LDA: LDA Object
In ldaPrototype: Prototype of Multiple Latent Dirichlet Allocation Runs

Description Usage Arguments Details Value See Also Examples

Constructor for LDA objects used in this package.

LDA(
  x,
  param,
  assignments,
  topics,
  document_sums,
  document_expects,
  log.likelihoods
)

as.LDA(
  x,
  param,
  assignments,
  topics,
  document_sums,
  document_expects,
  log.likelihoods
)

is.LDA(obj, verbose = FALSE)

`x`	[`named list`] Output from `lda.collapsed.gibbs.sampler`. Alternatively each element can be passed for individual results. Individually set elements overwrite elements from `x`.
`param`	[`named list`] Parameters of the function call `lda.collapsed.gibbs.sampler`. List always should contain names "K", "alpha", "eta" and "num.iterations".
`assignments`	Individual element for LDA object.
`topics`	Individual element for LDA object.
`document_sums`	Individual element for LDA object.
`document_expects`	Individual element for LDA object.
`log.likelihoods`	Individual element for LDA object.
`obj`	[`R` object] Object to test.
`verbose`	[`logical(1)`] Should test information be given in the console?

The functions LDA and as.LDA do exactly the same. If you call LDA on an object x which already is of the structure of an LDA object (in particular a LDA object itself), the additional arguments param, assignments, ... may be used to override the specific elements.

[named list] LDA object.

Other constructor functions: as.LDABatch(), as.LDARep()

Other LDA functions: LDABatch(), LDARep(), getTopics()

res = LDARep(docs = reuters_docs, vocab = reuters_vocab, n = 1, K = 10)
lda = getLDA(res)

LDA(lda)
# does not change anything

LDA(lda, assignments = NULL)
# creates a new LDA object without the assignments element

LDA(param = getParam(lda), topics = getTopics(lda))
# creates a new LDA object with elements param and topics