8000 Fix average precision score test on numpy 1.3 by arjoly · Pull Request #2629 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

Fix average precision score test on numpy 1.3 #2629

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
merged 2 commits into from
Dec 2, 2013
Merged

Fix average precision score test on numpy 1.3 #2629

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a01a5c
TST more corner case tests
arjoly Dec 2, 2013
848eab3
TST ensure that exceptions are properly raised on np 1.3
arjoly Dec 2, 2013
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
198 changes: 114 additions & 84 deletions sklearn/metrics/tests/test_metrics.py
View file
Open in desktop
10000
Original file line number Diff line number Diff line change
Expand Up @@ -556,6 +556,21 @@ def test_roc_curve_toydata():
assert_array_almost_equal(fpr, [0, 1])
assert_almost_equal(roc_auc, .5)

y_true = [0, 0]
y_score = [0.25, 0.75]
tpr, fpr, _ = roc_curve(y_true, y_score)
assert_raises(ValueError, roc_auc_score, y_true, y_score)
assert_array_almost_equal(tpr, [ 0. , 0.5, 1. ])
assert_array_almost_equal(fpr, [ np.nan, np.nan, np.nan])

y_true = [1, 1]
y_score = [0.25, 0.75]
tpr, fpr, _ = roc_curve(y_true, y_score)
assert_raises(ValueError, roc_auc_score, y_true, y_score)
assert_array_almost_equal(tpr, [ np.nan, np.nan])
assert_array_almost_equal(fpr, [ 0.5, 1. ])


# Multi-label classification task
y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [0, 1]])
Expand Down Expand Up @@ -1101,91 +1116,106 @@ def test_precision_recall_curve_errors():


def test_precision_recall_curve_toydata():
# Binary classification
y_true = [0, 1]
y_score = [0, 1]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [1, 1])
assert_array_almost_equal(r, [1, 0])
assert_almost_equal(auc_prc, 1.)

y_true = [0, 1]
y_score = [1, 0]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [ 0.5, 0. , 1. ])
assert_array_almost_equal(r, [ 1., 0., 0.])
assert_almost_equal(auc_prc, 0.25)

y_true = [1, 0]
y_score = [1, 1]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [0.5, 1])
assert_array_almost_equal(r, [1., 0])
assert_almost_equal(auc_prc, .75)

y_true = [1, 0]
y_score = [1, 0]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [1, 1])
assert_array_almost_equal(r, [1, 0])
assert_almost_equal(auc_prc, 1.)
with np.errstate(all="raise"):
# Binary classification
y_true = [0, 1]
y_score = [0, 1]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [1, 1])
assert_array_almost_equal(r, [1, 0])
assert_almost_equal(auc_prc, 1.)

y_true = [0, 1]
y_score = [1, 0]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [ 0.5, 0. , 1. ])
assert_array_almost_equal(r, [ 1., 0., 0.])
assert_almost_equal(auc_prc, 0.25)

y_true = [1, 0]
y_score = [1, 1]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [0.5, 1])
assert_array_almost_equal(r, [1., 0])
assert_almost_equal(auc_prc, .75)

y_true = [1, 0]
y_score = [1, 0]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [1, 1])
assert_array_almost_equal(r, [1, 0])
assert_almost_equal(auc_prc, 1.)

y_true = [1, 0]
y_score = [0.5, 0.5]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [0.5, 1])
assert_array_almost_equal(r, [1, 0.])
assert_almost_equal(auc_prc, .75)

y_true = [0, 0]
y_score = [0.25, 0.75]
assert_raises(Exception, precision_recall_curve, y_true, y_score)
assert_raises(Exception, average_precision_score, y_true, y_score)

y_true = [1, 1]
y_score = [0.25, 0.75]
p, r, _ = precision_recall_curve(y_true, y_score)
assert_almost_equal(average_precision_score(y_true, y_score), 1.)
assert_array_almost_equal(p, [ 1. , 1., 1.])
assert_array_almost_equal(r, [1, 0.5, 0.])


# Multi-label classification task
y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [0, 1]])
assert_raises(Exception, average_precision_score, y_true, y_score,
average="macro")
assert_raises(Exception, average_precision_score, y_true, y_score,
average="weighted")
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 1.)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 1.)

y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_raises(Exception, average_precision_score, y_true, y_score,
average="macro")
assert_raises(Exception, average_precision_score, y_true, y_score,
average="weighted")
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.625)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.625)

y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_almost_equal(average_precision_score(y_true, y_score,
average="macro"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="weighted"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.25)

y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0.5, 0.5], [0.5, 0.5]])
assert_almost_equal(average_precision_score(y_true, y_score,
average="macro"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="weighted"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.75)

y_true = [1, 0]
y_score = [0.5, 0.5]
p, r, _ = precision_recall_curve(y_true, y_score)
auc_prc = average_precision_score(y_true, y_score)
assert_array_almost_equal(p, [0.5, 1])
assert_array_almost_equal(r, [1, 0.])
assert_almost_equal(auc_prc, .75)

# Multi-label classification task
y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [0, 1]])
assert_raises(ValueError, average_precision_score, y_true, y_score,
average="macro")
assert_raises(ValueError, average_precision_score, y_true, y_score,
average="weighted")
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 1.)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 1.)

y_true = np.array([[0, 1], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_raises(ValueError, average_precision_score, y_true, y_score,
average="macro")
assert_raises(ValueError, average_precision_score, y_true, y_score,
average="weighted")
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.625)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.625)

y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0, 1], [1, 0]])
assert_almost_equal(average_precision_score(y_true, y_score,
average="macro"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="weighted"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.25)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.25)

y_true = np.array([[1, 0], [0, 1]])
y_score = np.array([[0.5, 0.5], [0.5, 0.5]])
assert_almost_equal(average_precision_score(y_true, y_score,
average="macro"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="weighted"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="samples"), 0.75)
assert_almost_equal(average_precision_score(y_true, y_score,
average="micro"), 0.75)

def test_score_scale_invariance():
# Test that average_precision_score and roc_auc_score are invariant by
Expand Down
0