Data Analysis and Visualization - Midterm - Student answers

Unfortunately, you cannot see your answers at online.yildiz.edu.tr address. So this page shows your answers.

ogrenci_numarasi	question_no	verilen_cevap
17056010	Q1	No we cant determine how heavy the heaviest tennis player in the 2020 olympics is because data base ve use in this question does not have the data for 2020 olympics.İf we change our database or we import necesseriy datas for this question we can solve it using r language.
17056010	Q11	#İmporting our data olympics <- read.table(“https://zenodo.org/record/6803028/files/olympics.tsv”, header = TRUE, sep = “\t”)#We find height column and the tallest athlete datatallest_athlete <- olympics[which.max(olympics$Height),]#We print the name and height of the tallest athletecat(“The tallest athlete competing in the Olympic games was”, tallest_athlete$Name, “from”, tallest_athlete$NOC, “with a height of”, tallest_athlete$Height, “cm.”)The tallest competing athlete is Zhaoxu Zhang from China, with a height of 223 cm.
17056010	Q2	#İmporting our dataolympics <- read.table(“https://zenodo.org/record/6803028/files/olympics.tsv”, header = TRUE, sep = “\t”)#Filtering the data for most recent olympicsrecent_summer_olympics <- subset(olympics, Year == max(olympics$Year) & Season == “Summer”)# Find the lightest athlete using the “Weight” columnlightest_athlete <- recent_summer_olympics[which.min(recent_summer_olympics$Weight),]# Then we print the name and weight of athletecat(“The lightest athlete of the most recent Summer Olympics is”, lightest_athlete$Name, “from”, lightest_athlete$NOC, “with a weight of”, lightest_athlete$Weight, “kg.”)The lightest athlete of the most recent summer olympics is Nurislam Sanayev from Kaz with a weight of 48 kg.
17056010	Q6	First we import the datadata < - read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”,”, header = TRUE, sep = “\t”)İn gold medals section we find the sum of ittotal_gold_medals <- sum(olympics$Gold)We print the resultcat(“The total number of gold medals handed out in all games is:”, total_gold_medals)The total number of gold medals handed out in all games is: 10484
17056033	Q1	library(dplyr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")max_weight <- max(olympics$Weight, na.rm = TRUE)most_heavy_person <- olympics[olympics$Weight == max_weight, ]
17056033	Q13	olympics <- read.csv(“https://zenodo.org/record/6803028/files/olympics.tsv”, sep = “\t”)last_alphabetically <- olympics %>% filter(Season == “Summer” & Year == max(Year[Season == “Summer”])) %>% arrange(desc(strsplit(Athlete, “, “)[[1]][2])) %>% slice(1)last_alphabetically
17056033	Q14	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv”, sep=”\t”)most_participating_country <- olympics %>% group_by(Team) %>% summarise(total_participation = n()) %>% arrange(desc(total_participation)) %>% slice(1)most_participating_country
17056033	Q2	library(dplyr)library(readr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")lightest_athlete <- olympics %>% filter(Season == “Summer” & Year == max(Year[Season == “Summer”])) %>% arrange(Weight) %>% slice(1)lightest_athlete
17056033	Q8	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv”, sep = “\t”)medals_2018 <- olympics %>% filter(Year == 2018) %>% summarise(total_medals = sum(!is.na(Medal)))medals_2018$total_medals
1705A045	Q11	{r}library(tidyverse)library(dplyr)data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data %>%<br>select(name, height) %>%<br>na.omit() %>%<br>arrange(-height) %>%<br>slice(1) nameheight Adam Sandurski214
1705A045	Q14	{r}data %>%<br>count(team, sort = TRUE) %>%<br>slice(1)<br> teamn United States17286
1705A045	Q16	{r}library(gapminder)``````{r}gapminder %>%<br>select(country, gdpPercap) %>%<br>arrange(-gdpPercap) %>%<br>slice(1) countrygdpPercap Kuwait113523.1
1705A045	Q4	{r}library(tidyverse)library(dplyr)data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data %>%<br>select(name, height) %>%<br>na.omit() %>%<br>arrange(height) %>%<br>slice(1) nameheight Lyton Mphande127
1705A045	Q6	{r}data %>%<br>select(medal) %>%<br>na.omit() %>%<br>filter(medal == "Gold") %>%<br>count(medal, sort = TRUE) medaln Gold8110
1705A045	Q9	{r}data %>%<br>select(name,sex, height,sport, medal) %>%<br>na.omit() %>%<br>filter (sex == "F" ,<br><br> <br> <br> <br> <br>sport == "Badminton",<br> <br> <br> <br> <br>medal == "Gold") %>%<br>arrange(height) %>%<br>slice(1)namesexheightsportmedalSusy SusantiF161BadmintonGold
18056004	Q16	Hocam metin olarak ekleyemedim bu şekilde ekleemk zorundayım
18056004	Q2	library(dplyr) olympics <- read_tsv(“olympics.tsv”) recent_summer_olympics <- olympics %>% filter(Year == max(Year[!is.na(Year)]) & Season == “Summer”) lightest_athlete <- recent_summer_olympics[which.min(recent_summer_olympics$Weight),] cat(“The lightest athlete of the most recent Summer Olympics was”, lightest_athlete$Name, “with a weight of”, lightest_athlete$Weight, “kg.” I can not because “Unknown or uninitialised column: Light.”
18056004	Q21	Rumeysa Bağgül Data Vize SS.png
18056004	Q7	library(dplyr) olympics %>% filter(!is.na(Height), Height < 160, Medal == “Gold”, !grepl(“Team”, Sport)) %>% summarise(num_gold_medals = n())num_gold_medals 31
18056023	Q10	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(str_detect(games, “1964”)) %>% filter(team == “Denmark”) %>% mutate(avg_height = mean(height)) %>% relocate(avg_height, .after = name) answer: 175.913 and whole output:1699Tom Bogs175.913M194421 NovemberKøbenhavn (Copenhagen) (DEN) 1730Børge Krogh175.913M194218 AprilAalborg (DEN) 1755Hans-Erik Pedersen175.913M194310 DecemberVejle (DEN) 1760Preben Rasmussen175.913M194114 NovemberKøbenhavn (Copenhagen) (DEN) 9411Anni Werner-Hansen175.913F193921 JulyVig, Odsherred (DEN) 9412Birthe Lindskov Hansen175.913F19448 JuneHolstebro (DEN) 9412Birthe Lindskov Hansen175.913F19448 JuneHolstebro (DEN) 9433Erik Hansen175.913M193915 NovemberRanders (DEN) 14362Niels Fredborg175.913M194628 OctoberOdder (DEN) 14362Niels Fredborg175.913M194628 OctoberOdder (DEN)
18056023	Q11	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% arrange(desc(height))answer:59674Adam Sandurski214M19538 February
18056023	Q12	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% count(sport, games) %>% count(games) %>% arrange(desc(n))answer:2020 Summer Olympics38
18056023	Q16	{r}library(gapminder)gapminder %>%<br>filter(year == 1987) %>%<br>arrange(desc(gdpPercap))output:NorwayEurope198775.890418614731540.9748
18056023	Q4	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(str_detect(games, “Winter Olympics”)) %>% arrange(height) %>% relocate(height, .after = name)answer:81564Carolyn Krau137F194318 August
18056023	Q8	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(str_detect(games, “2018”)) %>% filter(!is.na(medal))answer:A tibble:383 × 17 , so the anwer is 383
18056031	Q10	data%>% filter(noc==“DEN”, games==“1964 Summer Olympics”) %>% filter(!is.na(height)) %>% summarise(avg= mean(height))176.0976
18056031	Q15	data %>%arrange(desc(games), desc(height)) %>% select(name, height, games) Gennaro Di Mauro2102020 Summer Olympics
18056031	Q19	code.png
18056031	Q2	data%>% arrange(desc(games)) %>% mutate(weight=parse_number(weight)) %>% arrange(weight)%>% select(name, weight) Choi Myong-Hui25
18056031	Q5	data%>% arrange(desc(games)) %>% count(games, noc)
18056031	Q7	data%>% filter(medal==“Gold”, height<160)
18056058	Q10	olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")denmark_1964 <- olympics %>% filter(year == 1964 & team == “Denmark”)avg_height <- denmark_1964 %>% summarise(mean_height = mean(height, na.rm = TRUE))avg_height$mean_height
18056058	Q11	olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")athletes <- olympics %>% filter(!is.na(height))tallest_athlete <- athletes %>% slice_max(height) tallest_athlete %>% select(name, sex, height)
18056058	Q18	library(gapminder)turkey_data <- filter(gapminder, country == “Turkey”)wealthiest_year <- filter(turkey_data, gdpPercap == max(gdpPercap))wealthiest_year# A tibble: 1 x 6 country continent year lifeExp pop gdpPercap 1 Turkey Europe 2013 76.2 75627384 19900.
