Project1

Introduction

This project analyzes chess tournament results from a text file. The goal is to extract relevant player information, including names, states, total points, and pre-tournament ratings and calculate the average pre-rating of each player’s opponents. The data is later compiled into a clean csv file for future analysis or database import.

Extract player names

lines <- readLines('https://raw.githubusercontent.com/vincent-usny/project1/refs/heads/main/project1.txt', warn = FALSE)
data <- lines[-c(1:4)] #remove first 4 lines

#get player names
players_lines <- data[seq(1, length(data), by = 3)]
parts_line1 <- strsplit(players_lines, '\\|')
names <- sapply(parts_line1, function(x) trimws(x[2]))

Extract player states

#get states
state_lines <- data[seq(2, length(data), by = 3)]
parts_line2 <- strsplit(state_lines, '\\|')
states <- sapply(parts_line2, function(x) trimws(x[1]))

Extract each player’s total_points and pre-tournament ratings

#get total points
total_points <- sapply(parts_line1, function(x) trimws(x[3]))

#get pre-rating
ratings <- sapply(parts_line2, function(x) x[2])
pre_rating <- as.numeric(sapply(ratings, function(x) {
  sub(".*R: *(\\d+).*", "\\1", x)
}))

Calculate each player’s avg_rating of all opponents

pair_nums <- sapply(players_lines, function(x) as.numeric(strsplit(x, "\\|")[[1]][1]))
pre_rating_lookup <- setNames(pre_rating, pair_nums)

avg_opp_rating <- sapply(parts_line1, function(y) {
  rounds <- y[4:10]
  opps <-c()
  for (r in rounds){
    r <- trimws(r)
    result <- substr(r,1,1)
    if (result %in% c('W','L','D')) {
    opp_num <- as.numeric(strsplit(r, "\\s+")[[1]][2])
    opps <- c(opps, pre_rating_lookup[opp_num])
    }
  }
  mean(opps)
})

avg_opp_rating <- round(avg_opp_rating)

Export csv file

chess_df <- data.frame(
  Player = names,
  State = states,
  Total_points = total_points,
  Pre_rating = pre_rating,
  Avg_opp_rating = avg_opp_rating
)

head(chess_df)

##                Player State Total_points Pre_rating Avg_opp_rating
## 1            GARY HUA    ON          6.0       1794           1605
## 2     DAKSHESH DARURI    MI          6.0       1553           1469
## 3        ADITYA BAJAJ    MI          6.0       1384           1564
## 4 PATRICK H SCHILLING    MI          5.5       1716           1574
## 5          HANSHI ZUO    MI          5.5       1655           1501
## 6         HANSEN SONG    OH          5.0       1686           1519

write.csv(chess_df, 'chess_tournament.csv', row.names = FALSE)

Conclusion

The tournament data was successfully extracted and cleaned, creating a new dataset containing players’ names, states, total points, pre-tournament ratings, and average ratings of each player’s opponents. The csv file is now available to be imported into MySQL or other data tools.