olympic <- read.csv("2024_US_Olympic.csv", stringsAsFactors = FALSE)
#Ensure required columns
req <- c("First_Name","Last_Name","Gender","Hometown_City","Hometown_State","Sport","Event")
for (nm in req) if (!nm %in% names(olympic)) olympic[[nm]] <- NA_character_
#Trim extra spaces in first and last name columns
olympic$First_Name <- gsub("^\\s+|\\s+$", "", olympic$First_Name)
olympic$Last_Name <- gsub("^\\s+|\\s+$", "", olympic$Last_Name)
head(olympic, 5)## First_Name Last_Name Sport Hometown_City Hometown_State
## 1 BRADY ELLISON Archery Billings Montana
## 2 CATALINA GNORIEGA Archery San Diego California
## 3 CASEY KAUFHOLD Archery Lancaster Pennsylvania
## 4 JENNIFER MUCINO-FERNANDEZ Archery Chula Vista California
## 5 ANITA ALVAREZ Artistic Swimming Buffalo New York
## Gender Event
## 1 Male Men's Individual
## 2 Female Women's Individual, Women's Team
## 3 Female Women's Individual, Women's Team
## 4 Female Women's Individual, Women's Team
## 5 Female TeamVOWELS <- "AEIOUaeiou"
CONSONANTS <- "BCDFGHJKLMNPQRSTVWXYZbcdfghjklmnpqrstvwxyz"
starts_with_vowel <- function(x) grepl(paste0("^[", VOWELS, "]"), x)
ends_with_vowel <- function(x) grepl(paste0("[", VOWELS, "]$"), x)
is_letters_only_one_word <- function(x) grepl("^[A-Za-z]+$", x)
attach(olympic)#Question 1: There are 100 first names that begin with a vowel. Women are more likely to have a first name with a vowel.
is_vowel_start <- starts_with_vowel(First_Name)
# Total of first names that begin with a vowel
sum(is_vowel_start, na.rm = TRUE)## [1] 100# One-way frequency table (gender among those names)
table(Gender[is_vowel_start])##
## Female Male
## 71 29#Question 2: There are 211 first names that end with a vowel. Women are more likely to have a first name that ends with a vowel.
is_vowel_end <- ends_with_vowel(First_Name)
# Total
sum(is_vowel_end, na.rm = TRUE)## [1] 211# Frequency table by gender
table(Gender[is_vowel_end])##
## Female Male
## 174 37#Question 3: There are 31 first names that are not typical.
is_typical_first <- is_letters_only_one_word(First_Name)
# Count
sum(!is_typical_first & !is.na(First_Name))## [1] 31# Show all of the unique non-typical names
head(unique(First_Name[!is_typical_first]), 31)## [1] "A'JA" "JOSHUA TIMOTHY" "MARIA CELIA"
## [4] "KATELYN MORGAN" "RYLAN WILLIAM" "ADA CLAUDIA"
## [7] "HENRY TURNER" "DERRICK SCOTT" "RYANN PAIGE"
## [10] "CONNER LYNN" "AUSTEN JEWELL" "RACHEL LEIGHANNE"
## [13] "MARY CAROLYNN" "DANIA JO" "JOHN JOHN"
## [16] "AALIYAH NICKOLE" "JAMES ANDRES" "JEREMIAH JASHON"
## [19] "ANNETTE NNEKA" "JASMINE MARI" "BRYNN TAYLOR"
## [22] "MONAE'" "SHA'CARRI" "GRACE ELIZABETH"
## [25] "PARKER ALYS" "ISABELLA MARIE" "QUINCY ALEXANDER"
## [28] "NICOLAS MACPHERSON" "EMILY MARY" "CHASE WILLIAM"
## [31] "JENNA MICHELLE"#Question 4:The first name that starts with Z/ZH and ends with Y is Zachary. There are no first names that have more than three vowels in a row or five consonants in a row.
