GamesFielding.R

library( package = 'dplyr' )
library( package = 'data.table' )
library( package = 'reshape2' )

# Column names
l_e_names <- c( 'GAME_ID','CATCHER','FIRST_BASEMAN','SECOND_BASEMAN'
              , 'THIRD_BASEMAN','SHORTSTOP','LEFT_FIELDER','CENTER_FIELDER'
              , 'RIGHT_FIELDER', 'EVENT_OUTS_CT' ,'TEAM_ID' 
              )
              
# Column types
l_e_cols <- c( 'character'
             , rep( x = 'NULL',      times = 17 )
             , rep( x = 'character', times = 8  )
             , rep( x = 'NULL',      times = 14 )
             , 'numeric'
             , rep( x = 'NULL',      times = 58 )
             , 'character'
             , rep( x = 'NULL',      times = 58 )
             ) 

# Push the 1970 season into the environment.
d_e_1970 <- fread( input      = 'all1970.csv'
                 , sep        = ','
                 , colClasses = l_e_cols 
                 , col.names  = l_e_names
                 ) 

# Transform the dataset:
# IDs: GAME_ID, OUTS & FIELDING TEAM
# Measures: All fielding positions, except for pitcher
d_r_1970  <- melt( data            = d_e_1970
                 , id.vars         = l_e_names[ c( 1, 10, 11 ) ]
                 , measure.vars    = l_e_names[ -c( 1, 10, 11 ) ]
                 , variable.name   = 'POSITION'
                 , value.name      = 'PLAYER_ID'
                 , variable.factor = F
                 )

# Get Games, Innings and Outs per player & team
d_p_games <- group_by( .data = d_r_1970, TEAM_ID, PLAYER_ID, POSITION ) %>%
            summarise( T_O  = sum( x = EVENT_OUTS_CT, na.rm = T ) )     %>%
               mutate( G    = T_O %/% 27 
                     , I    = ( T_O %% 27 ) %/% 3
                     , O    = ( T_O %% 27 ) %% 3
                     , TEXT = paste( G,'game(s),'
                                   , I, 'inning(s) and'
                                   , O, 'out(s)'
                                   , sep = ' ' 
                                   )
                     )