DATA 607 Assignment 07

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.4.3

## Warning: package 'ggplot2' was built under R version 4.4.3

## Warning: package 'dplyr' was built under R version 4.4.3

library(openintro)

## Warning: package 'openintro' was built under R version 4.4.3

We will choose three books and deliverable would be the three source files.

Package

# Install zoo if not already installed
if (!requireNamespace("xml2", quietly = TRUE)) {install.packages("xml2")}
if (!requireNamespace("jsonlite", quietly = TRUE)) {install.packages("jsonlite")}
if (!requireNamespace("rvest", quietly = TRUE)) install.packages("rvest")

LIBRARY

# Load necessary libraries
library(xml2)

## Warning: package 'xml2' was built under R version 4.4.3

library(jsonlite)

## Warning: package 'jsonlite' was built under R version 4.4.3

## 
## Attaching package: 'jsonlite'

## The following object is masked from 'package:purrr':
## 
##     flatten

library(rvest)

## 
## Attaching package: 'rvest'

## The following object is masked from 'package:readr':
## 
##     guess_encoding

Load dat afor HTML

# Load HTML file
html_data <- read_html("https://raw.githubusercontent.com/tanzil64/DATA-607-Assignment-07/refs/heads/main/books.html")
table_data <- html_table(html_nodes(html_data, "table")[[1]])
#print("HTML Data:")
#print(table_data)
df_html <-data.frame(table_data)
print(df_html)

##                                                                                             Title
## 1 The Politics of Innovation: Why Some Countries Are Better Than Others at Science and Technology
## 2                               How the West Came to Rule: The Geopolitical Origins of Capitalism
## 3                                                                The Fourth Industrial Revolution
##                                             Authors
## 1                               Mark Zachary Taylor
## 2 Alexander Anievas, Kerem NiÅ\u009fancıoÄ\u009flu
## 3                                      Klaus Schwab
##                                                           Interesting.Attributes
## 1     Explores how politics, rather than institutions, drive S&T competitiveness
## 2 Challenges Eurocentric views by arguing capitalism's rise was a global process
## 3                        Discusses technological advancements shaping the future

Load dat afor XML

# Load XML file using xml2
xml_data <- read_xml("https://raw.githubusercontent.com/tanzil64/DATA-607-Assignment-07/refs/heads/main/books.xml")
xml_books <- xml_find_all(xml_data, "//book")
books_list <- lapply(xml_books, function(book) {
  list(
    title = xml_text(xml_find_first(book, "title")),
    authors = xml_text(xml_find_all(book, "authors/author")),
    attributes = xml_text(xml_find_all(book, "attributes/attribute"))
  )
})


df_xml <-data.frame(books_list)
print(df_xml)

##                                                                                             title
## 1 The Politics of Innovation: Why Some Countries Are Better Than Others at Science and Technology
## 2 The Politics of Innovation: Why Some Countries Are Better Than Others at Science and Technology
##               authors
## 1 Mark Zachary Taylor
## 2 Mark Zachary Taylor
##                                                                   attributes
## 1 Explores how politics, rather than institutions, drive S&T competitiveness
## 2 Explores how politics, rather than institutions, drive S&T competitiveness
##                                                             title.1
## 1 How the West Came to Rule: The Geopolitical Origins of Capitalism
## 2 How the West Came to Rule: The Geopolitical Origins of Capitalism
##           authors.1
## 1 Alexander Anievas
## 2 Kerem Nişancıoğlu
##                                                                     attributes.1
## 1 Challenges Eurocentric views by arguing capitalism's rise was a global process
## 2 Challenges Eurocentric views by arguing capitalism's rise was a global process
##                            title.2    authors.2
## 1 The Fourth Industrial Revolution Klaus Schwab
## 2 The Fourth Industrial Revolution Klaus Schwab
##                                              attributes.2
## 1 Discusses technological advancements shaping the future
## 2 Discusses technological advancements shaping the future

##print("XML Data:")
#print(books_list)

Load dat afor Json

# Load JSON file
json_data <- fromJSON("https://raw.githubusercontent.com/tanzil64/DATA-607-Assignment-07/refs/heads/main/books.json")
df_json <-data.frame(json_data)
print(df_json)

##                                                                                       books.title
## 1 The Politics of Innovation: Why Some Countries Are Better Than Others at Science and Technology
## 2                               How the West Came to Rule: The Geopolitical Origins of Capitalism
## 3                                                                The Fourth Industrial Revolution
##                          books.authors
## 1                  Mark Zachary Taylor
## 2 Alexander Anievas, Kerem Nişancıoğlu
## 3                         Klaus Schwab
##                                                                 books.attributes
## 1     Explores how politics, rather than institutions, drive S&T competitiveness
## 2 Challenges Eurocentric views by arguing capitalism's rise was a global process
## 3                        Discusses technological advancements shaping the future

#print("JSON Data:")
#print(json_data)

Check Identical

# Check if df_html and df_xml are identical
identical(df_html, df_xml)

## [1] FALSE

# Check if df_html and df_json are identical
identical(df_html, df_json)

## [1] FALSE

# Check if df_xml and df_json are identical
identical(df_xml, df_json)

## [1] FALSE

Conclusion: In conclusion we can say that the files are in different format and not identical.