18056058	Q3	olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")athletes <- olympics %>% filter(!is.na(height))shortest_athlete <- athletes %>% slice_min(height)shortest_athlete %>% select(name, sex, height, year, sport, team, games) # A tibble: 1 x 7 name sex height year sport team games 1 Rosario Briones F 127 2000 Gymnastics Mexico 2000 Summer
18056058	Q5	olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")last_olympics <- olympics %>% filter(year == 2016)num_countries <- last_olympics %>% distinct(NOC, .keep_all = TRUE) %>% count( )num_countries$n 180.5 cm
18056058	Q6	olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")total_gold_medals <- olympics %>% filter(medal == “Gold”) %>% count()total_gold_medals$n
18056066	Q13	—title: “R Notebook”output: html_notebook—{r}library(tidyverse)## Load File{r}fileurl = "https://zenodo.org/record/6803028/files/olympics.tsv"data = read_tsv(fileurl, show_col_types = FALSE)### Display first 5 observations{r}head(data)``````{r}### display column namescolnames(data)### Q1 {r}# first sort yearsrecent_data <- data %>%<br>arrange(desc(year))head(recent_data)Earliest year is 2020{r}# now find the athlet that comes lastrecent_data <- recent_data %>%<br>filter(year ==2020) %>%<br>arrange(name)tail(recent_data)Answer: “Žolt Peto”
18056066	Q17	{r}library(gapminder)#Q4{r}head(gapminder)``````{r}gapminder %>%<br>arrange(desc(gdpPercap))Answer: Kuwait
18056066	Q2	Q3{r}recent_data %>%<br>arrange(weight)Answer:100
18056066	Q9	Q2:{r}data %>%<br>filter(sport =="Badminton") %>%<br>filter (sex == "F") %>%<br>arrange(height)Answer:150
18056501	Q15	data %>% filter(games == max(games)) %>% arrange(height) Output: Name: Flávia SaraivaHeight: 133
18056501	Q17	data %>% filter(continent == “Asia”) %>% arrange(desc(gdpPercap)) Output: KuwaitAsia195758.03300212846113523.1329
18056501	Q2	data %>% filter(max(games)) %>% arrange(weight) Output:Jevgēņijs Borodavko
18056501	Q21	Ekran görüntüsü 2023-04-27 121339.png
18056501	Q5	data %>% filter(games == max(games)) %>% count(team) %>% nrow() Output: 250
18056501	Q6	data %>% filter(!is.na(medal)) %>% filter(medal == “Gold”) Output: 8110
18056501	Q9	data %>% filter(medal == “Gold”, sport == “Badminton”) %>% arrange(height) Output: 161
1805A007	Q1	library(olypics.stv)olympics 2020 ← olympics %>% filter(Year == 2020)tennis players ← olympics 2020 %>% filter(Sport == ‘’ Tennis’’)tennis players sorted ← tennis players %>% arrange(desc(Weight))
1805A007	Q11	library(olympics.stv)tallest athlete ← athlete events %>% filter(Height) %>% filter(Height == max(Height))
1805A007	Q14	library(olympics.stv)participations by country ← athlete event %>% group_by(Team) %>% summarize(participations)most_participations ← participations by country %>% filter(participations == max(participations))
1805A007	Q18	library(gapminder)turkey data ← gapminder %>% filter(country == ‘’Turkey’’wealthiest year ← turkey data %>% filter(gdpPercap == max(gpdPercap))
1805A007	Q3	library(olympics.stv)athlete heights ← athlete events %>% filter(Height == min(Height)
1805A007	Q8	library(olympics.stv)medals_2018 ← medals %>% filter(Year == 2018) count(medals_2018)
1805A009	Q13	library(olympics)olympics %>%slice_max(year, n=1)arrange(name)
1805A009	Q16	install.packages(“gapminder”)library(gapminder)gapminder %>%group_by(country) %>%filter(year == 1987) %>%summarize(maxGdpPercap = max(gdpPercap))KuwaitAsia195758.033212846113523.1329
1805A009	Q4	library(olympics)olympics %>%group_by(game == athletism) %>%filter(season == summer) %>%slice_min(height, n=1)
1805A009	Q5	library(olympics)olympics%>%group_by(country) %>%summarize(total_country= sum(Country)
1805A009	Q6	library(olympics)olympics %>%filter( medal == gold) %>%summarize(total_medal = sum(medal))
1805A009	Q9	library(olympics)olympics %>%filter(game == badminton, sex == woman) %>%group_by(medal == gold) %>%slice_min(height, n=1)
1805A015	Q15	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv")tallest_athlete <- olympics %>% filter( year == max(year)) %>% filter((Height)) %>% arrange(desc(Height)) %>% select(Name, Height) %>% slice(1)
1805A015	Q18	library(gapminder)turkey_gdp <- gapminder %>% filter(country == “Turkey”) %>% arrange(desc(gdpPercap))wealthiest_year_turkey <- turkey_gdp[1,]wealthiest_year_turkey country continent year lifeExp pop gdpPercap 1 Turkey Europe 2007 71.8 71158647 8458.
1805A015	Q4	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv")winter_olympics <- olympics %>% filter(season == “Winter”) %>% shortest_athlete <- winter_olympics %>% filter((Height)) %>% arrange(Height) %>% slice(1)shortest_athlete
1805A015	Q5	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv")num_countries <- olympics %>% filter(year == max(year)) %>% distinct(Team, .keep_all = TRUE) %>% summarize(num_countries = n()) slice(1)num_countries
1805A015	Q8	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics_2018 <- olympics %>% group_by(medal) %>% mutate(number_medals = count(medal) %>% summarize(total_medals = sum(number_medals))total_medals
1805A015	Q9	olympics <- read.delim(“https://zenodo.org/record/6803028/files/olympics.tsv")winter_olympics <- olympics %>% filter(season == “Winter”, sex == “Women”, sport == “Badminton”, medal == “Gold”) %>% shortest_women <- winter_olympics %>% filter((Height)) %>% arrange(Height) %>% slice(1)shortest_women
1805A034	Q11	Add your R code here!library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")tallest_athlete <- olympics %>%filter(!is.na(Height)) %>%arrange(desc(Height)) %>%slice(1) %>%select(Name, Height)cat(“The tallest athlete is”, tallest_athlete$Name, “with a height of”, tallest_athlete$Height, “cm.”)
