Reading in the text file via github.
library(readr)
#string of Text file uploaded from github.
urlfile<-"https://raw.githubusercontent.com/catcho1632/607-Project-1/main/tournamentinfo.txt"
#The text file is assigned as a string to the variable ELO
ELO<-read_file(url(urlfile))
Extracting strings of interest from ELO (text file), and creating string vectors for each. The strings were extracted using package stringr.
library(stringr)
#Player's Name extracted using str_extract_all and regular expressions of different name structuring is defined. (i.e. First name and last name...First name middle initial last name...first name middle name last name...first name and last name only). Then the string is "unlisted" after splitting the string per name.
w<-str_extract_all(ELO,"([A-Z]+\\s[A-Z]+\\s[A-Z]+-[A-Z]+)|([A-Z]+\\s[A-Z]\\s[A-Z]+(\\s|-)[A-Z]+)|([A-Z]+\\s[A-Z]+\\s[A-Z]+)|([A-Z]+\\s[A-Z]+)",simplify = TRUE)
names_unlist<-unlist(strsplit(w, "^[A-Z]+\\s[A-Z]+$)"))
names<-names_unlist[-1]
#Player's state extracted using str_extract_all and all states in the text file has at least 2 spaces preceding 2 capital cased letters.
x<-str_extract_all(ELO,"\\s\\s[A-Z]{2}",simplify = TRUE)
state<-unlist(str_extract(x, "[A-Z][A-Z]"))
#Total Number of Points is extracted using str_extract_all and is identified by the digit decimal digit regular expression. These are the only text value with this combination.
y<-str_extract_all(ELO,"\\d\\.\\d",simplify = TRUE)
points<-unlist(str_extract(y, "\\d\\.\\d"))
#Player's Pre-Rating is identified using regular expression that captures every character after "R: " and before "-".The string is then extracted by digits only. The numeric values are strings and converted to dbl in order to utilize the numeric value.
z<-str_extract_all(ELO,"[R]\\:\\s.+\\-",simplify = TRUE)
pre_rating<-as.double(unlist(str_extract(z, "\\d\\d\\d+")))
Calculating the average pre chess rating of opponents.
library(matrixStats)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following object is masked from 'package:matrixStats':
##
## count
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
#Dataframe ELO_rating is constructed in order to summarize the results thus far generated.
pair_num<-1:64
ELO_rating<-data.frame(pair_num,names,state,points,pre_rating,round1_pre_r,round2_pre_r,round3_pre_r,round4_pre_r,round5_pre_r,round6_pre_r,round7_pre_r)
ELO_rating
## pair_num names state points pre_rating round1_pre_r
## 1 1 GARY HUA ON 6.0 1794 1436
## 2 2 DAKSHESH DARURI MI 6.0 1553 1175
## 3 3 ADITYA BAJAJ MI 6.0 1384 1641
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1363
