Chess Results

Load Packages

Import Data

setwd("C:/Users/cassandra/Desktop/607")
chess <- read.csv("chess.txt")

Remove first two rows

chessnew <- chess[-c(1:2),]

Subsetting player info

name<-chessnew[seq(2, length(chessnew), 3)]
head(name,5)

## [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|
## 131 Levels: ----------------------------------------------------------------------------------------- ...

Subsetting rating info

rating<-chessnew[seq(3, length(chessnew), 3)]
head(rating,5)

## [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    |
## 131 Levels: ----------------------------------------------------------------------------------------- ...

Applying data transformation

id <- c(1:64)

Extract relevant data

#Extract name
playername <- str_trim(str_extract(name, "[[:alpha:]].+? {2,3}"))
#Extract points
totalpoint<- as.numeric(str_extract(name, "\\d.\\d"))
#Extract rating
prerating <- as.integer(str_extract(str_extract(rating, "\\D\\d{3,4}\\D"), "\\d+")) 
#Extract state
state <- str_extract(rating, "\\w\\w")
#Extract opponent id
opponentid <- str_extract_all(str_extract_all(name, "\\d+\\|"), "\\d+")

Find average of opponent player rating

opporatingavg <- length(name)
for (i in 1:length(name)) 
{ 
  opporatingavg[i] <- round(mean(prerating[as.numeric(unlist(opponentid[id[i]]))]), digits = 0)
}

Create dtaframe

chessdf <- data_frame(playername, state, totalpoint, prerating, opporatingavg)

Rename columns

colnames(chessdf) <-  c("Player's Name", "Player's State", "Total Number of Points", "Player's Pre-Rating", "Opponents' Average Ratings")
chessdf

## # A tibble: 64 x 5
##    `Player's Name` `Player's State` `Total Number o~ `Player's Pre-R~
##    <chr>           <chr>                       <dbl>            <int>
##  1 GARY HUA        ON                            6               1794
##  2 DAKSHESH DARURI MI                            6               1553
##  3 ADITYA BAJAJ    MI                            6               1384
##  4 PATRICK H SCHI~ MI                            5.5             1716
##  5 HANSHI ZUO      MI                            5.5             1655
##  6 HANSEN SONG     OH                            5               1686
##  7 GARY DEE SWATH~ MI                            5               1649
##  8 EZEKIEL HOUGHT~ MI                            5               1641
##  9 STEFANO LEE     ON                            5               1411
## 10 ANVIT RAO       MI                            5               1365
## # ... with 54 more rows, and 1 more variable: `Opponents' Average
## #   Ratings` <dbl>

Export csv file

write.csv(chessdf, file = "chessresults.csv")