640           0.0                 1.0     None           0    0  \n",
       "1    0.0721           0.0                 0.0     None           0    0  \n",
       "2    0.1132           0.0                 0.0     None           1    0  \n",
       "3    0.1230           0.0                 1.0        N           0    0  \n",
       "4    0.1370           0.0                 0.0     None           0    0  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "q4['throwsLeft'] = np.where( q4['throws'] == 'L', 1, 0)\n",
    "q4['hof'] = np.where( q4['inducted'] == 'Y', 1, 0)\n",
    "q4['CareerAllStarGames'] = q4['CareerAllStarGames'].fillna(0)\n",
    "q4['CyYoungCount'] = q4['CyYoungCount'].fillna(0)\n",
    "\n",
    "q4.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Percentage of lefties: 27.66 %\n"
     ]
    }
   ],
   "source": [
    "print('Percentage of lefties:', round(q4['throwsLeft'].mean()*100,2), '%')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Interestingly, the estimated percentage of humans across the entire population is only approximately 10%. The percentage of left handed pitchers throughout the MLB is almost three times as high. Could scouts and GMs be overvaluing lefties or is it true that lefties are better so therefore they advance to higher levels of play?\n",
    "\n",
    "Let's check the correlation between all the variables in our dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>CareerIP</th>\n",
       "      <th>CareerWin%</th>\n",
       "      <th>CareerSV%</th>\n",
       "      <th>CareerERA</th>\n",
       "      <th>CareerBAOpp</th>\n",
       "      <th>CyYoungCount</th>\n",
       "      <th>CareerAllStarGames</th>\n",
       "      <th>throwsLeft</th>\n",
       "      <th>hof</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>CareerIP</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.629394</td>\n",
       "      <td>-0.101820</td>\n",
       "      <td>-0.281966</td>\n",
       "      <td>-0.138885</td>\n",
       "      <td>0.344512</td>\n",
       "      <td>0.546038</td>\n",
       "      <td>0.007857</td>\n",
       "      <td>0.194122</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CareerWin%</th>\n",
       "      <td>0.629394</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.447870</td>\n",
       "      <td>-0.086793</td>\n",
       "      <td>0.000800</td>\n",
       "      <td>0.244419</td>\n",
       "      <td>0.340442</td>\n",
       "      <td>-0.028722</td>\n",
       "      <td>0.123552</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CareerSV%</th>\n",
       "      <td>-0.101820</td>\n",
       "      <td>-0.447870</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.402751</td>\n",
       "      <td>-0.378583</td>\n",
       "      <td>-0.051543</td>\n",
       "      <td>0.133375</td>\n",
       "      <td>-0.078002</td>\n",
       "      <td>0.015781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CareerERA</th>\n",
       "      <td>-0.281966</td>\n",
       "      <td>-0.086793</td>\n",
       "      <td>-0.402751</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.697269</td>\n",
       "      <td>-0.116060</td>\n",
       "      <td>-0.311941</td>\n",
       "      <td>-0.009776</td>\n",
       "      <td>-0.086569</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CareerBAOpp</th>\n",
       "      <td>-0.138885</td>\n",
       "      <td>0.000800</td>\n",
       "      <td>-0.378583</td>\n",
       "      <td>0.697269</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.088022</td>\n",
       "      <td>-0.266598</td>\n",
       "      <td>0.025050</td>\n",
       "      <td>-0.063089</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CyYoungCount</th>\n",
       "      <td>0.344512</td>\n",
       "      <td>0.244419</td>\n",
       "      <td>-0.051543</td>\n",
       "      <td>-0.116060</td>\n",
       "      <td>-0.088022</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.566680</td>\n",
       "      <td>0.011804</td>\n",
       "      <td>0.459367</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CareerAllStarGames</th>\n",
       "      <td>0.546038</td>\n",
       "      <td>0.340442</td>\n",
       "      <td>0.133375</td>\n",
       "      <td>-0.311941</td>\n",
       "      <td>-0.266598</td>\n",
       "      <td>0.566680</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.012709</td>\n",
       "      <td>0.485215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>throwsLeft</th>\n",
       "      <td>0.007857</td>\n",
       "      <td>-0.028722</td>\n",
       "      <td>-0.078002</td>\n",
       "      <td>-0.009776</td>\n",
       "      <td>0.025050</td>\n",
       "      <td>0.011804</td>\n",
       "      <td>0.012709</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.023290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>hof</th>\n",
       "      <td>0.194122</td>\n",