1805A034	Q14	Add your R code# Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")# Count the number of times each country appears in the dataparticipations <- olympics %>% count(country, name = “participations”)
1805A034	Q16	install.packages(“gapminder”)library(gapminder)library(dplyr) gapminder %>% group_by(continent, year) %>% filter(continent == “Asia”) %>%slice_max(gdpPercap)
1805A034	Q19	library(readr) # Import the file data <- read_delim(“https://raw.githubusercontent.com/alperyilmaz/data/main/import/problematic_file1.txt”, delim = “,”, col_names = FALSE, skip = 2, comment = “#”) # Rename the columns colnames(data) <- c(“ID”, “Final_Grade”) # Calculate the average final grade per student avg_final_grade <- aggregate(Final_Grade ~ ID, data = data, FUN = mean) # Print the result avg_final_grade
1805A034	Q3	Add your R code here# Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")# Find the height of the shortest athleteshortest_athlete <- olympics %>% filter(!is.na(Height)) %>% arrange(Height) %>% slice(1) %>% select(Name, Height)# Print the resultcat(“The shortest athlete is”, shortest_athlete$Name, “with a height of”, shortest_athlete$Height, “cm.”)
1805A034	Q8	Add your R code here# Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv?downloaded=1")# Filter for the 2018 Olympics and sum the medalsmedals_2018 <- olympics %>%filter(Year == 2018) %>%summarise(total_medals = sum(Total.Medals))# Print the resultcat(“The total number of medals handed out during the 2018 Olympics was”, medals_2018$total_medals)
1805A034	Q9	data %>% filter(medal == “Gold”, sport == “Badminton”) %>% arrange(height)
1805A048	Q1	We can arrange the heavy of the tennis player and we can choose the heaviest player by limiting the row
1805A048	Q3	olympicdata ←read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")%>% select (weight)%>% filter(arrange(desc(weight)))
1805A048	Q5	library(tidyverse)lastolympics←lastolympics <- read_csv(“datacam/p- data/tidy-olympics/presentation.html”)%>% count(countries)%>% rename(num_countries=n)
1805A051	Q12	Load necessary librarieslibrary(dplyr)# Read in Olympics dataolympics <- read.csv(“olympics.tsv”)# Group data by Year and count number of unique sportssports_by_year <- olympics %>% group_by(Year) %>% summarize(num_sports = n_distinct(Sport))# Find Year with most unique sportsmost_sports_index <- which.max(sports_by_year$num_sports)most_sports_year <- sports_by_year[most_sports_index, “Year”]# Print resultscat(paste(“The Olympics with the most different sports was in”, most_sports
1805A051	Q15	Load necessary librarieslibrary(dplyr)# Read in Olympics dataolympics <- read.csv(“olympics.tsv”)# Filter data to include only Tokyo 2020 athletestokyo_2020 <- olympics %>% filter(Year == 2021 & Season == “Summer”)# Find tallest athletetallest_index <- which.max(tokyo_2020$Height)tallest_name <- olympics[tallest_index, “Name”]tallest_height <- olympics[tallest_index, “Height”]# Print resultscat(paste(“The tallest athlete from the Olympics was”, tallest_name, “at a height of”, tallest_height, “cm.”))
1805A051	Q8	Load necessary librarieslibrary(dplyr)# Read in Olympics dataolympics <- read.csv(“olympics.tsv”)# Filter data to include only 2018 Winter Olympics eventsAmadel <- olympics %>%# Count number of medals handed outmedal_count <- sum(Amadel$Gold, Amadel$Silver, Amadel$Bronze)# Print resultscat(paste(“A total of”, medal_count, “medals Olympics.”))
19056008	Q15	The Code# Load Datasetwd(“C:\Users\adnan\Downloads\olympics.tsv”)# Read in the olympics.tsv file using read.table() functionolympics_data <- read.table(“olympics.tsv”, sep=”\t”, header=TRUE)# Filter the data to include only athletes from the most recent Olympicsrecent_olympics_data <- olympics_data[olympics_data$Year == 2020,]# Find the row with the tallest athletetallest_athlete_row <- which.max(recent_olympics_data$Height)# Extract the name and height of the tallest athletetallest_athlete_name <- recent_olympics_data$Name[tallest_athlete_row]tallest_athlete_height <- recent_olympics_data$Height[tallest_athlete_row]# Print the resultcat(“The tallest athlete from the most recent Olympics was”, tallest_athlete_name, “who was”, tallest_athlete_height, “cm tall.”)
19056008	Q17	The Code# Load gapminder librarylibrary(gapminder)# Filter for Asia continentasia_data <- gapminder %>% filter(continent == “Asia”)# Find row with highest gdpPercapwealthiest_country <- asia_data[which.max(asia_data$gdpPercap),]# Print resultwealthiest_country The Result country continent year lifeExp pop gdpPercap 1 Kuwait Asia 1957 58.0 2128465 113523
19056008	Q6	The Code# Set the working directory to the location where your .tsv file is savedsetwd(“C:\Users\adnan\Downloads\olympics.tsv”) # Read in the olympics.tsv file using read.table() functionolympics_data <- read.table(“olympics.tsv”, sep=”\t”, header=TRUE) # Use the sum() function to calculate the total number of gold medalstotal_gold_medals <- sum(olympics_data$Gold) # Print the resultcat(“The total number of gold medals handed out in all games is”, total_gold_medals)
19056011	Q11	library(tidyverse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% arrange(desc(height)) %>% select(name, height) %>% slice(1L)Answer from Posit Cloud :Adam Sandurski2.14
19056011	Q12	library(tidyverse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% count(games, sport) %>% count(games, sort = TRUE) Answer From Posit Cloud :2020 Summer Olympics38
19056011	Q3	library(tidyverse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>%arrange(athlete) %>%select(name, height)
19056011	Q6	library(tidyverse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(medal == “Gold”, !is.na(medal)) %>% count(medal)Answer from Posit Cloud :Gold8110
19056011	Q9	library(tidyverse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(sport == “Badminton”, medal == “Gold”) %>% arrange(height) %>% slice(1L) Answer from Posit Cloud :243Susy SusantiF197111 FebruaryTasikmalaya (INA)1.61NAIndonesiaINA
19056035	Q13	library(tidyverse)# Load the Summer Olympics datasetdf <- read_csv(“https://raw.githubusercontent.com/rgriffin/day2-olympic-history/main/athlete_events.csv")# Filter the dataset to include only the most recent Summer Olympicsrecent_olympics <- df %>% filter(Year == max(Year) & Season == “Summer”)# Find the athlete who comes last by alphabetlast_athlete <- recent_olympics %>% arrange(desc(Name)) %>% # sort by name in descending order slice(1) # select the last row# Print the name and team of the last athletecat(“The athlete who comes last by alphabet in the most recent Summer Olympics is”, last_athlete$Name, “from”, last_athlete$Team, “.”)
19056035	Q16	Load the gapminder librarylibrary(gapminder)# Filter the dataset to include only Asia continentasia_df <- filter(gapminder, continent == “Asia”)# Find the row with the highest gdpPercap valuewealthiest_country <- asia_df[which.max(asia_df$gdpPercap),]# Print the resulting rowwealthiest_countryresult is down below # A tibble: 1 x 6 country continent year lifeExp pop gdpPercap 1 Kuwait Asia 1957 58.0 212846 113523.
19056035	Q2	library(tidyverse)# Load the Summer Olympics datasetdf <- read_csv(“https://raw.githubusercontent.com/rgriffin/day2-olympic-history/main/athlete_events.csv")# Filter the dataset to include only the most recent Summer Olympicsrecent_olympics <- df %>% filter(Year == max(Year) & Season == “Summer”)# Find the lightest athlete of the most recent Summer Olympicslightest_athlete <- recent_olympics %>% arrange(Weight) %>% slice(1)# Print the name and weight of the lightest athletecat(“The lightest athlete of the most recent Summer Olympics was”, lightest_athlete$Name, “from”, lightest_athlete$Team, “with a weight of”, lightest_athlete$Weight, “kg.”)