## 5 5 HANSHI ZUO MI 5.5 1655 1242
## 6 6 HANSEN SONG OH 5.0 1686 1399
## 7 7 GARY DEE SWATHELL MI 5.0 1649 1092
## 8 8 EZEKIEL HOUGHTON MI 5.0 1641 1384
## 9 9 STEFANO LEE ON 5.0 1411 1745
## 10 10 ANVIT RAO MI 5.0 1365 1604
## 11 11 CAMERON WILLIAM MC MI 4.5 1712 1423
## 12 12 KENNETH J TACK MI 4.5 1663 1332
## 13 13 TORRANCE HENRY JR MI 4.5 1666 1355
## 14 14 BRADLEY SHAW MI 4.5 1610 1270
## 15 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1564
## 16 16 MIKE NIKITIN MI 4.0 1604 1365
## 17 17 RONALD GRZEGORCZYK MI 4.0 1629 1382
## 18 18 DAVID SUNDEEN MI 4.0 1600 1362
## 19 19 DIPANKAR ROY MI 4.0 1564 1220
## 20 20 JASON ZHENG MI 4.0 1595 1348
## 21 21 DINH DANG BUI ON 4.0 1563 1283
## 22 22 EUGENE L MCCLURE MI 4.0 1555 1163
## 23 23 ALAN BUI ON 4.0 1363 1716
## 24 24 MICHAEL R ALDRICH MI 4.0 1229 1507
## 25 25 LOREN SCHWIEBERT MI 3.5 1745 1411
## 26 26 MAX ZHU ON 3.5 1579 1291
## 27 27 GAURAV GIDWANI MI 3.5 1552 1011
## 28 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1229
## 29 29 CHIEDOZIE OKORIE MI 3.5 1602 1056
## 30 30 GEORGE AVERY JONES ON 3.5 1522 935
## 31 31 RISHI SHETTY MI 3.5 1494 917
## 32 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 955
## 33 33 JADE GE MI 3.5 1449 967
## 34 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1686
## 35 35 JOSHUA DAVID LEE MI 3.5 1438 377
## 36 36 SIDDHARTH JHA MI 3.5 1355 1666
## 37 37 AMIYATOSH PWNANANDAM MI 3.5 980 NA
## 38 38 BRIAN LIU MI 3.0 1423 1712
## 39 39 JOEL R HENDON MI 3.0 1436 1794
## 40 40 FOREST ZHANG MI 3.0 1348 1595
## 41 41 KYLE WILLIAM MURPHY MI 3.0 1403 853
## 42 42 JARED GE MI 3.0 1332 1663
## 43 43 ROBERT GLEN VASEY MI 3.0 1283 1563
## 44 44 JUSTIN D SCHILLING MI 3.0 1199 NA
## 45 45 DEREK YAN MI 3.0 1242 1655
## 46 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1438
## 47 47 ERIC WRIGHT MI 2.5 1362 1600
## 48 48 DANIEL KHAIN MI 2.5 1382 1629
## 49 49 MICHAEL J MARTIN MI 2.5 1291 1579
## 50 50 SHIVAM JHA MI 2.5 1056 1602
## 51 51 TEJAS AYYAGARI MI 2.5 1011 1552
## 52 52 ETHAN GUO MI 2.5 935 1522
## 53 53 JOSE C YBARRA MI 2.0 1393 NA
## 54 54 LARRY HODGE MI 2.0 1270 1610
## 55 55 ALEX KONG MI 2.0 1186 1530
## 56 56 MARISA RICCI MI 2.0 1153 NA
## 57 57 MICHAEL LU MI 2.0 1092 1649
## 58 58 VIRAJ MOHILE MI 2.0 917 1494
## 59 59 SEAN M MC CORMICK MI 2.0 853 1403
## 60 60 JULIA SHEN MI 1.5 967 1449
## 61 61 JEZZEL FARKAS ON 1.5 955 1441
## 62 62 ASHWIN BALAJI MI 1.0 1530 1186
## 63 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1553
## 64 64 BEN LI MI 1.0 1163 1555
## round2_pre_r round3_pre_r round4_pre_r round5_pre_r round6_pre_r
## 1 1563 1600 1610 1649 1663
## 2 917 1716 1629 1604 1595
## 3 955 1745 1563 1712 1666
## 4 1507 1553 1579 1655 1564
## 5 980 1663 1666 1716 1610
## 6 1602 1712 1438 1365 1552
## 7 377 1666 1712 1794 1411
## 8 1441 1610 1411 1362 1507
## 9 1600 