[GRASS-dev] Re: [GRASS GIS] #576: i.pca fails to center data prior to analysis

[GRASS GIS]

#576: i.pca fails to center data prior to analysis
--------------------------------------------------------------+-------------
 Reporter:  nikos                                             |       Owner:  grass-dev@…              
     Type:  defect                                            |      Status:  new                      
 Priority:  normal                                            |   Milestone:  6.5.0                    
Component:  Raster                                            |     Version:  svn-develbranch6         
 Keywords:  i.pca, data centering, prcomp(), R, eigenvectors  |    Platform:  Unspecified              
      Cpu:  Unspecified                                       |  
--------------------------------------------------------------+-------------

Comment(by mmetz):

 Replying to [ticket:576 nikos]:
 > I have spotted one case where ''i.pca'' does not work as expected. I
 have a set of 3 MODIS surface reflectance bands. Performing PCA on those
 using ''i.pca'' '''does not center''' the data before the analysis, that
 is, the mean of each dimension (band) is not subtracted from the dimension
 itself to give a dataset that has zero mean which is an integral part of
 the solution to PCA.
 [...]
 >
 > * Using the same data with the ''prcomp(x, center=TRUE, scale=FALSE)''
 function in R, which centers the dataset by default anyway if not told
 otherwise, gives different results:
 >
 {{{
 >                PC1         PC2        PC3
 > mod07_b2 0.4372107  0.83099407 -0.3439413
 > mod07_b6 0.7210155 -0.09527873  0.6863371
 > mod07_b7 0.5375718 -0.54806096 -0.6408165
 }}}

 I get identical results with i.pca in trunk r49090 if I create a MASK
 first, thus excluding any NULL cells (some cells are NULL in one band but
 not NULL in another band).

 {{{
 # making use of NULL propagation
 r.mapcalc "MASK = mod_b2 + mod_b6 + mod_b7 + 1"
 }}}

 `i.pca` gives now

 {{{
 Eigen values, (vectors), and [percent importance]:
 PC1 778244.03 ( 0.4372, 0.7210, 0.5376) [79.20%]
 PC2 192494.58 ( 0.8310,-0.0953,-0.5481) [19.59%]
 PC3  11876.45 ( 0.3439,-0.6863, 0.6408) [ 1.21%]
 }}}

 which is identical to the above output of ''prcomp(x, center=TRUE,
 scale=FALSE)''

 Markus M

-- 
Ticket URL: <https://trac.osgeo.org/grass/ticket/576#comment:1>
GRASS GIS <http://grass.osgeo.org>