Assignment7

Books Info in 3 different file formats

Load libraries

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(xml2)

## Warning: package 'xml2' was built under R version 4.3.3

library(rjson)
library(XML)

## Warning: package 'XML' was built under R version 4.3.2

library(DT)

## Warning: package 'DT' was built under R version 4.3.3

library(rvest)

## Warning: package 'rvest' was built under R version 4.3.3

library(tibble)
library(jsonlite)

## 
## Attaching package: 'jsonlite'

## The following objects are masked from 'package:rjson':
## 
##     fromJSON, toJSON

Load html file

book_info_html <- read_html("https://raw.githubusercontent.com/topkelama/lfsStorage/main/info_books.html")

Convert to dataframe

tables1 <- html_table(book_info_html)
book_df_html <- data.frame(tables1[[1]], stringsAsFactors = FALSE)
book_df_html

##                             Title           Authors Pages Release.Year Price
## 1   Cloud Essentials+ Study Guide    Quentin Docter   368         2020 35.56
## 2   Cloud Essentials+ Study Guide        Cory Fuchs   368         2020 35.56
## 3 Data Science Using Python and R Chantal D. Larose   247         2019 90.15
## 4 Data Science Using Python and R  Daniel T. Larose   247         2019 90.15
## 5       Kubernetes Up and Running     Brendan Burns   277         2019 47.82
## 6       Kubernetes Up and Running          Joe Beda   277         2019 47.82
## 7       Kubernetes Up and Running  Kelsey Hightower   277         2019 47.82
##                ISBN
## 1 978-1-119-64222-0
## 2 978-1-119-64222-0
## 3     9781119526834
## 4     9781119526834
## 5 978-1-492-04653-0
## 6 978-1-492-04653-0
## 7 978-1-492-04653-0

Load xml file

book_info_xml <- read_xml("https://raw.githubusercontent.com/topkelama/lfsStorage/main/info_books.xml")

convert to dataframe

bookInfo_parse <- xmlParse(book_info_xml)
book_xml_df <- xmlToDataFrame(bookInfo_parse, stringsAsFactors = FALSE)

book_xml_df

##                             Title                               Authors Pages
## 1   Cloud Essentials+ Study Guide              Quentin DocterCory Fuchs   368
## 2 Data Science Using Python and R      Chantal D. LaroseDaniel T.Larose   247
## 3       Kubernetes Up and Running Brendan BurnsJoe BedaKelsey Hightower   277
##   Release_Year Price              ISBN
## 1         2020 35.56 978-1-119-64222-0
## 2         2019 90.15     9781119526834
## 3         2019 47.82 978-1-492-04653-0

Load json file

json_file <- "https://raw.githubusercontent.com/topkelama/lfsStorage/main/info_books.json"
download.file(json_file, destfile = "info_books.json", quiet = TRUE)

# Read and parse the JSON file
book_info_json <- fromJSON("info_books.json")

# Expand the Authors list into separate rows
book_info_json <- book_info_json %>%
  mutate(Authors = lapply(Authors, toString)) %>%
  unnest(Authors)
book_info_json

## # A tibble: 3 × 6
##   Title                           Authors       Pages `Release Year` Price ISBN 
##   <chr>                           <chr>         <int>          <int> <dbl> <chr>
## 1 Cloud Essentials+ Study Guide   Quentin Doct…   368           2020  35.7 978-…
## 2 Data Science Using Python and R Chantal D. L…   247           2019  90.2 9781…
## 3 Kubernetes Up and Running       Brendan Burn…   277           2019  47.8 978-…

File links:- XML File JSON File HTML File

Conclusion:- The JSON file did not have issue with the nested lists such as Author column, where there are multiple authors for a single Title. It automatically, did put in long format. However, with the xml and json, it did put multiple authors in a single row under the Authors column. Three dataframes have similarities but not identical.