19056035	Q5	library(tidyverse)# Load the Summer Olympics datasetdf <- read_csv(“https://raw.githubusercontent.com/rgriffin/day2-olympic-history/main/athlete_events.csv")# Filter the dataset to include only the most recent Olympicsrecent_olympics <- df %>% filter(Year == max(Year))# Count the number of unique countries in the recent Olympicsnum_countries <- recent_olympics %>% distinct(NOC) %>% nrow()# Print the number of countries that participated in the recent Olympicscat(“The number of countries that participated in the last Olympics is”, num_countries, “.”)
19056035	Q7	library(tidyverse)# Load the Summer Olympics datasetdf <- read_csv(“https://raw.githubusercontent.com/rgriffin/day2-olympic-history/main/athlete_events.csv")# Filter the dataset to include only athletes shorter than 160cm who won a gold medalshort_gold <- df %>% filter(Height < 160 & Medal == “Gold”)# Count the number of gold medals won by individuals shorter than 160cmnum_short_gold <- nrow(short_gold)# Print the number of gold medals won by individuals shorter than 160cmcat(“The number of gold medals won by individuals shorter than 160cm is”, num_short_gold, “.”)
19056035	Q9	library(tidyverse)# Load the Summer Olympics datasetdf <- read_csv(“https://raw.githubusercontent.com/rgriffin/day2-olympic-history/main/athlete_events.csv")# Filter the dataset to include only Badminton players who won a gold medalbadminton_gold <- df %>% filter(Sport == “Badminton” & Medal == “Gold”)# Find the height of the shortest woman Badminton player to win a gold medalshortest_woman <- badminton_gold %>% filter(Sex == “F”) %>% # filter only for women players arrange(Height) %>% # sort by height slice(1) # select the first row (shortest player)# Print the height of the shortest woman Badminton player to win a gold medalcat(“The height of the shortest woman Badminton player to win a gold medal is”, shortest_woman$Height, “cm.”)
19056044	Q11	library(tidyverse) olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) height_data <- olympics_data %>% filter(!is.na(Height)) tallest_athlete <- height_data %>% filter(Height == max(Height)) %>% select(Name, Height) tallest_athleteName Height WALENTINA BOND… 223
19056044	Q14	library(tidyverse) olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")participations_data <- olympics_data %>% group_by(NOC) %>% summarise(Unique_Athletes = n_distinct(ID)) most_participations <- participations_data %>% filter(Unique_Athletes == max(Unique_Athletes)) %>% select(NOC, Unique_Athletes) most_participations NOC Unique_Athletes USA 11519
19056044	Q18	library(gapminder)turkey_data <- filter(gapminder, country == “Turkey”)wealthiest_year <- turkey_data[which.max(turkey_data$gdpPercap), ]wealthiest_year country continent year lifeExp pop gdpPercap 1 Turkey Europe 2013 76.2 75627384 19900.
19056044	Q2	library(tidyverse) olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")recent_summer_data <- olympics_data %>% filter(Year == max(Year) & Season == “Summer”) lightest_athlete <- recent_summer_data %>% filter(Weight == min(Weight)) %>% select(Name, Weight) lightest_athlete Name Weight Nur Tatar Askari 49
19056044	Q21	dd.pdf
19056044	Q8	library(tidyverse) olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) winter2018_data <- olympics_data %>% filter(Year == 2018 & Season == “Winter”) medals_count <- winter2018_data %>% select(Medal) %>% na.omit() %>% count() medals_count n 102
19056044	Q9	library(tidyverse) olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")women_badminton_data <- olympics_data %>% filter(Sport == “Badminton” & Sex == “F”) shortest_gold_medalist <- women_badminton_data %>% filter(Medal == “Gold”) %>% filter(Height == min(Height)) %>% select(Name, Height) shortest_gold_medalist Name Height Zhang Ning (Chang… 162
19056066	Q1	data %>%filter(games == max(games)) %>%filter(sport==“Tennis”) %>% arrange(desc(weight)) athlete_idnamesexbirth_yearbirth_daybirth_placeheightweight 141097Yahor HerasimauM199211 NovemberMinsk (BLR)18890 141097Yahor HerasimauM199211 NovemberMinsk (BLR)18890 146702Lukáš KleinM199822 MarchSpišská Nová Ves (SVK)19490 146702Lukáš KleinM199822 MarchSpišská Nová Ves (SVK)19490 147662Stefanos TsitsipasM199812 AugustAthina (Athens) (GRE)19590 weightteamnocgamesyearseasoncitysporteventmedal 90BelarusBLR2020 Summer Olympics2020SummerTokyoTennisDoubles, Men 90BelarusBLR2020 Summer Olympics2020SummerTokyoTennisSingles, Men 90SlovakiaSVK2020 Summer Olympics2020SummerTokyoTennisDoubles, Men 90SlovakiaSVK2020 Summer Olympics2020SummerTokyoTennis
19056066	Q13	data %>%arrange(desc(name)) we can see the athlete comes last on alphabet on the top.87557Þröstur JóhannessonM195521 AugustNA
19056066	Q3	data %>% arrange(height) 4530Lyton MphandeM196314 MayNA127 28832Rosario BrionesF19535 OctoberSan Luis Potosí, San Luis Potosí (MEX)127 28832Rosario BrionesF19535 OctoberSan Luis Potosí, San Luis Potosí (MEX)127
19056066	Q5	data %>% filter(games == max(games)) %>% count(team) %>% We can see 250 rows in the output. So 250 countries participated in the last Olympics.teamn Afghanistan5 Albania10 Albania Kosovo2 Algeria44 American Samoa4 Andorra3 Angola4 Antigua and Barbuda6 Argentina70 Armenia19 1-10 of 250 rows
19056066	Q7	data %>%filter(height < 160) %>% filter(medal==“Gold”)We can see 384 rows under the table, so it means 384 gold medals were won by individuals shorter than 160cm.A tibble:384 × 17 athlete_idnamesexbirth_yearbirth_daybirth_placeheight 781Deng YapingF19736 FebruaryZhengzhou, Henan (CHN)150 781Deng YapingF19736 FebruaryZhengzhou, Henan (CHN)150 781Deng YapingF19736 FebruaryZhengzhou, Henan (CHN)150 781Deng YapingF19736 FebruaryZhengzhou, Henan (CHN)150 1176Lefty GwynneM19125 OctoberToronto, Ontario (CAN)157 1645Joel CasamayorM197112 JulyGuantánamo (CUB)154 1659Ángel HerreraM19572 AugustGuantánamo (CUB)159 1659Ángel HerreraM19572 AugustGuantánamo (CUB)159 1663Juan Carlos LemusM19656 FebruaryPinar del Río (CUB)159 1664Rogelio MarceloM196511 JuneGuantánamo (CUB)150 1-10 of 384 rows | 1-7 of 17 columns
19056902	Q11	olympics %>%select(name, height) %>%arrange(desc(height)) %>%top_n(1)answer: adam sandurski 214cmAdam Sandurski214
19056902	Q14	olympics %>%
19056902	Q16	gapminder %>%summarize(wealthiest = max(highest gdpPercap))slice_max(highest gdpPercap, 1)
19056902	Q4	olympics %>%filter(!is.na(height)) %>%arrange(height) %>%top_n(1) answer: 136 cm Lu li28252Lu LiF197630 August
19056902	Q7	olympics %>%filter(medal == “Gold”, height < 160)answer : 384
19056902	Q9	olympics %>%filter(sex == “F”, sport == “Badminton”, medal == “Gold”) %>%arrange(height) %>%top_n(1) answer: susy susanti 161cm243Susy SusantiF197111 FebruaryTasikmalaya (INA)161
1905A001	Q10	CODE :{r}data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data %>%<br>filter(team =="Denmark", year=="1964")%>%<br>mutate(average_height = sum(height)/46)ANSWER : 175.913 cm
1905A001	Q12	CODE : {r}data%>%<br>group_by(games)count(sport) <br> <br> <br> <br><br>ANSWER : The 2020 Summer Olympics, 38
1905A001	Q13	CODE :{r}data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data %>%<br>arrange(desc(year),desc(name)) ANSWER: Zuzana Rehák Štefečeková (in 2020 Summer Olympics)
1905A001	Q17	CODE :{r}library(gapminder)``````{r}gapminder %>%<br>group_by(continent,year)%>%<br>filter(continent =="Asia")%>%<br>slice_max(gdpPercap)ANSWER : Kuwait , 113523
1905A001	Q3	CODE :{r}data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data%>%<br>filter(!is.na(height))%>%<br>arrange(height)ANSWER : Lyton Mphande, 127 cm
1905A001	Q8	CODE :{r}data <- read_tsv("https://zenodo.org/record/6803028/files/olympics.tsv")data %>%<br>filter(year == 2018)%>%<br>filter(!is.na(medal))%>%<br>count(medal)ANSWER : 383 medalsbronze 127gold 131silver 125
1905A008	Q13	CODE = library(tidyverse) data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% arrange(desc(games), desc(name))ANSWER = athlete_idnamesexbirth_yearbirth_daybirth_place 146605Žolt PetoM198730 NovemberNA
1905A008	Q14	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>%group_by(team) %>% count(team) %>% arrange(desc(n))ANSWERteamn United States17286 Answer is the row above, but when we run code we get other rows as well in descending order.
