In-class 6

pacman::p_load(corporaexplorer, tidyverse, stringi, rvest)

bible <- readr::read_lines("http://www.gutenberg.org/cache/epub/10/pg10.txt")

bible <- paste(bible, collapse = "\n")
start_v <- stri_locate_first_fixed(bible, "The First Book of Moses: Called Genesis")[1]
end_v <- stri_locate_last_fixed(bible, "Amen.")[2]
bible <- stri_sub(bible, start_v, end_v)
books <- stri_split_regex(bible, "\n{5}") %>%
    unlist %>%
    .[-40]  

books <- str_replace_all(books, "\n{2,}", "NEW_PARAGRAPH") %>%
    str_replace_all("\n", " ") %>%
    str_replace_all("NEW_PARAGRAPH", "\n\n")
books <- books[3:68]

chapters <- str_replace_all(books, "(\\d+:1 )", "NEW_CHAPTER\\1") %>%
    stri_split_regex("NEW_CHAPTER")

chapters <- lapply(chapters, function(x) x[-1])

book_titles <- read_html("https://www.esv.org/resources/esv-global-study-bible/list-of-abbreviations") %>%
  html_nodes("td:nth-child(1)") %>%
  html_text() %>%
  .[13:78]

testament <- c(rep("Old", 39), rep("New", 27))


bible_df <- tibble::tibble(Text = chapters,
                           Book = book_titles,
                           Testament = testament)

bible_df <- tidyr::unnest(bible_df, Text)

KJB <- prepare_data(dataset = bible_df,
                    date_based_corpus = FALSE,
                    grouping_variable = "Book",
                    columns_doc_info = c("Testament", "Book"))

Starting.

Document data frame done.

Corpus is not date based. Calendar data frame skipped.

Document term matrix: text processed.

Document term matrix: tokenising completed.

Document term matrix: word list created.

Document term matrix done.

Done.

explore(KJB)

Exploring 1,175 documents

Loading required package: shiny

PhantomJS not found. You can install it with webshot::install_phantomjs(). If it is installed, please make sure the phantomjs executable can be found via the PATH variable.

Shiny applications not supported in static R Markdown documents