       "      <td>0.123552</td>\n",
       "      <td>0.015781</td>\n",
       "      <td>-0.086569</td>\n",
       "      <td>-0.063089</td>\n",
       "      <td>0.459367</td>\n",
       "      <td>0.485215</td>\n",
       "      <td>-0.023290</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    CareerIP  CareerWin%  CareerSV%  CareerERA  CareerBAOpp  \\\n",
       "CareerIP            1.000000    0.629394  -0.101820  -0.281966    -0.138885   \n",
       "CareerWin%          0.629394    1.000000  -0.447870  -0.086793     0.000800   \n",
       "CareerSV%          -0.101820   -0.447870   1.000000  -0.402751    -0.378583   \n",
       "CareerERA          -0.281966   -0.086793  -0.402751   1.000000     0.697269   \n",
       "CareerBAOpp        -0.138885    0.000800  -0.378583   0.697269     1.000000   \n",
       "CyYoungCount        0.344512    0.244419  -0.051543  -0.116060    -0.088022   \n",
       "CareerAllStarGames  0.546038    0.340442   0.133375  -0.311941    -0.266598   \n",
       "throwsLeft          0.007857   -0.028722  -0.078002  -0.009776     0.025050   \n",
       "hof                 0.194122    0.123552   0.015781  -0.086569    -0.063089   \n",
       "\n",
       "                    CyYoungCount  CareerAllStarGames  throwsLeft       hof  \n",
       "CareerIP                0.344512            0.546038    0.007857  0.194122  \n",
       "CareerWin%              0.244419            0.340442   -0.028722  0.123552  \n",
       "CareerSV%              -0.051543            0.133375   -0.078002  0.015781  \n",
       "CareerERA              -0.116060           -0.311941   -0.009776 -0.086569  \n",
       "CareerBAOpp            -0.088022           -0.266598    0.025050 -0.063089  \n",
       "CyYoungCount            1.000000            0.566680    0.011804  0.459367  \n",
       "CareerAllStarGames      0.566680            1.000000    0.012709  0.485215  \n",
       "throwsLeft              0.011804            0.012709    1.000000 -0.023290  \n",
       "hof                     0.459367            0.485215   -0.023290  1.000000  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "q4.iloc[:,2:7] = q4.iloc[:,2:7].apply(pd.to_numeric, errors='coerce')\n",
    "q4.corr()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Not very high correlation between any of the variables on the `throwsLeft` dummy variable. Pictures are nice so lets see if we can learn anything from some plots."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(2, 2)\n",
    "\n",
    "ax = sns.boxplot(x=\"throws\", y=\"CareerIP\", data=q4, orient='v', \n",
    "    ax=axes[0, 0])\n",
    "ax = sns.boxplot(x=\"throws\", y=\"CareerWin%\", data=q4, orient='v', \n",
    "    ax=axes[0, 1])\n",
    "ax = sns.boxplot(x=\"throws\", y=\"CareerSV%\", data=q4, orient='v', \n",
    "    ax=axes[1, 0])\n",
    "ax = sns.boxplot(x=\"throws\", y=\"CareerBAOpp\", data=q4, orient='v', \n",
    "    ax=axes[1, 1])\n",
    "plt.subplots_adjust(left=0.1,\n",
    "                bottom=0.1, \n",
    "                right=0.9, \n",
    "                top=0.9, \n",
    "                wspace=0.4, \n",
    "                hspace=0.4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There isn't much difference across the four statistical metrics that I used when comparing righies to lefties. There medians are nearly identical and the interquartile ranges are slightly lower for `Career Win %` and `Career Save %`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(2, 2)\n",
    "sns.histplot(hue=\"throws\", x='throws', weights=\"CareerAllStarGames\", data=q4, \n",
    "ax= axes[0,0],binwidth=1).set_ylabel('Total All Star Games')\n",
    "sns.histplot(hue=\"throws\", x='throws', weights=\"CyYoungCount\", data=q4,\n",
    "ax= axes[0,1], binwidth=1).set_ylabel('Total Cy Youngs')\n",
    "sns.histplot(hue=\"throws\", x='throws', weights=\"hof\", data=q4,\n",
    "ax= axes[1,0], binwidth=1).set_ylabel('Number of HoFers')\n",
    "sns.histplot(hue=\"throws\", x='throws', data=q4,\n",
    "ax= axes[1,1], binwidth=1).set_ylabel('Total Pitchers')\n",
    "plt.subplots_adjust(left=0.1,\n",
    "                    bottom=0.1, \n",
    "                    right=0.9, \n",
    "                    top=0.9, \n",
    "                    wspace=0.4, \n",
    "                    hspace=0.4)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From the career achievement metrics such as All-Star appearances and Cy Youngs, there isn't much difference betweent the ratios of righties to lefties as there is to the entrie population of pitchers. Remember, about 27% of the pitchers in MLB history are left handed. The proportion of All-Star appearances for R vs L is identical to the overall population. While the proportion of Cy Youngs is slightly higher (32% L) and far lower for HoF inductees (15%).\n",
    "\n",
