library(stringr)
library(XML)
library(RCurl)## Loading required package: bitopslibrary(bitops)
library(tau)
library(plyr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionreferenced for initial load . . . http://stackoverflow.com/questions/21114598/importing-a-text-file-into-r
theUrl <- "/Users/scottkarr/IS607Spring2016/project1/tournamentinfo.txt"
l <- readLines(theUrl)## Warning in readLines(theUrl): incomplete final line found on '/Users/
## scottkarr/IS607Spring2016/project1/tournamentinfo.txt'remove unnecessary lines
l <- grep("^\\|?-+\\|?$|^$", l, value = TRUE, invert = TRUE)split
lsplit <- strsplit(l, "\\s*\\|")set names
dat <- setNames(data.frame(do.call(rbind, lsplit[-1])[ ,-1]), paste(lsplit[[1]],lsplit[[2]])[-1])## Warning in (function (..., deparse.level = 1) : number of columns of result
## is not a multiple of vector length (arg 2)add back last column name
colnames(dat)[10] <- "Pair Num"1st 2 rows were combined for header so remove row 1 which is still left
dat <- dat[-c(1), ]convert list to data frame
df1 <- data.frame(dat)subset child and parent recs
df1[,"IsChildRec"] <- str_detect(df1[,1],"[[:digit:]]{1,}")
df1.Csub <- subset(df1,df1$IsChildRec == TRUE )
df1.Psub <- subset(df1,df1$IsChildRec == FALSE )
colnames(df1.Psub)[1] <- "Name"
colnames(df1.Csub)[1] <- "Name" build output dataframe
df1.Output <- data.frame(df1.Psub$Pair.Num)
colnames(df1.Output)[1] <- "ID"
df1.Output["Name"] <- df1.Psub$Name
df1.Output["State"] <- df1.Csub$Pair.Num
df1.Output["Ttl-Pts"] <- df1.Psub$Total..Pts
df1.Output["Pre-Rating"] <- str_trim(str_extract(str_trim(df1.Csub$Name), "[:blank:][:digit:]{1,4}"))
df1.Output["Opp1"] <- as.numeric(str_extract(df1.Psub$Round...1, "[:digit:]{1,}$"))
df1.Output["Opp2"] <- as.numeric(str_extract(df1.Psub$Round...2, "[:digit:]{1,}$"))
df1.Output["Opp3"] <- as.numeric(str_extract(df1.Psub$Round...3, "[:digit:]{1,}$"))
df1.Output["Opp4"] <- as.numeric(str_extract(df1.Psub$Round...4, "[:digit:]{1,}$"))
df1.Output["Opp5"] <- as.numeric(str_extract(df1.Psub$Round...5, "[:digit:]{1,}$"))
df1.Output["Opp6"] <- as.numeric(str_extract(df1.Psub$Round...6, "[:digit:]{1,}$"))
df1.Output["Opp7"] <- as.numeric(str_extract(df1.Psub$Round...7, "[:digit:]{1,}$"))Last derived column uses lapply to scan each row and apply dplyr to filter indexed data point (scores). While lapply is perhaps more direct then nested loops, I’m uncomfortable with it. Too much indirection. Should be able to collapse the hardcoded column indexes as well, but for another time.
