Convert: Convert
In mRcSchwering/abacus: abacus

Description Usage Arguments Details Value See Also Examples

This functions converts a matrix according to a supplied data.frame. This can be used to convert an analytics base table into a structure which matches to a saved model.

1	Convert(abt, feats, ref)

`abt`	`num matrix` which should be converted
`feats`	`data.frame` with columns name and value which identifies the columns of `abt` with `chr` values
`ref`	`data.frame` with columns name and value which identifies the columns of the desired matrix with `chr` values (columns missing in `abt` will be 0)

Matrix columns are identified with a data.frame with columns name and value. name:value must be unique in the data.frame. Columns of matrix abt are identified by feats. abt is converted into a matrix of the form described with ref. Columns identified in ref not appearing in feats will be filled with 0's.

num matrix with columns as identified in ref

Other machine learning: CV, FeatureExtraction, Prediction, Training

abt1 <- matrix(1:20, 5,4)
feats1 <- data.frame(
  name = letters[1:4], 
  value = letters[1:4]
)
feats2 <- data.frame(
  name = rep(letters[1:2], 2), 
  value = rep(letters[1:2], each = 2)
)
Convert(abt1, feats1, feats2)