tournament <- readLines(
"https://raw.githubusercontent.com/mj-nurse/mnurse-data_607/refs/heads/main/project-01-chess-tournament/tournamentinfo.txt"
)## Warning in
## readLines("https://raw.githubusercontent.com/mj-nurse/mnurse-data_607/refs/heads/main/project-01-chess-tournament/tournamentinfo.txt"):
## incomplete final line found on
## 'https://raw.githubusercontent.com/mj-nurse/mnurse-data_607/refs/heads/main/project-01-chess-tournament/tournamentinfo.txt'head(tournament, 10)## [1] "-----------------------------------------------------------------------------------------"
## [2] " Pair | Player Name |Total|Round|Round|Round|Round|Round|Round|Round| "
## [3] " Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | 6 | 7 | "
## [4] "-----------------------------------------------------------------------------------------"
## [5] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [6] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [7] "-----------------------------------------------------------------------------------------"
## [8] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [9] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [10] "-----------------------------------------------------------------------------------------"# Number of players in the tournament
n_players <- 64
# Create an empty data frame for the player information
players <- data.frame(
Pair_Num = integer(n_players),
Player_Name = character(n_players),
Player_State = character(n_players),
Total_Points = numeric(n_players),
Pre_Rating = integer(n_players)
)
# Create an empty matrix for the 7 opponents
opponents <- matrix(
NA_integer_,
nrow = n_players,
ncol = 7
)
colnames(opponents) <- paste0("Round_", 1:7)
# Go through each player
for (i in 1:n_players) {
# Each player has two lines followed by a separator
player_line <- tournament[5 + (i - 1) * 3]
detail_line <- tournament[6 + (i - 1) * 3]
# Split the lines at each |
player_parts <- strsplit(player_line, "|", fixed = TRUE)[[1]]
detail_parts <- strsplit(detail_line, "|", fixed = TRUE)[[1]]
# Extract basic player information
players$Pair_Num[i] <- as.integer(trimws(player_parts[1]))
players$Player_Name[i] <- trimws(player_parts[2])
players$Total_Points[i] <- as.numeric(trimws(player_parts[3]))
players$Player_State[i] <- trimws(detail_parts[1])
# Extract the pre-tournament rating
rating <- strsplit(detail_parts[2], "R:", fixed = TRUE)[[1]][2]
rating <- strsplit(rating, "->", fixed = TRUE)[[1]][1]
rating <- strsplit(trimws(rating), "P", fixed = TRUE)[[1]][1]
players$Pre_Rating[i] <- as.integer(trimws(rating))
# Extract opponent numbers from each round
for (round in 1:7) {
round_text <- trimws(player_parts[3 + round])
if (nchar(round_text) > 1) {
opponent_number <- trimws(
substr(round_text, 2, nchar(round_text))
)
opponents[i, round] <- as.integer(opponent_number)
} else {
opponents[i, round] <- NA
}
}
}
# Show the first few results
head(players)## Pair_Num Player_Name Player_State Total_Points Pre_Rating
## 1 1 GARY HUA ON 6.0 1794
## 2 2 DAKSHESH DARURI MI 6.0 1553
## 3 3 ADITYA BAJAJ MI 6.0 1384
## 4 4 PATRICK H SCHILLING MI 5.5 1716
## 5 5 HANSHI ZUO MI 5.5 1655
## 6 6 HANSEN SONG OH 5.0 1686head(opponents)## Round_1 Round_2 Round_3 Round_4 Round_5 Round_6 Round_7
## [1,] 39 21 18 14 7 12 4
## [2,] 63 58 4 17 16 20 7
## [3,] 8 61 25 21 11 13 12
## [4,] 23 28 2 26 5 19 1
## [5,] 45 37 12 13 4 14 17
## [6,] 34 29 11 35 10 27 21# Create a new column for average opponent rating
players$Average_Opponent_Rating <- NA
# Go through each player
for (i in 1:n_players) {
# Get this player's opponent numbers
opponent_numbers <- opponents[i, ]
# Remove rounds where there was no opponent
opponent_numbers <- opponent_numbers[!is.na(opponent_numbers)]
# Create a place to store the opponent ratings
opponent_ratings <- numeric(length(opponent_numbers))
# Look up each opponent's pre-tournament rating
for (j in 1:length(opponent_numbers)) {
opponent_row <- match(
opponent_numbers[j],
players$Pair_Num
)
opponent_ratings[j] <- players$Pre_Rating[opponent_row]
}
# Calculate the average opponent rating
players$Average_Opponent_Rating[i] <- round(
mean(opponent_ratings)
)
}
# Keep only the columns required for the assignment
final_results <- players[, c(
"Player_Name",
"Player_State",
"Total_Points",
"Pre_Rating",
"Average_Opponent_Rating"
)]
head(final_results)## Player_Name Player_State Total_Points Pre_Rating
## 1 GARY HUA ON 6.0 1794
## 2 DAKSHESH DARURI MI 6.0 1553
## 3 ADITYA BAJAJ MI 6.0 1384
## 4 PATRICK H SCHILLING MI 5.5 1716
## 5 HANSHI ZUO MI 5.5 1655
## 6 HANSEN SONG OH 5.0 1686
## Average_Opponent_Rating
## 1 1605
## 2 1469
## 3 1564
## 4 1574
## 5 1501
## 6 1519write.csv(
final_results,
"chess_tournament_results.csv",
row.names = FALSE
)
# Final checks
nrow(final_results)## [1] 64head(final_results)## Player_Name Player_State Total_Points Pre_Rating
## 1 GARY HUA ON 6.0 1794
## 2 DAKSHESH DARURI MI 6.0 1553
## 3 ADITYA BAJAJ MI 6.0 1384
## 4 PATRICK H SCHILLING MI 5.5 1716
## 5 HANSHI ZUO MI 5.5 1655
## 6 HANSEN SONG OH 5.0 1686
## Average_Opponent_Rating
## 1 1605
## 2 1469
## 3 1564
## 4 1574
## 5 1501
## 6 1519tail(final_results)## Player_Name Player_State Total_Points Pre_Rating
## 59 SEAN M MC CORMICK MI 2.0 853
## 60 JULIA SHEN MI 1.5 967
## 61 JEZZEL FARKAS ON 1.5 955
## 62 ASHWIN BALAJI MI 1.0 1530
## 63 THOMAS JOSEPH HOSMER MI 1.0 1175
## 64 BEN LI MI 1.0 1163
## Average_Opponent_Rating
## 59 1319
## 60 1330
## 61 1327
## 62 1186
## 63 1350
## 64 1263The tournament text file was transformed into a structured dataset containing each player’s name, state, total points, pre-tournament rating, and average opponent pre-rating. The final dataset contains 64 players and was exported to a CSV file.