plotRemoved: Plot documents, words and tokens removed at various word...

In bstewart/stm: Estimation of the Structural Topic Model

Plot documents, words and tokens removed at various word thresholds

Description

A plot function which shows the results of using different thresholds in prepDocuments on the size of the corpus.

Usage

plotRemoved(documents, lower.thresh)

Arguments

documents	The documents to be used for the stm model
lower.thresh	A vector of integers, each of which will be tested as a lower threshold for the prepDocuments function.

Details

For a lower threshold, prepDocuments will drop words which appear in fewer than that number of documents, and remove documents which contain no more words. This function allows the user to pass a vector of lower thresholds and observe how prepDocuments will handle each threshold. This function produces three plots, showing the number of words, the number of documents, and the total number of tokens removed as a function of threshold values. A dashed red line is plotted at the total number of documents, words and tokens respectively.

Value

Invisibly returns a list of

lower.thresh	The sorted threshold values
ndocs	The number of documents dropped for each value of the lower threshold
nwords	The number of entries of the vocab dropped for each value of the lower threshold.
ntokens	The number of tokens dropped for each value of the lower threshold.

See Also

prepDocuments

Examples

plotRemoved(poliblog5k.docs, lower.thresh=seq(from = 10, to = 1000, by = 10))

bstewart/stm documentation built on Jan. 3, 2024, 6:58 p.m.