In this project, youโre 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:
tournament.data <- read.csv(paste0("https://raw.githubusercontent.com/szx868/data607/master/Project1/tournamentinfo.txt"), header=F)results <- tournament.data[-c(1:3),]
head(results)## [1] "-----------------------------------------------------------------------------------------"
## [2] " 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|"
## [3] " ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |"
## [4] "-----------------------------------------------------------------------------------------"
## [5] " 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|"
## [6] " MI | 14598900 / R: 1553 ->1663 |N:2 |B |W |B |W |B |W |B |"library(stringr)
player.name <- unlist(str_extract_all(results, "\\w+[^USCF|a-z] ?\\w+ \\w+"))
player.state <- unlist(str_extract_all(results, "(?:^|\\W)ON | MI | OH(?:$|\\W)"))
player.points <- unlist(str_extract_all(results, "\\d\\.\\d"))
pre.rating.step1 <- unlist(str_extract_all(results, "(R:\\s*)(\\d+)"))
pre.rating.step1[1]## [1] "R: 1794"pre.rating <- unlist(str_extract_all(pre.rating.step1, "(\\d+)"))
is.vector(pre.rating)## [1] TRUEpre.rating <- as.numeric(pre.rating)
pre.rating[1]## [1] 1794avg.calc.step1 <- unlist(str_extract_all(results, "\\|[0-9].*"))
avg.calc.step1[16]## [1] "|4.0 |D 10|W 15|H |W 39|L 2|W 36|U |"avg.calc.step2 <- str_replace_all(avg.calc.step1, "\\s{1,2}\\|","00|")
avg.calc.step2[16]## [1] "|4.000|D 10|W 15|H 00|W 39|L 2|W 36|U 00|"avg.calc.step3 <- (str_extract_all(avg.calc.step2, "\\s\\d{1,2}"))
avg.calc.step3[16]## [[1]]
## [1] " 10" " 15" " 00" " 39" " 2" " 36" " 00"matrix.calc <- matrix(unlist(avg.calc.step3), byrow=TRUE, nrow=length(avg.calc.step3) )
dim(matrix.calc)## [1] 64 7new.matrix <- t(apply(matrix.calc, 1,as.numeric))
dim(new.matrix)## [1] 64 7for (i in 1:nrow(new.matrix))
{
for (j in 1:ncol(new.matrix))
{
if (new.matrix[i,j] == 0){
new.matrix[i,j] = NA
}
else{
new.matrix[i,j] <- pre.rating[new.matrix[i,j]]
}
}
}avg.opponents <- c(rowMeans(new.matrix, na.rm = TRUE))
csv <- data.frame(player.name,player.state, player.points,pre.rating,avg.opponents)
colnames(csv) <- c("Player Name","Player State", "Total Points", "Player Pre-Rating", "Opponents Rating")
csv## Player Name Player State Total Points Player Pre-Rating
