instance_text: Transform an instance back into text

In agoldst/dfrtopics: Tools for exploring topic models of text

Transform an instance back into text

Description

"Reads" a MALLET instance as a text string for quick inspection.

Usage

instance_text(instance, vocab = instances_vocabulary(instance), collapse = " ")

Arguments

instance	reference to an instance
vocab	character vector giving the vocabulary
collapse	passed on to paste

Details

In the case of DfR data, the resulting string will not have meaningful word order: not very informative except for spot-checks for garbage data, correct stop-wording, etc.

Repeated calls will be much faster if you retrieve the vocabulary separately and pass that in as vocab. An InstanceList guarantees that all Instances have the same vocabulary.

Value

A string "spelling out" the instance text

agoldst/dfrtopics documentation built on July 15, 2022, 4:13 p.m.