Get Data from Github
raw_data <- read.csv(paste0("https://raw.githubusercontent.com/omerozeren/DATA607/master/PROJECT_1/tournamentinfo.txt"))
head(raw_data)
## X.........................................................................................
## 1 Pair | Player Name |Total|Round|Round|Round|Round|Round|Round|Round|
## 2 Num | USCF ID / Rtg (Pre->Post) | Pts | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
## 3 -----------------------------------------------------------------------------------------
## 4 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4|
## 5 ON | 15445895 / R: 1794 ->1817 |N:2 |W |B |W |B |W |B |W |
## 6 -----------------------------------------------------------------------------------------
Removing Column Headers
raw_data <- raw_data[-c(1:2),]
head(raw_data,6)
## [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 |
## 131 Levels: ----------------------------------------------------------------------------------------- ...
Cleaning the Data
clean_data =raw_data[seq(2,length(raw_data),3)]
knitr::kable(head(clean_data,5), digits=2, align=c(rep("l", 4) ) )
| 1 | GARY HUA |6.0 |W 39|W 21|W 18|W 14|W 7|D 12|D 4| |
| 2 | DAKSHESH DARURI |6.0 |W 63|W 58|L 4|W 17|W 16|W 20|W 7| |
| 3 | ADITYA BAJAJ |6.0 |L 8|W 61|W 25|W 21|W 11|W 13|W 12| |
| 4 | PATRICK H SCHILLING |5.5 |W 23|D 28|W 2|W 26|D 5|W 19|D 1| |
| 5 | HANSHI ZUO |5.5 |W 45|W 37|D 12|D 13|D 4|W 14|W 17| |
Players ID
id <- as.numeric(str_extract(substr(unlist(clean_data),1,length(raw_data)),"\\d+"))
id
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
## [47] 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64
Player Names
names <- str_trim(unlist(str_extract_all(raw_data, "[A-Z]+ [A-Z]+ ([A-Z-]+)? ([A-Z]+)?")))
names
## [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 STANESCU-BELLU"
## [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"
Player States
region <- unlist(str_extract_all(raw_data, "[[:upper:]]. \\|"))
region <- str_trim(str_replace_all(region, " \\|", ""))
region
## [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"
Player Points
points <- as.numeric(unlist(str_extract_all(raw_data, "(\\d)\\.(\\d)")))
points
## [1] 6.0 6.0 6.0 5.5 5.5 5.0 5.0 5.0 5.0 5.0 4.5 4.5 4.5 4.5 4.5 4.0 4.0
## [18] 4.0 4.0 4.0 4.0 4.0 4.0 4.0 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5 3.5
## [35] 3.5 3.5 3.5 3.0 3.0 3.0 3.0 3.0 3.0 3.0 3.0 3.0 2.5 2.5 2.5 2.5 2.5
## [52] 2.5 2.0 2.0 2.0 2.0 2.0 2.0 2.0 1.5 1.5 1.0 1.0 1.0
Player Pre Ratings
pre_rating <- unlist(str_extract_all(raw_data, "R:\\s+?(\\d)+"))
pre_rating <- str_replace_all(pre_rating , "R:\\s+", "")
pre_rating <- as.integer(pre_rating )
pre_rating
## [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
Player Opponents
opponents <- str_extract_all(str_extract_all(clean_data, "\\d+\\|"), "\\d+")
head(opponents,5)
## [[1]]
## [1] "39" "21" "18" "14" "7" "12" "4"
##
## [[2]]
## [1] "63" "58" "4" "17" "16" "20" "7"
##
## [[3]]
## [1] "8" "61" "25" "21" "11" "13" "12"
##
## [[4]]
## [1] "23" "28" "2" "26" "5" "19" "1"
##
## [[5]]
## [1] "45" "37" "12" "13" "4" "14" "17"
Create DataFrame
df <- data.frame(id, names, region, points, pre_rating)
colnames(df)<- c("Player Number","Player Names","Player State","Total Points","Pre Rating")
df[,"Average_Pre_Chess_Rating"] <- NA
for (i in 1:nrow(df)){
df$Average_Pre_Chess_Rating[i] <- round(mean(pre_rating[as.integer(unlist(opponents[id[i]]))]), digits = 0)
}
knitr::kable(df, digits=2, align=c(rep("l", 4) ) )
| 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 LEMAN |
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-BELLU |
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 CORMICK |
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 |
1263 |
Writing results in csv file
write.csv(df, file = "tournament_results.csv")