gabartomeoDATA607project01

Getting the Text File into R

fileName <- "https://raw.githubusercontent.com/gabartomeo/data607-cunysps/master/Project01/tournamentinfo.txt"
connection <- file(fileName, "r")
txt <- readLines(connection, warn = F)
close(connection)

Breaking the Text File Apart

# This initial part is to split the table into pieces using the pipe | as a separator
txtList <- strsplit(txt, "\\|")

# This strips out any leading and trailing whitespace
txtList <- lapply(txtList, trimws)

# This skips any lines with dashes
txtList <- txtList[sort(c(seq(5, length(txtList), 3), seq(6, length(txtList), 3)))]
txtList <- Filter(length, txtList)

# This makes a data frame, just so we have the whole table in front of us
txtFrameOdd <- do.call(rbind, txtList[seq(1, length(txtList), 2)])
txtFrameOdd <- as.data.frame(txtFrameOdd)
txtFrameEven <- do.call(rbind, txtList[seq(2, length(txtList), 2)])
txtFrameEven <- as.data.frame(txtFrameEven)
txtFrame <- cbind(txtFrameOdd, txtFrameEven)
names(txtFrame) <- c("Number", "Player's Name", "Total Number of Points", "Round 1", "Round 2", "Round 3", "Round 4", "Round 5", "Round 6", "Round 7", "Player's State", "Rating", "N", "Round 1 Status", "Round 2 Status", "Round 3 Status", "Round 4 Status", "Round 5 Status", "Round 6 Status", "Round 7 Status")

Adding Columns We Need

# Let's add the ratings alone onto the data frame with what we need
ratings <- gsub(" ", "", txtFrame$"Rating")
ratingsReg <- gregexpr("(?<=:)(\\d+)(?=-|P)", ratings, perl=TRUE)
txtFrame$"Player's Pre-Rating" <- regmatches(ratings, ratingsReg)
txtFrame$"Player's Pre-Rating" <- as.numeric(unlist(txtFrame$"Player's Pre-Rating", use.names=F))

# Make a separate rounds table, makes things easier
rounds <- txtFrame[c("Round 1", "Round 2", "Round 3", "Round 4", "Round 5", "Round 6", "Round 7")]
rounds <- lapply(rounds, function (x) as.numeric(gsub("[^\\d]", "", x, perl=T)))
rounds <- as.data.frame(rounds)

# Get the average ratings using the rounds table and a new ratings table
playerRatings <- sapply(rounds, function(x) ifelse(x=="NULL", NA, unlist(txtFrame$"Player's Pre-Rating"[x])))
playerRatings <- as.data.frame(playerRatings)
playerRatings <- as.data.frame(sapply(playerRatings, function(x) as.numeric(as.character(x))))

# From here, averages are easy!
txtFrame$"Average Pre Chess Rating of Opponents" <- rowMeans(playerRatings, na.rm=T)

Setting up the Data Frame and Outputting the CSV

output <- txtFrame[c("Player's Name", "Player's State", "Total Number of Points", "Player's Pre-Rating", "Average Pre Chess Rating of Opponents")]
write.csv(output, file=file("tournamentinfo.csv", "w"), row.names=F, na="")