map_to_dtm: Create a document term matrix using a vectoriser

In mdneuzerling/DrakeModelling: Using drake to Train and Execute a Model in a Custom Package

Description

This function uses a vectoriser created with the text2vec package to map a new piece of text, or vector of text, onto a document term matrix (dtm). The vectoriser has a concept of a vocabulary, a set of tokens which determine the columns of the resulting document term matrix. Any term that doesn't match to a token in the vocabulary will be ignored. Optionally, the document term matrix can be weighted by a term frequency-inverse document frequency (tfidf) object, created with the text2vec::TfIdf function.

Usage

map_to_dtm(x, vectoriser, tfidf = NULL)

Arguments

x	A character or vector of characters, usually sentences, paragraphs or similar pieces of natural language.
vectoriser	A vectoriser constructed with the text2vec package.
tfidf	A tfidf object constructed with the text2vec package. If no tfidf is NULL, then an unweighted document term matrix will be returned.

Value

A document-term matrix with rows representing the textual objects in x, and columns representing the tokens in the vocabulary used to generate the given vectoriser.

mdneuzerling/DrakeModelling documentation built on June 26, 2020, 1:25 p.m.