model_seq: Model sequence
In pmcharrison/ppm: Prediction by Partial Matching

Description Usage Arguments Value

View source: R/model-seq.R

Analyses or generates a sequence using a PPM model.

model_seq(
  model,
  seq,
  time = NULL,
  zero_indexed = FALSE,
  train = TRUE,
  predict = TRUE,
  return_distribution = TRUE,
  return_entropy = TRUE,
  generate = FALSE
)

`model`	A PPM model object as produced by (for example) `new_ppm_simple` or `new_ppm_decay`.
`seq`	When `generate = FALSE` an integer vector defining the input sequence (equivalently a numeric vector containing solely integers, or a factor vector, both of which which will be coerced to integer vectors). When `generate = TRUE`, an integer scalar giving the desired length of the generated sequence.
`time`	(NULL or a numeric vector) Timepoints corresponding to each element of the sequence. Only used by certain model types (e.g. decay-based models).
`zero_indexed`	(Logical scalar) Whether or not the `seq` argument is 0-indexed (i.e. drawn from an alphabet with a minimum value of 0). If FALSE, it is assumed that the sequence is 1-indexed (i.e. drawn from an alphabet with a minimum value of 1).
`train`	(Logical scalar) Whether or not the model should learn from the incoming sequence.
`predict`	(Logical scalar) Whether or not to generate predictions for each element of the incoming sequence.
`return_distribution`	(Logical scalar) Whether or not to return the conditional distribution over each potential continuation as part of the model output (ignored if `predict = FALSE`).
`return_entropy`	(Logical scalar) Whether or not to return the entropy of each event prediction (ignored if `predict = FALSE`).
`generate`	(Logical scalar) If `TRUE`, the output will correspond to a newly generated sequence with length as specified by the `seq` argument, produced by sampling from the model's predictive distribution. The default is `FALSE`.

A tibble which will be empty if predict = FALSE and otherwise will contain one row for each element in the sequence, with the following columns:

symbol - the symbol being predicted. This should be identical to the input argument seq, with indexing determined by the argument 0-indexed.
model_order - the model order used for generating predictions.
information_content - the information content (i.e. negative log probability, base 2) of the observed symbol.
entropy - the expected information content when predicting the symbol.
distribution - the predictive probability distribution for the symbol, conditioned on the preceding symbols.