def test_with_confusion_matrix_on_multiclass(self):
learner = random_learner
ds = data.Table("iris")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
scores = self.score(cm[0])
self.assertIsInstance(scores, float)
def test_construct_confusion_matrix_from_biclass(self):
learner = random_learner
ds = data.Table("monks-1")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
self.assertTrue(hasattr(cm[0], "TP"))
def test_with_confusion_matrices_on_biclass(self):
learner = random_learner
ds = data.Table("monks-1")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
scores = self.score(cm)
self.assertIsInstance(scores, list)
def test_construct_confusion_matrix_from_biclass(self):
learner = random_learner
ds = data.Table("monks-1")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
self.assertTrue(hasattr(cm[0], "TP"))
def test_construct_confusion_matrix_from_multiclass(self):
learner = random_learner
ds = data.Table("iris")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt)
self.assertTrue(isinstance(cm[0], list))
def acc(sta,sto,subject):
data = Orange.data.Table("../data/"+str(subject)+'-'+str(sta)+"-"+str(sto)+".csv")
classes = data.domain.classVar.values
#ma = Orange.feature.scoring.score_all(data)
highest_precision = 0
highest_precision_recall = 0
highest_recall = 0
highest_recall_precision = 0
for mid_node in range(5,20):
ann = Orange.classification.neural.NeuralNetworkLearner(n_mid=mid_node, reg_fact=1, max_iter=200, rand=random, normalize=True)
results = Orange.evaluation.testing.cross_validation([ann], data, folds=10)
# print "analyze "+classes[0]+":"
cm = scoring.confusion_matrices( results, class_index=0, ignore_weights=False, cutoff=0.5)[0]
# print "TP: %i, FP: %i, FN: %s, TN: %i" % (cm.TP, cm.FP, cm.FN, cm.TN)
if cm.TP+cm.FP!=0:
if cm.TP/(cm.TP+cm.FP)>highest_precision:
highest_precision = cm.TP/(cm.TP+cm.FP)
highest_precision_recall = cm.TP/(cm.TP+cm.FN)
if cm.TP+cm.FN!=0:
if cm.TP/(cm.TP+cm.FN)>highest_recall:
highest_recall = cm.TP/(cm.TP+cm.FN)
highest_recall_precision = cm.TP/(cm.TP+cm.FP)
return format(highest_precision,'.3f'),format(highest_precision_recall,'.3f')
def test_construct_confusion_matrix_from_multiclass(self):
learner = random_learner
ds = data.Table("iris")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt)
self.assertTrue(isinstance(cm[0], list))
def test_with_confusion_matrix_on_multiclass(self):
learner = random_learner
ds = data.Table("iris")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
scores = self.score(cm[0])
self.assertIsInstance(scores, float)
def test_with_confusion_matrices_on_biclass(self):
learner = random_learner
ds = data.Table("monks-1")
pt = testing.proportion_test([learner], ds, times=1)
cm = scoring.confusion_matrices(pt, class_index=1)
scores = self.score(cm)
self.assertIsInstance(scores, list)
def acc(sta, sto, subject):
# print str(sta)+"-"+str(sto)
# data = Orange.data.Table("../data/"+str(subject)+'-'+str(sta)+"-"+str(sto)+".csv")
data = Orange.data.Table("../data/"+str(subject)+'-'+str(sta)+"-"+str(sto)+"_attr.csv")
classes = data.domain.classVar.values
# print "analyze "+classes[0]+":"
highest_precision = 0
highest_precision_recall = 0
highest_recall = 0
highest_recall_precision = 0
for i in range(1,101):
# for i in range(1,2):
j=float(i)/100
# svm_l = Orange.classification.svm.SVMLearner(kernel_type=Orange.classification.svm.kernels.Linear)
# rfe = Orange.classification.svm.RFE(learner=svm_l)
# data_with_subset_of_features = rfe(data, 10)
# print data_with_subset_of_features.domain
# n = 10
# ma = Orange.feature.scoring.score_all(data)
# best = Orange.feature.selection.top_rated(ma, n)
# print 'Best %d features:' % n
# for s in best:
# print s
learner = svm.SVMLearner(gamma=j, verbose=False)