853 1641 1579 1649
## 10 1564 1186 1494 1686 1745
## 11 1153 1686 1649 1384 1399
## 12 1449 1655 1423 NA 1794
## 13 1552 1649 1655 1449 1384
## 14 1199 1641 1794 1552 1655
## 15 1604 1522 1555 1270 1449
## 16 1220 NA 1436 1553 1355
## 17 1403 1579 1553 1363 1555
## 18 1411 1794 1441 1564 1423
## 19 1365 935 1507 1600 1716
## 20 1291 1363 1403 1507 1553
## 21 1794 1362 1384 1348 1436
## 22 935 1507 1220 NA 1629
## 23 1283 1595 917 1629 980
## 24 1362 1283 1745 967 1199
## 25 1393 1384 1229 1399 1365
## 26 1348 1629 1716 1411 1441
## 27 1666 377 980 1610 1686
## 28 1716 1555 1564 1595 1641
## 29 1686 1423 1399 935 1382
## 30 1163 1220 1186 1494 955
## 31 1186 1163 1365 1522 1056
## 32 1641 1199 1600 1011 1579
## 33 1663 1056 1355 1666 1220
## 34 967 980 1602 1745 1712
## 35 1423 1153 1686 1092 935
## 36 1092 1011 1449 NA 1604
## 37 1655 1399 1552 NA 1363
## 38 1438 1602 1663 NA 1600
## 39 1270 1348 1604 1199 1563
## 40 1579 1436 853 1563 1153
## 41 1629 917 1595 NA NA
## 42 1056 1092 967 955 1163
## 43 1363 1229 1175 853 377
## 44 1610 1441 1393 1436 1229
## 45 1011 967 1153 1175 1186
## 46 1649 1552 1056 1163 1283
## 47 1229 1563 955 1641 1011
## 48 1175 NA 935 NA 1602
## 49 1595 1175 1163 917 NA
## 50 1332 1449 377 NA 1494
## 51 1242 1355 1092 1441 1362
## 52 1555 1564 1382 1602 1438
## 53 1745 NA 1199 NA 1092
## 54 1436 955 NA 1220 853
## 55 1494 1365 1522 NA 1242
## 56 1712 1438 1242 NA 1348
## 57 1355 1332 1011 1438 1393
## 58 1553 1403 1363 1291 NA
## 59 NA 1411 1348 1283 1270
## 60 1399 1242 1332 1229 NA
## 61 1384 1270 1362 1332 1522
## 62 NA NA NA NA NA
## 63 1382 1291 1283 1242 NA
## 64 1522 1494 1291 377 1332
## round7_pre_r
## 1 1716
## 2 1649
## 3 1663
## 4 1794
## 5 1629
## 6 1563
## 7 1553
## 8 1564
## 9 1595
## 10 1600
## 11 1579
## 12 1384
## 13 1441
## 14 1494
## 15 1423
## 16 NA
## 17 1655
## 18 1365
## 19 1641
## 20 1411
## 21 1686
## 22 1348
## 23 377
## 24 1436
## 25 1362
## 26 1712
## 27 NA
## 28 1355
## 29 NA
## 30 1056
## 31 1610
## 32 1666
## 33 1011
## 34 935
## 35 1382
## 36 1507
## 37 955
## 38 1220
## 39 1229
## 40 1555
## 41 NA
## 42 1153
## 43 1186
## 44 853
## 45 917
## 46 1363
## 47 1745
## 48 1438
## 49 NA
## 50 1522
## 51 1449
## 52 1399
## 53 NA
## 54 1163
## 55 1283
## 56 1332
## 57 NA
## 58 1242
## 59 1199
## 60 NA
## 61 980
## 62 NA
## 63 NA
## 64 1270
#The mean is calculated per row (average of opponent pre-rating) and the final values are added to dataframe ELO_rating and is now called ELO_rating_Mean.
ELO_rating_Mean<-ELO_rating %>% mutate(Opp_pre_mean = apply(.[(6:12)],1,mean,na.rm=TRUE))
#Subsetting Mean Column from ELO_rating_Mean dataframe. Each value represents the mean of each player's oppponent's pre-ratings for rounds 1-7.
