preprocess: preProcess

In ABMI/SOCRATex: Staged Optimization of Curation, Regularization, and Annotation of clinical Text

Description

This is a preprocessing function which can perform basic proprocessing rules.

Usage

preProcess(text, english = F, whitespace = F, stopwords = F,
  number = F, punc = F, stem = F, lower = F)

Arguments

text	text corpus want to analyze.
english	if TRUE then alphabets except English will be deleted from the courpus.
whitespace	if TRUE then extra whitespaces will be deleted from the courpus.
stopwords	if TRUE then only English stopwords will be deleted. The stopwords are from tm package.
number	if TRUE then numbers will be deleted from the corpus
punc	if TRUE then punctuations will be deleted from the courpus.
stem	if TRUE then terms in the corpus will be stemmed. The stemming logic is from tm package.
lower	if TRUE then English characters will be lowered. If other languages except English are included the function will not work.

ABMI/SOCRATex documentation built on March 20, 2021, 11:01 a.m.