Week 7 Assignment

library(tibble)
library(jsonlite)
library(XML)
library(arrow)
library(htmlTable)

Create the data and display it in a dataframe

Here, I key in the data and then create a dataframe.

# Create the data frame
mart_data <- tibble::tribble(
  ~Category, ~Item_Name, ~Item_ID, ~Brand, ~Price, ~Variation_ID, ~Variation_Details,
  "Electronics", "Smartphone", 101, "TechBrand", 699.99, "101-A", "Color: Black, Storage: 64GB",
  "Electronics", "Smartphone", 101, "TechBrand", 699.99, "101-B", "Color: White, Storage: 128GB",
  "Electronics", "Laptop", 102, "CompuBrand", 1099.99, "102-A", "Color: Silver, Storage: 256GB",
  "Electronics", "Laptop", 102, "CompuBrand", 1099.99, "102-B", "Color: Space Gray, Storage: 512GB",
  "Home Appliances", "Refrigerator", 201, "HomeCool", 899.99, "201-A", "Color: Stainless Steel, Capacity: 20 cu ft",
  "Home Appliances", "Refrigerator", 201, "HomeCool", 899.99, "201-B", "Color: White, Capacity: 18 cu ft",
  "Home Appliances", "Washing Machine", 202, "CleanTech", 499.99, "202-A", "Type: Front Load, Capacity: 4.5 cu ft",
  "Home Appliances", "Washing Machine", 202, "CleanTech", 499.99, "202-B", "Type: Top Load, Capacity: 5.0 cu ft",
  "Clothing", "T-Shirt", 301, "FashionCo", 19.99, "301-A", "Color: Blue, Size: S",
  "Clothing", "T-Shirt", 301, "FashionCo", 19.99, "301-B", "Color: Red, Size: M",
  "Clothing", "T-Shirt", 301, "FashionCo", 19.99, "301-C", "Color: Green, Size: L",
  "Clothing", "Jeans", 302, "DenimWorks", 49.99, "302-A", "Color: Dark Blue, Size: 32",
  "Clothing", "Jeans", 302, "DenimWorks", 49.99, "302-B", "Color: Light Blue, Size: 34",
  "Books", "Fiction Novel", 401, "-", 14.99, "401-A", "Format: Hardcover, Language: English",
  "Books", "Fiction Novel", 401, "-", 14.99, "401-B", "Format: Paperback, Language: Spanish",
  "Books", "Non-Fiction Guide", 402, "-", 24.99, "402-A", "Format: eBook, Language: English",
  "Books", "Non-Fiction Guide", 402, "-", 24.99, "402-B", "Format: Paperback, Language: French",
  "Sports Equipment", "Basketball", 501, "SportsGear", 29.99, "501-A", "Size: Size 7, Color: Orange",
  "Sports Equipment", "Tennis Racket", 502, "RacketPro", 89.99, "502-A", "Material: Graphite, Color: Black",
  "Sports Equipment", "Tennis Racket", 502, "RacketPro", 89.99, "502-B", "Material: Aluminum, Color: Silver"
)

print(mart_data)

## # A tibble: 20 × 7
##    Category        Item_Name Item_ID Brand  Price Variation_ID Variation_Details
##    <chr>           <chr>       <dbl> <chr>  <dbl> <chr>        <chr>            
##  1 Electronics     Smartpho…     101 Tech…  700.  101-A        Color: Black, St…
##  2 Electronics     Smartpho…     101 Tech…  700.  101-B        Color: White, St…
##  3 Electronics     Laptop        102 Comp… 1100.  102-A        Color: Silver, S…
##  4 Electronics     Laptop        102 Comp… 1100.  102-B        Color: Space Gra…
##  5 Home Appliances Refriger…     201 Home…  900.  201-A        Color: Stainless…
##  6 Home Appliances Refriger…     201 Home…  900.  201-B        Color: White, Ca…
##  7 Home Appliances Washing …     202 Clea…  500.  202-A        Type: Front Load…
##  8 Home Appliances Washing …     202 Clea…  500.  202-B        Type: Top Load, …
##  9 Clothing        T-Shirt       301 Fash…   20.0 301-A        Color: Blue, Siz…
## 10 Clothing        T-Shirt       301 Fash…   20.0 301-B        Color: Red, Size…
## 11 Clothing        T-Shirt       301 Fash…   20.0 301-C        Color: Green, Si…
## 12 Clothing        Jeans         302 Deni…   50.0 302-A        Color: Dark Blue…
## 13 Clothing        Jeans         302 Deni…   50.0 302-B        Color: Light Blu…
## 14 Books           Fiction …     401 -       15.0 401-A        Format: Hardcove…
## 15 Books           Fiction …     401 -       15.0 401-B        Format: Paperbac…
## 16 Books           Non-Fict…     402 -       25.0 402-A        Format: eBook, L…
## 17 Books           Non-Fict…     402 -       25.0 402-B        Format: Paperbac…
## 18 Sports Equipme… Basketba…     501 Spor…   30.0 501-A        Size: Size 7, Co…
## 19 Sports Equipme… Tennis R…     502 Rack…   90.0 502-A        Material: Graphi…
## 20 Sports Equipme… Tennis R…     502 Rack…   90.0 502-B        Material: Alumin…