Opp_Pre_Mean<-round(subset(ELO_rating_Mean,select=c(Opp_pre_mean)))
#Final dataframe summarizing player number, name, state, total points, pre-rating, opponent pre-rating average
pair_num<-1:64
ELO_final<-data.frame(pair_num,names,state,points,pre_rating,Opp_Pre_Mean)
ELO_final
## pair_num names state points pre_rating Opp_pre_mean
## 1 1 GARY HUA ON 6.0 1794 1605
## 2 2 DAKSHESH DARURI MI 6.0 1553 1469
## 3 3 ADITYA BAJAJ MI 6.0 1384 1564
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1574
## 5 5 HANSHI ZUO MI 5.5 1655 1501
## 6 6 HANSEN SONG OH 5.0 1686 1519
## 7 7 GARY DEE SWATHELL MI 5.0 1649 1372
## 8 8 EZEKIEL HOUGHTON MI 5.0 1641 1468
## 9 9 STEFANO LEE ON 5.0 1411 1523
## 10 10 ANVIT RAO MI 5.0 1365 1554
## 11 11 CAMERON WILLIAM MC MI 4.5 1712 1468
## 12 12 KENNETH J TACK MI 4.5 1663 1506
## 13 13 TORRANCE HENRY JR MI 4.5 1666 1498
## 14 14 BRADLEY SHAW MI 4.5 1610 1515
## 15 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1484
## 16 16 MIKE NIKITIN MI 4.0 1604 1386
## 17 17 RONALD GRZEGORCZYK MI 4.0 1629 1499
## 18 18 DAVID SUNDEEN MI 4.0 1600 1480
## 19 19 DIPANKAR ROY MI 4.0 1564 1426
## 20 20 JASON ZHENG MI 4.0 1595 1411
## 21 21 DINH DANG BUI ON 4.0 1563 1470
## 22 22 EUGENE L MCCLURE MI 4.0 1555 1300
## 23 23 ALAN BUI ON 4.0 1363 1214
## 24 24 MICHAEL R ALDRICH MI 4.0 1229 1357
## 25 25 LOREN SCHWIEBERT MI 3.5 1745 1363
## 26 26 MAX ZHU ON 3.5 1579 1507
## 27 27 GAURAV GIDWANI MI 3.5 1552 1222
## 28 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1522
## 29 29 CHIEDOZIE OKORIE MI 3.5 1602 1314
## 30 30 GEORGE AVERY JONES ON 3.5 1522 1144
## 31 31 RISHI SHETTY MI 3.5 1494 1260
## 32 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 1379
## 33 33 JADE GE MI 3.5 1449 1277
## 34 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1375
## 35 35 JOSHUA DAVID LEE MI 3.5 1438 1150
## 36 36 SIDDHARTH JHA MI 3.5 1355 1388
## 37 37 AMIYATOSH PWNANANDAM MI 3.5 980 1385
## 38 38 BRIAN LIU MI 3.0 1423 1539
## 39 39 JOEL R HENDON MI 3.0 1436 1430
## 40 40 FOREST ZHANG MI 3.0 1348 1391
## 41 41 KYLE WILLIAM MURPHY MI 3.0 1403 1248
## 42 42 JARED GE MI 3.0 1332 1150
## 43 43 ROBERT GLEN VASEY MI 3.0 1283 1107
## 44 44 JUSTIN D SCHILLING MI 3.0 1199 1327
## 45 45 DEREK YAN MI 3.0 1242 1152
## 46 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1358
## 47 47 ERIC WRIGHT MI 2.5 1362 1392
## 48 48 DANIEL KHAIN MI 2.5 1382 1356
## 49 49 MICHAEL J MARTIN MI 2.5 1291 1286
## 50 50 SHIVAM JHA MI 2.5 1056 1296
## 51 51 TEJAS AYYAGARI MI 2.5 1011 1356
## 52 52 ETHAN GUO MI 2.5 935 1495
## 53 53 JOSE C YBARRA MI 2.0 1393 1345
## 54 54 LARRY HODGE MI 2.0 1270 1206
## 55 55 ALEX KONG MI 2.0 1186 1406
## 56 56 MARISA RICCI MI 2.0 1153 1414
## 57 57 MICHAEL LU MI 2.0 1092 1363
## 58 58 VIRAJ MOHILE MI 2.0 917 1391
## 59 59 SEAN M MC CORMICK MI 2.0 853 1319
## 60 60 JULIA SHEN MI 1.5 967 1330
## 61 61 JEZZEL FARKAS ON 1.5 955 1327
## 62 62 ASHWIN BALAJI MI 1.0 1530 1186
## 63 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1350
## 64 64 BEN LI MI 1.0 1163 1263