options(repos = c(CRAN = "https://cran.rstudio.com"))req_packages <- c("DBI","RMySQL","dplyr","dbplyr","knitr","tidyr", "readr", "stringr","tibble", "rmarkdown", "purrr", "lubridate", "here", "httr2", "RCurl")
for (pkg in req_packages) {
if (!require(pkg, character.only = TRUE)) {
message(paste("Installing package:", pkg))
install.packages(pkg, dependencies = TRUE)
} else {
message(paste(pkg, " already installed."))
}
library(pkg, character.only = TRUE)
}## Loading required package: DBI## DBI already installed.## Loading required package: RMySQL## RMySQL already installed.## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## dplyr already installed.## Loading required package: dbplyr##
## Attaching package: 'dbplyr'## The following objects are masked from 'package:dplyr':
##
## ident, sql## dbplyr already installed.## Loading required package: knitr## knitr already installed.## Loading required package: tidyr## tidyr already installed.## Loading required package: readr## readr already installed.## Loading required package: stringr## stringr already installed.## Loading required package: tibble## tibble already installed.## Loading required package: rmarkdown## rmarkdown already installed.## Loading required package: purrr## purrr already installed.## Loading required package: lubridate##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union## lubridate already installed.## Loading required package: here## here() starts at /Users/paulabrown/Documents/CUNY SPS- Data 607/Week 5 Assignments## here already installed.## Loading required package: httr2## httr2 already installed.## Loading required package: RCurl##
## Attaching package: 'RCurl'## The following object is masked from 'package:tidyr':
##
## complete## RCurl already installed.This step will check if the raw data from the “tournamentinfo.txt” file exists in my GitHub repository and then reads the lines in the file if it does exist. Otherwise, a message “File not found at the specified GitHub URL” is displayed.
url <- "https://raw.githubusercontent.com/PaulaB989/data/main/tournamentinfo.txt"
if (RCurl::url.exists(url)) {
file_lines <- readLines(url)
} else {
stop("File not found at the specified GitHub URL.")
}## Warning in readLines(url): incomplete final line found on
## 'https://raw.githubusercontent.com/PaulaB989/data/main/tournamentinfo.txt'This is one example of regex use in this project (“^\s*\d+\s\|“)
#Grab lines that start with a player number and contains chess match data.
# ^ = start of line
# \\s* = optional whitespace
# \\d+ = 1 or more digits (player number)
# \\s\\| = space followed by a pipe ("|")
player_lines <- file_lines[str_detect(file_lines, "^\\s*\\d+\\s\\|")]
# Grab lines that start with a state abbreviation and contains player info like pre-rating
# ^ = start of line
# \\s* = optional whitespace
# [A-Z]{2} = 2 capital letters (State abbreviation, i.e. OH, NY, etc...)
# \\s\\| = space followed by a pipe ("|")
state_lines <- file_lines[str_detect(file_lines, "^\\s*[A-Z]{2}\\s\\|")]chessplayer_df <- tibble(
name = str_trim(str_sub(player_lines, 8, 38)),
points = as.numeric(str_trim(str_sub(player_lines, 42, 44))),
opponents = str_extract_all(player_lines, "\\d{1,2}(?=\\|)")
# "\\d{1,2}(?=\\|)" = one or two digits followed by pipe character ("|") using a 'lookahead'("(?=\\|)") - what comes after current position.
)playerstaterating_df <- tibble(
state = str_trim(str_sub(state_lines, 4, 5)),
pre_rating = as.numeric(str_extract(state_lines, "(?<=R: )\\s?\\d+"))
# "(?<=R: )" = a positive lookbehind (what came before current position). It matches a position in the string that is preceded by the exact text "R: " — but it doesn't include "R: " in the match result.
# "\\s?" = optional space ** The 3 digit pre-ratings has an additional space after "R: " without using "\\s?" the pre-rating values for those lines returns "NA".
