Data607_Project1
Dan Wigodsky
February 20, 2018
Chess Tournament Project
Task: Take an unformatted file and, using regular expressions, order it into a
csv with accessible data. Create a column that relies on data from multiple rows.
Our final table is presented here. The code used to accomplish our task are found at the bottom of this document.
## Player State_or_Province Tournament_Points Prior_Rating Opponents'_Average_Rating
## 1 GARY HUA ON 6.0 1794 1605.29
## 2 DAKSHESH DARURI MI 6.0 1553 1469.29
## 3 ADITYA BAJAJ MI 6.0 1384 1563.57
## 4 PATRICK H SCHILLING MI 5.5 1716 1573.57
## 5 HANSHI ZUO MI 5.5 1655 1500.86
## 6 HANSEN SONG OH 5.0 1686 1518.71
## 7 GARY DEE SWATHELL MI 5.0 1649 1372.14
## 8 EZEKIEL HOUGHTON MI 5.0 1641 1468.43
## 9 STEFANO LEE ON 5.0 1411 1523.14
## 10 ANVIT RAO MI 5.0 1365 1554.14
## 11 CAMERON WILLIAM MCLEMAN MI 4.5 1712 1467.57
## 12 KENNETH J TACK MI 4.5 1663 1506.17
## 13 TORRANCE HENRY JR MI 4.5 1666 1497.86
## 14 BRADLEY SHAW MI 4.5 1610 1515.00
## 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1483.86
## 16 MIKE NIKITIN MI 4.0 1604 1385.80
## 17 RONALD GRZEGORCZYK MI 4.0 1629 1498.57
## 18 DAVID SUNDEEN MI 4.0 1600 1480.00
## 19 DIPANKAR ROY MI 4.0 1564 1426.29
## 20 JASON ZHENG MI 4.0 1595 1410.86
## 21 DINH DANG BUI ON 4.0 1563 1470.43
## 22 EUGENE L MCCLURE MI 4.0 1555 1300.33
## 23 ALAN BUI ON 4.0 1363 1213.86
## 24 MICHAEL R ALDRICH MI 4.0 1229 1357.00
## 25 LOREN SCHWIEBERT MI 3.5 1745 1363.29
## 26 MAX ZHU ON 3.5 1579 1506.86
## 27 GAURAV GIDWANI MI 3.5 1552 1221.67
## 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1522.14
## 29 CHIEDOZIE OKORIE MI 3.5 1602 1313.50
## 30 GEORGE AVERY JONES ON 3.5 1522 1144.14
## 31 RISHI SHETTY MI 3.5 1494 1259.86
## 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 1378.71
## 33 JADE GE MI 3.5 1449 1276.86
## 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1375.29
## 35 JOSHUA DAVID LEE MI 3.5 1438 1149.71
## 36 SIDDHARTH JHA MI 3.5 1355 1388.17
## 37 AMIYATOSH PWNANANDAM MI 3.5 980 1384.80
## 38 BRIAN LIU MI 3.0 1423 1539.17
## 39 JOEL R HENDON MI 3.0 1436 1429.57
## 40 FOREST ZHANG MI 3.0 1348 1390.57
## 41 KYLE WILLIAM MURPHY MI 3.0 1403 1248.50
## 42 JARED GE MI 3.0 1332 1149.86
## 43 ROBERT GLEN VASEY MI 3.0 1283 1106.57
## 44 JUSTIN D SCHILLING MI 3.0 1199 1327.00
## 45 DEREK YAN MI 3.0 1242 1152.00
## 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1357.71
## 47 ERIC WRIGHT MI 2.5 1362 1392.00
## 48 DANIEL KHAIN MI 2.5 1382 1355.80
## 49 MICHAEL J MARTIN MI 2.5 1291 1285.80
## 50 SHIVAM JHA MI 2.5 1056 1296.00
## 51 TEJAS AYYAGARI MI 2.5 1011 1356.14
## 52 ETHAN GUO MI 2.5 935 1494.57
## 53 JOSE C YBARRA MI 2.0 1393 1345.33
## 54 LARRY HODGE MI 2.0 1270 1206.17
## 55 ALEX KONG MI 2.0 1186 1406.00
## 56 MARISA RICCI MI 2.0 1153 1414.40
## 57 MICHAEL LU MI 2.0 1092 1363.00
## 58 VIRAJ MOHILE MI 2.0 917 1391.00
## 59 SEAN M MCCORMICK MI 2.0 853 1319.00
## 60 JULIA SHEN MI 1.5 967 1330.20
## 61 JEZZEL FARKAS ON 1.5 955 1327.29
## 62 ASHWIN BALAJI MI 1.0 1530 1186.00
## 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1350.20
## 64 BEN LI MI 1.0 1163 1263.00We are curious as to whether a player’s point total from the tournament is related to his or her original rating. Did better players do better? We might think that better players would easily do better, but better players tended to be matched with better players, as shown below:
We first show the relationship between a player’s rating and the points earned during the tournament.
