# load data in
data = readLines('tournamentinfo.txt')
## Warning in readLines("tournamentinfo.txt"): incomplete final line found on
## 'tournamentinfo.txt'
# get rid of the long sets of dashes
dashes = "-----------------------------------------------------------------------------------------"
# make whitespace more manageable
data = setdiff(data, dashes)
data = str_replace_all(data, "[ ]{2,}", "")
# consecutive rows are about same person
# split consecutive rows
df1 = data[c(TRUE, FALSE)]
df2 = data[c(FALSE, TRUE)]
# (?=|) grabs upto the right "|" symbol
# get names
names = trimws(str_extract_all(tail(df1,-1), "[A-Z- ]{2,}(?=|)"))
# get state
states = trimws(str_extract_all(tail(df2,-1), "[A-Z]{2}(?=|)"))
# get points
points = trimws(str_extract_all(tail(df1,-1), "[0-9].[0-9](?=|)"))
# get prerating
prerating = trimws(str_extract(tail(df2,-1), "[0-9]+(?=P|-)"))
fdf = as.data.frame(cbind(names, states, points, prerating))
fdf$points = as.numeric(as.character(fdf$points))
fdf$prerating = as.numeric(as.character(fdf$prerating))
# get avg_opp_pre
# need ratings of opponents played and how many games played
opp_ids = str_extract_all(tail(df1,-1), "(?<=[A-Z])[0-9]+(?=|)")
games_played = lengths(opp_ids)
opp_ids = lapply(opp_ids, as.numeric)
sums = c()
for(i in 1:length(opp_ids)) {
p_row = unlist(opp_ids[i])
p_sum = sum(fdf$prerating[p_row])
sums[i] = p_sum
}
avg_opp_pre = sums/games_played
fdf$avg_opp_pre = avg_opp_pre
fdf
## names states points prerating avg_opp_pre
## 1 GARY HUA ON 6.0 1794 1605.286
## 2 DAKSHESH DARURI MI 6.0 1553 1469.286
## 3 ADITYA BAJAJ MI 6.0 1384 1563.571
## 4 PATRICK H SCHILLING MI 5.5 1716 1573.571
## 5 HANSHI ZUO MI 5.5 1655 1500.857
## 6 HANSEN SONG OH 5.0 1686 1518.714
## 7 GARY DEE SWATHELL MI 5.0 1649 1372.143
## 8 EZEKIEL HOUGHTON MI 5.0 1641 1468.429
## 9 STEFANO LEE ON 5.0 1411 1523.143
## 10 ANVIT RAO MI 5.0 1365 1554.143
## 11 CAMERON WILLIAM MC LEMAN MI 4.5 1712 1467.571
## 12 KENNETH J TACK MI 4.5 1663 1506.167
## 13 TORRANCE HENRY JR MI 4.5 1666 1497.857
## 14 BRADLEY SHAW MI 4.5 1610 1515.000
## 15 ZACHARY JAMES HOUGHTON MI 4.5 1220 1483.857
## 16 MIKE NIKITIN MI 4.0 1604 1385.800
## 17 RONALD GRZEGORCZYK MI 4.0 1629 1498.571
## 18 DAVID SUNDEEN MI 4.0 1600 1480.000
## 19 DIPANKAR ROY MI 4.0 1564 1426.286
## 20 JASON ZHENG MI 4.0 1595 1410.857
## 21 DINH DANG BUI ON 4.0 1563 1470.429
## 22 EUGENE L MCCLURE MI 4.0 1555 1300.333
## 23 ALAN BUI ON 4.0 1363 1213.857
## 24 MICHAEL R ALDRICH MI 4.0 1229 1357.000
## 25 LOREN SCHWIEBERT MI 3.5 1745 1363.286
## 26 MAX ZHU ON 3.5 1579 1506.857
## 27 GAURAV GIDWANI MI 3.5 1552 1221.667
## 28 SOFIA ADINA STANESCU-BELLU MI 3.5 1507 1522.143
## 29 CHIEDOZIE OKORIE MI 3.5 1602 1313.500
## 30 GEORGE AVERY JONES ON 3.5 1522 1144.143
## 31 RISHI SHETTY MI 3.5 1494 1259.857
## 32 JOSHUA PHILIP MATHEWS ON 3.5 1441 1378.714
## 33 JADE GE MI 3.5 1449 1276.857
## 34 MICHAEL JEFFERY THOMAS MI 3.5 1399 1375.286
## 35 JOSHUA DAVID LEE MI 3.5 1438 1149.714
## 36 SIDDHARTH JHA MI 3.5 1355 1388.167
## 37 AMIYATOSH PWNANANDAM MI 3.5 980 1384.800
## 38 BRIAN LIU MI 3.0 1423 1539.167
## 39 JOEL R HENDON MI 3.0 1436 1429.571
## 40 FOREST ZHANG MI 3.0 1348 1390.571
## 41 KYLE WILLIAM MURPHY MI 3.0 1403 1248.500
## 42 JARED GE MI 3.0 1332 1149.857
## 43 ROBERT GLEN VASEY MI 3.0 1283 1106.571
## 44 JUSTIN D SCHILLING MI 3.0 1199 1327.000
## 45 DEREK YAN MI 3.0 1242 1152.000
## 46 JACOB ALEXANDER LAVALLEY MI 3.0 377 1357.714
## 47 ERIC WRIGHT MI 2.5 1362 1392.000
## 48 DANIEL KHAIN MI 2.5 1382 1355.800
## 49 MICHAEL J MARTIN MI 2.5 1291 1285.800
## 50 SHIVAM JHA MI 2.5 1056 1296.000
## 51 TEJAS AYYAGARI MI 2.5 1011 1356.143
## 52 ETHAN GUO MI 2.5 935 1494.571
## 53 JOSE C YBARRA MI 2.0 1393 1345.333
## 54 LARRY HODGE MI 2.0 1270 1206.167
## 55 ALEX KONG MI 2.0 1186 1406.000
## 56 MARISA RICCI MI 2.0 1153 1414.400
## 57 MICHAEL LU MI 2.0 1092 1363.000
## 58 VIRAJ MOHILE MI 2.0 917 1391.000
## 59 SEAN M MC CORMICK MI 2.0 853 1319.000
## 60 JULIA SHEN MI 1.5 967 1330.200
## 61 JEZZEL FARKAS ON 1.5 955 1327.286
## 62 ASHWIN BALAJI MI 1.0 1530 1186.000
## 63 THOMAS JOSEPH HOSMER MI 1.0 1175 1350.200
## 64 BEN LI MI 1.0 1163 1263.000
write.csv(fdf, 'tournament_info.csv')
# verify
df = read_csv('tournament_info.csv')
## Warning: Missing column names filled in: 'X1' [1]
## Parsed with column specification:
## cols(
## X1 = col_double(),
## names = col_character(),
## states = col_character(),
## points = col_double(),
## prerating = col_double(),
## avg_opp_pre = col_double()
## )
df
## # A tibble: 64 x 6
## X1 names states points prerating avg_opp_pre
## <dbl> <chr> <chr> <dbl> <dbl> <dbl>
## 1 1 GARY HUA ON 6 1794 1605.
## 2 2 DAKSHESH DARURI MI 6 1553 1469.
## 3 3 ADITYA BAJAJ MI 6 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 1686 1519.
## 7 7 GARY DEE SWATHELL MI 5 1649 1372.
## 8 8 EZEKIEL HOUGHTON MI 5 1641 1468.
## 9 9 STEFANO LEE ON 5 1411 1523.
## 10 10 ANVIT RAO MI 5 1365 1554.
## # … with 54 more rows