# "\\d+" = matches one or more digits (0–9). The double backslash is used in R to escape the backslash in strings.
)chessplayer_df <- bind_cols(chessplayer_df, playerstaterating_df)# Build lookup table of player number to pre-rating
player_numbers <- str_extract(player_lines, "^\\s*\\d+")
rating_lookup <- tibble(
number = as.integer(player_numbers),
rating = playerstaterating_df$pre_rating
)chessplayer_df <- chessplayer_df %>%
mutate(
opponent_nums = str_extract_all(player_lines, "\\d{1,2}(?=\\|)"),
opponent_ratings = lapply(opponent_nums, function(nums) {
nums <- as.integer(nums)
mean(rating_lookup$rating[match(nums, rating_lookup$number)], na.rm = TRUE)
}),
avg_opponent_rating = round(unlist(opponent_ratings), 0)
) %>%
select(name, state, points, pre_rating, avg_opponent_rating)chessplayer_df <- chessplayer_df %>%
mutate(
expected_score = round(1 / (1 + 10^((avg_opponent_rating - pre_rating) / 400)), 2),
performance_diff = round(points - expected_score, 2)
)# Top 5 overperformers
top_overperformers <- chessplayer_df %>%
arrange(desc(performance_diff)) %>%
slice_head(n = 5)
top_overperformers## # A tibble: 5 × 7
## name state points pre_rating avg_opponent_rating expected_score
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ADITYA BAJAJ MI 6 1384 1564 0.26
## 2 DAKSHESH DARURI MI 6 1553 1469 0.62
## 3 GARY HUA ON 6 1794 1605 0.75
## 4 PATRICK H SCHILLING MI 5.5 1716 1574 0.69
## 5 HANSHI ZUO MI 5.5 1655 1501 0.71
## # ℹ 1 more variable: performance_diff <dbl># Top 5 underperformers
top_underperformers <- chessplayer_df %>%
arrange(performance_diff) %>%
slice_head(n = 5)
top_underperformers## # A tibble: 5 × 7
## name state points pre_rating avg_opponent_rating expected_score
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ASHWIN BALAJI MI 1 1530 1186 0.88
## 2 BEN LI MI 1 1163 1263 0.36
## 3 THOMAS JOSEPH HOSM… MI 1 1175 1350 0.27
## 4 JULIA SHEN MI 1.5 967 1330 0.11
## 5 JEZZEL FARKAS ON 1.5 955 1327 0.11
## # ℹ 1 more variable: performance_diff <dbl>write_csv(chessplayer_df, here::here("tournament_results.csv"))
# "here::here" = helps you build file paths that are robust and reproducible, especially in R projects.chessplayer_df <- read_csv(here("tournament_results.csv"))## Rows: 64 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): name, state
## dbl (5): points, pre_rating, avg_opponent_rating, expected_score, performanc...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.##Summarize the data in the .csv file
knitr::kable(chessplayer_df)| name | state | points | pre_rating | avg_opponent_rating | expected_score | performance_diff |
|---|---|---|---|---|---|---|
| GARY HUA | ON | 6.0 | 1794 | 1605 | 0.75 | 5.25 |
| DAKSHESH DARURI | MI | 6.0 | 1553 | 1469 | 0.62 | 5.38 |
| ADITYA BAJAJ | MI | 6.0 | 1384 | 1564 | 0.26 | 5.74 |
