term.freq: Get a table of term frequencies

In DeducerText: Deducer GUI for Text Data

Description

Get a table of term frequencies.

Usage

term.freq( d, 
		topN = 0, 
		percent = 0,
		sorted = c("none", "alpha", "freq"),
		decreasing = FALSE,
		useDocFreq = FALSE,		
		minFreq = 1 )

Arguments

d	The corpus from which term frequencies are calculated.
topN	If specified, only the 'topN' most frequent terms are returned. If more terms are requested than available, all terms are returned. If both 'topN' and 'percent' are zero, then all terms are returned.
percent	If specified, only the top 'percent' % most frequent terms are returned. If more terms are requested than available, all terms are returned. If both 'topN' and 'percent' are zero, then all terms are returned.
sorted	A string specifying how to sort the terms. 'none' for no sorting, 'alpha' for alphanumeric sorting, and 'freq' for sorting by frequency.
decreasing	If TRUE, terms are sorted in decreasing order, if FALSE, sorted ascending order.
useDocFreq	If TRUE, the returned frequencies are for the total number of documents in which the term occurs. If false, they are the total number of occurrences.
minFreq	Terms with *TOTAL* frequencies below this threshold will not be included in the output.

Value

A name vector of the term frequencies.

Examples

if(require(tm)){
data(crude)
term.freq(d=crude, percent=0, topN=10, minFreq=0,useDocFreq=FALSE,sorted="alpha", decreasing=TRUE)
}

DeducerText documentation built on May 2, 2019, 5:44 p.m.