Extra Credit
Heleine Fouda
2023-11-05
ASSIGNMENT: Working with the two JSON files available through the API at nobelprize.org, ask and answer 4 interesting questions, e.g. “Which country”lost” the most nobel laureates (who were born there but received their Nobel prize as a citizen of a different country)?”
Getting started
Retrieve data from the API and parse it as JSON:
Various options for importing the Json file:
# Option 1
api_url <- "https://api.nobelprize.org/2.1/laureates?_ga=2./1901-2023"
response <- GET(api_url)
response## Response [https://api.nobelprize.org/2.1/laureates?_ga=2./1901-2023]
## Date: 2023-11-06 02:45
## Status: 200
## Content-Type: application/json;charset=utf-8
## Size: 90.7 kB# option 2
api_url1 <- "https://api.nobelprize.org/2.1/laureates?_ga=2.155154616.1232644105.1699062535-556212721.1698729641"
api_url2 <- "https://api.nobelprize.org/2.1/nobelPrizes?_ga=2.123220747.1232644105.1699062535-556212721.1698729641"
full_url <- paste0(api_url1,api_url2)
response <- GET(full_url)
response## Response [https://api.nobelprize.org/2.1/laureates?_ga=2.155154616.1232644105.1699062535-556212721.1698729641https://api.nobelprize.org/2.1/nobelPrizes?_ga=2.123220747.1232644105.1699062535-556212721.1698729641]
## Date: 2023-11-06 02:45
## Status: 200
## Content-Type: application/json;charset=utf-8
## Size: 90.7 kB# Option 3, retrieving the data set from the github repository
prize_url <- "https://raw.githubusercontent.com/Heleinef/Data-Science-Master_Heleine/main/Laureates"
prize_json <- GET(prize_url)
prize_json## Response [https://raw.githubusercontent.com/Heleinef/Data-Science-Master_Heleine/main/Laureates]
## Date: 2023-11-06 02:45
## Status: 200
## Content-Type: text/plain; charset=utf-8
## Size: 119 kB
## {"laureates":[{"id":"745","knownName":{"en":"A. Michael Spence","se":"A. Mich...
## {"nobelPrizes":[{"awardYear":"1901","category":{"en":"Chemistry","no":"Kjemi"...# Check if the request was successful
prize_json$status_code## [1] 200Converting the JSON file into a data frame:
nobel_data <- content(response, "text", encoding = "UTF-8")
nobel_df <- jsonlite::fromJSON(nobel_data)# Summary
summary(nobel_df) ## Length Class Mode
## laureates 14 data.frame list
## meta 6 -none- list
## links 4 -none- listNobels_df <- as.data.frame(nobel_df)
tibble(Nobels_df)## # A tibble: 25 × 24
## laureates.id laureates.knownName$en $se laureates.givenName$en
## <chr> <chr> <chr> <chr>
## 1 745 A. Michael Spence A. Michael Spence A. Michael
## 2 102 Aage N. Bohr Aage N. Bohr Aage N.
## 3 779 Aaron Ciechanover Aaron Ciechanover Aaron
## 4 259 Aaron Klug Aaron Klug Aaron
## 5 1004 Abdulrazak Gurnah Abdulrazak Gurnah Abdulrazak
## 6 114 Abdus Salam Abdus Salam Abdus
## 7 982 Abhijit Banerjee Abhijit Banerjee Abhijit
## 8 981 Abiy Ahmed Ali Abiy Ahmed Ali Abiy
## 9 843 Ada E. Yonath Ada E. Yonath Ada E.
## 10 866 Adam G. Riess Adam G. Riess Adam G.
## # ℹ 15 more rows
## # ℹ 22 more variables: laureates.givenName$se <chr>,
## # laureates.familyName <df[,2]>, laureates.fullName <df[,2]>,
## # laureates.fileName <chr>, laureates.gender <chr>, laureates.birth <df[,2]>,
## # laureates.wikipedia <df[,2]>, laureates.wikidata <df[,2]>,
## # laureates.sameAs <list>, laureates.links <list>,
## # laureates.nobelPrizes <list>, laureates.death <df[,2]>, …Our working data set from the retrieved data
Nobels_laureates <- Nobels_df %>%
select(laureates.id, laureates.fileName, laureates.gender,links.first)
Nobels_laureates## laureates.id laureates.fileName laureates.gender
## 1 745 spence male
## 2 102 bohr male
## 3 779 ciechanover male
## 4 259 klug male
## 5 1004 gurnah male
## 6 114 salam male
## 7 982 banerjee male
## 8 981 abiy male
## 9 843 yonath female
## 10 866 riess male
## 11 199 butenandt male
## 12 164 baeyer male
## 13 185 windaus male
## 14 541 esquivel male
## 15 292 zewail male
## 16 853 suzuki male
## 17 978 yoshino male
## 18 819 gore male
## 19 1012 aspect male
## 20 729 heeger male
## 21 376 hodgkin male
## 22 730 macdiarmid male
## 23 11 michelson male
## 24 628 camus male
## 25 403 claude male
## links.first
## 1 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 2 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 3 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 4 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 5 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 6 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 7 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 8 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 9 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 10 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 11 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 12 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 13 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 14 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 15 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 16 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 17 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 18 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 19 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 20 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 21 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 22 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 23 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 24 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25
## 25 https://masterdataapi.nobelprize.org/2.1/laureates?offset=0&limit=25laureates names
Nobels_name <- Nobels_df %>%
select(laureates.fileName)
Nobels_name ## laureates.fileName
## 1 spence
## 2 bohr
## 3 ciechanover
## 4 klug
## 5 gurnah
## 6 salam
## 7 banerjee
## 8 abiy
## 9 yonath
## 10 riess
## 11 butenandt
## 12 baeyer
## 13 windaus
## 14 esquivel
## 15 zewail
## 16 suzuki
## 17 yoshino
## 18 gore
## 19 aspect
## 20 heeger
## 21 hodgkin
## 22 macdiarmid
## 23 michelson
## 24 camus
## 25 claudeLaureates ids
Nobels_id<- Nobels_df %>%
select(laureates.id)
Nobels_id## laureates.id
## 1 745
## 2 102
## 3 779
## 4 259
## 5 1004
## 6 114
## 7 982
## 8 981
## 9 843
## 10 866
## 11 199
## 12 164
## 13 185
## 14 541
## 15 292
## 16 853
## 17 978
## 18 819
## 19 1012
## 20 729
## 21 376
## 22 730
## 23 11
## 24 628
## 25 403Gender distribution
nobels_gender <- Nobels_df %>%
select(laureates.gender)
nobels_gender ## laureates.gender
## 1 male
## 2 male
## 3 male
## 4 male
## 5 male
## 6 male
## 7 male
## 8 male
## 9 female
## 10 male
## 11 male
## 12 male
## 13 male
## 14 male
## 15 male
## 16 male
## 17 male
## 18 male
## 19 male
## 20 male
## 21 male
## 22 male
## 23 male
## 24 male
## 25 maleNobels_laureates <- Nobels_df %>%
select(laureates.id, laureates.fileName, laureates.gender)
ggplot(Nobels_laureates, aes(y = laureates.id, color = laureates.gender)) +
geom_bar()