# Load Raw Text file Data from github
file_path <- 'https://raw.githubusercontent.com/Badigun/Data-607-Assignments/refs/heads/main/chess%20tournament%20file.txt'
tournament_data <- read_lines(file_path)
# View the first few lines of the Data
head(tournament_data)
## [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 |"
tail(tournament_data)
## [1] " 63 | THOMAS JOSEPH HOSMER |1.0 |L 2|L 48|D 49|L 43|L 45|H |U |"
## [2] " MI | 15057092 / R: 1175 ->1125 | |W |B |W |B |B | | |"
## [3] "-----------------------------------------------------------------------------------------"
## [4] " 64 | BEN LI |1.0 |L 22|D 30|L 31|D 49|L 46|L 42|L 54|"
## [5] " MI | 15006561 / R: 1163 ->1112 | |B |W |W |B |W |B |B |"
## [6] "-----------------------------------------------------------------------------------------"
I observe that the data follows a specific pattern. The first four lines contain non-data information, so they are excluded from the dataset. After that, the player details and game statistics appear in a repeating sequence every three lines. The data is then organize into two matrices, one for player information and the other for their game statistics, to structure it like a more conventional dataset.
Each player has two lines in the file, which includes;
Line 1: Name, total points, and opponent numbers.
Line 2: State and pre-rating.
# Name, total points, and opponent numbers
edit_tournament_data <- matrix(unlist(tournament_data), byrow=TRUE)
m1 <- edit_tournament_data[seq(5,length(edit_tournament_data),3)]
head(m1)
## [1] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [2] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [3] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [4] " 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1|"
## [5] " 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17|"
## [6] " 6 | HANSEN SONG |5.0 |W 34|D 29|L 11|W 35|D 10|W 27|W 21|"
Another way to extract player information for Line 1: Name, total points, and opponent numbers
player_lines <- tournament_data[grep("^\\s*\\d+", tournament_data)]
# Identify lines that contain player information
player_lines <- tournament_data[grep("^\\s*\\d+", tournament_data)]
# Extract Player's Name, Points, and Opponents
players_info <- lapply(player_lines, function(line) {
elements <- unlist(strsplit(line, "\\|"))
elements <- trimws(elements) # Remove leading and trailing spaces
# Extract fields
name <- elements[2] # Player Name
total_points <- as.numeric(elements[3]) # Total Points
opponents <- unlist(str_extract_all(elements[6:length(elements)], "\\d+")) # Opponent Numbers
return(list(name, total_points, opponents))
})
# Convert to DataFrame
players_df <- data.frame(
Name = sapply(players_info, `[[`, 1),
Points = sapply(players_info, `[[`, 2),
Opponents = sapply(players_info, function(x) paste(x[[3]], collapse = ",")), # Convert list to string
stringsAsFactors = FALSE
)
head(players_df)
## Name Points Opponents
## 1 GARY HUA 6.0 18,14,7,12,4
## 2 DAKSHESH DARURI 6.0 4,17,16,20,7
## 3 ADITYA BAJAJ 6.0 25,21,11,13,12
## 4 PATRICK H SCHILLING 5.5 2,26,5,19,1
## 5 HANSHI ZUO 5.5 12,13,4,14,17
## 6 HANSEN SONG 5.0 11,35,10,27,21
This code is to extract Line 2: State and pre-rating
m2 <- edit_tournament_data[seq(6,length(edit_tournament_data),3)]
head(m2)
## [1] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [2] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [3] " MI | 14959604 / R: 1384 ->1640 |N:2 |W |B |W |B |W |B |W |"
## [4] " MI | 12616049 / R: 1716 ->1744 |N:2 |W |B |W |B |W |B |B |"
## [5] " MI | 14601533 / R: 1655 ->1690 |N:2 |B |W |B |W |B |W |B |"
## [6] " OH | 15055204 / R: 1686 ->1687 |N:3 |W |B |W |B |B |W |B |"
Another way to extract Line 2: State and pre-rating
# Find the second line for each player's entry (contains state & rating)
rating_lines <- tournament_data[grep("R:\\s*\\d+", tournament_data)]
# Extract State and Pre-Rating
ratings_info <- lapply(rating_lines, function(line) {
elements <- unlist(strsplit(line, "\\|"))
elements <- trimws(elements)
state <- substr(elements[1], 1, 2) # Extract first two letters as state
pre_rating <- as.numeric(str_extract(elements[2], "(?<=R:\\s)\\d+")) # Extract pre-rating
return(list(state, pre_rating))
})
# Add to DataFrame
players_df$State <- sapply(ratings_info, `[[`, 1)
players_df$Pre_Rating <- sapply(ratings_info, `[[`, 2)
Since the Data is more organized, capturing of the data featured can be done
# Convert m1 and m2 to character vectors
m1 <- as.character(m1)
m2 <- as.character(m2)
# matching first numbers
ID <- as.numeric(str_extract(m1, '\\d+'))
# matching the first combination of a letter, any amount of characters and "|"
Name <- str_extract(m1, '[A-z].{1,32}')
# extracting the name
Name <- str_trim(str_extract(Name, '.+\\s{2,}'))
# matching the first two letters (state) in the second matrix
State <- str_extract(m2, '[A-Z]{2}')
# matching at least 1 number, a period, and 1 number
Total_Points <- as.numeric(str_extract(m1, '\\d+\\.\\d'))
# matching the combination of "R", any characters and "-"
PreRating <- str_extract(m2, 'R:.{8,}-')
# matching first 4 numbers
PreRating <- as.numeric(str_extract(PreRating, '\\d{1,4}'))
# matching all combinations of 1 letter 2 spaces and any numbers
Rounds <- str_extract_all(m1, '[A-Z]\\s{2,}\\d+')
# matching numbers
Rounds <- str_extract_all(Rounds, '\\d+')
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
Compute the average pre-rating of opponents using the vectors from the previous step
AvgOpp_Rating <- c()
for(i in c(1:length(Rounds))){
AvgOpp_Rating[i] <- round(mean(PreRating[as.numeric(Rounds[[i]])]),0)
}
AvgOpp_Rating
## [1] 1605 1469 1564 1574 1501 1519 1372 1468 1523 1554 1468 1506 1498 1515 1484
## [16] 1386 1499 1480 1426 1411 1470 1300 1214 1357 1363 1507 1222 1522 1314 1144
## [31] 1260 1379 1277 1375 1150 1388 1385 1539 1430 1391 1248 1150 1107 1327 1152
## [46] 1358 1392 1356 1286 1296 1356 1495 1345 1206 1406 1414 1363 1391 1319 1330
## [61] 1327 1186 1350 1263
Project1_Data607 <- data.frame(ID,Name,State,Total_Points,PreRating,AvgOpp_Rating)
head(Project1_Data607)
## ID Name State Total_Points PreRating AvgOpp_Rating
## 1 1 GARY HUA ON 6.0 1794 1605
## 2 2 DAKSHESH DARURI MI 6.0 1553 1469
## 3 3 ADITYA BAJAJ MI 6.0 1384 1564
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1574
## 5 5 HANSHI ZUO MI 5.5 1655 1501
## 6 6 HANSEN SONG OH 5.0 1686 1519
write_csv(Project1_Data607, "ChessTournament_results.csv")