Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Check predict_proba shape in ThresholdScorer #12486

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 19 commits into from
Nov 14, 2018
Merged

Check predict_proba shape in ThresholdScorer #12486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
41a220c
ck estimator is classifier & num_classes>=2 in score.py
Oct 30, 2018
73489b3
fixed formatting issues after using flake8
Oct 30, 2018
7cfe9ea
putting assert error in 1 line instead of 2
Oct 30, 2018
9054e97
added test for this pull request
Oct 30, 2018
7336082
adding mixture test
Oct 30, 2018
15a4397
add regression test, also add fix for proba scorers
amueller Nov 9, 2018
d083449
Merge branch 'master' of https://github.com/scikit-learn/scikit-learn…
Nov 11, 2018
c08cb2e
updating scorer and test per edits by amueller
Nov 11, 2018
210424a
updating error description
Nov 11, 2018
78a75ea
updating scorer, formatting
Nov 11, 2018
4ae5b54
Merge branch 'master' of https://github.com/scikit-learn/scikit-learn…
Nov 11, 2018
a9e873e
uh, fixed merge conflict
Nov 11, 2018
f021674
make error message wording consistent
Nov 11, 2018
e9e492e
use consistent wording for error in both places
Nov 11, 2018
389482e
added shape value to error message
Nov 13, 2018
b4be4aa
Merge branch 'master' of https://github.com/scikit-learn/scikit-learn…
Nov 13, 2018
dbda7a2
fixed formatting error from flake8 test
Nov 13, 2018
8495900
made updates after running pytests
Nov 13, 2018
4a256f1
line 198 too long, fixed formatting
Nov 13, 2018
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
17 changes: 15 additions & 2 deletions sklearn/metrics/scorer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,13 @@ def __call__(self, clf, X, y, sample_weight=None):
y_type = type_of_target(y)
y_pred = clf.predict_proba(X)
if y_type == "binary":
y_pred = y_pred[:, 1]
if y_pred.shape[1] == 2:
y_pred = y_pred[:, 1]
else:
raise ValueError('got predict_proba of shape {},'
' but need classifier with two'
' classes for {} scoring'.format(
y_pred.shape, self._score_func.__name__))
if sample_weight is not None:
return self._sign * self._score_func(y, y_pred,
sample_weight=sample_weight,
Expand Down Expand Up @@ -183,7 +189,14 @@ def __call__(self, clf, X, y, sample_weight=None):
y_pred = clf.predict_proba(X)

if y_type == "binary":
y_pred = y_pred[:, 1]
if y_pred.shape[1] == 2:
y_pred = y_pred[:, 1]
else:
raise ValueError('got predict_proba of shape {},'
' but need classifier with two'
' classes for {} scoring'.format(
y_pred.shape,
self._score_func.__name__))
elif isinstance(y_pred, list):
y_pred = np.vstack([p[:, -1] for p in y_pred]).T

Expand Down
25 changes: 20 additions & 5 deletions sklearn/metrics/tests/test_score_objects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,10 +186,11 @@ def check_scoring_validator_for_single_metric_usecases(scoring_validator):


def check_multimetric_scoring_single_metric_wrapper(*args, **kwargs):
# This wraps the _check_multimetric_scoring to take in single metric
# scoring parameter so we can run the tests that we will run for
# check_scoring, for check_multimetric_scoring too for single-metric
# usecases
# This wraps the _check_multimetric_scoring to take in
# single metric scoring parameter so we can run the tests
# that we will run for check_scoring, for check_multimetric_scoring
# too for single-metric usecases

scorers, is_multi = _check_multimetric_scoring(*args, **kwargs)
# For all single metric use cases, it should register as not multimetric
assert_false(is_multi)
Expand Down Expand Up @@ -370,7 +371,21 @@ def test_thresholded_scorers():
X, y = make_blobs(random_state=0, centers=3)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf.fit(X_train, y_train)
assert_raises(ValueError, get_scorer('roc_auc'), clf, X_test, y_test)
with pytest.raises(ValueError, match="multiclass format is not supported"):
get_scorer('roc_auc')(clf, X_test, y_test)

# test error is raised with a single class present in model
# (predict_proba shape is not suitable for binary auc)
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X_train, np.zeros_like(y_train))
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('roc_auc')(clf, X_test, y_test)

# for proba scorers
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('neg_log_loss')(clf, X_test, y_test)


def test_thresholded_scorers_multilabel_indicator_data():
Expand Down