Project 1

CHESS ELO

packages:

#install.packages("tidyverse", repos = "http://cran.us.r-project.org")
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   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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 errors

library(dplyr)
library(tidyr)

read table from github:

#load it in
my_data <- read.table("https://raw.githubusercontent.com/GuillermoCharlesSchneider/DATA-607/main/Project-1/tournamentinfo.txt", sep ="|", fill = TRUE)

cleaning:

# data frame, and 
my_data <- data.frame(my_data[-1, ])
#remove every third line to remove the dashes
my_data <- my_data[-(seq(3,to=nrow(my_data),by=3)),]
#remove the empty last column
my_data <- my_data[-11]
#remove header
my_data <- data.frame(my_data[-(1:2), ])

split into two, every other line, and remerge:

L <- my_data[-(seq(2,to=nrow(my_data),by=2)),]
R <- my_data[-(seq(1,to=nrow(my_data),by=2)),]
updated <- cbind(L, R)
updated <- updated[-(13:20)] #remove the W and B playing colors

clean pre and post, and remove the provisional scores, seperate on any nonalphanumeric:

seperated <- updated %>% separate(12, c(NA, 'ID', NA,'Pre', 'Post'), extra="merge")
seperated <- seperated %>% separate(13, sep = 'P', c('Pre', NA), extra="merge")

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 54 rows [1, 2, 3, 4, 5,
## 6, 7, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 22, 23, ...].

seperated <- seperated %>% separate(14, sep = 'P', c('Post', NA), extra="merge")

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 56 rows [1, 2, 3, 4, 5,
## 6, 7, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, ...].

remove W and L:

seperated$V4 <- str_remove_all(seperated$V4, "\\D")
seperated$V5 <- str_remove_all(seperated$V5, "\\D")
seperated$V6 <- str_remove_all(seperated$V6, "\\D")
seperated$V7<- str_remove_all(seperated$V7, "\\D")
seperated$V8 <- str_remove_all(seperated$V8, "\\D")
seperated$V9 <- str_remove_all(seperated$V9, "\\D")
seperated$V10 <- str_remove_all(seperated$V10, "\\D")

FIND opps score. if not NA, replace with the opps score, repeat for each rounds column:

avg_scores <- seperated

#columns, rounds 1-6
for(j in 4:10){
#rows, all 64 players
for (i in 1:64){
  if (!is.na(avg_scores[i,j]))
    {avg_scores[i,j] <- avg_scores[as.numeric(avg_scores[i,j]),13]
  } else
    avg_scores[i,j] <- NA 
}
}

row means:

#char to numeric
avg_scores[, c(4:10)] <- sapply(avg_scores[, c(4:10)], as.numeric)

#row means, ignore na, and round
avg_scores$v15 <- rowMeans(avg_scores[,c(4:10)], na.rm=T)
avg_scores$v15 <- round(avg_scores$v15)

#grab just the columns we need
final <- avg_scores[,c(2,11,3,13,15)]
colnames(final) <- c("Player’s Name","Player’s State","Total Number of Points","Player’s Pre-Rating","Average Pre Chess Rating of Opponents")
print(final[c(1:5),])

##                        Player’s Name Player’s State Total Number of Points
## 5   GARY HUA                                    ON                   6.0  
## 8   DAKSHESH DARURI                             MI                   6.0  
## 11  ADITYA BAJAJ                                MI                   6.0  
## 14  PATRICK H SCHILLING                         MI                   5.5  
## 17  HANSHI ZUO                                  MI                   5.5  
##    Player’s Pre-Rating Average Pre Chess Rating of Opponents
## 5                 1794                                  1605
## 8                 1553                                  1469
## 11                1384                                  1564
## 14                1716                                  1574
## 17                1655                                  1501

**CSV:*

#csv
write.csv(final, "chessELO.csv", row.names=FALSE)