Skip to content
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

Jump to bottom

[FIX] Fix classification trees for data with repeated feature values #6488

Merged
merged 2 commits into from
Jul 13, 2023
Merged

[FIX] Fix classification trees for data with repeated feature values #6488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1852c10
test_orangetree: use numpy's asserts
markotoplak Jun 21, 2023
cbe2e11
fix tree's find_threshold_entropy for repeated values
markotoplak Jun 22, 2023
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
2 changes: 1 addition & 1 deletion Orange/classification/_tree_scorers.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ def find_threshold_entropy(const double[:] x, const double[:] y,
curr_y = <int>y[idx[i]]
distr[curr_y] -= 1
distr[n_classes + curr_y] += 1
if curr_y != y[idx[i + 1]] and x[idx[i]] != x[idx[i + 1]]:
if x[idx[i]] != x[idx[i + 1]]:
entro = (i + 1) * log(i + 1) + (N - i - 1) * log(N - i - 1)
for j in range(2 * n_classes):
if distr[j]:
Expand Down
36 changes: 35 additions & 1 deletion Orange/tests/test_orangetree.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@

import numpy as np
import scipy.sparse as sp
from Orange.classification._tree_scorers import find_threshold_entropy

from Orange.data import Table, Domain, DiscreteVariable, ContinuousVariable
from Orange.classification.tree import \
Expand Down Expand Up @@ -34,7 +35,7 @@ def test_full_tree(self):
learn = self.TreeLearner(**self.no_pruning_args)
clf = learn(table)
pred = clf(table)
self.assertTrue(np.all(table.Y.flatten() == pred))
np.testing.assert_equal(table.Y.flatten(), pred)

def test_min_samples_split(self):
clf = self.TreeLearner(
Expand Down Expand Up @@ -448,3 +449,36 @@ def test_compile_and_run_cont_sparse(self):
[14, 2, 1]], dtype=float
))
np.testing.assert_equal(model.get_values(x), expected_values)


class TestScorers(unittest.TestCase):

def test_find_threshold_entropy(self):
x = np.array([1, 2, 3, 4], dtype=float)
y = np.array([0, 0, 1, 1], dtype=float)
ind = np.argsort(x, kind="stable")
e, t = find_threshold_entropy(x, y, ind, 2, 1)
self.assertAlmostEqual(e, 1)
self.assertEqual(t, 2.0)

def test_find_threshold_entropy_repeated(self):
x = np.array([1, 1, 1, 2, 2, 2], dtype=float)
y = np.array([0, 0, 0, 0, 1, 1], dtype=float)
ind = np.argsort(x, kind="stable")
e, t = find_threshold_entropy(x, y, ind, 2, 1)
self.assertAlmostEqual(e, 0.459147917027245)
self.assertEqual(t, 1.0)

x = np.array([1, 1, 1, 2, 2, 2], dtype=float)
y = np.array([0, 0, 1, 1, 1, 1], dtype=float)
ind = np.argsort(x, kind="stable")
e, t = find_threshold_entropy(x, y, ind, 2, 1)
self.assertAlmostEqual(e, 0.459147917027245)
self.assertEqual(t, 1.0)

x = np.array([1, 1, 1, 2, 2, 2], dtype=float)
y = np.array([0, 1, 1, 1, 1, 1], dtype=float)
ind = np.argsort(x, kind="stable")
e, t = find_threshold_entropy(x, y, ind, 2, 1)
self.assertAlmostEqual(e, 0.19087450462110966)
self.assertEqual(t, 1.0)
Loading