In UBC-MDS/Karl:

This section lists some examples of public HTTP APIs that publish data in JSON format. These are great to get a sense of the complex structures that are encountered in real world JSON data. All services are free, but some require registration/authentication. Each example returns lots of data, therefore not all output is printed in this document.

library(jsonlite)

Github

Github is an online code repository and has APIs to get live data on almost all activity. Below some examples from a well known R package and author:

hadley_orgs <- fromJSON("https://api.github.com/users/hadley/orgs")
hadley_repos <- fromJSON("https://api.github.com/users/hadley/repos")
gg_commits <- fromJSON("https://api.github.com/repos/hadley/ggplot2/commits")
gg_issues <- fromJSON("https://api.github.com/repos/hadley/ggplot2/issues")

#latest issues
paste(format(gg_issues$user$login), ":", gg_issues$title)

 [1] "jsta            : fix broken stowers link"                                                               
 [2] "krlmlr          : Log transform on geom_bar() silently omits layer"                                      
 [3] "yutannihilation : Fix a broken link in README"                                                           
 [4] "raubreywhite    : Fix theme_gray's legend/panels for large base_size"                                    
 [5] "batuff          : Add minor ticks to axes"                                                               
 [6] "mcol            : overlapping boxes with geom_boxplot(varwidth=TRUE)"                                    
 [7] "karawoo         : Fix density calculations for groups with one or two elements"                          
 [8] "Thieffen        : fix typo"                                                                              
 [9] "Thieffen        : fix typo"                                                                              
[10] "thjwong         : `axis.line` works, but not `axis.line.x` and `axis.line.y`"                            
[11] "schloerke       : scale_discrete not listening to 'breaks' arg"                                          
[12] "hadley          : Consider use of vwline"                                                                
[13] "JTapper         : geom_polygon accessing data$y"                                                         
[14] "Ax3man          : Added linejoin parameter to geom_segment."                                             
[15] "LSanselme       : geom_density with groups of 1 or 2 elements"                                           
[16] "philstraforelli : (feature request) Changing facet_wrap strip colour based on variable in data frame"    
[17] "eliocamp        : geom_tile() + coord_map() is extremely slow."                                          
[18] "eliocamp        : facet_wrap() doesn't play well with expressions in facets. "                           
[19] "dantonnoriega   : Request: Quick visual example for each geom at http://ggplot2.tidyverse.org/reference/"
[20] "randomgambit    : it would be nice to have date_breaks('0.2 sec')"                                       
[21] "adrfantini      : Labels can overlap in coord_sf()"                                                      
[22] "adrfantini      : borders() is incompatible with coord_sf() with projected coordinates"                  
[23] "adrfantini      : coord_proj() is superior to coord_map() and could be included in the default ggplot"   
[24] "adrfantini      : Coordinates labels and gridlines are wrong in coord_map()"                             
[25] "jonocarroll     : Minor typo: monotonous -> monotonic"                                                   
[26] "FabianRoger     : label.size in geom_label is ignored when printing to pdf"                              
[27] "andrewdolman    : Add note recommending annotate"                                                        
[28] "Henrik-P        : scale_identity doesn't play well with guide = \"legend\""                              
[29] "cpsievert       : stat_sf(geom = \"text\")"                                                              
[30] "hadley          : Automatically fill in x for univariate boxplot"                                        

CitiBike NYC

A single public API that shows location, status and current availability for all stations in the New York City bike sharing imitative.

citibike <- fromJSON("http://citibikenyc.com/stations/json")
stations <- citibike$stationBeanList
colnames(stations)

 [1] "id"                    "stationName"          
 [3] "availableDocks"        "totalDocks"           
 [5] "latitude"              "longitude"            
 [7] "statusValue"           "statusKey"            
 [9] "availableBikes"        "stAddress1"           
[11] "stAddress2"            "city"                 
[13] "postalCode"            "location"             
[15] "altitude"              "testStation"          
[17] "lastCommunicationTime" "landMark"             

nrow(stations)

[1] 666

Ergast

The Ergast Developer API is an experimental web service which provides a historical record of motor racing data for non-commercial purposes.

res <- fromJSON('http://ergast.com/api/f1/2004/1/results.json')
drivers <- res$MRData$RaceTable$Races$Results[[1]]$Driver
colnames(drivers)

