Week 7 Assignment

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

library(jsonlite)

json_data <- toJSON(data, pretty = TRUE)
write(json_data, file = "json_data.json")

# Save the json document to a file
print(json_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": "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"
##   }
## ]

#JSON- * 1.Pros: Easy to read, and use. JSON support most of the modern programming languages.More compact than XML. * 2. Cons: Not optimized for large data, not as efficient when handling large datasets.

library(knitr)
html_data <- kable(data, format = "html")

# Save the html document to a file
write(html_data, file = "html_data.html")

html_data

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
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

#HTML- * 1. Pros: Like JOSON, HTML is easy to read too. Can be interactive with CSS / JavaScript. Designed can be use to displayed in the web browsers.

2. Cons: HTML don’t have complex data type, and not efficient for data storage(not for big data)

library("xtable")
html_data <- data
print(xtable(html_data), type="html", file="example.html")

library(xml2)

# Create a root node
xml_root <- xml_new_root("inventory")

# Loop through the data frame and create child nodes for each row
for (i in 1:nrow(data)) {

  item_node <- xml_add_child(xml_root, "item")
  
  xml_add_child(item_node, "Category", data$Category[i])
  xml_add_child(item_node, "Item_Name", data$Item_Name[i])
  xml_add_child(item_node, "Item_ID", as.character(data$Item_ID[i]))
  xml_add_child(item_node, "Brand", data$Brand[i])
  xml_add_child(item_node, "Price", as.character(data$Price[i]))
  xml_add_child(item_node, "Variation_ID", data$Variation_ID[i])
  xml_add_child(item_node, "Variation_Details", data$Variation_Details[i])
}

# Save the XML document to a file
write_xml(xml_root, file = "inventory_data_fixed.xml")

print(xml_root)

## {xml_document}
## <inventory>
##  [1] <item>\n  <Category>Electronics</Category>\n  <Item_Name>Smartphone</Ite ...
##  [2] <item>\n  <Category>Electronics</Category>\n  <Item_Name>Smartphone</Ite ...
##  [3] <item>\n  <Category>Electronics</Category>\n  <Item_Name>Laptop</Item_Na ...
##  [4] <item>\n  <Category>Electronics</Category>\n  <Item_Name>Laptop</Item_Na ...
##  [5] <item>\n  <Category>Home Appliances</Category>\n  <Item_Name>Refrigerato ...
##  [6] <item>\n  <Category>Home Appliances</Category>\n  <Item_Name>Refrigerato ...
##  [7] <item>\n  <Category>Home Appliances</Category>\n  <Item_Name>Washing Mac ...
##  [8] <item>\n  <Category>Home Appliances</Category>\n  <Item_Name>Washing Mac ...
##  [9] <item>\n  <Category>Clothing</Category>\n  <Item_Name>T-Shirt</Item_Name ...
## [10] <item>\n  <Category>Clothing</Category>\n  <Item_Name>T-Shirt</Item_Name ...
## [11] <item>\n  <Category>Clothing</Category>\n  <Item_Name>T-Shirt</Item_Name ...
## [12] <item>\n  <Category>Clothing</Category>\n  <Item_Name>Jeans</Item_Name>\ ...
## [13] <item>\n  <Category>Books</Category>\n  <Item_Name>Fiction Novel</Item_N ...
## [14] <item>\n  <Category>Books</Category>\n  <Item_Name>Fiction Novel</Item_N ...
## [15] <item>\n  <Category>Books</Category>\n  <Item_Name>Non-Fiction Guide</It ...
## [16] <item>\n  <Category>Books</Category>\n  <Item_Name>Non-Fiction Guide</It ...
## [17] <item>\n  <Category>Sports Equipment</Category>\n  <Item_Name>Basketball ...
## [18] <item>\n  <Category>Sports Equipment</Category>\n  <Item_Name>Tennis Rac ...

#XML- * 1. Pros: XML fellows a strict structure, each element has a clear meaning. * 2. Cons: Large file size, and slow parsing. Not for big data.

library(arrow)

## 
## Attaching package: 'arrow'

## The following object is masked from 'package:utils':
## 
##     timestamp

write_parquet(data, "inventory_data.parquet")

# To read the data back into R
parquet_data <- read_parquet("inventory_data.parquet")

print(parquet_data)

##            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            Books     Fiction Novel     401          -   14.99        401-A
## 14            Books     Fiction Novel     401          -   14.99        401-B
## 15            Books Non-Fiction Guide     402          -   24.99        402-A
## 16            Books Non-Fiction Guide     402          -   24.99        402-B
## 17 Sports Equipment        Basketball     501 SportsGear   29.99        501-A
## 18 Sports Equipment     Tennis Racket     502  RacketPro   89.99        502-A
##                             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       Format: Hardcover, Language: English
## 14       Format: Paperback, Language: Spanish
## 15           Format: eBook, Language: English
## 16        Format: Paperback, Language: French
## 17                Size: Size 7, Color: Orange
## 18           Material: Graphite, Color: Black

#Parquet - * 1. Pros: Good for big data procressing. Fast read time. * 2. Cons: Parquet may be overhead for small datasets, and its more complex, may require additional learning for a new user.