Information Gain calculation with Scikit-learn

Question

I am using Scikit-learn for text classification. I want to calculate the Information Gain for each attribute with respect to a class in a (sparse) document-term matrix.

Answer 1

Using pure python:

def ig(class_, feature):
  classes = set(class_)

  Hc = 0
  for c in classes:
    pc = class_.count(c)/len(class_)
    Hc += - pc * math.log(pc, 2)
  print('Overall Entropy:', Hc)
  feature_values = set(feature)

  Hc_feature = 0
  for feat in feature_values:

    pf = feature.count(feat)/len(feature)
    indices = [i for i in range(len(feature)) if feature[i] == feat]
    clasess_of_feat = [class_[i] for i in indices]
    for c in classes:
        pcf = clasess_of_feat.count(c)/len(clasess_of_feat)
        if pcf != 0:
            temp_H = - pf * pcf * math.log(pcf, 2)
            Hc_feature += temp_H
  ig = Hc - Hc_feature
  return ig