[1] "driverId"        "code"            "url"             "givenName"      
[5] "familyName"      "dateOfBirth"     "nationality"     "permanentNumber"

drivers[1:10, c("givenName", "familyName", "code", "nationality")]

   givenName    familyName code nationality
1    Michael    Schumacher  MSC      German
2     Rubens   Barrichello  BAR   Brazilian
3   Fernando        Alonso  ALO     Spanish
4       Ralf    Schumacher  SCH      German
5       Juan Pablo Montoya  MON   Colombian
6     Jenson        Button  BUT     British
7      Jarno        Trulli  TRU     Italian
8      David     Coulthard  COU     British
9     Takuma          Sato  SAT    Japanese
10 Giancarlo    Fisichella  FIS     Italian

ProPublica

Below an example from the ProPublica Nonprofit Explorer API where we retrieve the first 10 pages of tax-exempt organizations in the USA, ordered by revenue. The rbind_pages function is used to combine the pages into a single data frame.

#store all pages in a list first
baseurl <- "https://projects.propublica.org/nonprofits/api/v1/search.json?order=revenue&sort_order=desc"
pages <- list()
for(i in 0:10){
  mydata <- fromJSON(paste0(baseurl, "&page=", i), flatten=TRUE)
  message("Retrieving page ", i)
  pages[[i+1]] <- mydata$filings
}

#combine all into one
filings <- rbind_pages(pages)

#check output
nrow(filings)

[1] 275

filings[1:10, c("organization.sub_name", "organization.city", "totrevenue")]

               organization.sub_name organization.city  totrevenue
1  KAISER FOUNDATION HEALTH PLAN INC           OAKLAND 40148558254
2  KAISER FOUNDATION HEALTH PLAN INC           OAKLAND 37786011714
3        KAISER FOUNDATION HOSPITALS           OAKLAND 20796549014
4        KAISER FOUNDATION HOSPITALS           OAKLAND 17980030355
5    PARTNERS HEALTHCARE SYSTEM INC         SOMERVILLE 10619215354
6                              UPMC         PITTSBURGH 10098163008
7    UAW RETIREE MEDICAL BENEFITS TR           DETROIT  9890722789
8   THRIVENT FINANCIAL FOR LUTHERANS       MINNEAPOLIS  9475129863
9   THRIVENT FINANCIAL FOR LUTHERANS       MINNEAPOLIS  9021585970
10                    DIGNITY HEALTH     SAN FRANCISCO  8718896265

New York Times

The New York Times has several APIs as part of the NYT developer network. These interface to data from various departments, such as news articles, book reviews, real estate, etc. Registration is required (but free) and a key can be obtained at here. The code below includes some example keys for illustration purposes.

#search for articles
article_key <- "&api-key=b75da00e12d54774a2d362adddcc9bef"
url <- "http://api.nytimes.com/svc/search/v2/articlesearch.json?q=obamacare+socialism"
req <- fromJSON(paste0(url, article_key))
articles <- req$response$docs
colnames(articles)

 [1] "web_url"           "snippet"           "lead_paragraph"   
 [4] "abstract"          "print_page"        "blog"             
 [7] "source"            "multimedia"        "headline"         
[10] "keywords"          "pub_date"          "document_type"    
[13] "news_desk"         "section_name"      "subsection_name"  
[16] "byline"            "type_of_material"  "_id"              
[19] "word_count"        "slideshow_credits"

#search for best sellers
books_key <- "&api-key=76363c9e70bc401bac1e6ad88b13bd1d"
url <- "http://api.nytimes.com/svc/books/v2/lists/overview.json?published_date=2013-01-01"
req <- fromJSON(paste0(url, books_key))
bestsellers <- req$results$list
category1 <- bestsellers[[1, "books"]]
subset(category1, select = c("author", "title", "publisher"))

           author                title                  publisher
1   Gillian Flynn            GONE GIRL           Crown Publishing
2    John Grisham        THE RACKETEER Knopf Doubleday Publishing
3       E L James FIFTY SHADES OF GREY Knopf Doubleday Publishing
4 Nicholas Sparks           SAFE HAVEN   Grand Central Publishing
5  David Baldacci        THE FORGOTTEN   Grand Central Publishing

#movie reviews
movie_key <- "&api-key=b75da00e12d54774a2d362adddcc9bef"
url <- "http://api.nytimes.com/svc/movies/v2/reviews/dvd-picks.json?order=by-date"
req <- fromJSON(paste0(url, movie_key))
reviews <- req$results
colnames(reviews)

