def id3(data):
if all(x['analito'] == 'glicose' for x in data):
return Leaf('glicose')
if all(x['analito'] == 'triglicerideo' for x in data):
return Leaf('triglicerideo')
if len([k for k in data[0].keys() if k != 'analito']) <= 0:
return Leaf(most_common([d['analito'] for d in data]))
# Entropia dos atributos
splited = {k: entropy([x[k] for x in data.copy()]) for k in data[0].keys()}
splited.pop('analito')
# Atributo separador
separator = min(splited.items(), key=lambda x: x[1])[0]
node = Node(separator)
if is_continuous(data[0][separator]):
for x in data:
x[separator] = round(x[separator], PRECISION)
for v in set(x[separator] for x in data):
aux = [x for x in data.copy() if separator in x and x[separator] == v]
for i in aux:
i.pop(separator)
node.add_son({v: id3(aux)})
return node
def predict(element, tree):
if type(tree) is Leaf:
return tree.answer
if is_continuous(element[tree.attr]):
return predict(element, tree.sons[nearest(element[tree.attr],
list(tree.sons.keys()),
precision=PRECISION)])
return predict(element, tree.sons[element[tree.attr]])