textshape (version 1.6.0)

tidy_colo_tdm: Convert a DocumentTermMatrix/TermDocumentMatrix into Collocating Words in Tidy Form

Description

Converts non-zero elements of a DocumentTermMatrix/TermDocumentMatrix into a tidy data set made of collocating words.

Usage

tidy_colo_tdm(x, ...)
tidy_colo_dtm(x, ...)

Arguments

x

A DocumentTermMatrix/TermDocumentMatrix.

…

Ignored.

Value

Returns a tidied data.frame.

See Also

unique_pairs

Examples

# NOT RUN {
data(simple_dtm)

tidied <- tidy_colo_dtm(simple_dtm)
tidied
unique_pairs(tidied)

# }
# NOT RUN {
if (!require("pacman")) install.packages("pacman")
pacman::p_load_current_gh('trinker/gofastr', 'trinker/lexicon')
pacman::p_load(tidyverse, magrittr, ggstance)

my_dtm <- with(
    presidential_debates_2012, 
    q_dtm(dialogue, paste(time, tot, sep = "_"))
)

tidy_colo_dtm(my_dtm) %>%
    tbl_df() %>%
    filter(!term_1 %in% c('i', lexicon::sw_onix) & 
        !term_2 %in% lexicon::sw_onix
    ) %>%
    filter(term_1 != term_2) %>%
    unique_pairs() %>%
    filter(n > 15) %>%
    complete(term_1, term_2, fill = list(n = 0)) %>%
    ggplot(aes(x = term_1, y = term_2, fill = n)) +
        geom_tile() +
        scale_fill_gradient(low= 'white', high = 'red') +
        theme(axis.text.x = element_text(angle = 45, hjust = 1))
# }

Run the code above in your browser using DataCamp Workspace