1905A008	Q17	CODE = install.packages(“gapminder”)library(gapminder) library(dplyr) gapminder %>% group_by(continent, year) %>% filter(continent == “Asia”) %>%slice_max(gdpPercap)ANSWER =country continent year lifeExp pop gdpPercapAfghanistanAsia195228.801008425333779.4453
1905A008	Q2	CODE = library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>% filter(season == “Summer”) %>% mutate(weight = parse_number(weight)) %>% arrange(desc(year), weight)ANSWER = Flávia Saraiva - 31kg
1905A008	Q8	CODE = library(tidy verse)data ← read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(year == 2018) %>% count(medal)ANSWER = medaln Bronze127 Gold131 Silver125 NA3662
1905A008	Q9	CODE = library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>% filter(medal == “Gold”, sport == “Badminton”) %>% arrange(height)ANSWER = Susy Susanti , 161 cm
1905A017	Q1	The latest version of the Olympics dataset available in the “ggplot2” package is from the 2016 Olympics, so it does not include data for the 2020 Olympics. Therefore, I cannot answer question using the Olympics dataset.
1905A017	Q11	Code®:‘’’ {r}olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) tallest_athlete <- olympics %>%filter(!is.na(Height)) %>%arrange(desc(Height)) %>%slice(1)cat(“The tallest athlete is”, tallest_athlete$Name, “with a height of”, tallest_athlete$Height, “cm.”) ’’’Answer:The tallest athlete is Yao Ming with a height of 226 cm.
1905A017	Q14	Code:library(tidyverse)data(“olympics”, package = “ggplot2”)participations <- olympics %>% distinct(Country, Year) %>% group_by(Country) %>% summarise(participations = n())most_participations <- participations %>% arrange(desc(participations)) %>% slice(1)cat(most_participations$Country, “has had the most participations in the Olympics, with a total of”, most_participations$participations, “appearances.”)Answer:United States has had the most participations in the Olympics, with a total of 27 appearances.
1905A017	Q17	Code®:library(gapminder)gapminder_asia <- gapminder %>% filter(continent == “Asia”)wealthiest_country <- gapminder_asia %>% group_by(country) %>% summarise(max_gdpPercap = max(gdpPercap))wealthiest_country %>% arrange(desc(max_gdpPercap)) %>% slice(1)Answer:# A tibble: 1 x 2 country max_gdpPercap 1 Kuwait 113523.
1905A017	Q3	Code ®:data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data %>% filter(!is.na(height)) %>% arrange(height)Answer: Lyton Mphande, 127 cm
1905A017	Q7	Code:‘’’ {r}olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) olympics %>%filter( Height < 160, Medal == “Gold”) %>%count()‘’’Answer# A tibble: 1 x 1 n 1 13
1905A018	Q1	Unfortunately, as the 2020 Olympics have been postponed and are held in 2021, we cannot determine how much of the heaviest tennis player is using the data provided. The dataset provided only includes information on athletes competing in the Summer Olympics from 1896 to 2016. Therefore, we do not have data on the 2021 Olympics and using this dataset we cannot determine the weight of the heaviest tennis player in that event.library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")tennis_data <- data %>% filter(year == 2020, season == “Summer”, sport == “Tennis”)
1905A020	Q10	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>%filter(year== 1964, country==“DEN”)%>%summarize (average_height=mean(height))
1905A020	Q13	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>%arrange(desc(year),desc(name)) %>%select(name) answer: Žolt Peto
1905A020	Q4	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")data%>%filter(season== “Winter”)%>%arrange(height)%>%select(name,height,season)
1905A020	Q5	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>% arrange(desc(year))%>% count(countries, sort= TRUE)
1905A020	Q6	library(tidyverse)data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv”) data %>%group_by(game)%>%filter(medal== “Gold”) %>%count(medal)Answer: (A: 8,110)
1905A022	Q11	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics <- olympics %>% filter(!is.na(height))tallest_athlete <- olympics %>% slice_max(height)cat(“The height of the tallest athlete is”, tallest_athlete$height, “cm, and his/her name is”, tallest_athlete$name, “\n”) output :The height of the tallest athlete is 223 cm, and his/her name is Sun Mingming
1905A022	Q16	library(gapminder)data(gapminder)gapminder_1987 <- gapminder %>% filter(year == 1987)wealthiest_country <- gapminder_1987 %>% slice_max(gdpPercap)cat(“The wealthiest country in 1987 was”, wealthiest_country$country, “with a GDP per capita of”, wealthiest_country$gdpPercap, “.\n”) output: The wealthiest country in 1987 was Switzerland with a GDP per capita of 30281.28 .
1905A022	Q4	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")winter_olympics <- olympics %>% filter(season == “Winter”)winter_athletes <- winter_olympics %>% filter(!is.na(height))shortest_athlete <- winter_athletes %>% slice_min(height)cat(“The shortest athlete of the Winter Olympics is”, shortest_athlete$athlete_name, “with a height of”, shortest_athlete$height, “cm.\n”) output:The shortest athlete of the Winter Olympics is Kjetil Aukland with a height of 155 cm.
1905A022	Q5	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")last_olympics <- olympics %>% filter(season == “Summer” & year == “2016”) %>% distinct(nationality) %>% count()cat(“The number of countries participated in the last Olympics is”, last_olympics$n, “\n”) output:The number of countries participated in the last Olympics is 207
1905A022	Q6	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")total_gold_medals <- olympics %>% filter(medal == “Gold”) %>% summarize(total_gold_medals = n())cat(“The total number of gold medals handed out in all games is”, total_gold_medals$total_gold_medals, “.\n”) output:‘The total number of gold medals handed out in all games is 9850.’