Convert the dataset to JSON

# Converting the keyed to JSON
json_mart_data <- toJSON(mart_data, pretty = TRUE)
json_mart_data

## [
##   {
##     "Category": "Electronics",
##     "Item_Name": "Smartphone",
##     "Item_ID": 101,
##     "Brand": "TechBrand",
##     "Price": 699.99,
##     "Variation_ID": "101-A",
##     "Variation_Details": "Color: Black, Storage: 64GB"
##   },
##   {
##     "Category": "Electronics",
##     "Item_Name": "Smartphone",
##     "Item_ID": 101,
##     "Brand": "TechBrand",
##     "Price": 699.99,
##     "Variation_ID": "101-B",
##     "Variation_Details": "Color: White, Storage: 128GB"
##   },
##   {
##     "Category": "Electronics",
##     "Item_Name": "Laptop",
##     "Item_ID": 102,
##     "Brand": "CompuBrand",
##     "Price": 1099.99,
##     "Variation_ID": "102-A",
##     "Variation_Details": "Color: Silver, Storage: 256GB"
##   },
##   {
##     "Category": "Electronics",
##     "Item_Name": "Laptop",
##     "Item_ID": 102,
##     "Brand": "CompuBrand",
##     "Price": 1099.99,
##     "Variation_ID": "102-B",
##     "Variation_Details": "Color: Space Gray, Storage: 512GB"
##   },
##   {
##     "Category": "Home Appliances",
##     "Item_Name": "Refrigerator",
##     "Item_ID": 201,
##     "Brand": "HomeCool",
##     "Price": 899.99,
##     "Variation_ID": "201-A",
##     "Variation_Details": "Color: Stainless Steel, Capacity: 20 cu ft"
##   },
##   {
##     "Category": "Home Appliances",
##     "Item_Name": "Refrigerator",
##     "Item_ID": 201,
##     "Brand": "HomeCool",
##     "Price": 899.99,
##     "Variation_ID": "201-B",
##     "Variation_Details": "Color: White, Capacity: 18 cu ft"
##   },
##   {
##     "Category": "Home Appliances",
##     "Item_Name": "Washing Machine",
##     "Item_ID": 202,
##     "Brand": "CleanTech",
##     "Price": 499.99,
##     "Variation_ID": "202-A",
##     "Variation_Details": "Type: Front Load, Capacity: 4.5 cu ft"
##   },
##   {
##     "Category": "Home Appliances",
##     "Item_Name": "Washing Machine",
##     "Item_ID": 202,
##     "Brand": "CleanTech",
##     "Price": 499.99,
##     "Variation_ID": "202-B",
##     "Variation_Details": "Type: Top Load, Capacity: 5.0 cu ft"
##   },
##   {
##     "Category": "Clothing",
##     "Item_Name": "T-Shirt",
##     "Item_ID": 301,
##     "Brand": "FashionCo",
##     "Price": 19.99,
##     "Variation_ID": "301-A",
##     "Variation_Details": "Color: Blue, Size: S"
##   },
##   {
##     "Category": "Clothing",
##     "Item_Name": "T-Shirt",
##     "Item_ID": 301,
##     "Brand": "FashionCo",
##     "Price": 19.99,
##     "Variation_ID": "301-B",
##     "Variation_Details": "Color: Red, Size: M"
##   },
##   {
##     "Category": "Clothing",
##     "Item_Name": "T-Shirt",
##     "Item_ID": 301,
##     "Brand": "FashionCo",
##     "Price": 19.99,
##     "Variation_ID": "301-C",
##     "Variation_Details": "Color: Green, Size: L"
##   },
##   {
##     "Category": "Clothing",
##     "Item_Name": "Jeans",
##     "Item_ID": 302,
##     "Brand": "DenimWorks",
##     "Price": 49.99,
##     "Variation_ID": "302-A",
##     "Variation_Details": "Color: Dark Blue, Size: 32"
##   },
##   {
##     "Category": "Clothing",
##     "Item_Name": "Jeans",
##     "Item_ID": 302,
##     "Brand": "DenimWorks",
##     "Price": 49.99,
##     "Variation_ID": "302-B",
##     "Variation_Details": "Color: Light Blue, Size: 34"
##   },
##   {
##     "Category": "Books",
##     "Item_Name": "Fiction Novel",
##     "Item_ID": 401,
##     "Brand": "-",
##     "Price": 14.99,
##     "Variation_ID": "401-A",
##     "Variation_Details": "Format: Hardcover, Language: English"
##   },
##   {
##     "Category": "Books",
##     "Item_Name": "Fiction Novel",
##     "Item_ID": 401,
##     "Brand": "-",
##     "Price": 14.99,
##     "Variation_ID": "401-B",
##     "Variation_Details": "Format: Paperback, Language: Spanish"
##   },
##   {
##     "Category": "Books",
##     "Item_Name": "Non-Fiction Guide",
##     "Item_ID": 402,
##     "Brand": "-",
##     "Price": 24.99,
##     "Variation_ID": "402-A",
##     "Variation_Details": "Format: eBook, Language: English"
##   },
##   {
##     "Category": "Books",
##     "Item_Name": "Non-Fiction Guide",
##     "Item_ID": 402,
##     "Brand": "-",
##     "Price": 24.99,
##     "Variation_ID": "402-B",
##     "Variation_Details": "Format: Paperback, Language: French"
##   },
##   {
##     "Category": "Sports Equipment",
##     "Item_Name": "Basketball",
##     "Item_ID": 501,
##     "Brand": "SportsGear",
##     "Price": 29.99,
##     "Variation_ID": "501-A",
##     "Variation_Details": "Size: Size 7, Color: Orange"
##   },
##   {
##     "Category": "Sports Equipment",
##     "Item_Name": "Tennis Racket",
##     "Item_ID": 502,
##     "Brand": "RacketPro",
##     "Price": 89.99,
##     "Variation_ID": "502-A",
##     "Variation_Details": "Material: Graphite, Color: Black"
##   },
##   {
##     "Category": "Sports Equipment",
##     "Item_Name": "Tennis Racket",
##     "Item_ID": 502,
##     "Brand": "RacketPro",
##     "Price": 89.99,
##     "Variation_ID": "502-B",
##     "Variation_Details": "Material: Aluminum, Color: Silver"
##   }
## ]

