24 lines
753 B
Python
24 lines
753 B
Python
def gini_index(groups, classes):
|
|
# count all samples at split point
|
|
n_instances = float(sum([len(group) for group in groups]))
|
|
# sum weighted Gini index for each group
|
|
gini = 0.0
|
|
for group in groups:
|
|
size = float(len(group))
|
|
# avoid divide by zero
|
|
if size == 0:
|
|
continue
|
|
score = 0.0
|
|
# score the group based on the score for each class
|
|
for class_val in classes:
|
|
for row in group:
|
|
print(row[-1])
|
|
p = [row[-1] for row in group].count(class_val) / size
|
|
score += p * p
|
|
# weight the group score by its relative size
|
|
gini += (1.0 - score) * (size / n_instances)
|
|
return gini
|
|
|
|
# test Gini values
|
|
print(gini_index([[[1, 1], [1, 0]], [[1, 1], [1, 0]]], [0, 1]))
|
|
print(gini_index([[[1, 0], [1, 0]], [[1, 1], [1, 1]]], [0, 1])) |