1905A022	Q9	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")women_badminton <- olympics %>% filter(sport == “Badminton” & sex == “F” & medal == “Gold”)shortest_woman <- women_badminton %>% slice_min(height)cat(“The height of the shortest woman Badminton player to win a gold medal is”, shortest_woman$height, “cm.\n”) output:The height of the shortest woman Badminton player to win a gold medal is 150 cm.
1905A025	Q13	olympic %>% arrange(desc(year)) %>% arrange(desc(name)) athlete_idnamesexbirth_year 87557Þröstur JóhannessonM1955
1905A025	Q14	olympic %>% count(team, sort=TRUE)teamnUnited States17286
1905A025	Q2	library(tidyverse)olympics %>% filter(season == “Summer”) %>% mutate(weight = parse_number(weight)) %>% arrange(desc(year), weight)athlete_idnamesexbirth_year 129286Flávia SaraivaF1999
1905A025	Q7	olympic %>% group_by(medal, sport, sex) %>% filter(medal == “Bronze”) %>% slice_min(height, n=1) %>% select(name, height, sport)
1905A025	Q9	olympic %>% group_by(medal, sport, sex) %>% filter(medal == “Bronze”) %>% slice_min(height, n=1) %>% select(name, height, sport)medalsexnameheight BronzeFDanièle Debernard156
1905A026	Q10	Read the datadata <- read.table(“olympics.tsv”, header = TRUE, sep = ”\t”)# Filter for Denmark athletes in the 1964 Olympicsdenmark_1964 <- subset(data, Team == “DEN” & Year == 1964)# Calculate the average height of Denmark athletes in 1964avg_height <- mean(denmark_1964$Height, na.rm = TRUE)# Print the resultcat(“The average height of Denmark athletes in the 1964 Olympics was:”, round(avg_height, 2), “cm.”)
1905A026	Q15	data <- read.table(“olympics.tsv”, header = TRUE, sep = ”\t”)winter_data <- data[data$Season == “Winter”,]winter_heights <- winter_data$Heightmin_height <- min(winter_heights)shortest_athletes <- winter_data[winter_data$Height == min_height,]for (i in 1:nrow(shortest_athletes)) { cat(shortest_athletes[i, “Name”], “: “, shortest_athletes[i, “Height”], “\n”)}
1905A035	Q10	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")denmark_1964 <- olympics %>% filter(Games == “Tokyo 1964” & NOC == “DEN”)avg_height_denmark_1964 <- denmark_1964 %>% summarise(avg_height = mean(Height, na.rm = TRUE))print(avg_height_denmark_1964)
1905A035	Q11	library(readr)library(dplyr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% filter(!is.na(height)) %>% arrange(desc(height)) %>% slice_head() %>% select(name, height) answer:name height1 Gao Tian, 高天 223
1905A035	Q18	library(gapminder)turkey_data <- gapminder[gapminder$country == “Turkey”,]wealthiest_year <- turkey_data[turkey_data$gdpPercap == max(turkey_data$gdpPercap),]print(wealthiest_year)
1905A035	Q19	6c2a47ce-f93b-45c6-b189-0e2235fbc655.jpg
1905A035	Q2	library(readr)library(dplyr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% filter(season == “Summer”) %>% arrange(desc(year)) %>% filter(!is.na(weight)) %>% slice_head() %>% select(name, weight) answer:# A tibble: 1 x 2 name weight1 Hou Zhihui, 侯志慧 49
1905A035	Q5	library(readr)library(dplyr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% filter(season == “Summer”) %>% summarize(n_distinct(country)) answer:n_distinct(country)1 205
1905A035	Q8	library(dplyr)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")num_medals <- olympics %>% filter(year == 2018) %>% summarise(num_medals = n()) %>% pull(num_medals)
1905A051	Q10	Sample data (heights in centimeters) olympic_data = [{‘name’: ‘Ahmet’, ‘country’: ‘DEN’, ‘year’: 1964, ‘height’: 180},{‘name’: ‘Marta’, ‘country’: ‘USA’, ‘year’: 1964, ‘height’: 170}, {‘name’: ‘John’, ‘country’: ‘DEN’, ‘year’: 1964, ‘height’: 175}, {‘name’: ‘Sarah’, ‘country’: ‘DEN’, ‘year’: 1964, ‘height’: 182}, {‘name’: ‘Ali’, ‘country’: ‘EGY’, ‘year’: 1964, ‘height’: 190}, ]total_height = 0num_athletes = 0 for data in olympic_data:if data[‘country’] == ‘DEN’ and data[‘year’] == 1964:total_height += data[‘height’]num_athletes += 1 if num_athletes > 0:avg_height = total_height / num_athletesprint(f”The average height of Danish athletes in the 1964 Olympics was {avg_height:.2f} cm.”) else: print(“There were no Danish athletes in the 1964 Olympics.”)
1905A051	Q11	Sample data (heights in centimeters) athlete = [ {’Boetsch ‘: ‘’, ‘height’: 183}# Find the tallest athlete tallest_athlete = max(athletes, key=lambda a: a[‘height’]) # Print the tallest athlete’s name and height print(f”The tallest athlete is {tallest_athlete[‘name’]} with a height of {tallest_athlete[‘height’]} cm.”)
1905A051	Q16	library(gapminder) data_1987 <- gapminder[gapminder$year == 1987,] wealthiest_country <- data_1987[data_1987$gdpPercap == max(data_1987$gdpPercap),] print(wealthiest_country)
1905A051	Q3	shortest_athlete = min(athletes, key=lambda a: a[‘height’]) # Print the shortest athlete’s name and height print(f”The shortest athlete is {shortest_athlete[‘name’]} with a height of {shortest_athlete[‘height’]} cm.”)
1905A051	Q5	Sample data olympic_data = [ {‘country’: ‘USA’, ‘medal’: ‘gold’}, {‘country’: ‘China’, ‘medal’: ‘silver’}, {‘country’: ‘Russia’, ‘medal’: ‘bronze’}, {‘country’: ‘Japan’, ‘medal’: ‘gold’}, {‘country’: ‘USA’, ‘medal’: ‘silver’}, {‘country’: ‘Australia’, ‘medal’: ‘bronze’}, ] # Create a set of all participating countries countries = set() for data in olympic_data: countries.add(data[‘country’]) # Count the number of participating countries num_countries = len(countries) # Print the number of participating countries print(f”There were {num_countries} countries that participated in the last Olympics.”)
1905A051	Q8	library(tidyverse)df <- read_tsv(‘https://zenodo.org/record/6803028/files/olympics.tsv’) medal <- df %>% filter(year == 2018, !is.na(medal)) %>% count(medal) print(medal) medal n 1 Bronze 1272 Gold 1313 Silver 125sum(medal$n)[1] 383
1905A061	Q10	Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")# Calculate the average height of Danish athletes in the 1964 Olympicsavg_height_denmark_1964 <- olympics %>% filter(NOC == “DEN” & Year == 1964 & !is.na(Height)) %>% summarise(avg_height = mean(Height))# Print the resultcat(“The average height of Danish athletes in the 1964 Olympics was”, round(avg_height_denmark_1964$avg_height, 2), “cm.”)
1905A061	Q11	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")tallest_athlete <- olympics %>%filter(!is.na(Height)) %>%arrange(desc(Height)) %>%slice(1) %>%select(Name, Height)cat(“The tallest athlete is”, tallest_athlete$Name, “with a height of”, tallest_athlete$Height, “cm.”)
1905A061	Q12	Load the olympics datalibrary(tidyverse)olympics <- read.csv(“https://raw.githubusercontent.com/abulbasar/data/master/olympics.csv")# Count the number of unique sports in each Olympicssports_per_olympics <- olympics %>% group_by(Year, Season) %>% summarise(num_sports = n_distinct(Sport))# Find the Olympics with the most different sportsmost_sports <- sports_per_olympics %>% filter(num_sports == max(num_sports))# Print the resultcat(“The Olympics with the most different sports was the”, most_sports$Season[1], most_sports$Year[1], “Olympics with”, most_sports$num_sports[1], “different sports.”)
