Data-Science-Learning-Path/Data Scientist Career Path/11. Foundations of Machine Learning Supervised Learning/7. Advanced/2. Tree/3. gain.py at main · yusufarist/Data-Science-Learning-Path · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
from collections import Counter

unsplit_labels = ["unacc", "unacc", "unacc", "unacc", "unacc", "unacc", "good", "good", "good", "good", "vgood", "vgood", "vgood"]

split_labels_1 = [
  ["unacc", "unacc", "unacc", "unacc", "unacc", "unacc", "good", "good", "vgood"],
  [ "good", "good"],
  ["vgood", "vgood"]
]

split_labels_2 = [
  ["unacc", "unacc", "unacc", "unacc","unacc", "unacc", "good", "good", "good", "good"],
  ["vgood", "vgood", "vgood"]
]

def gini(dataset):
  impurity = 1
  label_counts = Counter(dataset)
  for label in label_counts:
    prob_of_label = label_counts[label] / len(dataset)
    impurity -= prob_of_label ** 2
  return impurity

info_gain = gini(unsplit_labels)
for subset in split_labels_1:
  info_gain -= gini(subset)

print(info_gain)