inst/examples/get-n-grams.R

In wordpredictor: Develop Text Prediction Models Based on N-Grams

# Start of environment setup code
# The level of detail in the information messages
ve <- 2
# The name of the folder that will contain all the files. It will be created in
# the current directory. NULL implies tempdir will be used
fn <- NULL
# The required files. They are default files that are part of the package
rf <- c("n2.RDS")
# An object of class EnvManager is created
em <- EnvManager$new(ve = ve, rp = "./")
# The required files are downloaded
ed <- em$setup_env(rf, fn)
# End of environment setup code

# The n-gram file name
nfn <- paste0(ed, "/n2.RDS")
# The DataAnalyzer object is created
da <- DataAnalyzer$new(nfn, ve = ve)
# Bi-grams starting with "and_" are returned
df <- da$get_ngrams(fn = nfn, c = 10, pre = "^and_*")
# The data frame is sorted by frequency
df <- df[order(df$freq, decreasing = TRUE), ]
# The data frame is printed
print(df)

# The test environment is removed. Comment the below line, so the files
# generated by the function can be viewed
em$td_env()