library("stringr")lines <- scan("data/tournamentinfo.txt", sep="\n", what="raw")
# preview data
print(lines[1:15])## [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 |"I decided to use use a data frame to store the data and leverage its capabilities to do subsetting, calculations, and generate a CSV.
tournament = data.frame(Player = integer(),
Name = character(),
State = character(),
Points = double(),
Pre_Rtg = integer(),
Opp_Rtg = double(),
Games = integer(),
Opponents = character(),
stringsAsFactors = FALSE)This is the meat of the work. Extensive use of R’s chaining and nesting capabilities were done to produce a single statement to produce most variables. I created a function to “camel case” the players’ names as per the project requirements.
# created function to convert names to camel case format
# preventing the need to loop through the segments of the name
camelCase = function(s){
# converts the first letter of each word to upper case and the other characters to lower case
return(str_c(toupper(str_sub(s,1,1)),tolower(str_sub(s,2,str_count(s)))))
}
i <- 5 #start at the 5th line
while (i <= length( lines ) ){
playerInfoRow1 <- str_trim(str_split(str_trim(lines[i]),"\\|")[[1]])
playerInfoRow2 <- str_trim(str_split(str_trim(lines[i + 1]),"\\|")[[1]])
playerNumber <- playerInfoRow1[1]
playerName <- paste(unlist(camelCase(str_split(playerInfoRow1[2],"\\s")[[1]])), collapse = " ")
playerState <- playerInfoRow2[1]
points <- playerInfoRow1[3]
playerRatings= str_trim(str_split(str_split(playerInfoRow2[2] ,":")[[1]][2],"->")[[1]])
playerPreRating <- str_split(playerRatings[1],"P")[[1]][1]
opponents= str_extract_all(str_sub(lines[i],-43),"[0-9]+")[[1]] #used as reference calc. average
gamesPlayed = length(opponents)
opponents=paste(unlist(opponents),collapse = "|")
tournament[nrow(tournament) + 1,] = list(playerNumber,
playerName,
playerState,
points,
playerPreRating,
0.0,
gamesPlayed,
opponents)
# increment in blocks of 3 to prevent unnecessary processing of dashes
i <- i + 3
}We now all the necessary information to perform necessary calculations and analysis.
print(subset(tournament, select = c("Name","State","Points","Pre_Rtg","Opponents")))## Name State Points Pre_Rtg Opponents
## 1 Gary Hua ON 6.0 1794 39|21|18|14|7|12|4
## 2 Dakshesh Daruri MI 6.0 1553 63|58|4|17|16|20|7
## 3 Aditya Bajaj MI 6.0 1384 8|61|25|21|11|13|12
## 4 Patrick H Schilling MI 5.5 1716 23|28|2|26|5|19|1
## 5 Hanshi Zuo MI 5.5 1655 45|37|12|13|4|14|17
## 6 Hansen Song OH 5.0 1686 34|29|11|35|10|27|21
## 7 Gary Dee Swathell MI 5.0 1649 57|46|13|11|1|9|2
## 8 Ezekiel Houghton MI 5.0 1641 3|32|14|9|47|28|19
## 9 Stefano Lee ON 5.0 1411 25|18|59|8|26|7|20
## 10 Anvit Rao MI 5.0 1365 16|19|55|31|6|25|18
## 11 Cameron William Mc Leman MI 4.5 1712 38|56|6|7|3|34|26
## 12 Kenneth J