library("XML")
library("methods")
library("rjson")
library("httr")
library("htmltab")
library("RCurl")The purpose of this assignment is to familiarize ourselves with the structures of json, extended markup language and html and how each stores objects and attributes. We generated a simple dataset of books with attributes such as title, author and publish date and created a separate file for each language to represent these books and attributes contained. These files were then read into r utilizing specific packages for this purpose and transformed into tidy dataframes for further use.
#read json file into R
books_json <- fromJSON(file="https://raw.githubusercontent.com/cassie-boylan/DATA-607/main/books_json_version.json")
#Convert json output to data frame
books_json_data_frame <- as.data.frame(books_json)
print(books_json_data_frame)## Title Author Rating
## 1 The Trespasser Tana French 4.41
## 2 Frankenstein Mary Shelley 4.53
## 3 Uprooted Nadia Novik 4.07
## 4 Vicious V.E. Schwab 4.20
## 5 Missing, Presumed Susie Steiner 3.49
## 6 Stay Sexy & Dont Get Murdered Karen Kilgariff,Georgia Hardstark 4.09
## Genre Year Publisher
## 1 Mystery 2016 Penguin
## 2 Classics 1818 Signet Classics
## 3 Fantasy 2015 Del Ray
## 4 Fantasy 2013 Tor Books
## 5 Mystery 2016 Random House
## 6 Memoir 2019 Forge Books#Convert xml output to data frame
books_xml_dataframe <- xmlToDataFrame("booksv2.xml")
print(books_xml_dataframe)## title author rating
## 1 The Trespasser Tana French 4.41
## 2 Frankenstein Mary Shelley 4.53
## 3 Uprooted Naomi Novik 4.07
## 4 Vicious V.E. Schwab 4.20
## 5 Missing,Presumed Susie Steiner 3.49
## 6 Stay Sexy and Dont Get Murdered Karen Kilgariff, Georgia Hardstark 4.09
## genre year publisher
## 1 Mystery 2016 Penguin
## 2 Classics 1818 Signet Classics
## 3 Fantasy 2015 Del Ray
## 4 Fantasy 2013 Del Ray
## 5 Mystery 2016 Random House
## 6 Memoir 2019 Forge Booksbooks_html <- htmltab("https://raw.githubusercontent.com/cassie-boylan/DATA-607/main/books.html", which =1)
print(books_html)## title author
## 2 The Trespasser Tana French
## 3 Frankenstein Mary Shelley
## 4 Uprooted Naomi Novik
## 5 Vicious V.E. Schwab
## 6 Missing, Presumed Susie Steiner
## 7 Stay Sexy & Don't Get Murdered Karen Kilgariff Georgia Hardstark
## genre rating year publisher
## 2 Mystery 4.41 2016 Penguin
## 3 Classics 4.53 1818 Signet Classics
## 4 Fantasy 4.07 2015 Del Ray
## 5 Fantasy 4.20 2013 Tor Books
## 6 Mystery 3.49 2016 Random House
## 7 Memoir 4.09 2019 Forge Books