library(stringr)## Warning: package 'stringr' was built under R version 3.3.3data <- "tournamentinfo.txt"
dat <- readLines(data)
head(dat, 33)## [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 |"
## [7] "-----------------------------------------------------------------------------------------"
## [8] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [9] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"
## [10] "-----------------------------------------------------------------------------------------"
## [11] " 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12|"
## [12] " MI | 14959604 / R: 1384 ->1640 |N:2 |W |B |W |B |W |B |W |"
## [13] "-----------------------------------------------------------------------------------------"
## [14] " 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1|"
## [15] " MI | 12616049 / R: 1716 ->1744 |N:2 |W |B |W |B |W |B |B |"
## [16] "-----------------------------------------------------------------------------------------"
## [17] " 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17|"
## [18] " MI | 14601533 / R: 1655 ->1690 |N:2 |B |W |B |W |B |W |B |"
## [19] "-----------------------------------------------------------------------------------------"
## [20] " 6 | HANSEN SONG |5.0 |W 34|D 29|L 11|W 35|D 10|W 27|W 21|"
## [21] " OH | 15055204 / R: 1686 ->1687 |N:3 |W |B |W |B |B |W |B |"
## [22] "-----------------------------------------------------------------------------------------"
## [23] " 7 | GARY DEE SWATHELL |5.0 |W 57|W 46|W 13|W 11|L 1|W 9|L 2|"
## [24] " MI | 11146376 / R: 1649 ->1673 |N:3 |W |B |W |B |B |W |W |"
## [25] "-----------------------------------------------------------------------------------------"
## [26] " 8 | EZEKIEL HOUGHTON |5.0 |W 3|W 32|L 14|L 9|W 47|W 28|W 19|"
## [27] " MI | 15142253 / R: 1641P17->1657P24 |N:3 |B |W |B |W |B |W |W |"
## [28] "-----------------------------------------------------------------------------------------"
## [29] " 9 | STEFANO LEE |5.0 |W 25|L 18|W 59|W 8|W 26|L 7|W 20|"
## [30] " ON | 14954524 / R: 1411 ->1564 |N:2 |W |B |W |B |W |B |B |"
## [31] "-----------------------------------------------------------------------------------------"
## [32] " 10 | ANVIT RAO |5.0 |D 16|L 19|W 55|W 31|D 6|W 25|W 18|"
## [33] " MI | 14150362 / R: 1365 ->1544 |N:3 |W |W |B |B |W |B |W |"Split the file into two tables by odd and even rows with the sequence function.
chessA <- dat[seq(5,195,3)]
head(chessA, 10)## [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|"
## [7] " 7 | GARY DEE SWATHELL |5.0 |W 57|W 46|W 13|W 11|L 1|W 9|L 2|"
## [8] " 8 | EZEKIEL HOUGHTON |5.0 |W 3|W 32|L 14|L 9|W 47|W 28|W 19|"
## [9] " 9 | STEFANO LEE |5.0 |W 25|L 18|W 59|W 8|W 26|L 7|W 20|"
## [10] " 10 | ANVIT RAO |5.0 |D 16|L 19|W 55|W 31|D 6|W 25|W 18|"chessB <- dat[seq(6,196,3)]
head(chessB, 10)## [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 |"
## [7] " MI | 11146376 / R: 1649 ->1673 |N:3 |W |B |W |B |B |W |W |"
## [8] " MI | 15142253 / R: 1641P17->1657P24 |N:3 |B |W |B |W |B |W |W |"
## [9] " ON | 14954524 / R: 1411 ->1564 |N:2 |W |B |W |B |W |B |B |"
## [10] " MI | 14150362 / R: 1365 ->1544 |N:3 |W |W |B |B |W |B |W |"Extract the name using str_extract_all on the odd rows. Use unlist to vectorize the output and str_trim to clean up the empty space.
name <- str_trim(unlist(str_extract_all(chessA,'[A-Z]+ [A-Z]+ ([A-Z-]+)? ([A-Z]+)?')))
head(name, 10)## [1] "GARY HUA" "DAKSHESH DARURI" "ADITYA BAJAJ"
## [4] "PATRICK H SCHILLING" "HANSHI ZUO" "HANSEN SONG"
## [7] "GARY DEE SWATHELL" "EZEKIEL HOUGHTON" "STEFANO LEE"
## [10] "ANVIT RAO"Extract the total pts using str_extract_all on the odd rows. Use unlist to vectorize the output and make it numeric.
total <- as.numeric(unlist(str_extract_all(chessA, "\\d\\.\\d")))
head(total, 10)## [1] 6.0 6.0 6.0 5.5 5.5 5.0 5.0 5.0 5.0 5.0Extract the state using str_extract_all on the even rows. Use unlist to vectorize the output and use str_trim to clean up the empty space.
state <- str_trim(unlist(str_extract_all(chessB, "\\s[A-Z]{2}\\ ")))
head(state, 10)## [1] "ON" "MI" "MI" "MI" "MI" "OH" "MI" "MI" "ON" "MI"Extract the player prerating using str_extract_all. Use unlist to vectorize the output. Complete a second pass of clean up and make it numeric.
