# Step 1 - Install the Lahman dataset - comment to run again as it will be already loaded.
install.packages("Lahman") 

# Step 2 - load the library
library(Lahman)

# Step 3 - ensure that the year is at least 2018
max(Batting$yearID) 

# Step 4 - View the Batting table
View(Batting)

# Step 5 - create the filter for 2018 (Batting and Pitching)
batting2018 <- Batting[Batting$yearID == 2018, ]

pitching2018 <- Pitching[Pitching$yearID == 2018, ]

# Step 5a - View the new batting2018 table
View(batting2018) # feel free to do this with pitching2018 too

# Step 6 - Add the batting average (BA) column
batting2018$BA = round(batting2018$H / batting2018$AB * 100, 0)

# step 7 - Filter out the NaN (see blog text)
batting2018 <- batting2018[batting2018$AB > 0, ]

# Step 8 - filter out players how have not played enough games (see blog text)
batting2018 <- batting2018[batting2018$G > 75, ]

# Step 9 - select the players at random and split into two teams
playerPicks <- sample(1:nrow(batting2018), 18, replace=FALSE)

homeTeam <- batting2018[playerPicks[1:9], ]

awayTeam <- batting2018[playerPicks[10:18], ]

# Step 10 - add player name to home and away teams
homeIndex <- match(homeTeam$playerID, People$playerID)

awayIndex <- match(awayTeam$playerID, People$playerID)

homeTeam$playerName <- paste(People[homeIndex, "nameFirst"], People[homeIndex, "nameLast"])

awayTeam$playerName <- paste(People[awayIndex, "nameFirst"], People[awayIndex, "nameLast"])

# Step 11 - print out in the format needed for game (see blog text)

homeTeam[, c("playerName", "BA")]
awayTeam[, c("playerName", "BA")]