Loading and reading the data

library(stringr)
library(readr)
url = 'https://raw.githubusercontent.com/Meccamarshall/Data607/main/tournamentinfo.txt'
chesstournament = readLines(url)
head(chesstournament)
## [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(chesstournament)
## [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] "-----------------------------------------------------------------------------------------"

Deconstructing the Data

After noticing that the first four lines were not apart of the dataset, I decided that it needed to be deconstructed. The first four lines are followed by player info and the games played and then repeated. I am going to seperate the data into two matrices to show a cleaner dataset.

cTournament <- matrix(unlist(chesstournament), byrow=TRUE)

c1 <- cTournament[seq(5,length(cTournament),3)]
head(c1)
## [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|"
c2 <- cTournament[seq(6,length(cTournament),3)]
head(c2)
## [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    |"

Capturing the data

I need to capture the values in vectors using regular expressions and string manipulation.

# matching first numbers
ID <- as.numeric(str_extract(c1, '\\d+'))

# matching the first combination of a letter, any amount of characters and "|"
Name <- str_extract(c1, '[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(c2, '[A-Z]{2}') 

# matching at least 1 number, a period, and 1 number
TotalNumberofPoints <- as.numeric(str_extract(c1, '\\d+\\.\\d'))

# matching the combination of "R", any characters and "-"
PreRating <- str_extract(c2, '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(c1, '[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

Calculating Average Pre Chess Rating of Opponents

AvgOppPreChessRating <- c()

for(i in c(1:length(Rounds))){
  AvgOppPreChessRating[i] <- round(mean(PreRating[as.numeric(Rounds[[i]])]),0)
}
AvgOppPreChessRating
##  [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

Constructing the data frame

Project1 <- data.frame(ID,Name,State,TotalNumberofPoints,PreRating,AvgOppPreChessRating)

head(Project1)
##   ID                Name State TotalNumberofPoints PreRating
## 1  1            GARY HUA    ON                 6.0      1794
## 2  2     DAKSHESH DARURI    MI                 6.0      1553
## 3  3        ADITYA BAJAJ    MI                 6.0      1384
## 4  4 PATRICK H SCHILLING    MI                 5.5      1716
## 5  5          HANSHI ZUO    MI                 5.5      1655
## 6  6         HANSEN SONG    OH                 5.0      1686
##   AvgOppPreChessRating
## 1                 1605
## 2                 1469
## 3                 1564
## 4                 1574
## 5                 1501
## 6                 1519

Writing the CVS file

write_csv(Project1, 'ChessTournament.csv' , append = FALSE)