First, we load our data and prepare it by separating contestant’s information from their rating list.
chess <- read.csv(file="/Users/omarpineda/Desktop/CUNY SPS MS Data Science/DATA607 Data Acquisition and Management/Week 4/tournamentinfo.txt", header=FALSE)
head(chess)## V1
## 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 |chess <- chess[c(5:196),] #removes the first four rows
contestant <- chess[seq(1, length(chess), 3)]
contestant2 <- chess[seq(2, length(chess), 3)]
head(contestant)## [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|
## 131 Levels: 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4| ...head(contestant2)## [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 |
## 131 Levels: 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4| ...Next, we use regular expressions to extract the needed information from our data.
library(stringr)
name <- str_trim(str_extract(contestant, "(\\w+\\s){2,3}"))
state <- str_extract(contestant2, "\\w+")
totalPoints <- as.numeric(str_extract(contestant, "\\d\\.\\d"))
preRating <- str_extract(contestant2, "[^\\d]\\d{3,4}[^\\d]")
preRating <- as.numeric(str_extract(preRating, "\\d+")) #removes possible characters in the pre-rating
opponents <- str_extract_all(contestant, "\\d+\\|")
opponents <- str_extract_all(opponents, "\\d+") #removes trailing pipe from the opponent's number## Warning in stri_extract_all_regex(string, pattern, simplify = simplify, :
## argument is not an atomic vector; coercingWe then calculate the average pre-chess rating of opponents for each contestant.
avgOpp <- 0
for (i in 1:length(contestant)) { #go through each of our contestants
opp <- as.numeric(unlist(opponents[[i]])) #save each contestant's opponents into a list
sum <- 0
for (n in 1:length(opp)) { #go through each opponent in the contestant's list of opponents
sum <- sum + preRating[opp[n]] #add up all of the opponents' corresponding pre-ratings
}
avgOpp[i] <- sum / length(opp) #find the average pre-rating for each contestant's opponents
}
avgOpp <- round(avgOpp, digits = 0)
avgOpp## [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 1263Finally, we save all of our vectors into a data frame and generate a CSV.
chessFinal <- data.frame(name, state, totalPoints, preRating, avgOpp)
chessFinal## name state totalPoints preRating avgOpp
## 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 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 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 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.csv(chessFinal, 'chess.csv')