library(stringr)dt <- readLines("tournamentinfo.txt")## Warning in readLines("tournamentinfo.txt"): incomplete final line found on
## 'tournamentinfo.txt'head(dt)## [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 |"dt <- dt[-c(1:4)]
head(dt)## [1] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [2] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [3] "-----------------------------------------------------------------------------------------"
## [4] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [5] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [6] "-----------------------------------------------------------------------------------------"# Remove rows
dt <- str_remove(dt,"[-]+")
# Remove empty rows
dt <- dt[dt!=""]
head(dt)## [1] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [2] " ON | 15445895 / R: 1794 >1817 |N:2 |W |B |W |B |W |B |W |"
## [3] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [4] " MI | 14598900 / R: 1553 >1663 |N:2 |B |W |B |W |B |W |B |"
## [5] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [6] " MI | 14959604 / R: 1384 >1640 |N:2 |W |B |W |B |W |B |W |"# subset
group1 <- dt[seq(1,128,2)]
group2 <- dt[seq(2,128,2)]id <- as.integer(str_extract(group1, "\\d+"))
name <- str_trim(str_extract(group1, "(\\w+\\s){2,3}"))
state <- str_extract(group2, "\\w+")
points <- as.numeric(str_extract(group1, "\\d+\\.\\d+"))
rating <- as.integer(str_extract(str_extract(group2, "[^\\d]\\d{3,4}[^\\d]"), "\\d+"))
opponents <- str_extract_all(str_extract_all(group1, "\\d+\\|"), "\\d+")## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercingwin <- str_count(group1, "\\Q|W")
loss <- str_count(group1, "\\Q|L")
draws <- str_count(group1,"\\Q|D")Opponent Rating
len <- length(group1)
opponent_rating <- len
for (i in 1:len)
{ opponent_rating[i] <- mean(rating[as.numeric(unlist(opponents[id[i]]))])
}
opponent_rating <- round(opponent_rating)
opponent_rating## [1] 1605 1469 1564 1574 1501 1519 1372 1468 1523 1554 1468 1506 1498 1515
## [15] 1484 1386 1499 1480 1426 1411 1470 1300 1214 1357 1363 1507 1222 1522
## [29] 1314 1144 1260 1379 1277 1375 1150 1388 1385 1539 1430 1391 1248 1150
## [43] 1107 1327 1152 1358 1392 1356 1286 1296 1356 1495 1345 1206 1406 1414
## [57] 1363 1391 1319 1330 1327 1186 1350 1263df <- data.frame("Playerâs Name"=name, "Playerâs State"=state, "Total Number of Points"=points,"Playerâs Pre-Rating"= rating,"Average Pre Chess Rating of Opponents"= opponent_rating);
df## Playerâ..s.Name Playerâ..s.State Total.Number.of.Points