write(json_mart_data, file = "json_data_file.json")

# Reading JSON back into R
json_mart_datafile <- fromJSON("C:\\Users\\HP\\Documents\\R projects\\Week 7\\json_data_file.json")
print(json_mart_datafile)

##            Category         Item_Name Item_ID      Brand   Price Variation_ID
## 1       Electronics        Smartphone     101  TechBrand  699.99        101-A
## 2       Electronics        Smartphone     101  TechBrand  699.99        101-B
## 3       Electronics            Laptop     102 CompuBrand 1099.99        102-A
## 4       Electronics            Laptop     102 CompuBrand 1099.99        102-B
## 5   Home Appliances      Refrigerator     201   HomeCool  899.99        201-A
## 6   Home Appliances      Refrigerator     201   HomeCool  899.99        201-B
## 7   Home Appliances   Washing Machine     202  CleanTech  499.99        202-A
## 8   Home Appliances   Washing Machine     202  CleanTech  499.99        202-B
## 9          Clothing           T-Shirt     301  FashionCo   19.99        301-A
## 10         Clothing           T-Shirt     301  FashionCo   19.99        301-B
## 11         Clothing           T-Shirt     301  FashionCo   19.99        301-C
## 12         Clothing             Jeans     302 DenimWorks   49.99        302-A
## 13         Clothing             Jeans     302 DenimWorks   49.99        302-B
## 14            Books     Fiction Novel     401          -   14.99        401-A
## 15            Books     Fiction Novel     401          -   14.99        401-B
## 16            Books Non-Fiction Guide     402          -   24.99        402-A
## 17            Books Non-Fiction Guide     402          -   24.99        402-B
## 18 Sports Equipment        Basketball     501 SportsGear   29.99        501-A
## 19 Sports Equipment     Tennis Racket     502  RacketPro   89.99        502-A
## 20 Sports Equipment     Tennis Racket     502  RacketPro   89.99        502-B
##                             Variation_Details
## 1                 Color: Black, Storage: 64GB
## 2                Color: White, Storage: 128GB
## 3               Color: Silver, Storage: 256GB
## 4           Color: Space Gray, Storage: 512GB
## 5  Color: Stainless Steel, Capacity: 20 cu ft
## 6            Color: White, Capacity: 18 cu ft
## 7       Type: Front Load, Capacity: 4.5 cu ft
## 8         Type: Top Load, Capacity: 5.0 cu ft
## 9                        Color: Blue, Size: S
## 10                        Color: Red, Size: M
## 11                      Color: Green, Size: L
## 12                 Color: Dark Blue, Size: 32
## 13                Color: Light Blue, Size: 34
## 14       Format: Hardcover, Language: English
## 15       Format: Paperback, Language: Spanish
## 16           Format: eBook, Language: English
## 17        Format: Paperback, Language: French
## 18                Size: Size 7, Color: Orange
## 19           Material: Graphite, Color: Black
## 20          Material: Aluminum, Color: Silver

Pros of JSON

1. Human-readable and easy to write.
2. Widely used for web APIs and configuration files.
3. Can be easily parsed and generated in R. ### Cons of JSON
4. Can be inefficient in terms of storage space for very large datasets.
5. Limited support for complex data types compared to some other formats.

