Expand the TS models across the factorial combination of LDA models, formulas, and number of change points

Source: R/TS_on_LDA.R

Expand the completely crossed combination of model inputs: LDA model results, formulas, and number of change points.

expand_TS(LDA_models, formulas, nchangepoints)

Arguments

LDA_models

List of LDA models (class LDA_set, produced by LDA_set) or a singular LDA model (class LDA, produced by LDA).
formulas

Vector of formula(s) for the continuous (non-change point) component of the time series models. Any predictor variable included in a formula must also be a column in the document_covariate_table. Each element (formula) in the vector is evaluated for each number of change points and each LDA model.
nchangepoints

Vector of integers corresponding to the number of change points to include in the time series models. 0 is a valid input corresponding to no change points (i.e., a singular time series model), and the current implementation can reasonably include up to 6 change points. Each element in the vector is the number of change points used to segment the data for each formula (entry in formulas) component of the TS model, for each selected LDA model.

Value

Expanded data.frame table of the three values (columns) for each unique model run (rows): [1] the LDA model (indicated as a numeric element reference to the LDA_models object), [2] the regressor formula, and [3] the number of changepoints.

Examples

# \donttest{
  data(rodents)
  document_term_table <- rodents$document_term_table
  document_covariate_table <- rodents$document_covariate_table
  LDAs <- LDA_set(document_term_table, topics = 2:3, nseeds = 2)
  LDA_models <- select_LDA(LDAs)
  weights <- document_weights(document_term_table)
  formulas <- c(~ 1, ~ newmoon)
  nchangepoints <- 0:1
  expand_TS(LDA_models, formulas, nchangepoints)
# }