Skip to content

[FIX] Naive Bayes: fix predictions with unknown values #6564

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
janezd merged 2 commits into from
Sep 1, 2023
Merged

[FIX] Naive Bayes: fix predictions with unknown values #6564

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
9b95c17
fix Naive Bayes predictions with unknown values
thocevar Sep 1, 2023
4bba14d
fix naive bayes for sparse matrices
thocevar Sep 1, 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
3 changes: 2 additions & 1 deletion Orange/classification/naive_bayes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ def _dense_probs(self, data, probs):
zeros = np.zeros((1, probs.shape[1]))
for col, attr_prob in zip(data.T, self.log_cont_prob):
col = col.copy()
col[np.isnan(col)] = attr_prob.shape[1] - 1
col[np.isnan(col)] = attr_prob.shape[1]
col = col.astype(int)
probs0 = np.vstack((attr_prob.T, zeros))
probs += probs0[col]
Expand All @@ -113,6 +113,7 @@ def _sparse_probs(self, data, probs):
p0 = p.T[0].copy()
probs[:] += p0
log_prob[i, :p.shape[1]] = p.T - p0
log_prob[i, n_vals-1] = -p0

dat = data.data.copy()
dat[np.isnan(dat)] = n_vals - 1
Expand Down
33 changes: 33 additions & 0 deletions Orange/tests/test_naive_bayes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,14 +101,17 @@ def test_compare_results_of_predict_and_predict_storage(self):
def test_predictions(self):
self._test_predictions(sparse=None)
self._test_predictions_with_absent_class(sparse=None)
self._test_predict_missing_attributes(sparse=None)

def test_predictions_csr_matrix(self):
self._test_predictions(sparse=sp.csr_matrix)
self._test_predictions_with_absent_class(sparse=sp.csr_matrix)
self._test_predict_missing_attributes(sparse=sp.csr_matrix)

def test_predictions_csc_matrix(self):
self._test_predictions(sparse=sp.csc_matrix)
self._test_predictions_with_absent_class(sparse=sp.csc_matrix)
self._test_predict_missing_attributes(sparse=sp.csc_matrix)

def _test_predictions(self, sparse):
x = np.array([
Expand Down Expand Up @@ -311,6 +314,36 @@ def _test_predictions_with_absent_class(self, sparse):
np.testing.assert_almost_equal(exp_probs, probs)
np.testing.assert_equal(values, np.argmax(exp_probs, axis=1))

def _test_predict_missing_attributes(self, sparse):
x = np.array([
[1, 0, 0],
[0, 1, 0],
[0, 0, 0],
[0, 1, 0],
[1, 1, 0],
[1, 2, 0],
[1, 2, np.nan]])
if sparse is not None:
x = sparse(x)
y = np.array([1,0,0,0,1,1,1])
domain = Domain(
[DiscreteVariable("a", values="ab"),
DiscreteVariable("b", values="abc"),
DiscreteVariable("c", values="a")],
DiscreteVariable("y", values="AB"))
data = Table.from_numpy(domain, x, y)

model = self.learner(data)
test_x = np.array([[np.nan, np.nan, np.nan],
[np.nan, 0, np.nan],
[0, np.nan, np.nan]])
if sparse is not None and sparse is not sp.csc_matrix:
test_x = sparse(test_x)
probs = model(test_x, ret=model.Probs)
np.testing.assert_almost_equal(probs, [[(3+1)/(7+2), (4+1)/(7+2)],
[(1+1)/(2+2), (1+1)/(2+2)],
[(3+1)/(3+2), (0+1)/(3+2)]])

def test_no_attributes(self):
y = np.array([0, 0, 0, 1, 1, 1, 2, 2])
domain = Domain([], DiscreteVariable("y", values="abc"))
Expand Down