1905A061	Q16	install.packages(“gapminder”)library(gapminder)library(dplyr) gapminder %>% group_by(continent, year) %>% filter(continent == “Asia”) %>%slice_max(gdpPercap)
1905A061	Q20	library(tidyverse) # Import file with appropriate arguments scores % group_by(Student) %>% summarise(avg_score = mean(Score)) # Print result avg_scores
1905A061	Q3	Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")# Find the shortest athlete ever to compete in the Olympicsshortest_athlete <- olympics %>% filter(!is.na(Height)) %>% arrange(Height) %>% slice(1) %>% select(Name, Height)# Print the resultcat(“The shortest athlete ever to compete in the Olympics is”, shortest_athlete$Name, “with a height of”, shortest_athlete$Height, “cm.”)
1905A061	Q6	Load the olympics datalibrary(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")# Count the number of gold medals in all gamesnum_gold_medals <- olympics %>% filter(Medal == “Gold”) %>% summarise(total_gold_medals = n())# Print the resultcat(“The total number of gold medals handed out in all games is”, num_gold_medals$total_gold_medals)
1905A606	Q1	library(readr)library(dplyr)df <- read_tsv(‘olympics.tsv’)tennis_players <- df %>% filter(sport == “Tennis” & year == 2020)heaviest_tennis_player <- tennis_players %>% filter(weight == max(weight))heaviest_tennis_player$weight
1905A606	Q13	library(readr)library(dplyr)df <- read_tsv(‘olympics.tsv’)recent_summer <- df %>% filter(Season == “Summer” & Year == max(Year))last_athlete <- recent_summer %>% arrange(desc(name)) %>% slice(1)last_athlete$name
1905A606	Q2	library(readr)library(dplyr)df <- read_tsv(‘olympics.tsv’)recent_summer <- summer %>% filter(Year == max(Year) & Season == “Summer”)lightest_athlete <- recent_summer %>% filter(weight == min(weight))lightest_athlete[, c(“name”, “weight”)]
1905A606	Q6	library(readr)library(dplyr)df <- read_tsv(‘olympics.tsv’)summer_gold <- summer %>% group_by(Year, Season, Medal) %>% summarize(total_gold = sum(Medal == “Gold”))winter_gold <- winter %>% group_by(Year, Season, Medal) %>% summarize(total_gold = sum(Medal == “Gold”))total_gold_medals <- sum(summer_gold$total_gold, winter_gold$total_gold)total_gold_medals
1905A608	Q10	library(dplyr)olympics_data <- read.table(“https://zenodo.org/record/6803028/files/olympics.tsv”, header = TRUE)denmark_avg_height <- olympics_data %>% filter(NOC == “DEN” & Year == 1964 & !is.na(Height)) %>% summarize(avg_height = mean(Height))cat(“The average height of athletes from Denmark in the 1964 Olympics was”, round(denmark_avg_height$avg_height, 2), “cm.”)
1905A608	Q14	library(readr)data <- read_tsv(’https://zenodo.org/record/6803028/files/olympics.tsv')country_counts <- table(data$NOC)max_country <- names(country_counts[which.max(country_counts)])cat(max_country)
1905A608	Q15	library(readr)data <- read_tsv(’https://zenodo.org/record/6803028/files/olympics.tsv')max_height_row <- data[which.max(data$Height), ]cat(max_height_row$Name, max_height_row$Height, “cm”)
1905A608	Q16	library(gapminder)wealthiest_1987 <- gapminder[gapminder$year == 1987,]wealthiest_1987[which.max(wealthiest_1987$gdpPercap),]
1905A608	Q2	library(tidyverse)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")summer_2020 <- olympics_data %>% filter(year == 2020 & season == “Summer”)summer_2020 %>% arrange(weight) %>% slice(1) %>% select(name, weight)
1905A608	Q6	library(tidyverse)olympics_data <- read_csv(“https://zenodo.org/record/6803028/files/olympics.tsv")total_gold_medals <- olympics_data %>% filter(medal == “Gold”) %>% summarize(total_gold_medals = n())total_gold_medals
1905A903	Q10	df %>% filter(year == 1964, noc == “DEN”) %>% summarise(avg.height = mean(height)) avg.height 1 176.
1905A903	Q15	library(tidyverse)df <- read_tsv(‘https://zenodo.org/record/6803028/files/olympics.tsv’) df %>% arrange(desc(year), desc(height))144189 Gennaro Di Mauro , height = 210, na= Italy
1905A903	Q18	df %>% filter(country == “Turkey”) %>% slice_max(gdpPercap) country continent year lifeExp pop gdpPercap 1 Turkey Europe 2007 71.8 71158647 8458.
1905A903	Q20	solution.png
1905A903	Q3	df %>% slice_min(height) athlete_id name sex birth_year birth_day birth_place height4530 Lyton Mph… M 1963 14 May NA 1278832 Rosario B… F 1953 5 October San Luis P… 127
1905A903	Q5	df %>% filter(year == 2020, season == “Summer”) %>% distinct(noc) ==> output gives 208 rows/ countries
1905A903	Q8	library(tidyverse)df <- read_tsv(‘https://zenodo.org/record/6803028/files/olympics.tsv’) medal <- df %>% filter(year == 2018, !is.na(medal)) %>% count(medal) print(medal) medal n 1 Bronze 127 2 Gold 131 3 Silver 125sum(medal$n)[1] 383
1905A916	Q14	library(dplyr)library(readr)athlete_events <- read_csv(“olympics.tsv”)country_participations <- athlete_events %>% group_by(NOC) %>% summarise(participations = n_distinct(Games)) %>% arrange(desc(participations))most_participations_country <- country_participations[1, ]print(most_participations_country)
1905A916	Q15	library(dplyr)library(readr)athlete_events <- read_csv(“olympic.tsv”)most_recent_year <- max(athlete_events$Year, na.rm = TRUE)most_recent_olympics <- athlete_events %>% filter(Year == most_recent_year) %>% arrange(desc(Height))tallest_athlete <- most_recent_olympics[1, c(“Name”, “Height”)]print(tallest_athlete)
1905A916	Q18	library(gapminder)library(dplyr)wealthiest_year_turkey <- gapminder %>% filter(country == “Turkey”) %>% arrange(desc(gdpPercap)) %>% slice(1)print(wealthiest_year_turkey)
1905A916	Q3	library(dplyr)library(readr)athlete_events <- read_csv(“olympics.tsv”)athletes_with_height <- athlete_events %>% filter(!is.na(Height)) %>% arrange(Height)shortest_athlete <- athletes_with_height[1, c(“Name”, “Height”)]print(shortest_athlete)
1905A916	Q7	library(dplyr)library(readr)athlete_events <- read_csv(“olympics.tsv”)short_athletes_gold_medals <- athlete_events %>% filter(Height < 160, Medal == “Gold”)gold_medals_count <- nrow(short_athletes_gold_medals)print(gold_medals_count)
1905A916	Q9	library(dplyr)library(readr)athlete_events <- read_csv(“olympics.tsv”)shortest_gold_medalist <- athlete_events %>% filter(Sport == “Badminton”, Sex == “F”, Medal == “Gold”, !is.na(Height)) %>% arrange(Height)shortest_gold_medalist_female_badminton <- shortest_gold_medalist[1, c(“Name”, “Height”)]print(shortest_gold_medalist_female_badminton)
20056603	Q10	Load the required packagelibrary(readr)# Set the path to the CSV file containing the datapath <- “path/to/1964_olympics.csv”# Read the data, skipping the first 4 rows which contain metadata and excluding comments starting with “#“data <- read_delim(path, delim = “,”, col_names = TRUE, skip = 4, comment = “#”)# Filter the data to include only athletes from Denmark (DEN) and the height columndenmark_data <- data %>% filter(NOC == “DEN”) %>% select(height)# Calculate the average height of athletes from Denmarkavg_height <- mean(denmark_data$height, na.rm = TRUE)# Print the resultcat(“The average height of athletes from Denmark in the 1964 Olympics is”, avg_height, “cm.”)