## 1 GARY HUA ON 6.0 1794
## 2 DAKSHESH DARURI MI 6.0 1553
## 3 ADITYA BAJAJ MI 6.0 1384
## 4 PATRICK H SCHILLING MI 5.5 1716
## 5 HANSHI ZUO MI 5.5 1655
## 6 HANSEN SONG OH 5.0 1686
## 7 GARY DEE SWATHELL MI 5.0 1649
## 8 EZEKIEL HOUGHTON MI 5.0 1641
## 9 STEFANO LEE ON 5.0 1411
## 10 ANVIT RAO MI 5.0 1365
## 11 CAMERON WILLIAM MC MI 4.5 1712
## 12 KENNETH J TACK MI 4.5 1663
## 13 TORRANCE HENRY JR MI 4.5 1666
## 14 BRADLEY SHAW MI 4.5 1610
## 15 ZACHARY JAMES HOUGHTON MI 4.5 1220
## 16 MIKE NIKITIN MI 4.0 1604
## 17 RONALD GRZEGORCZYK MI 4.0 1629
## 18 DAVID SUNDEEN MI 4.0 1600
## 19 DIPANKAR ROY MI 4.0 1564
## 20 JASON ZHENG MI 4.0 1595
## 21 DINH DANG BUI ON 4.0 1563
## 22 EUGENE L MCCLURE MI 4.0 1555
## 23 ALAN BUI ON 4.0 1363
## 24 MICHAEL R ALDRICH MI 4.0 1229
## 25 LOREN SCHWIEBERT MI 3.5 1745
## 26 MAX ZHU ON 3.5 1579
## 27 GAURAV GIDWANI MI 3.5 1552
## 28 SOFIA ADINA STANESCU MI 3.5 1507
## 29 CHIEDOZIE OKORIE MI 3.5 1602
## 30 GEORGE AVERY JONES ON 3.5 1522
## 31 RISHI SHETTY MI 3.5 1494
## 32 JOSHUA PHILIP MATHEWS ON 3.5 1441
## 33 JADE GE MI 3.5 1449
## 34 MICHAEL JEFFERY THOMAS MI 3.5 1399
## 35 JOSHUA DAVID LEE MI 3.5 1438
## 36 SIDDHARTH JHA MI 3.5 1355
## 37 AMIYATOSH PWNANANDAM MI 3.5 980
## 38 BRIAN LIU MI 3.0 1423
## 39 JOEL R HENDON MI 3.0 1436
## 40 FOREST ZHANG MI 3.0 1348
## 41 KYLE WILLIAM MURPHY MI 3.0 1403
## 42 JARED GE MI 3.0 1332
## 43 ROBERT GLEN VASEY MI 3.0 1283
## 44 JUSTIN D SCHILLING MI 3.0 1199
## 45 DEREK YAN MI 3.0 1242
## 46 JACOB ALEXANDER LAVALLEY MI 3.0 377
## 47 ERIC WRIGHT MI 2.5 1362
## 48 DANIEL KHAIN MI 2.5 1382
## 49 MICHAEL J MARTIN MI 2.5 1291
## 50 SHIVAM JHA MI 2.5 1056
## 51 TEJAS AYYAGARI MI 2.5 1011
## 52 ETHAN GUO MI 2.5 935
## 53 JOSE C YBARRA MI 2.0 1393
## 54 LARRY HODGE MI 2.0 1270
## 55 ALEX KONG MI 2.0 1186
## 56 MARISA RICCI MI 2.0 1153
## 57 MICHAEL LU MI 2.0 1092
## 58 VIRAJ MOHILE MI 2.0 917
## 59 SEAN M MC MI 2.0 853
## 60 JULIA SHEN MI 1.5 967
## 61 JEZZEL FARKAS ON 1.5 955
## 62 ASHWIN BALAJI MI 1.0 1530
## 63 THOMAS JOSEPH HOSMER MI 1.0 1175
## 64 BEN LI MI 1.0 1163
## Opponents Rating
## 1 1605.286
## 2 1469.286
## 3 1563.571
## 4 1573.571
## 5 1500.857
## 6 1518.714
## 7 1372.143
## 8 1468.429
## 9 1523.143
## 10 1554.143
## 11 1467.571
## 12 1506.167
## 13 1497.857
## 14 1515.000
## 15 1483.857
## 16 1385.800
## 17 1498.571
## 18 1480.000
## 19 1426.286
## 20 1410.857
## 21 1470.429
## 22 1300.333
## 23 1213.857
## 24 1357.000
## 25 1363.286
## 26 1506.857
## 27 1221.667
## 28 1522.143
## 29 1313.500
## 30 1144.143
## 31 1259.857
## 32 1378.714
## 33 1276.857
## 34 1375.286
## 35 1149.714
## 36 1388.167
## 37 1384.800
## 38 1539.167
## 39 1429.571
## 40 1390.571
## 41 1248.500
## 42 1149.857
## 43 1106.571
## 44 1327.000
## 45 1152.000
## 46 1357.714
## 47 1392.000
## 48 1355.800
## 49 1285.800
## 50 1296.000
## 51 1356.143
## 52 1494.571
## 53 1345.333
## 54 1206.167
## 55 1406.000
## 56 1414.400
## 57 1363.000
## 58 1391.000
## 59 1319.000
## 60 1330.200
## 61 1327.286
## 62 1186.000
## 63 1350.200
## 64 1263.000write.csv(csv, "DATA_607_Project1.csv", row.names=FALSE)