Convert the dataset to HTML

# Convert to HTML
html_data <- htmlTable::htmlTable(mart_data)
write(html_data, file = "html_data_file.html")
cat(html_data)

## <table class='gmisc_table' style='border-collapse: collapse; margin-top: 1em; margin-bottom: 1em;' >
## <thead>
## <tr><th style='border-bottom: 1px solid grey; border-top: 2px solid grey;'></th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Category</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Item_Name</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Item_ID</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Brand</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Price</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Variation_ID</th>
## <th style='font-weight: 900; border-bottom: 1px solid grey; border-top: 2px solid grey; text-align: center;'>Variation_Details</th>
## </tr>
## </thead>
## <tbody>
## <tr>
## <td style='text-align: left;'>1</td>
## <td style='text-align: center;'>Electronics</td>
## <td style='text-align: center;'>Smartphone</td>
## <td style='text-align: center;'>101</td>
## <td style='text-align: center;'>TechBrand</td>
## <td style='text-align: center;'>699.99</td>
## <td style='text-align: center;'>101-A</td>
## <td style='text-align: center;'>Color: Black, Storage: 64GB</td>
## </tr>
## <tr>
## <td style='text-align: left;'>2</td>
## <td style='text-align: center;'>Electronics</td>
## <td style='text-align: center;'>Smartphone</td>
## <td style='text-align: center;'>101</td>
## <td style='text-align: center;'>TechBrand</td>
## <td style='text-align: center;'>699.99</td>
## <td style='text-align: center;'>101-B</td>
## <td style='text-align: center;'>Color: White, Storage: 128GB</td>
## </tr>
## <tr>
## <td style='text-align: left;'>3</td>
## <td style='text-align: center;'>Electronics</td>
## <td style='text-align: center;'>Laptop</td>
## <td style='text-align: center;'>102</td>
## <td style='text-align: center;'>CompuBrand</td>
## <td style='text-align: center;'>1099.99</td>
## <td style='text-align: center;'>102-A</td>
## <td style='text-align: center;'>Color: Silver, Storage: 256GB</td>
## </tr>
## <tr>
## <td style='text-align: left;'>4</td>
## <td style='text-align: center;'>Electronics</td>
## <td style='text-align: center;'>Laptop</td>
## <td style='text-align: center;'>102</td>
## <td style='text-align: center;'>CompuBrand</td>
## <td style='text-align: center;'>1099.99</td>
## <td style='text-align: center;'>102-B</td>
## <td style='text-align: center;'>Color: Space Gray, Storage: 512GB</td>
## </tr>
## <tr>
## <td style='text-align: left;'>5</td>
## <td style='text-align: center;'>Home Appliances</td>
## <td style='text-align: center;'>Refrigerator</td>
## <td style='text-align: center;'>201</td>
## <td style='text-align: center;'>HomeCool</td>
## <td style='text-align: center;'>899.99</td>
## <td style='text-align: center;'>201-A</td>
## <td style='text-align: center;'>Color: Stainless Steel, Capacity: 20 cu ft</td>
## </tr>
## <tr>
## <td style='text-align: left;'>6</td>
## <td style='text-align: center;'>Home Appliances</td>
## <td style='text-align: center;'>Refrigerator</td>
## <td style='text-align: center;'>201</td>
## <td style='text-align: center;'>HomeCool</td>
## <td style='text-align: center;'>899.99</td>
## <td style='text-align: center;'>201-B</td>
## <td style='text-align: center;'>Color: White, Capacity: 18 cu ft</td>
## </tr>
## <tr>
## <td style='text-align: left;'>7</td>
## <td style='text-align: center;'>Home Appliances</td>
## <td style='text-align: center;'>Washing Machine</td>
## <td style='text-align: center;'>202</td>
## <td style='text-align: center;'>CleanTech</td>
## <td style='text-align: center;'>499.99</td>
## <td style='text-align: center;'>202-A</td>
## <td style='text-align: center;'>Type: Front Load, Capacity: 4.5 cu ft</td>
## </tr>
## <tr>
## <td style='text-align: left;'>8</td>
## <td style='text-align: center;'>Home Appliances</td>
## <td style='text-align: center;'>Washing Machine</td>
## <td style='text-align: center;'>202</td>
## <td style='text-align: center;'>CleanTech</td>
## <td style='text-align: center;'>499.99</td>
## <td style='text-align: center;'>202-B</td>
## <td style='text-align: center;'>Type: Top Load, Capacity: 5.0 cu ft</td>
## </tr>
## <tr>
## <td style='text-align: left;'>9</td>
## <td style='text-align: center;'>Clothing</td>
## <td style='text-align: center;'>T-Shirt</td>
## <td style='text-align: center;'>301</td>
## <td style='text-align: center;'>FashionCo</td>
## <td style='text-align: center;'>19.99</td>
## <td style='text-align: center;'>301-A</td>
## <td style='text-align: center;'>Color: Blue, Size: S</td>
## </tr>
## <tr>
## <td