buildCorpora: buildCorpora

In DataScienceSalon/predictifyR.3.0: Word Prediction Language Model Evaluation

Description

buildCorpora Build training, validation and test sets

Usage

buildCorpora(design, fullCorpus, training, validation, test)

Arguments

design	Dataframe containing pilot and corpora design
fullCorpus	List containing the meta data for the full corpus
training	List containing the meta data for the training corpora
validation	List containing the meta data for the validation corpus
test	List containing the meta data for the test corpus

Details

This function creates the training, validation, and test sets. Four training sets would be comprised of two, four, eight,and sixteen pilot corpora. The validation and test sets will be comprised of a single pilot corpus each,

Author(s)

John James, [e-mail]

DataScienceSalon/predictifyR.3.0 documentation built on May 23, 2019, 8:25 p.m.