def test_multiclass_classifier(self, clf):
# Force non-dataspecific C value.
# Otherwise multiclass libsvm builtin and our MultiClass would differ
# in results
svm = clf.clone() # operate on clone to avoid side-effects
if 'C' in svm.params and svm.params.C<0:
svm.params.C = 1.0 # reset C to be 1
svm2 = svm.clone()
svm2.ca.enable(['training_stats'])
mclf = MulticlassClassifier(clf=svm, enable_ca=['training_stats'])
# with explicit MaximalVote with the conditional attributes
# enabled
mclf_mv = MulticlassClassifier(clf=svm,
combiner=MaximalVote(enable_ca=['estimates', 'predictions']),
enable_ca=['training_stats'])
ds_train = datasets['uni2small']
for clf_ in svm2, mclf, mclf_mv:
clf_.train(ds_train)
s1 = str(mclf.ca.training_stats)
s2 = str(svm2.ca.training_stats)
s3 = str(mclf_mv.ca.training_stats)
self.assertEqual(s1, s2,
msg="Multiclass clf should provide same results as built-in "
"libsvm's %s. Got %s and %s" % (svm2, s1, s2))
self.assertEqual(s1, s3,
msg="%s should have used maxvote resolver by default"
"so results should have been identical. Got %s and %s"
% (mclf, s1, s3))
assert_equal(len(mclf_mv.combiner.ca.estimates),
len(mclf_mv.combiner.ca.predictions))
# They should have came from assessing training_stats ca being
# enabled
# recompute accuracy on predictions for training_stats
training_acc = np.sum(mclf_mv.combiner.ca.predictions ==
ds_train.targets) / float(len(ds_train))
# should match
assert_equal(mclf_mv.ca.training_stats.stats['ACC'], training_acc)
svm2.untrain()
self.assertTrue(svm2.trained == False,
msg="Un-Trained SVM should be untrained")
self.assertTrue(np.array([x.trained for x in mclf.clfs]).all(),
msg="Trained Boosted classifier should have all primary classifiers trained")
self.assertTrue(mclf.trained,
msg="Trained Boosted classifier should be marked as trained")
mclf.untrain()
self.assertTrue(not mclf.trained,
msg="UnTrained Boosted classifier should not be trained")
self.assertTrue(not np.array([x.trained for x in mclf.clfs]).any(),
msg="UnTrained Boosted classifier should have no primary classifiers trained")
def test_multiclass_classifier(self, clf):
# Force non-dataspecific C value.
# Otherwise multiclass libsvm builtin and our MultiClass would differ
# in results
svm = clf.clone() # operate on clone to avoid side-effects
if svm.params.has_key('C') and svm.params.C<0:
svm.params.C = 1.0 # reset C to be 1
svm2 = svm.clone()
svm2.ca.enable(['training_stats'])
mclf = MulticlassClassifier(clf=svm, enable_ca=['training_stats'])
# with explicit MaximalVote with the conditional attributes
# enabled
mclf_mv = MulticlassClassifier(clf=svm,
combiner=MaximalVote(enable_ca=['estimates', 'predictions']),
enable_ca=['training_stats'])
ds_train = datasets['uni2small']
for clf_ in svm2, mclf, mclf_mv:
clf_.train(ds_train)
s1 = str(mclf.ca.training_stats)
s2 = str(svm2.ca.training_stats)
s3 = str(mclf_mv.ca.training_stats)
self.assertEqual(s1, s2,
msg="Multiclass clf should provide same results as built-in "
"libsvm's %s. Got %s and %s" % (svm2, s1, s2))
self.assertEqual(s1, s3,
msg="%s should have used maxvote resolver by default"
"so results should have been identical. Got %s and %s"
% (mclf, s1, s3))
assert_equal(len(mclf_mv.combiner.ca.estimates),
len(mclf_mv.combiner.ca.predictions))
# They should have came from assessing training_stats ca being
# enabled
# recompute accuracy on predictions for training_stats
training_acc = np.sum(mclf_mv.combiner.ca.predictions ==
ds_train.targets) / float(len(ds_train))
# should match
assert_equal(mclf_mv.ca.training_stats.stats['ACC'], training_acc)
svm2.untrain()
self.assertTrue(svm2.trained == False,
msg="Un-Trained SVM should be untrained")
self.assertTrue(np.array([x.trained for x in mclf.clfs]).all(),
msg="Trained Boosted classifier should have all primary classifiers trained")
self.assertTrue(mclf.trained,
msg="Trained Boosted classifier should be marked as trained")
mclf.untrain()
self.assertTrue(not mclf.trained,
msg="UnTrained Boosted classifier should not be trained")
self.assertTrue(not np.array([x.trained for x in mclf.clfs]).any(),
msg="UnTrained Boosted classifier should have no primary classifiers trained")
