Skip to content

[FIX] Gini impurity: formula and docstring fixed. #1495

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lanzagar merged 1 commit into from
Sep 16, 2016
Merged

[FIX] Gini impurity: formula and docstring fixed. #1495

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions Orange/preprocess/score.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,9 +205,9 @@ def _entropy(D):

def _gini(D):
"""Gini index of class-distribution matrix"""
P = D / np.sum(D, axis=0)
return sum((np.ones(1 if len(D.shape) == 1 else D.shape[1]) - np.sum(np.square(P), axis=0))
* 0.5 * np.sum(D, axis=0) / np.sum(D))
P = np.asarray(D / np.sum(D, axis=0))
return np.sum((1 - np.sum(P ** 2, axis=0)) *
np.sum(D, axis=0) / np.sum(D))


def _symmetrical_uncertainty(X, Y):
Expand Down Expand Up @@ -287,8 +287,9 @@ def from_contingency(self, cont, nan_adjustment):

class Gini(ClassificationScorer):
"""
Gini index is the probability that two randomly chosen instances will have different
classes. See `Wikipedia entry on gini index <http://en.wikipedia.org/wiki/Gini_coefficient>`_.
Gini impurity is the probability that two randomly chosen instances will have different
classes. See `Wikipedia entry on Gini impurity
<https://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity>`_.
"""
def from_contingency(self, cont, nan_adjustment):
return (_gini(np.sum(cont, axis=1)) - _gini(cont)) * nan_adjustment
Expand Down
2 changes: 1 addition & 1 deletion Orange/tests/test_score_feature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ def test_gain_ratio(self):

def test_gini(self):
scorer = Gini()
correct = [0.11893, 0.10427, 0.13117, 0.14650, 0.05973]
correct = [0.23786, 0.20855, 0.26235, 0.29300, 0.11946]
np.testing.assert_almost_equal([scorer(self.zoo, a) for a in range(5)],
correct, decimal=5)

Expand Down
2 changes: 1 addition & 1 deletion Orange/widgets/data/owrank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ def table(shape, fill=None):
SCORES = [
score_meta("Information Gain", "Inf. gain", score.InfoGain),
score_meta("Gain Ratio", "Gain Ratio", score.GainRatio),
score_meta("Gini Gain", "Gini", score.Gini),
score_meta("Gini Decrease", "Gini", score.Gini),
score_meta("ANOVA", "ANOVA", score.ANOVA),
score_meta("Chi2", "Chi2", score.Chi2),
score_meta("Univariate Linear Regression", "Univar. Lin. Reg.", score.UnivariateLinearRegression),
Expand Down