## 1 GARY HUA ON 6.0
## 2 DAKSHESH DARURI MI 6.0
## 3 ADITYA BAJAJ MI 6.0
## 4 PATRICK H SCHILLING MI 5.5
## 5 HANSHI ZUO MI 5.5
## 6 HANSEN SONG OH 5.0
## 7 GARY DEE SWATHELL MI 5.0
## 8 EZEKIEL HOUGHTON MI 5.0
## 9 STEFANO LEE ON 5.0
## 10 ANVIT RAO MI 5.0
## 11 CAMERON WILLIAM MC MI 4.5
## 12 KENNETH J TACK MI 4.5
## 13 TORRANCE HENRY JR MI 4.5
## 14 BRADLEY SHAW MI 4.5
## 15 ZACHARY JAMES HOUGHTON MI 4.5
## 16 MIKE NIKITIN MI 4.0
## 17 RONALD GRZEGORCZYK MI 4.0
## 18 DAVID SUNDEEN MI 4.0
## 19 DIPANKAR ROY MI 4.0
## 20 JASON ZHENG MI 4.0
## 21 DINH DANG BUI ON 4.0
## 22 EUGENE L MCCLURE MI 4.0
## 23 ALAN BUI ON 4.0
## 24 MICHAEL R ALDRICH MI 4.0
## 25 LOREN SCHWIEBERT MI 3.5
## 26 MAX ZHU ON 3.5
## 27 GAURAV GIDWANI MI 3.5
## 28 SOFIA ADINA STANESCUBELLU MI 3.5
## 29 CHIEDOZIE OKORIE MI 3.5
## 30 GEORGE AVERY JONES ON 3.5
## 31 RISHI SHETTY MI 3.5
## 32 JOSHUA PHILIP MATHEWS ON 3.5
## 33 JADE GE MI 3.5
## 34 MICHAEL JEFFERY THOMAS MI 3.5
## 35 JOSHUA DAVID LEE MI 3.5
## 36 SIDDHARTH JHA MI 3.5
## 37 AMIYATOSH PWNANANDAM MI 3.5
## 38 BRIAN LIU MI 3.0
## 39 JOEL R HENDON MI 3.0
## 40 FOREST ZHANG MI 3.0
## 41 KYLE WILLIAM MURPHY MI 3.0
## 42 JARED GE MI 3.0
## 43 ROBERT GLEN VASEY MI 3.0
## 44 JUSTIN D SCHILLING MI 3.0
## 45 DEREK YAN MI 3.0
## 46 JACOB ALEXANDER LAVALLEY MI 3.0
## 47 ERIC WRIGHT MI 2.5
## 48 DANIEL KHAIN MI 2.5
## 49 MICHAEL J MARTIN MI 2.5
## 50 SHIVAM JHA MI 2.5
## 51 TEJAS AYYAGARI MI 2.5
## 52 ETHAN GUO MI 2.5
## 53 JOSE C YBARRA MI 2.0
## 54 LARRY HODGE MI 2.0
## 55 ALEX KONG MI 2.0
## 56 MARISA RICCI MI 2.0
## 57 MICHAEL LU MI 2.0
## 58 VIRAJ MOHILE MI 2.0
## 59 SEAN M MC MI 2.0
## 60 JULIA SHEN MI 1.5
## 61 JEZZEL FARKAS ON 1.5
## 62 ASHWIN BALAJI MI 1.0
## 63 THOMAS JOSEPH HOSMER MI 1.0
## 64 BEN LI MI 1.0
## Playerâ..s.Pre.Rating Average.Pre.Chess.Rating.of.Opponents
## 1 1794 1605
## 2 1553 1469
## 3 1384 1564
## 4 1716 1574
## 5 1655 1501
## 6 1686 1519
## 7 1649 1372
## 8 1641 1468
## 9 1411 1523
## 10 1365 1554
## 11 1712 1468
## 12 1663 1506
## 13 1666 1498
## 14 1610 1515
## 15 1220 1484
## 16 1604 1386
## 17 1629 1499
## 18 1600 1480
## 19 1564 1426
## 20 1595 1411
## 21 1563 1470
## 22 1555 1300
## 23 1363 1214
## 24 1229 1357
## 25 1745 1363
## 26 1579 1507
## 27 1552 1222
## 28 1507 1522
## 29 1602 1314
## 30 1522 1144
## 31 1494 1260
## 32 1441 1379
## 33 1449 1277
## 34 1399 1375
## 35 1438 1150
## 36 1355 1388
## 37 980 1385
## 38 1423 1539
## 39 1436 1430
## 40 1348 1391
## 41 1403 1248
## 42 1332 1150
## 43 1283 1107
## 44 1199 1327
## 45 1242 1152
## 46 377 1358
## 47 1362 1392
## 48 1382 1356
## 49 1291 1286
## 50 1056 1296
## 51 1011 1356
## 52 935 1495
## 53 1393 1345
## 54 1270 1206
## 55 1186 1406
## 56 1153 1414
## 57 1092 1363
## 58 917 1391
## 59 853 1319
## 60 967 1330
## 61 955 1327
## 62 1530 1186
## 63 1175 1350
## 64 1163 1263