In this project, you’re given a text file with chess tournament results where the information has some structure. Your job is to create an R Markdown file that generates a .CSV file (that could for example be imported into a SQL database) with the following information for all of the players: Player’s Name, Player’s State, Total Number of Points, Player’s Pre-Rating, and Average Pre Chess Rating of Opponents For the first player, the information would be: Gary Hua, ON, 6.0, 1794, 1605 1605 was calculated by using the pre-tournament opponents’ ratings of 1436, 1563, 1600, 1610, 1649, 1663, 1716, and dividing by the total number of games played.
tournament <- readLines("https://raw.githubusercontent.com/DaisyCai2019/Homework/master/tournamentinfo.txt")## Warning in readLines("https://raw.githubusercontent.com/DaisyCai2019/
## Homework/master/tournamentinfo.txt"): incomplete final line found
## on 'https://raw.githubusercontent.com/DaisyCai2019/Homework/master/
## tournamentinfo.txt'head(tournament)## [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 |"require(stringr)## Loading required package: stringr#Player’s Name
name<-unlist(str_extract_all(tournament, "\\w+[^USCF|a-z] ?\\w+ \\w+"))
name## [1] "GARY HUA" "DAKSHESH DARURI"
## [3] "ADITYA BAJAJ" "PATRICK H SCHILLING"
## [5] "HANSHI ZUO" "HANSEN SONG"
## [7] "GARY DEE SWATHELL" "EZEKIEL HOUGHTON"
## [9] "STEFANO LEE" "ANVIT RAO"
## [11] "CAMERON WILLIAM MC" "KENNETH J TACK"
## [13] "TORRANCE HENRY JR" "BRADLEY SHAW"
## [15] "ZACHARY JAMES HOUGHTON" "MIKE NIKITIN"
## [17] "RONALD GRZEGORCZYK" "DAVID SUNDEEN"
## [19] "DIPANKAR ROY" "JASON ZHENG"
## [21] "DINH DANG BUI" "EUGENE L MCCLURE"
## [23] "ALAN BUI" "MICHAEL R ALDRICH"
## [25] "LOREN SCHWIEBERT" "MAX ZHU"
## [27] "GAURAV GIDWANI" "SOFIA ADINA STANESCU"
## [29] "CHIEDOZIE OKORIE" "GEORGE AVERY JONES"
## [31] "RISHI SHETTY" "JOSHUA PHILIP MATHEWS"
## [33] "JADE GE" "MICHAEL JEFFERY THOMAS"
## [35] "JOSHUA DAVID LEE" "SIDDHARTH JHA"
## [37] "AMIYATOSH PWNANANDAM" "BRIAN LIU"
## [39] "JOEL R HENDON" "FOREST ZHANG"
## [41] "KYLE WILLIAM MURPHY" "JARED GE"
## [43] "ROBERT GLEN VASEY" "JUSTIN D SCHILLING"
## [45] "DEREK YAN" "JACOB ALEXANDER LAVALLEY"
## [47] "ERIC WRIGHT" "DANIEL KHAIN"
## [49] "MICHAEL J MARTIN" "SHIVAM JHA"
## [51] "TEJAS AYYAGARI" "ETHAN GUO"
## [53] "JOSE C YBARRA" "LARRY HODGE"
## [55] "ALEX KONG" "MARISA RICCI"
## [57] "MICHAEL LU" "VIRAJ MOHILE"
## [59] "SEAN M MC" "JULIA SHEN"
## [61] "JEZZEL FARKAS" "ASHWIN BALAJI"
## [63] "THOMAS JOSEPH HOSMER" "BEN LI"#Player’s State. We only have ON, MI and OH three states
state<-unlist(str_extract_all(tournament, "( MI )|( OH )|( ON )"))
state## [1] " ON " " MI " " MI " " MI " " MI " " OH " " MI " " MI " " ON " " MI "
## [11] " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI "
## [21] " ON " " MI " " ON " " MI " " MI " " ON " " MI " " MI " " MI " " ON "
## [31] " MI " " ON " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI "
## [41] " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI "
## [51] " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI " " MI "
## [61] " ON " " MI " " MI " " MI "#Total Number of Points
point<-unlist(str_extract_all(tournament, "\\d\\.\\d"))
point## [1] "6.0" "6.0" "6.0" "5.5" "5.5" "5.0" "5.0" "5.0" "5.0" "5.0" "4.5"
## [12] "4.5" "4.5" "4.5" "4.5" "4.0" "4.0" "4.0" "4.0" "4.0" "4.0" "4.0"
## [23] "4.0" "4.0" "3.5" "3.5" "3.5" "3.5" "3.5" "3.5" "3.5" "3.5" "3.5"
## [34] "3.5" "3.5" "3.5" "3.5" "3.0" "3.0" "3.0" "3.0" "3.0" "3.0" "3.0"
## [45] "3.0" "3.0" "2.5" "2.5" "2.5" "2.5" "2.5" "2.5" "2.0" "2.0" "2.0"
## [56] "2.0" "2.0" "2.0" "2.0" "1.5" "1.5" "1.0" "1.0" "1.0"#Player’s Pre-Rating
#extract information and remove "R:"
preRating<-str_replace(unlist(str_extract_all(tournament, "(R:\\s*)(\\d+)")),"R: ","")
#change to number
preRating<-as.numeric(preRating)
preRating## [1] 1794 1553 1384 1716 1655 1686 1649 1641 1411 1365 1712 1663 1666 1610
## [15] 1220 1604 1629 1600 1564 1595 1563 1555 1363 1229 1745 1579 1552 1507
## [29] 1602 1522 1494 1441 1449 1399 1438 1355 980 1423 1436 1348 1403 1332
## [43] 1283 1199 1242 377 1362 1382 1291 1056 1011 935 1393 1270 1186 1153
## [57] 1092 917 853 967 955 1530 1175 1163#Average Pre Chess Rating of Opponents
avgRating<-unlist(str_extract_all(tournament, "\\|[0-9].*"))
#Replace all the blanks without opponents’ information with 00 and extract the number
avgRating <- str_extract_all(str_replace_all(avgRating, "\\s{1,2}\\|","00|"),"\\s\\d{1,2}")
#change it to matrix and number
avgRating <- matrix(unlist(avgRating),byrow=TRUE, nrow=length(avgRating) )
avgRating <- t(apply(avgRating,1,as.numeric))
#Loop through the whole avgRating number to replace the opponents’ number with their actual rating.
for (i in 1:nrow(avgRating)) {
for (j in 1:ncol(avgRating)){
if (avgRating[i,j] == 0){
avgRating[i,j] = NA
}
else{avgRating[i,j] <- preRating[avgRating[i,j]]}
}
}
#Caculate the Rating of Opponents
avgRating <- c(rowMeans(avgRating, na.rm = TRUE))
avgRating<-round(avgRating,0)
avgRating## [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 1263final<-data.frame(name,state,point,preRating,avgRating)
final## name state point preRating avgRating
## 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 STANESCU 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(final, "data607_project1.csv", row.names=FALSE)