style='text-align: left;'>10</td>
## <td style='text-align: center;'>Clothing</td>
## <td style='text-align: center;'>T-Shirt</td>
## <td style='text-align: center;'>301</td>
## <td style='text-align: center;'>FashionCo</td>
## <td style='text-align: center;'>19.99</td>
## <td style='text-align: center;'>301-B</td>
## <td style='text-align: center;'>Color: Red, Size: M</td>
## </tr>
## <tr>
## <td style='text-align: left;'>11</td>
## <td style='text-align: center;'>Clothing</td>
## <td style='text-align: center;'>T-Shirt</td>
## <td style='text-align: center;'>301</td>
## <td style='text-align: center;'>FashionCo</td>
## <td style='text-align: center;'>19.99</td>
## <td style='text-align: center;'>301-C</td>
## <td style='text-align: center;'>Color: Green, Size: L</td>
## </tr>
## <tr>
## <td style='text-align: left;'>12</td>
## <td style='text-align: center;'>Clothing</td>
## <td style='text-align: center;'>Jeans</td>
## <td style='text-align: center;'>302</td>
## <td style='text-align: center;'>DenimWorks</td>
## <td style='text-align: center;'>49.99</td>
## <td style='text-align: center;'>302-A</td>
## <td style='text-align: center;'>Color: Dark Blue, Size: 32</td>
## </tr>
## <tr>
## <td style='text-align: left;'>13</td>
## <td style='text-align: center;'>Clothing</td>
## <td style='text-align: center;'>Jeans</td>
## <td style='text-align: center;'>302</td>
## <td style='text-align: center;'>DenimWorks</td>
## <td style='text-align: center;'>49.99</td>
## <td style='text-align: center;'>302-B</td>
## <td style='text-align: center;'>Color: Light Blue, Size: 34</td>
## </tr>
## <tr>
## <td style='text-align: left;'>14</td>
## <td style='text-align: center;'>Books</td>
## <td style='text-align: center;'>Fiction Novel</td>
## <td style='text-align: center;'>401</td>
## <td style='text-align: center;'>-</td>
## <td style='text-align: center;'>14.99</td>
## <td style='text-align: center;'>401-A</td>
## <td style='text-align: center;'>Format: Hardcover, Language: English</td>
## </tr>
## <tr>
## <td style='text-align: left;'>15</td>
## <td style='text-align: center;'>Books</td>
## <td style='text-align: center;'>Fiction Novel</td>
## <td style='text-align: center;'>401</td>
## <td style='text-align: center;'>-</td>
## <td style='text-align: center;'>14.99</td>
## <td style='text-align: center;'>401-B</td>
## <td style='text-align: center;'>Format: Paperback, Language: Spanish</td>
## </tr>
## <tr>
## <td style='text-align: left;'>16</td>
## <td style='text-align: center;'>Books</td>
## <td style='text-align: center;'>Non-Fiction Guide</td>
## <td style='text-align: center;'>402</td>
## <td style='text-align: center;'>-</td>
## <td style='text-align: center;'>24.99</td>
## <td style='text-align: center;'>402-A</td>
## <td style='text-align: center;'>Format: eBook, Language: English</td>
## </tr>
## <tr>
## <td style='text-align: left;'>17</td>
## <td style='text-align: center;'>Books</td>
## <td style='text-align: center;'>Non-Fiction Guide</td>
## <td style='text-align: center;'>402</td>
## <td style='text-align: center;'>-</td>
## <td style='text-align: center;'>24.99</td>
## <td style='text-align: center;'>402-B</td>
## <td style='text-align: center;'>Format: Paperback, Language: French</td>
## </tr>
## <tr>
## <td style='text-align: left;'>18</td>
## <td style='text-align: center;'>Sports Equipment</td>
## <td style='text-align: center;'>Basketball</td>
## <td style='text-align: center;'>501</td>
## <td style='text-align: center;'>SportsGear</td>
## <td style='text-align: center;'>29.99</td>
## <td style='text-align: center;'>501-A</td>
## <td style='text-align: center;'>Size: Size 7, Color: Orange</td>
## </tr>
## <tr>
## <td style='text-align: left;'>19</td>
## <td style='text-align: center;'>Sports Equipment</td>
## <td style='text-align: center;'>Tennis Racket</td>
## <td style='text-align: center;'>502</td>
## <td style='text-align: center;'>RacketPro</td>
## <td style='text-align: center;'>89.99</td>
## <td style='text-align: center;'>502-A</td>
## <td style='text-align: center;'>Material: Graphite, Color: Black</td>
## </tr>
## <tr>
## <td style='border-bottom: 2px solid grey; text-align: left;'>20</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>Sports Equipment</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>Tennis Racket</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>502</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>RacketPro</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>89.99</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>502-B</td>
## <td style='border-bottom: 2px solid grey; text-align: center;'>Material: Aluminum, Color: Silver</td>
## </tr>
## </tbody>
## </table>

