def train(self, num_classifiers=50):
bagged_datasets = DataHandler.create_bagged_datasets(
num_classifiers, self.examples, self.targets)
for bagged_dataset in bagged_datasets:
naive_bayes = NaiveBayes(bagged_dataset[0], bagged_dataset[1])
naive_bayes.train()
self.nb_classifiers.append(naive_bayes)
def train(self, forest_size=50, tree_depth=10):
self.forest = []
bagged_datasets = DataHandler.create_bagged_datasets(
forest_size, self.examples, self.targets)
for bagged_dataset in bagged_datasets:
examples = bagged_dataset[0]
targets = bagged_dataset[1]
num_attributes = len(examples[0])
num_chosen_attr = int(sqrt(num_attributes))
while num_chosen_attr > len(examples[0]):
DataHandler.rm_column(examples,
random.randint(1,
len(examples[0]) - 1))
id3 = ID3(examples, targets)
id3.train(tree_depth)
self.forest.append(id3)