| PATRICK H SCHILLING | MI | 5.5 | 1716 | 1574 | 0.69 | 4.81 |
| HANSHI ZUO | MI | 5.5 | 1655 | 1501 | 0.71 | 4.79 |
| HANSEN SONG | OH | 5.0 | 1686 | 1519 | 0.72 | 4.28 |
| GARY DEE SWATHELL | MI | 5.0 | 1649 | 1372 | 0.83 | 4.17 |
| EZEKIEL HOUGHTON | MI | 5.0 | 1641 | 1468 | 0.73 | 4.27 |
| STEFANO LEE | ON | 5.0 | 1411 | 1523 | 0.34 | 4.66 |
| ANVIT RAO | MI | 5.0 | 1365 | 1554 | 0.25 | 4.75 |
| CAMERON WILLIAM MC LEMAN | MI | 4.5 | 1712 | 1468 | 0.80 | 3.70 |
| KENNETH J TACK | MI | 4.5 | 1663 | 1506 | 0.71 | 3.79 |
| TORRANCE HENRY JR | MI | 4.5 | 1666 | 1498 | 0.72 | 3.78 |
| BRADLEY SHAW | MI | 4.5 | 1610 | 1515 | 0.63 | 3.87 |
| ZACHARY JAMES HOUGHTON | MI | 4.5 | 1220 | 1484 | 0.18 | 4.32 |
| MIKE NIKITIN | MI | 4.0 | 1604 | 1386 | 0.78 | 3.22 |
| RONALD GRZEGORCZYK | MI | 4.0 | 1629 | 1499 | 0.68 | 3.32 |
| DAVID SUNDEEN | MI | 4.0 | 1600 | 1480 | 0.67 | 3.33 |
| DIPANKAR ROY | MI | 4.0 | 1564 | 1426 | 0.69 | 3.31 |
| JASON ZHENG | MI | 4.0 | 1595 | 1411 | 0.74 | 3.26 |
| DINH DANG BUI | ON | 4.0 | 1563 | 1470 | 0.63 | 3.37 |
| EUGENE L MCCLURE | MI | 4.0 | 1555 | 1300 | 0.81 | 3.19 |
| ALAN BUI | ON | 4.0 | 1363 | 1214 | 0.70 | 3.30 |
| MICHAEL R ALDRICH | MI | 4.0 | 1229 | 1357 | 0.32 | 3.68 |
| LOREN SCHWIEBERT | MI | 3.5 | 1745 | 1363 | 0.90 | 2.60 |
| MAX ZHU | ON | 3.5 | 1579 | 1507 | 0.60 | 2.90 |
| GAURAV GIDWANI | MI | 3.5 | 1552 | 1222 | 0.87 | 2.63 |
| SOFIA ADINA STANESCU-BELLU | MI | 3.5 | 1507 | 1522 | 0.48 | 3.02 |
| CHIEDOZIE OKORIE | MI | 3.5 | 1602 | 1314 | 0.84 | 2.66 |
| GEORGE AVERY JONES | ON | 3.5 | 1522 | 1144 | 0.90 | 2.60 |
| RISHI SHETTY | MI | 3.5 | 1494 | 1260 | 0.79 | 2.71 |
| JOSHUA PHILIP MATHEWS | ON | 3.5 | 1441 | 1379 | 0.59 | 2.91 |
| JADE GE | MI | 3.5 | 1449 | 1277 | 0.73 | 2.77 |
| MICHAEL JEFFERY THOMAS | MI | 3.5 | 1399 | 1375 | 0.53 | 2.97 |
| JOSHUA DAVID LEE | MI | 3.5 | 1438 | 1150 | 0.84 | 2.66 |
| SIDDHARTH JHA | MI | 3.5 | 1355 | 1388 | 0.45 | 3.05 |
| AMIYATOSH PWNANANDAM | MI | 3.5 | 980 | 1385 | 0.09 | 3.41 |
| BRIAN LIU | MI | 3.0 | 1423 | 1539 | 0.34 | 2.66 |
| JOEL R HENDON | MI | 3.0 | 1436 | 1430 | 0.51 | 2.49 |
| FOREST ZHANG | MI | 3.0 | 1348 | 1391 | 0.44 | 2.56 |
| KYLE WILLIAM MURPHY | MI | 3.0 | 1403 | 1248 | 0.71 | 2.29 |
| JARED GE | MI | 3.0 | 1332 | 1150 | 0.74 | 2.26 |
| ROBERT GLEN VASEY | MI | 3.0 | 1283 | 1107 | 0.73 | 2.27 |
| JUSTIN D SCHILLING | MI | 3.0 | 1199 | 1327 | 0.32 | 2.68 |
| DEREK YAN | MI | 3.0 | 1242 | 1152 | 0.63 | 2.37 |
| JACOB ALEXANDER LAVALLEY | MI | 3.0 | 377 | 1358 | 0.00 | 3.00 |
| ERIC WRIGHT | MI | 2.5 | 1362 | 1392 | 0.46 | 2.04 |
| DANIEL KHAIN | MI | 2.5 | 1382 | 1356 | 0.54 | 1.96 |
| MICHAEL J MARTIN | MI | 2.5 | 1291 | 1286 | 0.51 | 1.99 |
| SHIVAM JHA | MI | 2.5 | 1056 | 1296 | 0.20 | 2.30 |
| TEJAS AYYAGARI | MI | 2.5 | 1011 | 1356 | 0.12 | 2.38 |
| ETHAN GUO | MI | 2.5 | 935 | 1495 | 0.04 | 2.46 |
