Getting and Cleaning Data in R - Week 2 Quiz

library(httr)
library(jsonlite)

# Question #1

# A. Find OAuth settings for github:
#    http://developer.github.com/v3/oauth/
oauth_endpoints("github")

## <oauth_endpoint>
##  authorize: https://github.com/login/oauth/authorize
##  access:    https://github.com/login/oauth/access_token

# B. To make your own application, register at
#    https://github.com/settings/developers. Use any URL for the homepage URL
#    (http://github.com is fine) and  http://localhost:1410 as the callback url
#
# Authenticate with key and secret below.
myapp <- oauth_app("github",
key = "ca3a9589ef2819e1566f",
secret = "e492571c91a14f0e4dc9373c48b102cf22fadcfb"
)

# C. Get OAuth credentials
github_token <- oauth2.0_token(oauth_endpoints("github"), myapp)

# C. Use API
gtoken <- config(token = github_token)
req <- GET("https://api.github.com/users/jtleek/repos", gtoken)
stop_for_status(req)
jsondata <- fromJSON("https://api.github.com/users/jtleek/repos")

#E. Get names of Prof. Leek's repositories
jsondata$name

##  [1] "2018"                    "ads2020"                
##  [3] "advdatasci"              "advdatasci-project"     
##  [5] "advdatasci-swirl"        "advdatasci15"           
##  [7] "advdatasci16"            "advdatasci_swirl"       
##  [9] "ballgown"                "big_course"             
## [11] "bookdown-start"          "capitalIn21stCenturyinR"
## [13] "careerplanning"          "COVID-19"               
## [15] "crsra"                   "cshlcg-labs"            
## [17] "dataanalysis"            "datascientist"          
## [19] "datasharing"             "datawomenontwitter"     
## [21] "day1"                    "derfinder"              
## [23] "derfinder-1"             "DSM"                    
## [25] "EDA-Project"             "escalatr"               
## [27] "euclideo"                "firstpaper"             
## [29] "futureofstats"           "gcd"

jsondata[19,47]

## [1] "2013-11-07T13:25:07Z"

# Question #2

# Download the .csv file and assign to the variable 'acs'

download.file("https://d396qusza40orc.cloudfront.net/getdata%2Fdata%2Fss06pid.csv","acs.csv")
acs <- read.csv("acs.csv")

library(sqldf)

## Loading required package: gsubfn

## Loading required package: proto

## Warning in doTryCatch(return(expr), name, parentenv, handler): unable to load shared object '/Library/Frameworks/R.framework/Resources/modules//R_X11.so':
##   dlopen(/Library/Frameworks/R.framework/Resources/modules//R_X11.so, 6): Library not loaded: /opt/X11/lib/libSM.6.dylib
##   Referenced from: /Library/Frameworks/R.framework/Versions/3.6/Resources/modules/R_X11.so
##   Reason: image not found

## Could not load tcltk.  Will use slower R code instead.

## Loading required package: RSQLite

head(sqldf("select pwgtp1 from acs where AGEP<50"))

##   pwgtp1
## 1     87
## 2     88
## 3     94
## 4     91
## 5    539
## 6    192

# Question #3

head(sqldf("select distinct AGEP from acs"))

##   AGEP
## 1   43
## 2   42
## 3   16
## 4   14
## 5   29
## 6   40

# Question #4

con <- url("http://biostat.jhsph.edu/~jleek/contact.html")
htmlCode <- readLines(con)
close(con)

num_chars <- nchar(htmlCode)
num_chars[c(10,20,30,100)]

## [1] 45 31  7 25

# Question #5

download.file("https://d396qusza40orc.cloudfront.net/getdata%2Fwksst8110.for","data.csv")
data <- read.fwf("data.csv",c(10,9,4,9),skip=4)
head(data)

##           V1   V2   V3   V4
## 1  03JAN1990 23.4 -0.4 25.1
## 2  10JAN1990 23.4 -0.8 25.2
## 3  17JAN1990 24.2 -0.3 25.3
## 4  24JAN1990 24.4 -0.5 25.5
## 5  31JAN1990 25.1 -0.2 25.8
## 6  07FEB1990 25.8  0.2 26.1

sum(data$V4)

## [1] 32426.7