def train(self):
"""
Learns a decision tree and saves
the model to a file.
"""
examples = self.data["train"]
features = set(examples[0].features.keys())
self.tree = d_tree(examples, features, [], 7)
f = open(self.out_file, "wb")
pickle.dump(self, f)
f.close()
def train(self, ensemble_size=5):
"""
Learns an ensemble using adaboost and
saves the model to a file.
"""
examples = self.data["train"]
features = set(examples[0].features.keys())
sample = WeightedSample(examples)
self.ensemble = []
for i in range(ensemble_size):
stump = d_tree(examples, features, [], 1)
error = 0
for ex in examples:
decision = stump.decide(ex)
if decision != ex.goal:
error += ex.weight
for j in range(len(examples)):
ex = examples[j]
decision = stump.decide(ex)
if decision == ex.goal:
new_weight = ex.weight * error/(sample.dist_sum - error)
sample.change_weight(j, new_weight)
sample.normalize()
stump.weight = math.log(sample.dist_sum - error)/error
self.ensemble.append(stump)
f = open(self.out_file, "wb")
pickle.dump(self, f)
f.close()