# Read HTML back into R
library(rvest)
html_content <- read_html("html_data_file.html")
imported_html_data <- html_content %>% html_table(fill = TRUE) %>% .[[1]]
print(imported_html_data)

## # A tibble: 20 × 8
##       `` Category  Item_Name Item_ID Brand  Price Variation_ID Variation_Details
##    <int> <chr>     <chr>       <int> <chr>  <dbl> <chr>        <chr>            
##  1     1 Electron… Smartpho…     101 Tech…  700.  101-A        Color: Black, St…
##  2     2 Electron… Smartpho…     101 Tech…  700.  101-B        Color: White, St…
##  3     3 Electron… Laptop        102 Comp… 1100.  102-A        Color: Silver, S…
##  4     4 Electron… Laptop        102 Comp… 1100.  102-B        Color: Space Gra…
##  5     5 Home App… Refriger…     201 Home…  900.  201-A        Color: Stainless…
##  6     6 Home App… Refriger…     201 Home…  900.  201-B        Color: White, Ca…
##  7     7 Home App… Washing …     202 Clea…  500.  202-A        Type: Front Load…
##  8     8 Home App… Washing …     202 Clea…  500.  202-B        Type: Top Load, …
##  9     9 Clothing  T-Shirt       301 Fash…   20.0 301-A        Color: Blue, Siz…
## 10    10 Clothing  T-Shirt       301 Fash…   20.0 301-B        Color: Red, Size…
## 11    11 Clothing  T-Shirt       301 Fash…   20.0 301-C        Color: Green, Si…
## 12    12 Clothing  Jeans         302 Deni…   50.0 302-A        Color: Dark Blue…
## 13    13 Clothing  Jeans         302 Deni…   50.0 302-B        Color: Light Blu…
## 14    14 Books     Fiction …     401 -       15.0 401-A        Format: Hardcove…
## 15    15 Books     Fiction …     401 -       15.0 401-B        Format: Paperbac…
## 16    16 Books     Non-Fict…     402 -       25.0 402-A        Format: eBook, L…
## 17    17 Books     Non-Fict…     402 -       25.0 402-B        Format: Paperbac…
## 18    18 Sports E… Basketba…     501 Spor…   30.0 501-A        Size: Size 7, Co…
## 19    19 Sports E… Tennis R…     502 Rack…   90.0 502-A        Material: Graphi…
## 20    20 Sports E… Tennis R…     502 Rack…   90.0 502-B        Material: Alumin…

Pros of HTML

1. Easily viewed in web browsers.
2. Can be styled using CSS for better presentation.
3. Interactive features can be added using JavaScript. ### Cons of HTML Not ideal for large datasets due to lack of efficient data handling. More complex to parse and manipulate compared to other data formats. ### Convert the dataset to XML

# Convert to XML
xml_data <- XML::newXMLNode("Inventory")
for (i in 1:nrow(mart_data)) {
  item <- XML::newXMLNode("Item", parent = xml_data)
  for (j in 1:ncol(mart_data)) {
    XML::newXMLNode(names(mart_data)[j], mart_data[i, j], parent = item)
  }
}

## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present
## Warning in removeNodes.list(kids[!vapply(kids, is.character, logical(1L))]):
## removeNode only works on internal nodes at present

XML::saveXML(xml_data, file = "xml_data_file.xml")