FN_UP <- toupper(First_Name)
# Z / ZH ... Y
head(unique(First_Name[grepl("^Z(H)?", FN_UP) & grepl("Y$", FN_UP)]), 5)## [1] "ZACHERY"# >3 vowels in a row
head(unique(First_Name[grepl("[AEIOUaeiou]{4,}", First_Name)]), 5)## character(0)# >5 consonants in a row
head(unique(First_Name[grepl(paste0("[", CONSONANTS, "]{6,}"), First_Name)]), 5)## character(0)#Question 5: There are 18 last names that are not typical.
is_typical_last <- is_letters_only_one_word(Last_Name)
# Count
sum(!is_typical_last & !is.na(Last_Name))## [1] 18# Show all unique non-typical last names
head(unique(Last_Name[!is_typical_last]), 18)## [1] "MUCINO-FERNANDEZ" "VAN LITH" "GUZZI VINCENTI"
## [4] "MAZZIO-MANSON" "O'CONNOR" "FUALA'AU"
## [7] "DALLMAN-WEISS" "NEWBERRY MOORE" "DAVIS-WOODHALL"
## [10] "KELATI-FREZGHI" "MALONE-HARDIN" "MCLAUGHLIN-LEVRONE"
## [13] "O'KEEFFE" "ST. PIERRE" "JENDRYK II"
## [16] "MA'A" "WONG-ORANTES" "THEISEN LAPPEN"#Question 6: The last names that end with TH are Van Lith, Kloth, Leibfarth, Hollingsworth, and Smith. The last name that ends with ZH is Zhang.
LN_UP <- toupper(Last_Name)
# Ends with TH
head(unique(Last_Name[grepl("TH$", LN_UP)]), 5) ## [1] "VAN LITH" "KLOTH" "LEIBFARTH" "HOLLINGSWORTH"
## [5] "SMITH"# Starts with ZH
head(unique(Last_Name[grepl("^ZH", LN_UP)]), 5) ## [1] "ZHANG"#Question 7: The first five full names are Brady Ellison, Catalina Gnoriega, Casey Kaufhold, Jennifer Mucino-fernandez, and Anita Alvarez.
first_fixed <- paste0(toupper(substr(First_Name,1,1)), tolower(substring(First_Name,2)))
last_fixed <- paste0(toupper(substr(Last_Name,1,1)), tolower(substring(Last_Name,2)))
head(paste(first_fixed, last_fixed), 5)## [1] "Brady Ellison" "Catalina Gnoriega"
## [3] "Casey Kaufhold" "Jennifer Mucino-fernandez"
## [5] "Anita Alvarez"#Question 8: There are 2 athletes who whose hometown city has more than 20 characters in the city name.
sum(nchar(Hometown_City) > 20, na.rm = TRUE)## [1] 2#Question 9: There are 11 athletes whose hometown city has 3 or more words in the city name.
sum(lengths(strsplit(Hometown_City, "\\s+")) >= 3, na.rm = TRUE)## [1] 11#Question 10:
has_paren <- grepl("\\(", Sport) & grepl("\\)", Sport)
# Original frequency
table(Sport[has_paren])##
## Basketball (3x3) Basketball (5x5) BMX (Freestyle)
## 8 24 4
## BMX (Racing) Cycling (Mountain Bike)
## 5 4# Convert "Name (Type)" -> "(Type) Name"
swapped <- Sport
swapped[has_paren] <- sub("^\\s*(.*?)\\s*\\((.*?)\\)\\s*$", "(\\2) \\1", Sport[has_paren])
# First 5 only
head(data.frame(original = Sport[has_paren],
converted = swapped[has_paren]), 5)## original converted
## 1 Basketball (3x3) (3x3) Basketball
## 2 Basketball (3x3) (3x3) Basketball
## 3 Basketball (3x3) (3x3) Basketball
## 4 Basketball (3x3) (3x3) Basketball
## 5 Basketball (3x3) (3x3) Basketball# Table
table(swapped[has_paren])##
## (3x3) Basketball (5x5) Basketball (Freestyle) BMX
## 8 24 4
## (Mountain Bike) Cycling (Racing) BMX
## 4 5#Question 11: There are 101 total number of athletes in team events.
team_sports <- c("Basketball","Field Hockey","Rugby","Soccer")
# Search
is_team_word <- grepl("Team", Event, ignore.case = TRUE, useBytes = TRUE)
# Find exact match
is_gender_only <- (Event == "Male" | Event == "Female" | Event == "male" | Event == "female")
is_team_sport <- Sport %in% team_sports
is_team_event <- is_team_word | (is_gender_only & is_team_sport)
sum(is_team_event, na.rm = TRUE)## [1] 101