df1.Output["AvgOppScore"] <-
unlist(
lapply(
1:nrow(df1.Output),
function(i) {
mean(
c(
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,6]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,7]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,8]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,9]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,10]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,11]+1)[5]),
as.numeric(dplyr::filter(df1.Output, as.numeric(ID) == df1.Output[i,12]+1)[5])
),
na.rm = TRUE
)
}
)
) remove opponent id references
df1.Output <- df1.Output[-c(6:12)]
df1.Output## ID Name State Ttl-Pts Pre-Rating AvgOppScore
## 1 1 GARY HUA ON 6.0 1794 1605.286
## 2 2 DAKSHESH DARURI MI 6.0 1553 1469.286
## 3 3 ADITYA BAJAJ MI 6.0 1384 1563.571
## 4 4 PATRICK H SCHILLING MI 5.5 1716 1573.571
## 5 5 HANSHI ZUO MI 5.5 1655 1500.857
## 6 6 HANSEN SONG OH 5.0 1686 1518.714
## 7 7 GARY DEE SWATHELL MI 5.0 1649 1372.143
## 8 8 EZEKIEL HOUGHTON MI 5.0 1641 1468.429
## 9 9 STEFANO LEE ON 5.0 1411 1523.143
## 10 10 ANVIT RAO MI 5.0 1365 1554.143
## 11 11 CAMERON WILLIAM MC LEMAN MI 4.5 1712 1467.571
## 12 12 KENNETH J TACK MI 4.5 1663 1506.167
## 13 13 TORRANCE HENRY JR MI 4.5 1666 1497.857
## 14 14 BRADLEY SHAW MI 4.5 1610 1515.000
## 15 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1483.857
## 16 16 MIKE NIKITIN MI 4.0 1604 1385.800
## 17 17 RONALD GRZEGORCZYK MI 4.0 1629 1498.571
## 18 18 DAVID SUNDEEN MI 4.0 1600 1480.000
## 19 19 DIPANKAR ROY MI 4.0 1564 1426.286
## 20 20 JASON ZHENG MI 4.0 1595 1410.857
## 21 21 DINH DANG BUI ON 4.0 1563 1470.429
## 22 22 EUGENE L MCCLURE MI 4.0 1555 1300.333
## 23 23 ALAN BUI ON 4.0 1363 1213.857
## 24 24 MICHAEL R ALDRICH MI 4.0 1229 1357.000
## 25 25 LOREN SCHWIEBERT MI 3.5 1745 1363.286
## 26 26 MAX ZHU ON 3.5 1579 1506.857
## 27 27 GAURAV GIDWANI MI 3.5 1552 1221.667
## 28 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1522.143
## 29 29 CHIEDOZIE OKORIE MI 3.5 1602 1313.500
## 30 30 GEORGE AVERY JONES ON 3.5 1522 1144.143
## 31 31 RISHI SHETTY MI 3.5 1494 1259.857
## 32 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 1378.714
## 33 33 JADE GE MI 3.5 1449 1276.857
## 34 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1375.286
## 35 35 JOSHUA DAVID LEE MI 3.5 1438 1149.714
## 36 36 SIDDHARTH JHA MI 3.5 1355 1388.167
## 37 37 AMIYATOSH PWNANANDAM MI 3.5 980 1384.800
## 38 38 BRIAN LIU MI 3.0 1423 1539.167
## 39 39 JOEL R HENDON MI 3.0 1436 1429.571
## 40 40 FOREST ZHANG MI 3.0 1348 1390.571
## 41 41 KYLE WILLIAM MURPHY MI 3.0 1403 1248.500
## 42 42 JARED GE MI 3.0 1332 1149.857
## 43 43 ROBERT GLEN VASEY MI 3.0 1283 1106.571
## 44 44 JUSTIN D SCHILLING MI 3.0 1199 1327.000
## 45 45 DEREK YAN MI 3.0 1242 1152.000
## 46 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1357.714
## 47 47 ERIC WRIGHT MI 2.5 1362 1392.000
## 48 48 DANIEL KHAIN MI 2.5 1382 1355.800
## 49 49 MICHAEL J MARTIN MI 2.5 1291 1285.800
## 50 50 SHIVAM JHA MI 2.5 1056 1296.000
## 51 51 TEJAS AYYAGARI MI 2.5 1011 1356.143
## 52 52 ETHAN GUO MI 2.5 935 1494.571
## 53 53 JOSE C YBARRA MI 2.0 1393 1345.333
## 54 54 LARRY HODGE MI 2.0 1270 1206.167
## 55 55 ALEX KONG MI 2.0 1186 1406.000
## 56 56 MARISA RICCI MI 2.0 1153 1414.400
## 57 57 MICHAEL LU MI 2.0 1092 1363.000
## 58 58 VIRAJ MOHILE MI 2.0 917 1391.000
## 59 59 SEAN M MC CORMICK MI 2.0 853 1319.000
## 60 60 JULIA SHEN MI 1.5 967 1330.200
## 61 61 JEZZEL FARKAS ON 1.5 955 1327.286
## 62 62 ASHWIN BALAJI MI 1.0 1530 1186.000
## 63 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1350.200
## 64 64 BEN LI MI 1.0 1163 1263.000Export to .csv to your current working directory
write.csv(df1.Output, file = "tournamentinfo.csv")