«
»

Retrosheet event record mapping completed

October 18, 2009, 9:53 pm

The Retrosheet project has kind of sat around for a while untouched, so I figured I would finish up the reading of the event records. I have decided to break the project into separate files, as if I kept it in one file, it would be obscenely long.

So, here is the main Program.cs file:

Program.cs

using System;
using System.Collections.Generic;
using System.Linq;
 
namespace RetrosheetReader
{
    class Program
    {
        static List<Team> teamList;
        static List<Player> playerList;
        static List<Event> eventList;
 
        const string DATA = "c:\\baseball_data\\";
 
        static void Main(string[] args)
        {
            Console.WriteLine("Retrosheet Reader");
            Console.WriteLine();
 
            teamList = Team.GetTeamList(DATA);
            playerList = Player.GetPlayerList(DATA);
            eventList = Event.GetEventList(DATA);
 
            Console.WriteLine("Number of teams: " + teamList.Count().ToString());
            Console.WriteLine("Number of players: " + playerList.Count().ToString());
            Console.WriteLine("Number of events: " + eventList.Count().ToString());
 
            Console.WriteLine();
            Console.Write("Strike any key to end...");
            Console.ReadKey();
        }
    }
}

There are now 3 class files, one each for a team, player, and event. The event file is the one with the most new stuff going on.

Team.cs

using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
 
namespace RetrosheetReader
{
    class Team
    {
        int year;
        string city;
        string nickname;
        string abbreviation;
        string league;
 
        public Team(int y, string[] a)
        {
            year = y;
            abbreviation = a[0];
            league = a[1];
            city = a[2];
            nickname = a[3];
        }
 
        public static List<Team> GetTeamList(string dir)
        {
            int y;
            string s;
            string[] splitLine;
            List<Team> teamList = new List<Team>();
 
            List<string> tfs = Directory.GetFiles(dir, "team*").ToList();
            foreach (string tf in tfs)
            {
                y = Convert.ToInt32(Path.GetFileName(tf).Substring(4));
                StreamReader sr = new StreamReader(tf);
                while ((s = sr.ReadLine()) != null)
                {
                    splitLine = s.Split(',');
                    if (splitLine.Count() == 4)
                    {
                        teamList.Add(new Team(y, splitLine));
                    }
                }
            }
 
            return teamList;
        }
    }
}

Player.cs

using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
 
namespace RetrosheetReader
{
    class Player
    {
        int year;
        string team;
        string playerID;
        string firstName;
        string lastName;
        string bats;
        string throws;
        string position;
 
        public Player(int y, string[] a)
        {
            year = y;
            playerID = a[0];
            lastName = a[1];
            firstName = a[2];
            bats = a[3];
            throws = a[4];
            team = a[5];
            position = a[6];
        }
 
        public static List<Player> GetPlayerList(string dir)
        {
            int y;
            string s;
            string[] splitLine;
            List<Player> playerList = new List<Player>();
 
            List<string> rfs = Directory.GetFiles(dir, "*.ros").ToList();
            foreach (string rf in rfs)
            {
                y = Convert.ToInt32(Path.GetFileName(rf).Substring(3).Split('.')[0]);
                StreamReader sr = new StreamReader(rf);
                while ((s = sr.ReadLine()) != null)
                {
                    splitLine = s.Split(',');
                    if (splitLine.Count() == 7)
                    {
                        playerList.Add(new Player(y, splitLine));
                    }
                }
            }
 
