Loading required libraries

library(stringr)     
library(dplyr)      
library(readr)        
library(knitr)

Load Required Libraries

library(stringr)      # For string manipulation
library(dplyr)        # For data manipulation
library(readr)        # For reading/writing files
library(knitr)        # For nice table display

Read and Parse the Chess Data

# Read the text file
chess_text <- readLines("chess_data.txt", warn = FALSE)

# Remove header lines and separators (lines with dashes)
clean_data <- chess_text[!grepl("^-+", chess_text) & chess_text != ""]

# Remove any remaining empty lines
clean_data <- clean_data[nzchar(trimws(clean_data))]

cat("Total lines in file:", length(chess_text), "\n")
## Total lines in file: 196
cat("Clean data lines:", length(clean_data), "\n")
## Clean data lines: 130

Extract Required Libraries

# Initialize vectors to store extracted data
player_names <- c()
states <- c()
total_points <- c()
pre_ratings <- c()
all_opponents <- list()

# Process data in pairs (player line + rating line)
for (i in seq(1, length(clean_data), 2)) {
  # Make sure we have both lines
  if (i + 1 <= length(clean_data)) {
    player_line <- clean_data[i]
    rating_line <- clean_data[i + 1]
    
    # Split by | and extract data
    player_parts <- str_split(player_line, "\\|")[[1]]
    rating_parts <- str_split(rating_line, "\\|")[[1]]
    
    # Skip if we don't have enough parts
    if (length(player_parts) < 3 || length(rating_parts) < 2) {
      next
    }
    
    # Extract name and points from player line
    name <- str_trim(player_parts[2])
    points <- as.numeric(str_trim(player_parts[3]))
    
    # Extract state from rating line
    state <- str_trim(rating_parts[1])
    
    # Extract pre-rating using simple string search
    rating_text <- rating_parts[2]
    
    # Find where "R: " appears and extract the number after it
    if (str_detect(rating_text, "R:")) {
      r_match <- str_extract(rating_text, "R:\\s*\\d+")
      pre_rating <- as.numeric(str_extract(r_match, "\\d+"))
    } else {
      pre_rating <- NA
    }
    
    # Extract opponent numbers from rounds (columns 4 and beyond)
    opponent_numbers <- c()
    for (round_col in 4:length(player_parts)) {
      round_result <- str_trim(player_parts[round_col])
      # Extract any number from the round result (opponent pair number)
      numbers <- str_extract_all(round_result, "\\d+")[[1]]
      if (length(numbers) > 0) {
        opponent_numbers <- c(opponent_numbers, as.numeric(numbers[1]))
      }
    }
    
    # Store data
    player_names <- c(player_names, name)
    states <- c(states, state)
    total_points <- c(total_points, points)
    pre_ratings <- c(pre_ratings, pre_rating)
    all_opponents[[length(player_names)]] <- opponent_numbers
  }
}

cat("Extracted", length(player_names), "players\n")
## Extracted 65 players

Calculate Average Opponent Ratings

# Calculate average opponent ratings
avg_opponent_ratings <- c()

for (i in 1:length(player_names)) {
  opponents <- all_opponents[[i]]
  
  if (length(opponents) > 0) {
    # Look up opponent ratings
    opponent_ratings <- c()
    for (opp_num in opponents) {
      if (opp_num <= length(pre_ratings) && !is.na(pre_ratings[opp_num])) {
        opponent_ratings <- c(opponent_ratings, pre_ratings[opp_num])
      }
    }
    
    # Calculate average
    if (length(opponent_ratings) > 0) {
      avg_opponent_ratings <- c(avg_opponent_ratings, round(mean(opponent_ratings), 0))
    } else {
      avg_opponent_ratings <- c(avg_opponent_ratings, NA)
    }
  } else {
    avg_opponent_ratings <- c(avg_opponent_ratings, NA)
  }
}

Making the Final Dataset

# Create dataframe with extracted data
chess_results <- data.frame(
  Player_Name = player_names,
  State = states,
  Total_Points = total_points,
  Pre_Rating = pre_ratings,
  Avg_Opponent_Rating = avg_opponent_ratings,
  stringsAsFactors = FALSE
)

# Display results
kable(head(chess_results, 10), caption = "First 10 Players")
First 10 Players
Player_Name State Total_Points Pre_Rating Avg_Opponent_Rating
Player Name Num NA NA NA
GARY HUA ON 6.0 1794 1585
DAKSHESH DARURI MI 6.0 1553 1440
ADITYA BAJAJ MI 6.0 1384 1454
PATRICK H SCHILLING MI 5.5 1716 1660
HANSHI ZUO MI 5.5 1655 1512
HANSEN SONG OH 5.0 1686 1472
GARY DEE SWATHELL MI 5.0 1649 1476
EZEKIEL HOUGHTON MI 5.0 1641 1412
STEFANO LEE ON 5.0 1411 1488 
# Show summary statistics
cat("\nSummary Statistics:\n")
## 
## Summary Statistics:
cat("Number of players:", nrow(chess_results), "\n")
## Number of players: 65
cat("States represented:", length(unique(chess_results$State)), "\n")
## States represented: 4
cat("Average pre-rating:", round(mean(chess_results$Pre_Rating, na.rm = TRUE), 0), "\n")
## Average pre-rating: 1378
cat("Average opponent rating:", round(mean(chess_results$Avg_Opponent_Rating, na.rm = TRUE), 0), "\n")
## Average opponent rating: 1396

Transferring the Data to a .csv

# Write to CSV file
write.csv(chess_results, "chess_tournament_results.csv", row.names = FALSE)

# Verify it worked
if (file.exists("chess_tournament_results.csv")) {
  cat("✓ Successfully created chess_tournament_results.csv\n")
  
  # Read back the CSV to verify
  test_data <- read.csv("chess_tournament_results.csv")
  cat("CSV file contains", nrow(test_data), "rows and", ncol(test_data), "columns\n")
  
  # Show first few rows of CSV
  kable(head(test_data, 5), caption = "Verification: First 5 rows of CSV file")
} else {
  cat("✗ Error: CSV file was not created\n")
}
## ✓ Successfully created chess_tournament_results.csv
## CSV file contains 65 rows and 5 columns
Verification: First 5 rows of CSV file
Player_Name State Total_Points Pre_Rating Avg_Opponent_Rating
Player Name Num NA NA NA
GARY HUA ON 6.0 1794 1585
DAKSHESH DARURI MI 6.0 1553 1440
ADITYA BAJAJ MI 6.0 1384 1454
PATRICK H SCHILLING MI 5.5 1716 1660