## [1] "xml_data_file.xml"

# Print the raw XML content to verify
cat(XML::saveXML(xml_data))

## <Inventory>
##   <Item>
##     <Category>Electronics</Category>
##     <Item_Name>Smartphone</Item_Name>
##     <Item_ID>101</Item_ID>
##     <Brand>TechBrand</Brand>
##     <Price>699.99</Price>
##     <Variation_ID>101-A</Variation_ID>
##     <Variation_Details>Color: Black, Storage: 64GB</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Electronics</Category>
##     <Item_Name>Smartphone</Item_Name>
##     <Item_ID>101</Item_ID>
##     <Brand>TechBrand</Brand>
##     <Price>699.99</Price>
##     <Variation_ID>101-B</Variation_ID>
##     <Variation_Details>Color: White, Storage: 128GB</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Electronics</Category>
##     <Item_Name>Laptop</Item_Name>
##     <Item_ID>102</Item_ID>
##     <Brand>CompuBrand</Brand>
##     <Price>1099.99</Price>
##     <Variation_ID>102-A</Variation_ID>
##     <Variation_Details>Color: Silver, Storage: 256GB</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Electronics</Category>
##     <Item_Name>Laptop</Item_Name>
##     <Item_ID>102</Item_ID>
##     <Brand>CompuBrand</Brand>
##     <Price>1099.99</Price>
##     <Variation_ID>102-B</Variation_ID>
##     <Variation_Details>Color: Space Gray, Storage: 512GB</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Home Appliances</Category>
##     <Item_Name>Refrigerator</Item_Name>
##     <Item_ID>201</Item_ID>
##     <Brand>HomeCool</Brand>
##     <Price>899.99</Price>
##     <Variation_ID>201-A</Variation_ID>
##     <Variation_Details>Color: Stainless Steel, Capacity: 20 cu ft</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Home Appliances</Category>
##     <Item_Name>Refrigerator</Item_Name>
##     <Item_ID>201</Item_ID>
##     <Brand>HomeCool</Brand>
##     <Price>899.99</Price>
##     <Variation_ID>201-B</Variation_ID>
##     <Variation_Details>Color: White, Capacity: 18 cu ft</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Home Appliances</Category>
##     <Item_Name>Washing Machine</Item_Name>
##     <Item_ID>202</Item_ID>
##     <Brand>CleanTech</Brand>
##     <Price>499.99</Price>
##     <Variation_ID>202-A</Variation_ID>
##     <Variation_Details>Type: Front Load, Capacity: 4.5 cu ft</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Home Appliances</Category>
##     <Item_Name>Washing Machine</Item_Name>
##     <Item_ID>202</Item_ID>
##     <Brand>CleanTech</Brand>
##     <Price>499.99</Price>
##     <Variation_ID>202-B</Variation_ID>
##     <Variation_Details>Type: Top Load, Capacity: 5.0 cu ft</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Clothing</Category>
##     <Item_Name>T-Shirt</Item_Name>
##     <Item_ID>301</Item_ID>
##     <Brand>FashionCo</Brand>
##     <Price>19.99</Price>
##     <Variation_ID>301-A</Variation_ID>
##     <Variation_Details>Color: Blue, Size: S</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Clothing</Category>
##     <Item_Name>T-Shirt</Item_Name>
##     <Item_ID>301</Item_ID>
##     <Brand>FashionCo</Brand>
##     <Price>19.99</Price>
##     <Variation_ID>301-B</Variation_ID>
##     <Variation_Details>Color: Red, Size: M</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Clothing</Category>
##     <Item_Name>T-Shirt</Item_Name>
##     <Item_ID>301</Item_ID>
##     <Brand>FashionCo</Brand>
##     <Price>19.99</Price>
##     <Variation_ID>301-C</Variation_ID>
##     <Variation_Details>Color: Green, Size: L</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Clothing</Category>
##     <Item_Name>Jeans</Item_Name>
##     <Item_ID>302</Item_ID>
##     <Brand>DenimWorks</Brand>
##     <Price>49.99</Price>
##     <Variation_ID>302-A</Variation_ID>
##     <Variation_Details>Color: Dark Blue, Size: 32</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Clothing</Category>
##     <Item_Name>Jeans</Item_Name>
##     <Item_ID>302</Item_ID>
##     <Brand>DenimWorks</Brand>
##     <Price>49.99</Price>
##     <Variation_ID>302-B</Variation_ID>
##     <Variation_Details>Color: Light Blue, Size: 34</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Books</Category>
##     <Item_Name>Fiction Novel</Item_Name>
##     <Item_ID>401</Item_ID>
##     <Brand>-</Brand>
##     <Price>14.99</Price>
##     <Variation_ID>401-A</Variation_ID>
##     <Variation_Details>Format: Hardcover, Language: English</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Books</Category>
##     <Item_Name>Fiction Novel</Item_Name>
##     <Item_ID>401</Item_ID>
##     <Brand>-</Brand>
##     <Price>14.99</Price>
##     <Variation_ID>401-B</Variation_ID>
##     <Variation_Details>Format: Paperback, Language: Spanish</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Books</Category>
##     <Item_Name>Non-Fiction Guide</Item_Name>
##     <Item_ID>402</Item_ID>
##     <Brand>-</Brand>
##     <Price>24.99</Price>
##     <Variation_ID>402-A</Variation_ID>
##     <Variation_Details>Format: eBook, Language: English</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Books</Category>
##     <Item_Name>Non-Fiction Guide</Item_Name>
##     <Item_ID>402</Item_ID>
##     <Brand>-</Brand>
##     <Price>24.99</Price>
##     <Variation_ID>402-B</Variation_ID>
##     <Variation_Details>Format: Paperback, Language: French</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Sports Equipment</Category>
##     <Item_Name>Basketball</Item_Name>
##     <Item_ID>501</Item_ID>
##     <Brand>SportsGear</Brand>
##     <Price>29.99</Price>
##     <Variation_ID>501-A</Variation_ID>
##     <Variation_Details>Size: Size 7, Color: Orange</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Sports Equipment</Category>
##     <Item_Name>Tennis Racket</Item_Name>
##     <Item_ID>502</Item_ID>
##     <Brand>RacketPro</Brand>
##     <Price>89.99</Price>
##     <Variation_ID>502-A</Variation_ID>
##     <Variation_Details>Material: Graphite, Color: Black</Variation_Details>
##   </Item>
##   <Item>
##     <Category>Sports Equipment</Category>
##     <Item_Name>Tennis Racket</Item_Name>
##     <Item_ID>502</Item_ID>
##     <Brand>RacketPro</Brand>
##     <Price>89.99</Price>
##     <Variation_ID>502-B</Variation_ID>
##     <Variation_Details>Material: Aluminum, Color: Silver</Variation_Details>
##   </Item>
## </Inventory>

# Read XML back into R
read_xml_data <- XML::xmlParse("C:\\Users\\HP\\Documents\\R projects\\Week 7\\xml_data_file.xml")

# Convert the XML back to a dataframe for verification
xml_root <- XML::xmlRoot(read_xml_data)
xml_to_df <- xmlToDataFrame(xml_root)