Now, we run a linear regression and we find that the difference is statistically significant in our t-statistic and f-statistic. But at .3714, our coefficient of determination is low and only accounts for a small amount of the variation in point attainment during the tournament. We replot our graph again, with our regression line included.
##
## Call:
## lm(formula = as.numeric(final.data[[3]]) ~ as.numeric(final.data[[4]]))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.86623 -0.56507 -0.06999 0.34002 2.54694
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.4635332 0.6562549 -0.706 0.483
## as.numeric(final.data[[4]]) 0.0028299 0.0004676 6.052 9.09e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9853 on 62 degrees of freedom
## Multiple R-squared: 0.3714, Adjusted R-squared: 0.3612
## F-statistic: 36.63 on 1 and 62 DF, p-value: 9.093e-08
library(stringr)
library(ggplot2)
fileName <- 'C:/Users/dawig/Documents/tournamentinfo.txt'
OurData<-readChar(fileName, file.info(fileName)$size)
#Extract all names in order
split.string<-unlist(str_sub(OurData,375,-1))
split.string<-unlist(str_replace_all(split.string,"MC ","MC"))
split.string2<-unlist(str_extract_all(split.string,"([A-Z]{1,20}[ ]{1}[A-Z]{1,20}[ ]{1}[A-Z]{1,20})|[A-Z]{1,20}[ ]{1}[A-Z]{1,20}"))
#Split each entry into a separate row in a data frame
split.by.player<-data.frame(nrow=64)
for (i in 1:63){
split.string3<-unlist(str_locate(split.string,split.string2[[i+1]]))
split.by.player[i,1]<-unlist(str_sub(split.string,0,split.string3[1,1]))
split.string<-unlist(str_sub(split.string,split.string3[1,1],-1))
}
#The last row is still in split.string and has to be dealt with separately.
split.by.player[64,1]<-split.string
for(i in 1:64){
split.string3<-unlist(str_locate(split.by.player[i,1],"\\s{2,25}"))
split.by.player[i,2]<-unlist(str_sub(split.by.player[i,1],split.string3[1,1],-1))
split.by.player[i,1]<-unlist(str_sub(split.by.player[i,1],0,split.string3[1,1]))
split.by.player[i,3]<-unlist(str_extract(split.by.player[i,2]," OH | ON | MI "))
split.by.player[i,4]<-unlist(str_extract(split.by.player[i,2],"[[:digit:]]\\.[[:digit:]]"))
split.by.player[i,5]<-unlist(str_extract(split.by.player[i,2],"R\\: {1,2}[[:digit:]]{3,4}"))
split.by.player[i,5]<-unlist(str_extract(split.by.player[i,5],"[[:digit:]]{3,4}"))
}
tempVar<-data.frame(nrow=64)
for(j in 1:7) {
for(i in 1:64){
helper<-unlist(str_locate(split.by.player[i,2], "\\|[WLDBU].+?[[:digit:]]"))
tempVar<-unlist(str_sub(split.by.player[i,2],helper[2],-1))
split.by.player[i,j+5]<-unlist(str_extract(tempVar,"[[:digit:]]{0,3}"))
split.by.player[i,2]<-unlist(str_sub(split.by.player[i,2],helper[2],-1))
}
}
for(h in 1:64){
split.by.player[h,13]<-0
split.by.player[h,14]<-0
for (i in 6:12){
if (!is.na(split.by.player[h,i])) {
split.by.player[h,13]<-split.by.player[h,13]+1
opponent.reference.for.rating<-split.by.player[h,i]
split.by.player[h,14]<-(as.numeric(split.by.player[opponent.reference.for.rating,5])+split.by.player[h,14])
}
split.by.player[h,15]<-(split.by.player[h,14]/split.by.player[h,13])
split.by.player[h,15]<-round(split.by.player[h,15], digits=2)
}}
final.data<-split.by.player[,c(1,3,4,5,15)]
colnames(final.data)<-c("Player","State_or_Province","Tournament_Points", "Prior_Rating", "Opponents'_Average_Rating")
final.data
write.csv(final.data, file = "Chess_Tournament_Data.csv")