library(stringr)chess_data <- read.table(url("https://raw.githubusercontent.com/Zchen116/assignment-2/master/tournamentinfo.txt"), sep = ",")
head(chess_data)## 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_data1 <- data.frame(str_replace_all(chess_data$V1,"-",""))
head(chess_data1)## str_replace_all.chess_data.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_data1 <- chess_data1[c(5:nrow(chess_data1)),]
head(chess_data1)## [1] 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|
## [2] ON | 15445895 / R: 1794 >1817 |N:2 |W |B |W |B |W |B |W |
## [3]
## [4] 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7|
## [5] MI | 14598900 / R: 1553 >1663 |N:2 |B |W |B |W |B |W |B |
## [6]
## 131 Levels: ...id <- "\\d{1,2}(?=\\s\\|)"
chess_id <- unlist(str_extract_all(unlist(chess_data1), id))name <- "([[:upper:]]+\\s){2,}"
chess_names <- unlist(str_extract_all(unlist(chess_data1), name))
str_trim(chess_names, side = "right")## [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 LEMAN" "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 STANESCUBELLU"
## [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 CORMICK" "JULIA SHEN"
## [61] "JEZZEL FARKAS" "ASHWIN BALAJI"
## [63] "THOMAS JOSEPH HOSMER" "BEN LI"state <- "([[:upper:]]){2}\\s(?=\\|)"
chess_states <- unlist(str_extract_all(unlist(chess_data1), state))
str_trim(chess_states, side = "right")## [1] "ON" "MI" "MI" "MI" "MI" "OH" "MI" "MI" "ON" "MI" "MI" "MI" "MI" "MI"
## [15] "MI" "MI" "MI" "MI" "MI" "MI" "ON" "MI" "ON" "MI" "MI" "ON" "MI" "MI"
## [29] "MI" "ON" "MI" "ON" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI"
## [43] "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI" "MI"
## [57] "MI" "MI" "MI" "MI" "ON" "MI" "MI" "MI"points <- "\\d\\.\\d"
chess_point <- unlist(str_extract_all(unlist(chess_data1), points))
chess_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"pre_rating <- "(?<!\\>\\s)(?<=\\s{1,2}|\\s\\:)(\\d{3,4}(?=\\s|P))"
chess_pre_rating <- unlist(str_extract_all(unlist(chess_data1), pre_rating))
chess_pre_rating <- str_trim(chess_pre_rating)
chess_pre_rating## [1] "1794" "1553" "1384" "1716" "1655" "1686" "1649" "1641" "1411" "1365"
## [11] "1712" "1663" "1666" "1610" "1220" "1604" "1629" "1600" "1564" "1595"
## [21] "1563" "1555" "1363" "1229" "1745" "1579" "1552" "1507" "1602" "1522"
## [31] "1494" "1441" "1449" "1399" "1438" "1355" "980" "1423" "1436" "1348"
## [41] "1403" "1332" "1283" "1199" "1242" "377" "1362" "1382" "1291" "1056"
## [51] "1011" "935" "1393" "1270" "1186" "1153" "1092" "917" "853" "967"
## [61] "955" "1530" "1175" "1163"opponents <- "(\\d{1,}|[[:blank:]]{1})(?=\\|)"
player_opponents <- unlist(str_extract_all(unlist(chess_data1), opponents))
player_opponents[player_opponents==" "] <- NA
opponent1 <- as.numeric(player_opponents[seq(4, length(player_opponents), 10)])
opponent1 <- as.numeric(opponent1[seq(1, length(opponent1), 2)])
opponent2 <- as.numeric(player_opponents[seq(5, length(player_opponents), 10)])
opponent2 <- as.numeric(opponent2[seq(1, length(opponent2), 2)])
opponent3 <- as.numeric(player_opponents[seq(6, length(player_opponents), 10)])
opponent3 <- as.numeric(opponent3[seq(1, length(opponent3), 2)])
opponent4 <- as.numeric(player_opponents[seq(7, length(player_opponents), 10)])
opponent4 <- as.numeric(opponent4[seq(1, length(opponent4), 2)])
opponent5 <- as.numeric(player_opponents[seq(8, length(player_opponents), 10)])
opponent5 <- as.numeric(opponent5[seq(1, length(opponent5), 2)])
opponent6 <- as.numeric(player_opponents[seq(9, length(player_opponents), 10)])
opponent6 <- as.numeric(opponent6[seq(1, length(opponent6), 2)])
opponent7 <- as.numeric(player_opponents[seq(10, length(player_opponents), 10)])
opponent7 <- as.numeric(opponent7[seq(1, length(opponent7), 2)])
player_opponents <- matrix(c(opponent1, opponent2, opponent3, opponent4, opponent5, opponent6, opponent7),nrow = 64, ncol = 7)chess_avg <- 0
chess_table <- 0
for (i in 1:(length(chess_id)))
chess_avg[i] <- mean(as.numeric(chess_pre_rating[player_opponents[i,]]), na.rm = T)ChessResults <- data.frame(chess_names, chess_states, chess_point, chess_pre_rating)
head(ChessResults, 5)## chess_names chess_states chess_point chess_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 1655write.csv(ChessResults, file = "Porject_ChessResults.csv")