def train(self, dataset):
def train_trees(examples_subset):
tree = DecisionTree()
#tree.train(examples_subset, splitting_func=ft.partial(random_subset_split, self.number_of_dimensions))
tree.train(examples_subset, splitting_func=totally_random_split)
#use identity function
tree.transform_input = identity
return tree
if self.number_of_dimensions == None:
self.number_of_dimensions = min(np.log2(dataset.num_attributes()) + 1, 1)
points_per_sample = dataset.num_examples() * 1.0 / 3.0
self.learners = map(train_trees, ds.bootstrap_samples(dataset, self.number_of_learners, points_per_sample))
def train(self, dataset):
def train_trees(examples_subset):
#select a subset of dimensions
dims = random_subset(self.number_of_dimensions, examples_subset.num_attributes())
subset_input = examples_subset.inputs[dims, :]
reduced_sample = Dataset(subset_input, examples_subset.outputs)
tree = DecisionTree(reduced_sample)
tree.dimensions_subset = dims
return tree
if self.number_of_dimensions == None:
self.number_of_dimensions = min(np.log2(dataset.num_attributes()) + 1, 1)
points_per_sample = dataset.num_examples() * 1.0 / 3.0
in_bags, out_bags = ds.bootstrap_samples(dataset,
self.number_of_learners,
points_per_sample)
self.learners = map(train_trees, in_bags)
def train(self, dataset):
def train_trees(examples_subset):
tree = DecisionTree()
#tree.train(examples_subset, splitting_func=ft.partial(random_subset_split, self.number_of_dimensions))
tree.train(examples_subset, splitting_func=totally_random_split)
#use identity function
tree.transform_input = identity
return tree
if self.number_of_dimensions == None:
self.number_of_dimensions = min(
np.log2(dataset.num_attributes()) + 1, 1)
points_per_sample = dataset.num_examples() * 1.0 / 3.0
self.learners = map(
train_trees,
ds.bootstrap_samples(dataset, self.number_of_learners,
points_per_sample))
def train(self, dataset):
def train_trees(examples_subset):
#select a subset of dimensions
dims = random_subset(self.number_of_dimensions,
examples_subset.num_attributes())
subset_input = examples_subset.inputs[dims, :]
reduced_sample = Dataset(subset_input, examples_subset.outputs)
tree = DecisionTree(reduced_sample)
tree.dimensions_subset = dims
return tree
if self.number_of_dimensions == None:
self.number_of_dimensions = min(
np.log2(dataset.num_attributes()) + 1, 1)
points_per_sample = dataset.num_examples() * 1.0 / 3.0
in_bags, out_bags = ds.bootstrap_samples(dataset,
self.number_of_learners,
points_per_sample)
self.learners = map(train_trees, in_bags)
