def test_auto_weight():
"""Test class weights for imbalanced data"""
from sklearn.linear_model import LogisticRegression
# we take as dataset a the two-dimensional projection of iris so
# that it is not separable and remove half of predictors from
# class 1
from sklearn.svm.base import _get_class_weight
X, y = iris.data[:, :2], iris.target
unbalanced = np.delete(np.arange(y.size), np.where(y > 1)[0][::2])
assert_true(np.argmax(_get_class_weight('auto', y[unbalanced])[0]) == 2)
C = len(X)
for clf in (svm.SVC(kernel='linear',
C=C), svm.LinearSVC(C=C), LogisticRegression(C=C)):
# check that score is better when class='auto' is set.
y_pred = clf.fit(X[unbalanced], y[unbalanced]).predict(X)
clf.set_params(class_weight='auto')
y_pred_balanced = clf.fit(
X[unbalanced],
y[unbalanced],
).predict(X)
assert_true(
metrics.f1_score(y, y_pred) <= metrics.f1_score(
y, y_pred_balanced))
def test_auto_weight():
"""Test class weights for imbalanced data"""
from sklearn.linear_model import LogisticRegression
# we take as dataset a the two-dimensional projection of iris so
# that it is not separable and remove half of predictors from
# class 1
from sklearn.svm.base import _get_class_weight
X, y = iris.data[:, :2], iris.target
unbalanced = np.delete(np.arange(y.size), np.where(y > 1)[0][::2])
assert np.argmax(_get_class_weight("auto", y[unbalanced])[0]) == 2
for clf in (svm.SVC(kernel="linear"), svm.LinearSVC(), LogisticRegression()):
# check that score is better when class='auto' is set.
y_pred = clf.fit(X[unbalanced], y[unbalanced], class_weight={}).predict(X)
y_pred_balanced = clf.fit(X[unbalanced], y[unbalanced], class_weight="auto").predict(X)
assert metrics.f1_score(y, y_pred) <= metrics.f1_score(y, y_pred_balanced)