[SOLVED] gaussian anamorphosis

If you have problems using RGeostats package or if you simply need some help on an unlisted subject.

[SOLVED] gaussian anamorphosis

Postby eman0706 » Fri Jun 16, 2017 9:52 am

Dear Friends,

I'm trying to tranform the Zn concentration (very skewed) into Gaussian.

I attempted such task in the following way:

Z_obs<-as.numeric(Chem_data.L1$Zn)

#Create a standard db-class and define its type (Grid or Point)
dbZ_obs<-db.create(Z_obs, flag.grid = FALSE, nx = NA, x0 = NA, dx = NA,
nech = NA, angles=NA, ndim = NA, nvar = NA, autoname = TRUE)

azmin<-min(Z_obs)
azmax<-max(Z_obs)

#Fit the Anamorphosis parameter
anam.fit(dbZ_obs, name="Z", type="gaus", nbpoly = 50, azmin =azmin, azmax = azmin, aymin = 0, aymax = 1,
ndisc= NA, sigma2e=NA, zcut=NA, maf=NA, draw=TRUE,verbose=FALSE)


but get the following error:

Error: Error in R_anam_fit_hermitian

Can someone help me??

ciao

eman
eman0706
 
Posts: 3
Joined: Wed Jul 03, 2013 8:20 am

Re: gaussian anamorphosis

Postby Didier Renard » Mon Jun 19, 2017 8:30 pm

The problem is simple.
You are creating a data base WITH NO COORDINATE. This is not standard in RGeostats as it will not let you perform any spatial procedure.
However, this is not a restriction when performing a purely statistical procedure, such as the anamorphosis.
But, if you look at the contents of the Db (called dbZ_obs) right after the db.create() function, you will see the no variable receives the locator "z1": we say that no field is locatorized as a variable.
But this is what the next procedure (i.e. anam.fit) requires.

In order to solve the problem, simply set the correct locator to the variable of interest, called "Z_obs" by typing:

dbZ_obs = db.locate(dbZ_obs,"Z_obs","z")

The rest of the procedure will work OK.
Didier Renard
 
Posts: 251
Joined: Thu Sep 20, 2012 4:22 pm


Return to Other Troubleshooting

Who is online

Users browsing this forum: No registered users and 1 guest

cron