make_analysis_df: Create analysis table

In Amherst-Statistics/katherinemansfieldr: A Package for Text Mining Katherine Mansfield's Short Stories

Description

Takes a collection of chapters, breaks them up into individual chapters, and returns summary dataset for each chapter. Output statistics include average sentence length, average token length, average type length, average variety (# type/# token), story length (number of words), number of occurences of words (expressed as ratio of frequency of word over total number of words), number of occurances of punctuation (expressed as ratio of frequency of punctuation mark over all punctuation marks) and average sentiment score (AFINN method).

Usage

make_analysis_df(text, book, chapters, titles, freqwords, punctlist)

Arguments

text	Character vector containing all the lines in a given text
book	Name of book or story collection from which chapters/stories are taken
chapters	Line index numbers associated with the first line/title line of each chapter
titles	Title of each story or chapter in output dataset
freqwords	Words whose frequency of appearance will be recorded
punctlist	Punctuation characters whose frequency of appearance will be recorded

Examples

sample <- gardenParty[1:452]
collection <- "The Garden Party"
breaks <- find_chapters(sample, " and other stories, by Katherine Mansfield : ")
stories <- c("At the Bay", "Her First Ball", "The Singing Lesson")
words <- c("the", "and", "a")
punctuation <- c(",", ".", "...")
make_analysis_df(text = sample, book = collection, chapters = breaks, titles = stories,
                 freqwords = words, punctlist = punctuation)

Amherst-Statistics/katherinemansfieldr documentation built on May 5, 2019, 4:55 a.m.