 [1] "display_title"    "mpaa_rating"      "critics_pick"    
 [4] "byline"           "headline"         "summary_short"   
 [7] "publication_date" "opening_date"     "date_updated"    
[10] "link"             "multimedia"      

reviews[1:5, c("display_title", "byline", "mpaa_rating")]

                    display_title            byline mpaa_rating
1                 Hermia & Helena       GLENN KENNY            
2             The Women's Balcony NICOLE HERRINGTON            
3               Long Strange Trip    DANIEL M. GOLD           R
4 Joshua: Teenager vs. Superpower    KEN JAWOROWSKI            
5                 Berlin Syndrome       GLENN KENNY           R

Sunlight Foundation

The Sunlight Foundation is a non-profit that helps to make government transparent and accountable through data, tools, policy and journalism. Register a free key at here. An example key is provided.

key <- "&apikey=39c83d5a4acc42be993ee637e2e4ba3d"

#Find bills about drones
drone_bills <- fromJSON(paste0("http://openstates.org/api/v1/bills/?q=drone", key))
drone_bills$title <- substring(drone_bills$title, 1, 40)
print(drone_bills[1:5, c("title", "state", "chamber", "type")])

                                     title state chamber type
1               AIRPORT AUTHORITIES-DRONES    il   upper bill
2 Study Drone Use By Public Safety Agencie    co   lower bill
3 AIRCRAFT/AVIATION:  Provides for the exc    la   upper bill
4           relative to the use of drones.    nh   lower bill
5 Use or Operation of a Drone by Certain O    fl   lower bill

#Local legislators
legislators <- fromJSON(paste0("http://congress.api.sunlightfoundation.com/",
  "legislators/locate?latitude=42.96&longitude=-108.09", key))
subset(legislators$results, select=c("last_name", "chamber", "term_start", "twitter_id"))

  last_name chamber term_start      twitter_id
1    Cheney   house 2017-01-03    RepLizCheney
2      Enzi  senate 2015-01-06     SenatorEnzi
3  Barrasso  senate 2013-01-03 SenJohnBarrasso

Twitter

The twitter API requires OAuth2 authentication. Some example code:

#Create your own appication key at https://dev.twitter.com/apps
consumer_key = "EZRy5JzOH2QQmVAe9B4j2w";
consumer_secret = "OIDC4MdfZJ82nbwpZfoUO4WOLTYjoRhpHRAWj6JMec";

#Use basic auth
secret <- jsonlite::base64_enc(paste(consumer_key, consumer_secret, sep = ":"))
req <- httr::POST("https://api.twitter.com/oauth2/token",
  httr::add_headers(
    "Authorization" = paste("Basic", gsub("\n", "", secret)),
    "Content-Type" = "application/x-www-form-urlencoded;charset=UTF-8"
  ),
  body = "grant_type=client_credentials"
);

#Extract the access token
httr::stop_for_status(req, "authenticate with twitter")
token <- paste("Bearer", httr::content(req)$access_token)

#Actual API call
url <- "https://api.twitter.com/1.1/statuses/user_timeline.json?count=10&screen_name=Rbloggers"
req <- httr::GET(url, httr::add_headers(Authorization = token))
json <- httr::content(req, as = "text")
tweets <- fromJSON(json)
substring(tweets$text, 1, 100)

 [1] "simmer 3.6.2 https://t.co/rRxgY2Ypfa #rstats #DataScience"                                           
 [2] "Getting data for every Census tract in the US with purrr and tidycensus https://t.co/B3NYJS8sLO #rst"
 [3] "Gender Roles with Text Mining and N-grams https://t.co/Rwj0IaTiAR #rstats #DataScience"              
 [4] "Data Science Podcasts https://t.co/SaAuO82a7M #rstats #DataScience"                                  
 [5] "Reflections on ROpenSci Unconference 2017 https://t.co/87kMldvrsd #rstats #DataScience"              
 [6] "Summarizing big data in R https://t.co/GMaZZ9sWiL #rstats #DataScience"                              
 [7] "Mining CRAN DESCRIPTION Files https://t.co/gWEIAYaBZF #rstats #DataScience"                          
 [8] "New package polypoly (helper functions for orthogonal polynomials) https://t.co/MzzzcIySym #rstats #"
 [9] "Hospital Infection Scores – R Shiny App https://t.co/Rf8wKNBPU6 #rstats #DataScience"                
[10] "New R job: Software Engineer in Test for RStudio https://t.co/X1bWkKlzYv #rstats #DataScience #jobs" 

UBC-MDS/Karl documentation built on May 22, 2019, 1:53 p.m.