vsp_fa: Create a vintage sparse factor analysis object
In RoheLab/vsp: Vintage Sparse PCA for Semi-Parametric Factor Analysis

vsp_fa

R Documentation

Create a vintage sparse factor analysis object

vsp_fa objects are a subclass of LRMF3::fa_like(), with additional fields u, d, v, transformers, R_U, and R_V

vsp_fa(
  u,
  d,
  v,
  Z,
  B,
  Y,
  transformers,
  R_U,
  R_V,
  rownames = NULL,
  colnames = NULL
)

`u`	A `matrix()` of "left singular-ish" vectors.
`d`	A `numeric()` vector of "singular-ish" values.
`v`	A `matrix()` of "right singular-ish" vectors.
`Z`	A matrix of embeddings for each observation.
`B`	A mixing matrix describing how observation embeddings and topics interact. Does not have to be diagonal!
`Y`	A matrix describing the compositions of various topics or factors.
`transformers`	A list of transformations from the `invertiforms` package.
`R_U`	Varimax rotation matrix use to transform `u` into `Z`.
`R_V`	Varimax rotation matrix use to transform `v` into `Y`.
`rownames`	Identifying names for each row of the original data. Defaults to `NULL`, in which cases each row is given a row number left-padded with zeros as a name.
`colnames`	Identifying names for each column of the original data. Defaults to `NULL`, in which cases each column is given a row column left-padded with zeros as a name.