20056603	Q12	Load the readr and dplyr packageslibrary(readr)library(dplyr)# Read in the Olympics dataset using read_delim functionolympics_data <- read_delim(“olympics.csv”, delim = “,”, col_names = TRUE, skip = 1, comment = “”)# Count the number of unique sports for each Olympics and find the one with the most sportsmost_sports_olympics <- olympics_data %>% group_by(Games) %>% summarize(num_sports = n_distinct(Sport)) %>% arrange(desc(num_sports)) %>% slice(1)# Print the resultcat(“The Olympics with the most different sports was”, most_sports_olympics$Games, “with”, most_sports_olympics$num_sports, “different sports.”)
20056603	Q13	Load the Olympics dataolympics <- read_delim(“olympics.csv”, delim = “,”, col_names = TRUE, skip = 1)# Show the last row of the data to check if it loaded correctlytail(olympics)# Filter the data to include only the most recent Olympicsrecent_olympics <- olympics %>% filter(year == max(year))# Sort the data by athlete name in descending orderlast_athlete <- recent_olympics %>% arrange(desc(name)) %>% slice_tail(n = 1)# Print the name of the last athleteprint(last_athlete$name)
20056603	Q17	Load the gapminder packagelibrary(gapminder)# Filter the gapminder dataset to include only Asian countriesasia_data <- gapminder %>% filter(continent == “Asia”)# Group the data by country and calculate the average GDP per capita across all yearscountry_gdp <- asia_data %>% group_by(country) %>% summarize(avg_gdp = mean(gdpPercap))# Find the row with the highest average GDP per capitawealthiest_country <- country_gdp %>% filter(avg_gdp == max(avg_gdp))# Print the resultwealthiest_country
20056603	Q2	Load the Olympics dataolympics <- read_delim(“olympics.csv”, delim = “,”, col_names = TRUE, skip = 1)# Show the last few rows of the data to make sure it loaded correctlytail(olympics) # Filter the data to the most recent Summer Olympicsrecent_summer_olympics <- olympics %>% filter(season == “Summer”, year == max(year))# Sort the data by weight in ascending orderlightest_athlete <- recent_summer_olympics %>% arrange(weight) %>% slice_head(n = 1)# Print the name and weight of the lightest athletecat(“The lightest athlete of the most recent Summer Olympics is”, lightest_athlete$name, “with a weight of”, lightest_athlete$weight, “kg.”)
20056603	Q6	Load the readr packagelibrary(readr)# Read in the Olympics dataset using read_delim functionolympics_data <- read_delim(“olympics.csv”, delim = “,”, col_names = TRUE, skip = 1, comment = “”)# Extract the number of gold medals awarded in all gamestotal_gold_medals <- sum(olympics_data$Gold)# Print the resultcat(“The total number of gold medals awarded in all games is:”, total_gold_medals)
20056605	Q13	Load the tidyverse library for data manipulation library(tidyverse)# Load the Olympics data olympics <- read_csv(“https://zenodo.org/record/6611769/files/olympics.csv?download=1")# Filter the data to keep only the most recent Olympicsrecent_olympics <- olympics %>% filter(year == max(year))# Find the athlete who comes last by alphabetlast_athlete <- recent_olympics %>% arrange(desc(name)) %>% slice_tail(n = 1) # Print the name of the last athletelast_athlete$name‘Östling, Henrik’
20056605	Q18	Load the gapminder librarylibrary(gapminder) # Filter the data to keep only Turkeyturkey <- gapminder %>% filter(country == “Turkey”) # Find the year with the highest gdpPercapwealthiest_year <- turkey %>% filter(gdpPercap == max(gdpPercap)) # Print the resulting rowwealthiest_year# A tibble: 1 x 6 country continent year lifeExp pop gdpPercap 1 Turkey Europe 2013 74.8 75627384 25129.
20056605	Q7	Load the dplyr library for data manipulationlibrary(dplyr) # Load the Olympics dataolympics <- read.csv(“https://zenodo.org/record/6611769/files/olympics.csv?download=1”) # Count the number of gold medals won by individuals shorter than 160cmgold_medals <- olympics %>% filter(Sport != “Art Competitions” & Medal == “Gold” & Height < 160) %>% count() # Print the resultgold_medals$n81
2005A043	Q11	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% arrange(desc(height))Answer : Adam Sandurski with 214 cm.
2005A043	Q12	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% group_by(year) %>% distinct(sport) %>% count(year, sort = TRUE)Answer : 1992 year with 40 different sports.
2005A043	Q18	library(gapminder)gapminder %>% filter(country == “Turkey”) %>% arrange(desc(gdpPercap))Answer : 2007countrycontinentyearlifeExppopgdpPercapTurkeyEurope200771.777711586478458.276
2005A043	Q3	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% arrange(height)Answer : Lython Mphande with 127 cm.
2005A043	Q8	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% filter(year == 2018, !is.na(medal))Answer : 383
2005A043	Q9	library(tidyverse)olympics <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics %>% filter(sport == “Badminton”, medal == “Gold”) %>% arrange(height)Answer : Susy Susanti with 161 cm.
2005A608	Q10	library(readr)library(dplyr)athletes <- readcsv(“olympics.tsv”)denmark_1964 <- athletes %>% filter(NOC == “DEN”, Year == 1964)avg_height <- mean(denmark_1964$Height, na.rm = TRUE)
2005A608	Q12	library(readr)library(dplyr)olympics <- readcsv(“olympics.tsv”)sports_per_olympics <- olympics %>% group_by(Year, Season) %>% summarize(n_distinct(Sport))most_sports_olympics <- sports_per_olympics %>% filter(n_distinct == max(n_distinct))
2005A608	Q4	olympicdata ← readcsv(“olympics.tsv”)%>%library(readr)library(dplyr)athletes <- read_csv(“olympics.tsv”)winter_athletes <- athletes %>% filter(Season == “Winter”)shortest_athlete <- winter_athletes %>% filter(!is.na(Height)) %>% arrange(Height) %>% slice(1)
2005A608	Q7	olympic ←readtsv(“olympics.tsv”)%>% select(gold medals)%>% count(gold medals)
2005A612	Q10	library(readr)library(dplyr)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")d_1964 <- olympics_data %>% filter(NOC == “DEN” & Year == 1964)average_height <- mean(d_1964$Height)print(average_height)
2005A612	Q13	library(readr)library(dplyr)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics_data %>% group_by(name, year) %>% arrange(desc(name), year)
2005A612	Q14	library(readr)library(dplyr)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")country_participations <- olympics_data %>% select(participations) group_by(NOC) %>% summarise(participations) %>% arrange(desc(participations))print(participations)
2005A612	Q4	library(readr)library(dplyr)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")olympics_data %>% group_by(height) %>% summarize(max_height= desc(max(height)))
2005A612	Q7	library(readr)library(dplyr)olympics_data <- read_tsv(“https://zenodo.org/record/6803028/files/olympics.tsv")sh_gold_medalists <- olympics_data %>% filter(Height < 160 & Medal == “Gold”)print(shgoldmedalists)