numero.subgroup {Numero} | R Documentation |
Plot self-organizing map colorings and let the user choose multi-district regions as subgroups
numero.subgroup(results, variables, elements = NULL, reference = NULL, gain = 1, detach = FALSE, capacity = 9)
results |
A list object that contains the self-organizing map and its statistical colorings. |
variables |
A string vector that contains names of variables to show on screen. |
elements |
A SOM topology or the output from a previous subgrouping session. |
reference |
Reference color ranges and scales. |
gain |
Modifier for overall color intensity. |
detach |
Use a detached window. |
capacity |
Maximum number of subplots to show on screen. |
The input results
must contain the output from
codenumero.evaluate() or similar.
The input argument elements
can be the topology of a SOM or with
additional columns as in the output from numero.subgroup()
.
The input argument reference
follows the output format from
numero.evaluate()
.
Setting detach to FALSE will also clear all devices whenever the figure is
refreshed. This may be inconvenient when using R from the terminal,
for example; please see the help page of numero.plot()
for
using detached window device instead.
If any districts are left unmarked, they are automatically collected into a subgroup of their own.
A data frame similar to the format returned by nroPlot()
.
Ville-Petteri Makinen
# Import data. fname <- system.file("extdata", "finndiane.txt", package = "Numero") dataset <- read.delim(file = fname) # Set identities and manage missing data. dataset <- numero.clean(dataset, identity = "INDEX") # Prepare training variables. trvars <- c("CHOL", "HDL2C", "TG", "CREAT", "uALB") trdata <- numero.prepare(data = dataset, variables = trvars) # Create a self-organizing map. modl <- numero.create(data = trdata) # Evaluate map statistics for all variables. stats <- numero.evaluate(model = modl, data = dataset) # Define subgroups, uncomment to launch interactive window. warning("Interactive example of numero.subrgoup() disabled.") #elem <- numero.subgroup(results = stats, variables = trvars)