# Print the dataframe to verify
print(xml_to_df)

##            Category         Item_Name Item_ID      Brand   Price Variation_ID
## 1       Electronics        Smartphone     101  TechBrand  699.99        101-A
## 2       Electronics        Smartphone     101  TechBrand  699.99        101-B
## 3       Electronics            Laptop     102 CompuBrand 1099.99        102-A
## 4       Electronics            Laptop     102 CompuBrand 1099.99        102-B
## 5   Home Appliances      Refrigerator     201   HomeCool  899.99        201-A
## 6   Home Appliances      Refrigerator     201   HomeCool  899.99        201-B
## 7   Home Appliances   Washing Machine     202  CleanTech  499.99        202-A
## 8   Home Appliances   Washing Machine     202  CleanTech  499.99        202-B
## 9          Clothing           T-Shirt     301  FashionCo   19.99        301-A
## 10         Clothing           T-Shirt     301  FashionCo   19.99        301-B
## 11         Clothing           T-Shirt     301  FashionCo   19.99        301-C
## 12         Clothing             Jeans     302 DenimWorks   49.99        302-A
## 13         Clothing             Jeans     302 DenimWorks   49.99        302-B
## 14            Books     Fiction Novel     401          -   14.99        401-A
## 15            Books     Fiction Novel     401          -   14.99        401-B
## 16            Books Non-Fiction Guide     402          -   24.99        402-A
## 17            Books Non-Fiction Guide     402          -   24.99        402-B
## 18 Sports Equipment        Basketball     501 SportsGear   29.99        501-A
## 19 Sports Equipment     Tennis Racket     502  RacketPro   89.99        502-A
## 20 Sports Equipment     Tennis Racket     502  RacketPro   89.99        502-B
##                             Variation_Details
## 1                 Color: Black, Storage: 64GB
## 2                Color: White, Storage: 128GB
## 3               Color: Silver, Storage: 256GB
## 4           Color: Space Gray, Storage: 512GB
## 5  Color: Stainless Steel, Capacity: 20 cu ft
## 6            Color: White, Capacity: 18 cu ft
## 7       Type: Front Load, Capacity: 4.5 cu ft
## 8         Type: Top Load, Capacity: 5.0 cu ft
## 9                        Color: Blue, Size: S
## 10                        Color: Red, Size: M
## 11                      Color: Green, Size: L
## 12                 Color: Dark Blue, Size: 32
## 13                Color: Light Blue, Size: 34
## 14       Format: Hardcover, Language: English
## 15       Format: Paperback, Language: Spanish
## 16           Format: eBook, Language: English
## 17        Format: Paperback, Language: French
## 18                Size: Size 7, Color: Orange
## 19           Material: Graphite, Color: Black
## 20          Material: Aluminum, Color: Silver

Pros of XML

1. Highly structured and supports complex data hierarchies.
2. Widely used in web services and for data interchange.
3. Can be validated using schemas.

Cons of XML

1. Verbose can be difficult to read.
2. Larger file size compared to JSON for similar data.

Convert the dataset to Parquet

# Convert to Parquet
arrow::write_parquet(mart_data, "parquet_data_file.parquet")

# Read Parquet back into R
imported_parquet_data <- arrow::read_parquet("C:\\Users\\HP\\Documents\\R projects\\Week 7\\parquet_data_file.parquet")

print(imported_parquet_data)

## # A tibble: 20 × 7
##    Category        Item_Name Item_ID Brand  Price Variation_ID Variation_Details
##    <chr>           <chr>       <dbl> <chr>  <dbl> <chr>        <chr>            
##  1 Electronics     Smartpho…     101 Tech…  700.  101-A        Color: Black, St…
##  2 Electronics     Smartpho…     101 Tech…  700.  101-B        Color: White, St…
##  3 Electronics     Laptop        102 Comp… 1100.  102-A        Color: Silver, S…
##  4 Electronics     Laptop        102 Comp… 1100.  102-B        Color: Space Gra…
##  5 Home Appliances Refriger…     201 Home…  900.  201-A        Color: Stainless…
##  6 Home Appliances Refriger…     201 Home…  900.  201-B        Color: White, Ca…
##  7 Home Appliances Washing …     202 Clea…  500.  202-A        Type: Front Load…
##  8 Home Appliances Washing …     202 Clea…  500.  202-B        Type: Top Load, …
##  9 Clothing        T-Shirt       301 Fash…   20.0 301-A        Color: Blue, Siz…
## 10 Clothing        T-Shirt       301 Fash…   20.0 301-B        Color: Red, Size…
## 11 Clothing        T-Shirt       301 Fash…   20.0 301-C        Color: Green, Si…
## 12 Clothing        Jeans         302 Deni…   50.0 302-A        Color: Dark Blue…
## 13 Clothing        Jeans         302 Deni…   50.0 302-B        Color: Light Blu…
## 14 Books           Fiction …     401 -       15.0 401-A        Format: Hardcove…
## 15 Books           Fiction …     401 -       15.0 401-B        Format: Paperbac…
## 16 Books           Non-Fict…     402 -       25.0 402-A        Format: eBook, L…
## 17 Books           Non-Fict…     402 -       25.0 402-B        Format: Paperbac…
## 18 Sports Equipme… Basketba…     501 Spor…   30.0 501-A        Size: Size 7, Co…
## 19 Sports Equipme… Tennis R…     502 Rack…   90.0 502-A        Material: Graphi…
## 20 Sports Equipme… Tennis R…     502 Rack…   90.0 502-B        Material: Alumin…

Pros of Parquet

1. Highly efficient in terms of storage and retrieval for large datasets.
2. It is columnar storage format, making it ideal for analytical queries.
3. It is supported by many big data tools and frameworks.

Cons of Parquet

1. Less human-readable compared to JSON and XML formats.
2. Requires specific libraries and tools to read and write.