title: “data607_Project01” author: “Md. Tanzil Ehsan” format: pdf editor: visual
# Load necessary libraries
if (!requireNamespace("rstudioapi", quietly = TRUE)) {install.packages("rstudioapi")}
if (!requireNamespace("readr", quietly = TRUE)){ install.packages("readr")}
if (!requireNamespace("ggplot2", quietly = TRUE)) {install.packages("ggplot2")}
if (!requireNamespace("tidyverse", quietly = TRUE)) {install.packages("tidyverse")}
if (!requireNamespace("tidyr", quietly = TRUE)) {install.packages("tidyr")}library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(readr)
library(tibble)
library(tidyr)
library(ggplot2)raw_data <- readLines("https://raw.githubusercontent.com/tanzil64/DATA607-Project-01/refs/heads/main/tournamentinfo.txt")##raw_data <- readLines ("C:/Users/tanzi/OneDrive/DATA/607/Week4/tournamentinfo.txt")You can add options to executable code like this
#| echo: false
# Extract the required data using regular expressions
player_num <- as.numeric(unlist(str_extract_all(raw_data,"(?<=\\s{3,4})\\d{1,2}(?=\\s)")))
player_name <- unlist(str_extract_all(raw_data,"(?<=\\d\\s\\|\\s)([A-z, -]*\\s){1,}[[:alpha:]]*(?=\\s*\\|)"))
player_state <- unlist(str_extract_all(raw_data, "[[:upper:]]{2}(?=\\s\\|)"))
total_pts <- as.numeric(unlist(str_extract_all(raw_data, "(?<=\\|)\\d\\.\\d")))
player_pre_rat <- as.numeric(unlist(str_extract_all(raw_data, "(?<=R:\\s{1,2})(\\d{3,4}(?=\\s))|(\\d{3,4}(?=P\\d{1,2}\\s*-))")))# Take the extracted data and put it into a data frame
processed_data <- data.frame(player_num, player_name, player_state, total_pts, player_pre_rat)# Check the data frame's structure to make sure it is as intended (i.e. number columns are numeric, character columns are character, etc..., and that it has the correct number of rows)
str(processed_data)## 'data.frame': 64 obs. of 5 variables:
## $ player_num : num 1 2 3 4 5 6 7 8 9 10 ...
## $ player_name : chr "GARY HUA " "DAKSHESH DARURI " "ADITYA BAJAJ " "PATRICK H SCHILLING " ...
## $ player_state : chr "ON" "MI" "MI" "MI" ...
## $ total_pts : num 6 6 6 5.5 5.5 5 5 5 5 5 ...
## $ player_pre_rat: num 1794 1553 1384 1716 1655 ...# Had some initial challenges doing this with only regex so to make it simpler and a bit more robust I created a new list that only had included the relevant rows from the raw data file.
# selects every third line starting at line 5.
secondary_rows <- raw_data[seq(5, 196, 3)]
#opponent_num will contain a vector of opponent numbers for each player.
opponent_num <- as.numeric(unlist(str_extract_all(secondary_rows, "(?<=\\|(W|L|D)\\s{2,3})[[:digit:]]{1,2}(?=\\|)|((?<!->)(?<=\\|(U|H|B|X))\\s{4}(?=\\|))")))# Create matrix to store data calculated in the for loop. Pre-populating values with NA for more efficient processing in R.
# Creates a 64-row by 2-column matrix filled with NA values.
# Each row represents a player (since there are 64 players).
# Columns:
#"total_opp_pcr" → The sum of all opponent pre-ratings.
#"avg_opp_pcr" → The average of opponent pre-ratings.
pcr_matrix <- matrix(data = NA, nrow = 64, ncol = 2)
# Assign readable names for the matrix
colnames(pcr_matrix) <- c("total_opp_pcr", "avg_opp_pcr")
# Initialize a variable to be used as a counter in the for loop to fill the corresponding matrix row
row_counter <- 0
# Start of for loop
# Each player plays 7 games, so we process their 7 opponents' numbers at a time.
#Loops through opponent_num in steps of 7.
# length(opponent_num) - 6 → Ensures we stop before exceeding the vector length.
for(i in seq(from=1, to=length(opponent_num)-6, by=7)){
row_counter <- row_counter + 1
# Perform a lookup of each competitor's score based on their player number and add the up for each row (corresponding to each sequence of 7 data points, w/ value from for loop serving as row 'anchor')
# Extract the opponent numbers for the current player
current_opponents <- opponent_num[seq(from=i, to=i+6, by=1)]
# Find the pre-tournament ratings of these opponents
opponent_ratings <- subset(processed_data$player_pre_rat,
processed_data$player_num %in% current_opponents)
# Calculate the total opponent pre-tournament rating
total_opp_pcr <- sum(opponent_ratings, na.rm = TRUE) # Use na.rm = TRUE to ignore NA values
# Store the result in the matrix
pcr_matrix[row_counter, 1] <- total_opp_pcr
# Calculate the average score for each row, excluding missing entries
pcr_matrix[row_counter, 2] <- pcr_matrix[row_counter, 1] / length(subset(opponent_num[seq(from=i, to=i+6, by=1)],!is.na(opponent_num[seq(from=i, to=i+6, by=1)])))
}
# End of for loop
# Verify that matrix was processed properly by looking at the first few rows of output
head(pcr_matrix, 5)## total_opp_pcr avg_opp_pcr
## [1,] 11237 1605.286
## [2,] 10285 1469.286
## [3,] 10945 1563.571
## [4,] 11015 1573.571
## [5,] 10506 1500.857pcr_matrix[, 2] <- round(pcr_matrix[,2], digits = 0)
# Add average scores to data frame with other processed data and rename for readability
processed_data <- cbind(processed_data, pcr_matrix[, 2])
processed_data <- rename(processed_data, avg_opp_pcr = `pcr_matrix[, 2]`)processed_datapath <- getwd()# Export file to working directory. The file.path function has been used to ensure platform independence (i.e. take into account the different path syntaxes for various operating systems)
write.csv(processed_data, file.path(path, "chess_processed_data.csv"), row.names = FALSE)head(processed_data, 5)