Model {fuseMLR} | R Documentation |
Model Class
Description
This class implements a model. A Model object can only exist as element of a TrainLayer or a TrainMetaLayer object. A Model object is automatically created by fitting a learner on a training data.
A Model object can compute predictions for a TestData object. See the predict
function below.
Methods
Public methods
Method new()
Constructor of Model class.
Usage
Model$new(lrner, train_data, base_model, train_layer)
Arguments
lrner
Lrner
The learner.train_data
TrainData(1)
Training data.base_model
object
Base model as returned by the original learn function.train_layer
TrainLayer
The current training layer on which the model is stored.
Returns
An object is returned.
Method print()
Printer
Usage
Model$print(...)
Arguments
...
any
Method summary()
Summary
Usage
Model$summary(...)
Arguments
...
any
Method getBaseModel()
Getter of the base model
Usage
Model$getBaseModel()
Method getTrainData()
Getter of the traning data
Usage
Model$getTrainData()
Method getTrainLabel()
Getter of the individual ID column in the training data.
Usage
Model$getTrainLabel()
Arguments
...
any
Method getLrner()
Getter of the learner use to fit the model.
Usage
Model$getLrner()
Method setId()
Setter of the model ID.
Usage
Model$setId(id)
Arguments
id
character
ID value
Method predict()
Predict target values for the new data (from class TestData) taken as into.
Usage
Model$predict(testing_data, use_var_sel, ind_subset = NULL)
Arguments
testing_data
TestData
An object from class TestData.use_var_sel
boolean
If TRUE, selected variables available at each layer are used.ind_subset
vector
Subset of individual IDs to be predicted....
Further parameters to be passed to the basic predict function.
Returns
The predicted object are returned. The predicted object must be either a vector or a list containing a field predictions with predictions.
Method clone()
The objects of this class are cloneable with this method.
Usage
Model$clone(deep = FALSE)
Arguments
deep
Whether to make a deep clone.