            return playerList;
        }
    }
}

Event.cs

using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
 
namespace RetrosheetReader
{
    class Event
    {
        string gameID;          // 0, A
        string visitingTeam;    // 1, B
        int inning;             // 2, C
        int battingTeam;        // 3, D
        int outs;               // 4, E
        int balls;              // 5, F
        int strikes;            // 6, G
        string pitchSequence;   // 7, H
        int visitorScore;       // 8, I
        int homeScore;          // 9, J
        string batter;          // 10, K
        string batterHand;      // 11, L
        string resBatter;       // 12, M
        string resBatterHand;   // 13, N
        string pitcher;         // 14, O
        string pitcherHand;     // 15, P
        string resPitcher;      // 16, Q
        string resPitcherHand;  // 17, R
        string catcher;         // 18, S
        string firstBase;       // 19, T
        string secondBase;      // 20, U
        string thirdBase;       // 21, V
        string shortstop;       // 22, W
        string leftField;       // 23, X
        string centerField;     // 24, Y
        string rightField;      // 25, Z
        string firstRunner;     // 26, AA
        string secondRunner;    // 27, AB
        string thirdRunner;     // 28, AC
        string eventText;       // 29, AD
        bool leadoffFlag;       // 30, AE
        bool pinchHitFlag;      // 31, AF
        int defensivePosition;  // 32, AG
        int lineupPosition;     // 33, AH
        int eventType;          // 34, AI
        bool batterEventFlag;   // 35, AJ
        bool abFlag;            // 36, AK
        int hitValue;           // 37, AL
        bool shFlag;            // 38, AM
        bool sfFlag;            // 39, AN
        int outsOnPlay;         // 40, AO
        bool doublePlayFlag;    // 41, AP
        bool triplePlayFlag;    // 42, AQ
        int rbiOnPlay;          // 43, AR
        bool wildPitchFlag;     // 44, AS
        bool passedBallFlag;    // 45, AT
        int fieldedBy;          // 46, AU
        string battedBallType;  // 47, AV
        bool buntFlag;          // 48, AW
        bool foulFlag;          // 49, AX
        string hitLocation;     // 50, AY
        int numErrors;          // 51, AZ
        int firstErrorPlayer;   // 52, BA
        string firstErrorType;  // 53, BB
        int secondErrorPlayer;  // 54, BC
        string secondErrorType; // 55, BD
        int thirdErrorPlayer;   // 56, BE
        string thirdErrorType;  // 57, BF
        int batterDest;         // 58, BG
        int runner1Dest;        // 59, BH
        int runner2Dest;        // 60, BI
        int runner3Dest;        // 61, BJ
        string playOnBatter;    // 62, BK
        string playOnRunner1;   // 63, BL
        string playOnRunner2;   // 64, BM
        string playOnRunner3;   // 65, BN
        bool sbRunner1Flag;     // 66, BO
        bool sbRunner2Flag;     // 67, BP
        bool sbRunner3Flag;     // 68, BQ
        bool csRunner1Flag;     // 69, BR
        bool csRunner2Flag;     // 70, BS
        bool csRunner3Flag;     // 71, BT
        bool poRunner1Flag;     // 72, BU
        bool poRunner2Flag;     // 73, BV
        bool poRunner3Flag;     // 74, BW
        string respPitcher1;    // 75, BX
        string respPitcher2;    // 76, BY
        string respPitcher3;    // 77, BZ
        bool newGameFlag;       // 78, CA
        bool endGameFlag;       // 79, CB
        bool pinchRunner1;      // 80, CC
        bool pinchRunner2;      // 81, CD
        bool pinchRunner3;      // 82, CE
        string removedForPR1;   // 83, CF
        string removedForPR2;   // 84, CG
        string removedForPR3;   // 85, CH
        string removedForPH;    // 86, CI
        int posRemovedForPH;    // 87, CJ
        int fielderWithPO1;     // 88, CK
        int fielderWithPO2;     // 89, CL
        int fielderWithPO3;     // 90, CM
        int fielderWithA1;      // 91, CN
        int fielderWithA2;      // 92, CO
        int fielderWithA3;      // 93, CP
        int fielderWithA4;      // 94, CQ
        int fielderWithA5;      // 95, CR
        int eventNum;           // 96, CS
 