| JOSE C YBARRA | MI | 2.0 | 1393 | 1345 | 0.57 | 1.43 |
| LARRY HODGE | MI | 2.0 | 1270 | 1206 | 0.59 | 1.41 |
| ALEX KONG | MI | 2.0 | 1186 | 1406 | 0.22 | 1.78 |
| MARISA RICCI | MI | 2.0 | 1153 | 1414 | 0.18 | 1.82 |
| MICHAEL LU | MI | 2.0 | 1092 | 1363 | 0.17 | 1.83 |
| VIRAJ MOHILE | MI | 2.0 | 917 | 1391 | 0.06 | 1.94 |
| SEAN M MC CORMICK | MI | 2.0 | 853 | 1319 | 0.06 | 1.94 |
| JULIA SHEN | MI | 1.5 | 967 | 1330 | 0.11 | 1.39 |
| JEZZEL FARKAS | ON | 1.5 | 955 | 1327 | 0.11 | 1.39 |
| ASHWIN BALAJI | MI | 1.0 | 1530 | 1186 | 0.88 | 0.12 |
| THOMAS JOSEPH HOSMER | MI | 1.0 | 1175 | 1350 | 0.27 | 0.73 |
| BEN LI | MI | 1.0 | 1163 | 1263 | 0.36 | 0.64 |
# kable() = creates a nicely formatted table from a data frame or tibble. readRenviron("~/Documents/CUNY SPS- Data 607/Week 2A Assignment/.Renviron")
databaseconnect <- dbConnect(
RMySQL::MySQL(),
host = Sys.getenv("DB3_HOST"),
port = as.integer(Sys.getenv("DB3_PORT")),
user = Sys.getenv("DB3_USER"),
password = Sys.getenv("DB3_PASSWORD")
)
dbExecute(databaseconnect, "CREATE DATABASE IF NOT EXISTS Chess_Tournament")## [1] 1dbDisconnect(databaseconnect)## [1] TRUEreadRenviron("~/Documents/CUNY SPS- Data 607/Week 2A Assignment/.Renviron")
newDB <- dbConnect(
RMySQL::MySQL(),
dbname = Sys.getenv("DB3_NAME"),
host = Sys.getenv("DB3_HOST"),
port = as.integer(Sys.getenv("DB3_PORT")),
user = Sys.getenv("DB3_USER"),
password = Sys.getenv("DB3_PASSWORD"),
client.flag = CLIENT_LOCAL_FILES
)dbWriteTable(newDB, "tournament_results", chessplayer_df, row.names = FALSE, overwrite = TRUE)## [1] TRUEdbListTables(newDB)## [1] "tournament_results"dbGetQuery(newDB, "SELECT * FROM tournament_results")## name state points pre_rating avg_opponent_rating
## 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
## expected_score performance_diff
## 1 0.75 5.25
## 2 0.62 5.38
## 3 0.26 5.74
## 4 0.69 4.81
## 5 0.71 4.79
## 6 0.72 4.28
## 7 0.83 4.17
## 8 0.73 4.27
## 9 0.34 4.66
## 10 0.25 4.75
## 11 0.80 3.70
## 12 0.71 3.79
## 13 0.72 3.78
## 14 0.63 3.87
## 15 0.18 4.32
## 16 0.78 3.22
## 17 0.68 3.32
## 18 0.67 3.33
## 19 0.69 3.31
## 20 0.74 3.26
## 21 0.63 3.37
## 22 0.81 3.19
## 23 0.70 3.30
## 24 0.32 3.68
## 25 0.90 2.60
## 26 0.60 2.90
## 27 0.87 2.63
## 28 0.48 3.02
## 29 0.84 2.66
## 30 0.90 2.60
## 31 0.79 2.71
## 32 0.59 2.91
## 33 0.73 2.77
## 34 0.53 2.97
## 35 0.84 2.66
## 36 0.45 3.05
## 37 0.09 3.41
## 38 0.34 2.66
## 39 0.51 2.49
## 40 0.44 2.56
## 41 0.71 2.29
## 42 0.74 2.26
## 43 0.73 2.27
## 44 0.32 2.68
## 45 0.63 2.37
## 46 0.00 3.00
## 47 0.46 2.04
## 48 0.54 1.96
## 49 0.51 1.99
## 50 0.20 2.30
## 51 0.12 2.38
## 52 0.04 2.46
## 53 0.57 1.43
## 54 0.59 1.41
## 55 0.22 1.78
## 56 0.18 1.82
## 57 0.17 1.83
## 58 0.06 1.94
## 59 0.06 1.94
## 60 0.11 1.39
## 61 0.11 1.39
## 62 0.88 0.12
## 63 0.27 0.73
## 64 0.36 0.64