def continuous_info_gain(attribute, examples):
sortable = list(examples)
sortable.sort(cmp=lambda x,y: cmp(x.get(attribute), y.get(attribute)))
index = 0
total = len(sortable)
best_gain = 0
best_index = index + 1
while index < len(sortable):
# Skip over elements that have the same class under this attribute
current_goal = sortable[index].get_goal()
while (index < len(sortable)) and \
(current_goal == sortable[index].get_goal()):
index += 1
if index >= len(sortable):
continue
left = sortable[:index]
right = sortable[index:]
l_entropy = bool_entropy(dt_util.get_plurality_fraction(left))
r_entropy = bool_entropy(dt_util.get_plurality_fraction(right))
gain = (float(len(left)) / total) * l_entropy + \
(float(len(right)) / total) * r_entropy
if gain > best_gain:
best_gain = gain
best_index = index
split_point = float(sum([e.get(attribute) for e in
sortable[best_index-1:best_index+1]])) / 2
return best_gain, split_point
def continuous_info_gain(attribute, examples):
sortable = list(examples)
sortable.sort(cmp=lambda x, y: cmp(x.get(attribute), y.get(attribute)))
index = 0
total = len(sortable)
best_gain = 0
best_index = index + 1
while index < len(sortable):
# Skip over elements that have the same class under this attribute
current_goal = sortable[index].get_goal()
while (index < len(sortable)) and \
(current_goal == sortable[index].get_goal()):
index += 1
if index >= len(sortable):
continue
left = sortable[:index]
right = sortable[index:]
l_entropy = bool_entropy(dt_util.get_plurality_fraction(left))
r_entropy = bool_entropy(dt_util.get_plurality_fraction(right))
gain = (float(len(left)) / total) * l_entropy + \
(float(len(right)) / total) * r_entropy
if gain > best_gain:
best_gain = gain
best_index = index
split_point = float(
sum([
e.get(attribute) for e in sortable[best_index - 1:best_index + 1]
])) / 2
return best_gain, split_point
def discrete_info_gain(attribute, examples):
total = len(examples)
bucketed = bucket_examples_by_attribute(attribute, examples)
remainder = get_remainder_over_buckets(bucketed, total)
base_info = dt_util.get_plurality_fraction(examples)
return base_info - remainder
def discrete_info_gain(attribute, examples):
total = len(examples)
bucketed = bucket_examples_by_attribute(attribute, examples)
remainder = get_remainder_over_buckets(bucketed, total)
base_info = dt_util.get_plurality_fraction(examples)
return base_info - remainder
def get_remainder_over_buckets(bucketed, total_count):
remainder = 0
keys = bucketed.keys()
for k in keys:
elems = bucketed[k]
weight = float(len(elems)) / total_count
q = dt_util.get_plurality_fraction(elems)
remainder += weight * bool_entropy(q)
return remainder
def get_remainder_over_buckets(bucketed, total_count):
remainder = 0
keys = bucketed.keys()
for k in keys:
elems = bucketed[k]
weight = float(len(elems)) / total_count
q = dt_util.get_plurality_fraction(elems)
remainder += weight * bool_entropy(q)
return remainder
