classifier_selection_description: Classifies new documents on a labeled training set...

In gidonc/durhamevp: ESRC/AHRC Victorian Election Violence Project R Code (Durham University)

Classifies new documents on a labeled training set (description).

Description

Classifies new documents on a labeled training set (description).

Usage

classifier_selection_description(
  train,
  new_docs,
  text_field = "description",
  class_to_keep = 1,
  training_classify_var = "EV_article",
  prior = "uniform",
  classifier_type = "xgboost",
  stem_dfm = FALSE,
  return_logical = FALSE,
  logical_to_prob = FALSE,
  ...
)

Arguments

train	a data frame with the training documents.
new_docs	the documents to classify.
text_field	the text field (must be the same in the training documents and the documents to classify).
class_to_keep	the class (0 or 1) to keep.
training_classify_var	the variable containing the labels in the training set.
prior	for naive bayes classifier only.
classifier_type	which classifier to use (xgboost or nb (naive Bayes))
return_logical	return the subset of documents or a logical vector indicating that subset.
...	other arguments to be passed to preprocess_corpus.
stem	for preprocessing

gidonc/durhamevp documentation built on April 8, 2022, 10:31 a.m.