Tack MI 4.5 1663 42|33|5|38|1|3
## 13 Torrance Henry Jr MI 4.5 1666 36|27|7|5|33|3|32
## 14 Bradley Shaw MI 4.5 1610 54|44|8|1|27|5|31
## 15 Zachary James Houghton MI 4.5 1220 19|16|30|22|54|33|38
## 16 Mike Nikitin MI 4.0 1604 10|15|39|2|36
## 17 Ronald Grzegorczyk MI 4.0 1629 48|41|26|2|23|22|5
## 18 David Sundeen MI 4.0 1600 47|9|1|32|19|38|10
## 19 Dipankar Roy MI 4.0 1564 15|10|52|28|18|4|8
## 20 Jason Zheng MI 4.0 1595 40|49|23|41|28|2|9
## 21 Dinh Dang Bui ON 4.0 1563 43|1|47|3|40|39|6
## 22 Eugene L Mcclure MI 4.0 1555 64|52|28|15|17|40
## 23 Alan Bui ON 4.0 1363 4|43|20|58|17|37|46
## 24 Michael R Aldrich MI 4.0 1229 28|47|43|25|60|44|39
## 25 Loren Schwiebert MI 3.5 1745 9|53|3|24|34|10|47
## 26 Max Zhu ON 3.5 1579 49|40|17|4|9|32|11
## 27 Gaurav Gidwani MI 3.5 1552 51|13|46|37|14|6
## 28 Sofia Adina Stanescu-bellu MI 3.5 1507 24|4|22|19|20|8|36
## 29 Chiedozie Okorie MI 3.5 1602 50|6|38|34|52|48
## 30 George Avery Jones ON 3.5 1522 52|64|15|55|31|61|50
## 31 Rishi Shetty MI 3.5 1494 58|55|64|10|30|50|14
## 32 Joshua Philip Mathews ON 3.5 1441 61|8|44|18|51|26|13
## 33 Jade Ge MI 3.5 1449 60|12|50|36|13|15|51
## 34 Michael Jeffery Thomas MI 3.5 1399 6|60|37|29|25|11|52
## 35 Joshua David Lee MI 3.5 1438 46|38|56|6|57|52|48
## 36 Siddharth Jha MI 3.5 1355 13|57|51|33|16|28
## 37 Amiyatosh Pwnanandam MI 3.5 980 5|34|27|23|61
## 38 Brian Liu MI 3.0 1423 11|35|29|12|18|15
## 39 Joel R Hendon MI 3.0 1436 1|54|40|16|44|21|24
## 40 Forest Zhang MI 3.0 1348 20|26|39|59|21|56|22
## 41 Kyle William Murphy MI 3.0 1403 59|17|58|20
## 42 Jared Ge MI 3.0 1332 12|50|57|60|61|64|56
## 43 Robert Glen Vasey MI 3.0 1283 21|23|24|63|59|46|55
## 44 Justin D Schilling MI 3.0 1199 14|32|53|39|24|59
## 45 Derek Yan MI 3.0 1242 5|51|60|56|63|55|58
## 46 Jacob Alexander Lavalley MI 3.0 377 35|7|27|50|64|43|23
## 47 Eric Wright MI 2.5 1362 18|24|21|61|8|51|25
## 48 Daniel Khain MI 2.5 1382 17|63|52|29|35
## 49 Michael J Martin MI 2.5 1291 26|20|63|64|58
## 50 Shivam Jha MI 2.5 1056 29|42|33|46|31|30
## 51 Tejas Ayyagari MI 2.5 1011 27|45|36|57|32|47|33
## 52 Ethan Guo MI 2.5 935 30|22|19|48|29|35|34
## 53 Jose C Ybarra MI 2.0 1393 25|44|57
## 54 Larry Hodge MI 2.0 1270 14|39|61|15|59|64
## 55 Alex Kong MI 2.0 1186 62|31|10|30|45|43
## 56 Marisa Ricci MI 2.0 1153 11|35|45|40|42
## 57 Michael Lu MI 2.0 1092 7|36|42|51|35|53
## 58 Viraj Mohile MI 2.0 917 31|2|41|23|49|45
## 59 Sean M Mc Cormick MI 2.0 853 41|9|40|43|54|44
## 60 Julia Shen MI 1.5 967 33|34|45|42|24
## 61 Jezzel Farkas ON 1.5 955 32|3|54|47|42|30|37
## 62 Ashwin Balaji MI 1.0 1530 55
## 63 Thomas Joseph Hosmer MI 1.0 1175 2|48|49|43|45
## 64 Ben Li MI 1.0 1163 22|30|31|49|46|42|54This was done by referencing the players opponents by creating a list and using the %in% operator as input to the mean function.
