With the "Corrgram" package we can see patterns that can help us to recognize possible inter-correlations in a big matrix. This could be the case to see the correlation to every wavelength respect to all others. This way we can see the high correlation...

Thanks a lot to Kevin W., for his comment in my previous post.Corrgram, it a nice package and I found very nice information to understand it a little bit better on Internet apart from the R help page.Corrgrams: Exploratory displays for correlation matr...

It is important to understand as better as possible our sample set before to develop the regression. Continuing with the “Y” matrix (constituent’s matrix) we have to observe the correlation matrix.In the R Graph Gallery, we can get the code to dr...

From the previous post, we can make the difference spectrum (once the samples are sorted by moisture) between the sample with the lowest moisture value (position 1), from the sample with the highest moisture value (position 66). This spectra will help ...

I use to see the videos from:http://www.twotorials.com/and the video:How to order and sort stuff in Ris really useful to apply this concept to organize and understand better our sample sets before to proceed to develop a calibration.The idea of this po...

<img src=' [Read more...]

It is amazing the quantity of graphics you can develop with R, and how you can show and manage  these graphics. Here in the same plot we compare the raw demo spectra, treated with MSC, SNV and with the first derivative (differences between consecu...

We have in the Demo sample set “66” samples.  In this post we´ll see one way to divide the set in two parts: one for “Validation” and another for Training or Calibration.The selection will be random. And we are going to use the command:

########### RAW NIR Demo Data##################################demo

<img src=' [Read more...]

<img src=' [Read more...]

 

<img src=' [Read more...]

Derivatives are a good way to extract information to our spectra. As we know NIR contents overlapping bands, and spectra must be treated with math operations in order to extract as much information as possible and to correlate it with the constituent &...

Once we have chosen the model, we can continue acquiring spectra of new samples. Spectra is exported to a txt or csv file and we imported in R to be reprocessed.We use the function “predict” from the PLS package. I have done this with 20 new sample...

In one of the columns, for constituent C16_0, one sample (57) has a value of “zero” (we could see this in the histogram).The reason for that is that the laboratory did not supply this value. The PLS regression will consider the lab value as cero, s...

There are several algorithms to run a PLS regression (I recommend to consult the books: “Introduction to Multivariate Analysis in Chemometrics - Kurt Varmuza & Peter Filzmozer” and “Chemometrics with R – Ron Wehrens”).We are going to use ...

It is clear that MSC does not remove the entire scatter in the raw spectra, so some of the information is hidden by the scatter. Improvement of the sample presentation will help to remove the scatter.We know that the first loading is much related to th...

As I told you I´m a beginner in "R", so I realize that I have to prepare my data a little bit in order to continue from my previous post ( NIT: Fatty acids study in R - Part 002) after getting some errors. Anyway I´m really fascinated ...

__ library(chemometrics)__ fatmsc_nipals CPs matplot(CPs,t(fatmsc_nipals$T),lty=1,pch=21,  + xlab="PC_number",ylab="Explained_Var")In the 2D plot, we can see that with 3 or 4 principal...