        public Event(string[] a)
        {
            gameID = a[0].Replace("\"", "");
            visitingTeam = a[1].Replace("\"", "");
            inning = Convert.ToInt32(a[2]);
            battingTeam = Convert.ToInt32(a[3]);
            outs = Convert.ToInt32(a[4]);
            balls = Convert.ToInt32(a[5]);
            strikes = Convert.ToInt32(a[6]);
            pitchSequence = a[7].Replace("\"", "");
            visitorScore = Convert.ToInt32(a[8]);
            homeScore = Convert.ToInt32(a[9]);
            batter = a[10].Replace("\"", "");
            batterHand = a[11].Replace("\"", "");
            resBatter = a[12].Replace("\"", "");
            resBatterHand = a[13].Replace("\"", "");
            pitcher = a[14].Replace("\"", "");
            pitcherHand = a[15].Replace("\"", "");
            resPitcher = a[16].Replace("\"", "");
            resPitcherHand = a[17].Replace("\"", "");
            catcher = a[18].Replace("\"", "");
            firstBase = a[19].Replace("\"", "");
            secondBase = a[20].Replace("\"", "");
            thirdBase = a[21].Replace("\"", "");
            shortstop = a[22].Replace("\"", "");
            leftField = a[23].Replace("\"", "");
            centerField = a[24].Replace("\"", "");
            rightField = a[25].Replace("\"", "");
            firstRunner = a[26].Replace("\"", "");
            secondRunner = a[27].Replace("\"", "");
            thirdRunner = a[28].Replace("\"", "");
            eventText = a[29].Replace("\"", "");
            leadoffFlag = a[30].Contains('T');
            pinchHitFlag = a[31].Contains('T');
            defensivePosition = Convert.ToInt32(a[32]);
            lineupPosition = Convert.ToInt32(a[33]);
            eventType = Convert.ToInt32(a[34]);
            batterEventFlag = a[35].Contains('T');
            abFlag = a[36].Contains('T');
            hitValue = Convert.ToInt32(a[37]);
            shFlag = a[38].Contains('T');
            sfFlag = a[39].Contains('T');
            outsOnPlay = Convert.ToInt32(a[40]);
            doublePlayFlag = a[41].Contains('T');
            triplePlayFlag = a[42].Contains('T');
            rbiOnPlay = Convert.ToInt32(a[43]);
            wildPitchFlag = a[44].Contains('T');
            passedBallFlag = a[45].Contains('T');
            fieldedBy = Convert.ToInt32(a[46]);
            battedBallType = a[47].Replace("\"", "");
            buntFlag = a[48].Contains('T');
            foulFlag = a[49].Contains('T');
            hitLocation = a[50].Replace("\"", "");
            numErrors = Convert.ToInt32(a[51]);
            firstErrorPlayer = Convert.ToInt32(a[52]);
            firstErrorType = a[53].Replace("\"", "");
            secondErrorPlayer = Convert.ToInt32(a[54]);
            secondErrorType = a[55].Replace("\"", "");
            thirdErrorPlayer = Convert.ToInt32(a[56]);
            thirdErrorType = a[57].Replace("\"", "");
            batterDest = Convert.ToInt32(a[58]);
            runner1Dest = Convert.ToInt32(a[59]);
            runner2Dest = Convert.ToInt32(a[60]);
            runner3Dest = Convert.ToInt32(a[61]);
            playOnBatter = a[62].Replace("\"", "");
            playOnRunner1 = a[63].Replace("\"", "");
            playOnRunner2 = a[64].Replace("\"", "");
            playOnRunner3 = a[65].Replace("\"", "");
            sbRunner1Flag = a[66].Contains('T');
            sbRunner2Flag = a[67].Contains('T');
            sbRunner3Flag = a[68].Contains('T');
            csRunner1Flag = a[69].Contains('T');
            csRunner2Flag = a[70].Contains('T');
            csRunner3Flag = a[71].Contains('T');
            poRunner1Flag = a[72].Contains('T');
            poRunner2Flag = a[73].Contains('T');
            poRunner3Flag = a[74].Contains('T');
            respPitcher1 = a[75].Replace("\"", "");
            respPitcher2 = a[76].Replace("\"", "");
            respPitcher3 = a[77].Replace("\"", "");
            newGameFlag = a[78].Contains('T');
            endGameFlag = a[79].Contains('T');
            pinchRunner1 = a[80].Contains('T');
            pinchRunner2 = a[81].Contains('T');
            pinchRunner3 = a[82].Contains('T');
            removedForPR1 = a[83].Replace("\"", "");
            removedForPR2 = a[84].Replace("\"", "");
            removedForPR3 = a[85].Replace("\"", "");
            removedForPH = a[86].Replace("\"", "");
            posRemovedForPH = Convert.ToInt32(a[87]);
            fielderWithPO1 = Convert.ToInt32(a[88]);
            fielderWithPO2 = Convert.ToInt32(a[89]);
            fielderWithPO3 = Convert.ToInt32(a[90]);
            fielderWithA1 = Convert.ToInt32(a[91]);
            fielderWithA2 = Convert.ToInt32(a[92]);
            fielderWithA3 = Convert.ToInt32(a[93]);
            fielderWithA4 = Convert.ToInt32(a[94]);
            fielderWithA5 = Convert.ToInt32(a[95]);
            eventNum = Convert.ToInt32(a[96]);
        }
 
        public static List<Event> GetEventList(string dir)
        {
            string s;
            string[] splitLine;
            List<Event> eventList = new List<Event>();
 
            List<string> efs = Directory.GetFiles(dir, "*.csv").ToList();
            foreach (string ef in efs)
            {
                Console.WriteLine("Reading events in " + ef);
                StreamReader sr = new StreamReader(ef);
                while ((s = sr.ReadLine()) != null)
                {
                    splitLine = s.Split(',');
                    if (splitLine.Count() == 97)
                    {
                        eventList.Add(new Event(splitLine));
                    }
                }
            }
 
            return eventList;
        }
    }
}

I have zipped up the solution if you would like to work with it:

RetrosheetReader.zip

Next up will come some actual analysis of the data, now that it is completely being read in and stored.

Tags: ,
Category: .NET, C#, Retrosheet  |  Comment (RSS)  |  Trackback

Leave a Reply