library(readr)
library(stringr)
Url <- 'https://raw.githubusercontent.com/arinolan/Project-1/main/tournamentinfo.txt'
raw_data <- read_csv(file = Url, col_names = FALSE)
## Rows: 196 Columns: 1
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): X1
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
head(raw_data)
## # A tibble: 6 × 1
## X1
## <chr>
## 1 -----------------------------------------------------------------------------…
## 2 Pair | Player Name |Total|Round|Round|Round|Round|Round|R…
## 3 Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | …
## 4 -----------------------------------------------------------------------------…
## 5 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 1…
## 6 ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B …
tail(raw_data)
## # A tibble: 6 × 1
## X1
## <chr>
## 1 63 | THOMAS JOSEPH HOSMER |1.0 |L 2|L 48|D 49|L 43|L 45|H …
## 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 …
## 5 MI | 15006561 / R: 1163 ->1112 | |B |W |W |B |W |B …
## 6 -----------------------------------------------------------------------------…
m1 <- matrix(unlist(raw_data), byrow=TRUE)
m2 <- m1[seq(5, length(m1), 3)]
head(m2)
## [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|"
m3 <- m1[seq(6, length(m1), 3)]
head(m3)
## [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 |"
ID <- as.numeric(str_extract(m2, '\\d+'))
Name <- str_extract(m2, '[A-z].{1,32}')
Name <- str_trim(str_extract(Name, '.+\\s{2,}'))
State <- str_extract(m3, '[A-Z]{2}')
TotalNumberofPoints <- as.numeric(str_extract(m2, '\\d+\\.\\d'))
PreRating <- str_extract(m3, 'R:.{8,}-')
PreRating <- as.numeric(str_extract(PreRating, '\\d{1,4}'))
Rounds <- str_extract_all(m2, '[A-Z]\\s{2,}\\d+')
Rounds <- str_extract_all(Rounds, '\\d+')
## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercing
avgPreRating <- c()
for(i in c(1:length(Rounds))){
avgPreRating[i] <- round(mean(PreRating[as.numeric(Rounds[[i]])]), 0)
}
avgPreRating
## [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
output <- data.frame(ID,Name,State,TotalNumberofPoints,PreRating,avgPreRating)
head(output)
## ID Name State TotalNumberofPoints PreRating avgPreRating
## 1 1 GARY HUA ON 6.0 1794 1605
## 2 2 DAKSHESH DARURI MI 6.0 1553 1469
## 3 3 ADITYA BAJAJ MI 6.0 1384 1564
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1574
## 5 5 HANSHI ZUO MI 5.5 1655 1501
## 6 6 HANSEN SONG OH 5.0 1686 1519
write_csv(output, 'tournament.csv', append = FALSE)