# learner = svm.SVMLearner(kernel_type=Orange.classification.svm.kernels.Linear ,verbose=False)
# learner = Orange.feature.selection.FilteredLearner(learner, filter=Orange.feature.selection.FilterBestN(n=10), name='filtered')
results = testing.cross_validation([learner], data, folds=10)
# print scoring.CA(results)
# print "analyze "+classes[0]+":"
cm = scoring.confusion_matrices( results, class_index=0, ignore_weights=False, cutoff=0.52)[0]
# print "TP: %i, FP: %i, FN: %s, TN: %i" % (cm.TP, cm.FP, cm.FN, cm.TN)
if cm.TP+cm.FP!=0:
if cm.TP/(cm.TP+cm.FP)>highest_precision:
highest_precision = cm.TP/(cm.TP+cm.FP)
highest_precision_recall = cm.TP/(cm.TP+cm.FN)
if cm.TP+cm.FN!=0:
if cm.TP/(cm.TP+cm.FN)>highest_recall:
highest_recall = cm.TP/(cm.TP+cm.FN)
highest_recall_precision = cm.TP/(cm.TP+cm.FP)
# time.sleep(0.1)
return format(highest_precision,'.3f'),format(highest_precision_recall,'.3f'), len(data)
def test_ca_from_confusion_matrix_on_iris_se(self):
ds = data.Table("iris")
cv = testing.cross_validation([self.learner], ds, folds=5)
cm = scoring.confusion_matrices(cv, class_index=1)
ca = scoring.CA(cm[0], report_se=True)
self.assertEqual(len(ca), 1)
def test_ca_from_confusion_matrix_list_on_iris(self):
ds = data.Table("iris")
cv = testing.cross_validation([self.learner], ds, folds=5)
cm = scoring.confusion_matrices(cv)
ca = scoring.CA(cm)
self.assertEqual(len(ca), 1)
def test_ca_from_confusion_matrix_on_iris_se(self):
ds = data.Table("iris")
cv = testing.cross_validation([self.learner], ds, folds=5)
cm = scoring.confusion_matrices(cv, class_index=1)
ca = scoring.CA(cm[0], report_se=True)
self.assertEqual(len(ca), 1)
def test_ca_from_confusion_matrix_list_on_iris(self):
ds = data.Table("iris")
cv = testing.cross_validation([self.learner], ds, folds=5)
cm = scoring.confusion_matrices(cv)
ca = scoring.CA(cm)
self.assertEqual(len(ca), 1)
def run_tests(datasets, measures, tests, iterations=10):
for ds, ds_name in datasets:
for t, t_name in tests:
print "Testing %s on %s" % (t_name, ds_name)
test_results = [t(random_learner, ds) for _ in xrange(iterations)]
test(measures, test_results)
datasets = (
(data.Table("iris"), "Iris"),
(data.Table("monks-1"), "Monks")
)
measures = (
(lambda x:ca(x), "CA"),
(lambda x:ca(x, report_se=False, ignore_weights=False), "CA-SE-W"),
(lambda x:ca(x, report_se=True, ignore_weights=False), "CA+SE-W"),
(lambda x:[lambda x:[None]], ""),
(lambda x:ca(x, report_se=False, ignore_weights=True), "CA-SE+W"),
(lambda x:ca(x, report_se=True, ignore_weights=True), "CA+SE+W"),
(lambda x:[lambda x:[None]], ""),
)
tests = (
(lambda l, ds: testing.cross_validation([l],ds), "CV"),
(lambda l, ds: testing.proportion_test([l], ds, .7, 1), "Proportion test"),
(lambda l, ds: scoring.confusion_matrices(testing.proportion_test([l], ds, .7, 1)), "Confusion matrix"),
)
run_tests(datasets, measures, tests)
print
def run_tests(datasets, measures, tests, iterations=10):
for ds, ds_name in datasets:
for t, t_name in tests:
print "Testing %s on %s" % (t_name, ds_name)
test_results = [t(random_learner, ds) for _ in xrange(iterations)]
test(measures, test_results)
datasets = ((data.Table("iris"), "Iris"), (data.Table("monks-1"), "Monks"))
measures = (
(lambda x: ca(x), "CA"),
(lambda x: ca(x, report_se=False, ignore_weights=False), "CA-SE-W"),
(lambda x: ca(x, report_se=True, ignore_weights=False), "CA+SE-W"),
(lambda x: [lambda x: [None]], ""),
(lambda x: ca(x, report_se=False, ignore_weights=True), "CA-SE+W"),
(lambda x: ca(x, report_se=True, ignore_weights=True), "CA+SE+W"),
(lambda x: [lambda x: [None]], ""),
)
tests = (
(lambda l, ds: testing.cross_validation([l], ds), "CV"),
(lambda l, ds: testing.proportion_test([l], ds, .7, 1), "Proportion test"),
(lambda l, ds: scoring.confusion_matrices(
testing.proportion_test([l], ds, .7, 1)), "Confusion matrix"),
)
run_tests(datasets, measures, tests)