hyperSpec
objectR/decomposition.R
decomposition.Rd
Decomposition of the spectra matrix is a common procedure in chemometric
data analysis. scores
and loadings
convert the result matrices
into new hyperSpec
objects.
A hyperSpec
object.
matrix with the new content for object@data$spc
.
Its size must correspond to rows (for scores
) and to either columns
or rows (for loadings
) of object
.
for a scores-like x
: the new object@wavelength
.
The new label for the wavelength axis (if x
is scores-like). If not given, the label of object
is kept.
The new label for the spectra matrix. If not given, the
label of object
is kept.
is x
a scores-like matrix?
for loading-like decompostition (i.e. x
holds
loadings, pure component spectra or the like), the data columns need
special attention.
Columns with different values across the rows will be set to NA
if
retain.columns
is TRUE
, otherwise they will be deleted.
ignored.
A hyperSpec
object, updated according to x
Multivariate data are frequently decomposed by methods like principal component analysis, partial least squares, linear discriminant analysis, and the like. These methods yield latent spectra (or latent variables, loadings, components, ...) that are linear combination coefficients along the wavelength axis and scores for each spectrum and loading.
The loadings matrix gives a coordinate transformation, and the scores are values in that new coordinate system.
The obtained latent variables are spectra-like objects: a latent variable
has a coefficient for each wavelength. If such a matrix (with the same
number of columns as object
has wavelengths) is given to
decomposition
(also setting scores = FALSE
), the spectra
matrix is replaced by x
. Moreover, all columns of object@data
that did not contain the same value for all spectra are set to NA
.
Thus, for the resulting hyperSpec
object, plot_spc()
and
related functions are meaningful. plot_map()
cannot be
applied as the loadings are not laterally resolved.
The scores matrix needs to have the same number of rows as object
has
spectra. If such a matrix is given, decomposition
will replace the
spectra matrix is replaced by x
and object@wavelength
by
wavelength
. The information related to each of the spectra is
retained. For such a hyperSpec
object, plot_map()
and
plot_c()
and the like can be applied. It is also possible to use
the spectra plotting, but the interpretation is not that of the spectrum any
longer.
See %*% for matrix multiplication of hyperSpec
objects.
See e.g. stats::prcomp()
and stats::princomp()
for
principal component analysis, and package pls
for Partial Least
Squares Regression.