sits (version 0.13.0)

sits_mlr: Train a sits classification model using multinomial log-linear

Description

Use multinomial log-linear (mlr) fitting model to classify data. This function receives a tibble with a set of attributes X for each observation Y. These attributes are the values of the time series for each band. This function is a front-end to the "multinom" method in the "nnet" package. Please refer to the documentation in that package for more details.

Usage

sits_mlr(
  data = NULL,
  formula = sits_formula_linear(),
  n_weights = 20000,
  maxit = 2000,
  ...
)

Arguments

data

Time series with the training samples.

formula

Symbolic description of the model to be fit. (default: sits_formula_logref).

n_weights

Maximum number of weights (should be proportional to size of input data).

maxit

Maximum number of iterations (default 300).

...

Other parameters to be passed to nnet::multinom.

Value

Model fitted to input data (to be passed to sits_classify)

Examples

# NOT RUN {
# Retrieve the set of samples for  Mato Grosso region (provided by EMBRAPA)
samples_2bands <- sits_select(samples_modis_4bands, bands = c("NDVI", "EVI"))

# Build a machine learning model
ml_model <- sits_train(samples_2bands, sits_mlr())

# get a point and classify the point with the ml_model
point.tb <- sits_select(point_mt_6bands, bands = c("NDVI", "EVI"))
class.tb <- sits_classify(point.tb, ml_model)
plot(class.tb, bands = c("NDVI", "EVI"))
# }
# NOT RUN {
# }