def train(self, trainSet: InstanceList, parameters: RandomForestParameter):
"""
Training algorithm for random forest classifier. Basically the algorithm creates K distinct decision trees from
K bootstrap samples of the original training set.
PARAMETERS
----------
trainSet : InstanceList
Training data given to the algorithm
parameters : RandomForestParameter
Parameters of the bagging trees algorithm. ensembleSize returns the number of trees in the random forest.
"""
forestSize = parameters.getEnsembleSize()
forest = []
for i in range(forestSize):
bootstrap = trainSet.bootstrap(i)
tree = DecisionTree(
DecisionNode(InstanceList(bootstrap.getSample()), None,
parameters, False))
forest.append(tree)
self.model = TreeEnsembleModel(forest)
def train(self, trainSet: InstanceList, parameters: BaggingParameter):
"""
Bagging bootstrap ensemble method that creates individuals for its ensemble by training each classifier on a
random redistribution of the training set.
This training method is for a bagged decision tree classifier. 20 percent of the instances are left aside for
pruning of the trees 80 percent of the instances are used for training the trees. The number of trees
(forestSize) is a parameter, and basically the method will learn an ensemble of trees as a model.
PARAMETERS
----------
trainSet : InstanceList
Training data given to the algorithm.
parameters : Parameter
Parameters of the bagging trees algorithm. ensembleSize returns the number of trees in the bagged forest.
"""
forestSize = parameters.getEnsembleSize()
forest = []
for i in range(forestSize):
bootstrap = trainSet.bootstrap(i)
tree = DecisionTree(
DecisionNode(InstanceList(bootstrap.getSample())))
forest.append(tree)
self.model = TreeEnsembleModel(forest)