WK7 Data Science Books

library(rvest)
library(jsonlite)

# Read the local HTML file and select its first table.
html_page <- read_html("books.html")

html_data <- html_page |>
  html_element("table") |>
  html_table()

# Convert the imported table to a regular data frame.
# Use the same column types that will be used for the JSON data.
html_data <- as.data.frame(html_data, stringsAsFactors = FALSE)
html_data$Year <- as.integer(html_data$Year)
html_data$ISBN <- as.character(html_data$ISBN)

# Display the imported HTML records in the report.
knitr::kable(
  html_data,
  col.names = c("Title", "Authors", "Publication Year", "Publisher", "ISBN-13"),
  row.names = FALSE,
  caption = "Books Imported from HTML"
)

# Read the array of book objects from the local JSON file.
json_data <- fromJSON("books.json")

# Convert the result to a data frame and standardize its types.
json_data <- as.data.frame(json_data, stringsAsFactors = FALSE)
json_data$Year <- as.integer(json_data$Year)
json_data$ISBN <- as.character(json_data$ISBN)

# Display the imported JSON records in the report.
knitr::kable(
  json_data,
  col.names = c("Title", "Authors", "Publication Year", "Publisher", "ISBN-13"),
  row.names = FALSE,
  caption = "Books Imported from JSON"
)

# Put both data frames in the same column order.
columns <- c("Title", "Authors", "Year", "Publisher", "ISBN")

html_data <- html_data[, columns]
json_data <- json_data[, columns]

# Record the size, structure, and exact-match results.
comparison_summary <- data.frame(
  Check = c(
    "HTML dimensions",
    "JSON dimensions",
    "Column names match",
    "Column classes match",
    "All values and attributes match"
  ),
  Result = c(
    paste(dim(html_data), collapse = " x "),
    paste(dim(json_data), collapse = " x "),
    identical(names(html_data), names(json_data)),
    identical(vapply(html_data, class, character(1)),
              vapply(json_data, class, character(1))),
    identical(html_data, json_data)
  ),
  stringsAsFactors = FALSE
)

knitr::kable(comparison_summary, row.names = FALSE,
             caption = "HTML and JSON Comparison")

# Check whether a value follows the ISBN-13 check-digit formula.
validate_isbn13 <- function(isbn) {
  # Remove punctuation so only the 13 digits remain.
  isbn <- gsub("[^0-9]", "", isbn)

  if (nchar(isbn) != 13) {
    return(FALSE)
  }

  # Apply alternating weights of 1 and 3 to the first 12 digits.
  digits <- as.integer(strsplit(isbn, "")[[1]])
  weights <- rep(c(1, 3), 6)
  total <- sum(digits[1:12] * weights)
  check_digit <- (10 - (total %% 10)) %% 10

  # The calculated check digit must equal the last digit.
  check_digit == digits[13]
}

# Count missing cells and duplicated complete rows in each source.
quality_summary <- data.frame(
  Check = c("Missing cells", "Duplicate complete rows"),
  HTML = c(sum(is.na(html_data)), sum(duplicated(html_data))),
  JSON = c(sum(is.na(json_data)), sum(duplicated(json_data)))
)

# Run the ISBN-13 check on each book identifier.
isbn_validation <- data.frame(
  ISBN = html_data$ISBN,
  Valid_ISBN13 = vapply(html_data$ISBN, validate_isbn13, logical(1)),
  stringsAsFactors = FALSE
)

knitr::kable(quality_summary, row.names = FALSE,
             caption = "Missing-Value and Duplicate Checks")

knitr::kable(isbn_validation, row.names = FALSE,
             col.names = c("ISBN-13", "Valid ISBN-13"),
             caption = "ISBN-13 Check-Digit Results")