prerate <- unlist(str_extract_all(chessB, ":\\s+\\d{3,4}"))
prerate <- as.numeric(unlist(str_extract_all(prerate, "\\d{1,4}")))
head(prerate, 10)## [1] 1794 1553 1384 1716 1655 1686 1649 1641 1411 1365Describing the for loop:
The tables have 64 rows. For each row:
step 1: extract the W,D, or L and opponent number from each row
step 2: clean up the W,D, or L and spacing using str_replace, and make number numeric
step 3: extract the player rating of the row number assigned to each of the values of step 2
step 4: clean up the extraction with str_replace_all and make opponent ratings numeric
step 5: sum up the row of opponent ratings and divide by the amount of opponents
opp.rate <- vector()
for (i in 1:64){
s1 <- unlist(str_extract_all(chessA[i], "(W|D|L)\\s+(\\d)+"))
s2 <- as.numeric(str_replace_all(s1, "(W|D|L)\\s+", ""))
s3 <- str_extract(chessB[s2[1:length(s2)]], ":\\s+\\d{3,4}")
s4 <- as.numeric(str_replace_all(s3, ":\\s+", ""))
s5 <- round(sum(s4)/length(s4))
opp.rate <- c(opp.rate, s5)
}
head(opp.rate, 10)## [1] 1605 1469 1564 1574 1501 1519 1372 1468 1523 1554Create a data frame with the five columns created above
chess_df <- data.frame(
PlayerName = name,
State = state,
TotalPts = total,
AvgPrerating = prerate,
OppAvgPrerating = opp.rate
)
chess_df## PlayerName State TotalPts AvgPrerating OppAvgPrerating
## 1 GARY HUA ON 6.0 1794 1605
## 2 DAKSHESH DARURI MI 6.0 1553 1469
## 3 ADITYA BAJAJ MI 6.0 1384 1564
## 4 PATRICK H SCHILLING MI 5.5 1716 1574
## 5 HANSHI ZUO MI 5.5 1655 1501
## 6 HANSEN SONG OH 5.0 1686 1519
## 7 GARY DEE SWATHELL MI 5.0 1649 1372
## 8 EZEKIEL HOUGHTON MI 5.0 1641 1468
## 9 STEFANO LEE ON 5.0 1411 1523
## 10 ANVIT RAO MI 5.0 1365 1554
## 11 CAMERON WILLIAM MC LEMAN MI 4.5 1712 1468
## 12 KENNETH J TACK MI 4.5 1663 1506
## 13 TORRANCE HENRY JR MI 4.5 1666 1498
## 14 BRADLEY SHAW MI 4.5 1610 1515
## 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1484
## 16 MIKE NIKITIN MI 4.0 1604 1386
## 17 RONALD GRZEGORCZYK MI 4.0 1629 1499
## 18 DAVID SUNDEEN MI 4.0 1600 1480
## 19 DIPANKAR ROY MI 4.0 1564 1426
## 20 JASON ZHENG MI 4.0 1595 1411
## 21 DINH DANG BUI ON 4.0 1563 1470
## 22 EUGENE L MCCLURE MI 4.0 1555 1300
## 23 ALAN BUI ON 4.0 1363 1214
## 24 MICHAEL R ALDRICH MI 4.0 1229 1357
## 25 LOREN SCHWIEBERT MI 3.5 1745 1363
## 26 MAX ZHU ON 3.5 1579 1507
## 27 GAURAV GIDWANI MI 3.5 1552 1222
## 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1522
## 29 CHIEDOZIE OKORIE MI 3.5 1602 1314
## 30 GEORGE AVERY JONES ON 3.5 1522 1144
## 31 RISHI SHETTY MI 3.5 1494 1260
## 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 1379
## 33 JADE GE MI 3.5 1449 1277
## 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1375
## 35 JOSHUA DAVID LEE MI 3.5 1438 1150
## 36 SIDDHARTH JHA MI 3.5 1355 1388
## 37 AMIYATOSH PWNANANDAM MI 3.5 980 1385
## 38 BRIAN LIU MI 3.0 1423 1539
## 39 JOEL R HENDON MI 3.0 1436 1430
## 40 FOREST ZHANG MI 3.0 1348 1391
## 41 KYLE WILLIAM MURPHY MI 3.0 1403 1248
## 42 JARED GE MI 3.0 1332 1150
## 43 ROBERT GLEN VASEY MI 3.0 1283 1107
## 44 JUSTIN D SCHILLING MI 3.0 1199 1327
## 45 DEREK YAN MI 3.0 1242 1152
## 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1358
## 47 ERIC WRIGHT MI 2.5 1362 1392
## 48 DANIEL KHAIN MI 2.5 1382 1356
## 49 MICHAEL J MARTIN MI 2.5 1291 1286
## 50 SHIVAM JHA MI 2.5 1056 1296
## 51 TEJAS AYYAGARI MI 2.5 1011 1356
## 52 ETHAN GUO MI 2.5 935 1495
## 53 JOSE C YBARRA MI 2.0 1393 1345
## 54 LARRY HODGE MI 2.0 1270 1206
## 55 ALEX KONG MI 2.0 1186 1406
## 56 MARISA RICCI MI 2.0 1153 1414
## 57 MICHAEL LU MI 2.0 1092 1363
## 58 VIRAJ MOHILE MI 2.0 917 1391
## 59 SEAN M MC CORMICK MI 2.0 853 1319
## 60 JULIA SHEN MI 1.5 967 1330
## 61 JEZZEL FARKAS ON 1.5 955 1327
## 62 ASHWIN BALAJI MI 1.0 1530 1186
## 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1350
## 64 BEN LI MI 1.0 1163 1263Write to csv and remove the row numbers
write.csv(chess_df, file = "tournamenttable.csv", row.names = FALSE)