wavethresh (version 4.7.3)

putC.mwd: Put smoothed data into wavelet structure

Description

The smoothed and original data from a multiple wavelet decomposition structure, mwd.object, (e.g. returned from mwd) are packed into a single matrix in that structure. This function copies the mwd.object, replaces some smoothed data in the copy, and then returns the copy.

Usage

# S3 method for mwd
putC(mwd, level, M, boundary = FALSE, index = FALSE, ...)

Value

An object of class mwd.object if index is FALSE, otherwise the index numbers indicating where the M matrix would have been inserted into the mwd$C object are returned.

Arguments

mwd

Multiple wavelet decomposition structure whose coefficients you wish to replace.

level

The level that you wish to replace.

M

Matrix of replacement coefficients.

boundary

If boundary is FALSE then only the "real" data is replaced (and it is easy to predict the required length of M). If boundary is TRUE then you can replace the boundary values at a particular level as well (but it is hard to predict the required length of M, and the information has to be obtained from the mfirst.last database component of mwd).

index

If index is TRUE then the index numbers into the mwd$C array where the matrix M would be stored is returned. Otherwise, (default) the modified mwd.object is returned.

...

any other arguments

RELEASE

Version 3.9.6 (Although Copyright Tim Downie 1995-6).

Author

G P Nason

Details

The mwd function produces a wavelet decomposition structure.

The need for this function is a consequence of the pyramidal structure of Mallat's algorithm and the memory efficiency gain achieved by storing the pyramid as a linear matrix of coefficients. PutC obtains information about where the smoothed data appears from the fl.dbase component of mwd, in particular the array fl.dbase$first.last.c which gives a complete specification of index numbers and offsets for mwd$C.

Note also that this function only puts information into mwd class objects. To extract coefficients from mwd structures you have to use the accessC.mwd function.

See Downie and Silverman, 1998.

See Also

accessC.mwd, accessD.mwd, draw.mwd, mfirst.last, mfilter.select, mwd, mwd.object, mwr, plot.mwd, print.mwd, putD.mwd, summary.mwd, threshold.mwd, wd, wr.mwd.

Examples

#
# Generate an mwd object
#
tmp <- mwd(rnorm(32))
#
# Now let's examine the finest resolution smooth...
#
accessC(tmp, level=3)
#           [,1]       [,2]       [,3]       [,4]        [,5]      [,6] 
#[1,] -0.4669103 -1.3150580 -0.7094966 -0.1979214  0.32079986 0.5052254
#[2,] -0.7645379 -0.8680941  0.1004062  0.6633268 -0.05860848 0.5757286
#          [,7]       [,8] 
#[1,] 0.5187380  0.6533843
#[2,] 0.2864293 -0.4433788
#
# A matrix. There are two rows one for each father wavelet in this 
# two-ple multiple wavelet transform and at level 3 there are 2^3 columns.
#
# Let's set the coefficients of the first father wavelet all equal to zero
# for this examples
#
newcmat <- accessC(tmp, level=3)
newcmat[1,] <- 0
#
# Ok, let's insert it back at level 3
#
tmp2 <- putC(tmp, level=3, M=newcmat)
#
# And check it
#
accessC(tmp2, level=3)   
#           [,1]       [,2]      [,3]      [,4]        [,5]      [,6]      [,7] 
#[1,]  0.0000000  0.0000000 0.0000000 0.0000000  0.00000000 0.0000000 0.0000000
#[2,] -0.7645379 -0.8680941 0.1004062 0.6633268 -0.05860848 0.5757286 0.2864293
#           [,8] 
#[1,]  0.0000000
#[2,] -0.4433788
#
# Yep, all the first father wavelet coefficients at level 3 are now zero.