i <- 1
while(i <= nrow(tournament)){
oppMean <- mean(as.integer(subset(tournament,
Player %in% as.integer(str_split(tournament$Opponents[i],
"\\|")[[1]]),select=c("Pre_Rtg"))$Pre_Rtg))
tournament$Opp_Rtg[i] <- oppMean
i <- i + 1
} print(subset(tournament, select = c("Name","State","Points","Pre_Rtg","Opp_Rtg")))## Name State Points Pre_Rtg Opp_Rtg
## 1 Gary Hua ON 6.0 1794 1605.286
## 2 Dakshesh Daruri MI 6.0 1553 1469.286
## 3 Aditya Bajaj MI 6.0 1384 1563.571
## 4 Patrick H Schilling MI 5.5 1716 1573.571
## 5 Hanshi Zuo MI 5.5 1655 1500.857
## 6 Hansen Song OH 5.0 1686 1518.714
## 7 Gary Dee Swathell MI 5.0 1649 1372.143
## 8 Ezekiel Houghton MI 5.0 1641 1468.429
## 9 Stefano Lee ON 5.0 1411 1523.143
## 10 Anvit Rao MI 5.0 1365 1554.143
## 11 Cameron William Mc Leman MI 4.5 1712 1467.571
## 12 Kenneth J Tack MI 4.5 1663 1506.167
## 13 Torrance Henry Jr MI 4.5 1666 1497.857
## 14 Bradley Shaw MI 4.5 1610 1515.000
## 15 Zachary James Houghton MI 4.5 1220 1483.857
## 16 Mike Nikitin MI 4.0 1604 1385.800
## 17 Ronald Grzegorczyk MI 4.0 1629 1498.571
## 18 David Sundeen MI 4.0 1600 1480.000
## 19 Dipankar Roy MI 4.0 1564 1426.286
## 20 Jason Zheng MI 4.0 1595 1410.857
## 21 Dinh Dang Bui ON 4.0 1563 1470.429
## 22 Eugene L Mcclure MI 4.0 1555 1300.333
## 23 Alan Bui ON 4.0 1363 1213.857
## 24 Michael R Aldrich MI 4.0 1229 1357.000
## 25 Loren Schwiebert MI 3.5 1745 1363.286
## 26 Max Zhu ON 3.5 1579 1506.857
## 27 Gaurav Gidwani MI 3.5 1552 1221.667
## 28 Sofia Adina Stanescu-bellu MI 3.5 1507 1522.143
## 29 Chiedozie Okorie MI 3.5 1602 1313.500
## 30 George Avery Jones ON 3.5 1522 1144.143
## 31 Rishi Shetty MI 3.5 1494 1259.857
## 32 Joshua Philip Mathews ON 3.5 1441 1378.714
## 33 Jade Ge MI 3.5 1449 1276.857
## 34 Michael Jeffery Thomas MI 3.5 1399 1375.286
## 35 Joshua David Lee MI 3.5 1438 1149.714
## 36 Siddharth Jha MI 3.5 1355 1388.167
## 37 Amiyatosh Pwnanandam MI 3.5 980 1384.800
## 38 Brian Liu MI 3.0 1423 1539.167
## 39 Joel R Hendon MI 3.0 1436 1429.571
## 40 Forest Zhang MI 3.0 1348 1390.571
## 41 Kyle William Murphy MI 3.0 1403 1248.500
## 42 Jared Ge MI 3.0 1332 1149.857
## 43 Robert Glen Vasey MI 3.0 1283 1106.571
## 44 Justin D Schilling MI 3.0 1199 1327.000
## 45 Derek Yan MI 3.0 1242 1152.000
## 46 Jacob Alexander Lavalley MI 3.0 377 1357.714
## 47 Eric Wright MI 2.5 1362 1392.000
## 48 Daniel Khain MI 2.5 1382 1355.800
## 49 Michael J Martin MI 2.5 1291 1285.800
## 50 Shivam Jha MI 2.5 1056 1296.000
## 51 Tejas Ayyagari MI 2.5 1011 1356.143
## 52 Ethan Guo MI 2.5 935 1494.571
## 53 Jose C Ybarra MI 2.0 1393 1345.333
## 54 Larry Hodge MI 2.0 1270 1206.167
## 55 Alex Kong MI 2.0 1186 1406.000
## 56 Marisa Ricci MI 2.0 1153 1414.400
## 57 Michael Lu MI 2.0 1092 1363.000
## 58 Viraj Mohile MI 2.0 917 1391.000
## 59 Sean M Mc Cormick MI 2.0 853 1319.000
## 60 Julia Shen MI 1.5 967 1330.200
## 61 Jezzel Farkas ON 1.5 955 1327.286
## 62 Ashwin Balaji MI 1.0 1530 1186.000
## 63 Thomas Joseph Hosmer MI 1.0 1175 1350.200
## 64 Ben Li MI 1.0 1163 1263.000Only the necessary variables are written to the CSV file.
write.csv(subset(tournament, select = c("Name","State","Points","Pre_Rtg","Opp_Rtg")),
file = "tournament.csv", quote = FALSE, row.names = FALSE)