    "I would argue that left-handers are not better at the MLB level. It could be because professional hitters are good enough or have seen enough lefties that the lefty advantage is limited. However, there are a lot higher proportion of left-handed pitchers than there are left-handed people overall. Could it be that lefties are more successful at a young age and against lower competition. This advantage becomes a self-fulfilling prophecy as the lefties continually succeed due to their advantage all. They in turn earn more accolades and attention from scouts, promoting them to higher and higher levels of competition until their advantage is eliminated by talented, professional batters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "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>CareerIP</th>\n",
       "      <th>CareerWin%</th>\n",
       "      <th>CareerSV%</th>\n",
       "      <th>CareerERA</th>\n",
       "      <th>CareerBAOpp</th>\n",
       "      <th>CyYoungCount</th>\n",
       "      <th>CareerAllStarGames</th>\n",
       "      <th>throwsLeft</th>\n",
       "      <th>hof</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>823.000000</td>\n",
       "      <td>823.000000</td>\n",
       "      <td>818.000000</td>\n",
       "      <td>823.000000</td>\n",
       "      <td>823.000000</td>\n",
       "      <td>823.000000</td>\n",
       "      <td>823.000000</td>\n",
       "      <td>823.0</td>\n",
       "      <td>823.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>528.822357</td>\n",
       "      <td>0.141138</td>\n",
       "      <td>0.155578</td>\n",
       "      <td>4.444022</td>\n",
       "      <td>0.262090</td>\n",
       "      <td>0.036452</td>\n",
       "      <td>0.393682</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.003645</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>632.450992</td>\n",
       "      <td>0.118188</td>\n",
       "      <td>0.215680</td>\n",
       "      <td>0.936183</td>\n",
       "      <td>0.024835</td>\n",
       "      <td>0.293702</td>\n",
       "      <td>1.155989</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.060302</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>50.700000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.230000</td>\n",
       "      <td>0.145900</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>116.000000</td>\n",
       "      <td>0.049700</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.840000</td>\n",
       "      <td>0.246650</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>286.300000</td>\n",
       "      <td>0.093000</td>\n",
       "      <td>0.040250</td>\n",
       "      <td>4.290000</td>\n",
       "      <td>0.261800</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>670.800000</td>\n",
       "      <td>0.212700</td>\n",
       "      <td>0.250000</td>\n",
       "      <td>4.910000</td>\n",
       "      <td>0.277200</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>4413.300000</td>\n",
       "      <td>0.502400</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>9.170000</td>\n",
       "      <td>0.345100</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          CareerIP  CareerWin%   CareerSV%   CareerERA  CareerBAOpp  \\\n",
       "count   823.000000  823.000000  818.000000  823.000000   823.000000   \n",
       "mean    528.822357    0.141138    0.155578    4.444022     0.262090   \n",
       "std     632.450992    0.118188    0.215680    0.936183     0.024835   \n",
       "min      50.700000    0.000000    0.000000    2.230000     0.145900   \n",
       "25%     116.000000    0.049700    0.000000    3.840000     0.246650   \n",
       "50%     286.300000    0.093000    0.040250    4.290000     0.261800   \n",
       "75%     670.800000    0.212700    0.250000    4.910000     0.277200   \n",
       "max    4413.300000    0.502400    1.000000    9.170000     0.345100   \n",
       "\n",
       "       CyYoungCount  CareerAllStarGames  throwsLeft         hof  \n",
       "count    823.000000          823.000000       823.0  823.000000  \n",
       "mean       0.036452            0.393682         1.0    0.003645  \n",
       "std        0.293702            1.155989         0.0    0.060302  \n",
       "min        0.000000            0.000000         1.0    0.000000  \n",
       "25%        0.000000            0.000000         1.0    0.000000  \n",
       "50%        0.000000            0.000000         1.0    0.000000  \n",
       "75%        0.000000            0.000000         1.0    0.000000  \n",
       "max        5.000000           10.000000         1.0    1.000000  "
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "q4[q4['throws'] == 'L'].describe()\n"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
  },
  "kernelspec": {
   "display_name": "Python 3.9.1 64-bit",
   "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": "3.9.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}