def distances_tests():
HAUS_S_D = 0.0673441488
haus = image_template.modified_hausdorff_distance
assert abs(haus(temp_s, temp_d) - HAUS_S_D) < 0.0001
assert image_template.list_classification(temp_s, [temp_d, temp_s])[0] == "temp_s"
test = page.image_templates[0]
train = page.image_templates[1:50]
assert image_template.list_classification_vec(test, train) == \
image_template.list_classification(test, train)
dist_matrix = image_template.distance_matrix([temp_s, temp_d, temp_s])
assert np.allclose(dist_matrix, np.array([[ 0. , HAUS_S_D, 0. ],
[ HAUS_S_D, 0. , HAUS_S_D],
[ 0. , HAUS_S_D, 0. ]]))
def character_rec(dim=48, resample=True):
print "Building data"
pages = load_pages(base_directory, dim=dim, resample=resample)
accuracies = []
total_temps = 0.0
total_right = 0.0
for i, (test, train) in enumerate(holdout(pages)):
print i, "Classifiying"
train_images = [image for page in train
for image in page.image_templates
if image.name != "NO LABEL"]
grouped_labels = [list_classification(t, train_images)[0]
for t in test.image_templates]
predicted_labels = distribute_labels(test.groups,
grouped_labels,
test.num_temps)
real_labels = test.labels
# num_right = np.sum([1.0 if predicted_labels[i] == real_labels[i]
# else 0.0
# for i in range(len(real_labels))])
# accuracies.append(num_right/test.num_temps)
num_right = num_correct_labels(predicted_labels, real_labels)
total_temps += test.num_temps
total_right += num_right
accuracies.append(num_right/len(test.labels))
avg_accuracy = total_right/total_temps
return (accuracies, avg_accuracy)
def ensemble_rec():
print "Building data"
pages = load_pages(base_directory)
accuracies = []
for i, (test, train) in enumerate(holdout(pages)):
print i, "Grouping"
group_clf = create_grouping_classifier(train, tree.DecisionTreeClassifier)
(g_acc, grouped_test) = group_classify(test, group_clf)
print i, "Classifiying"
train_images = [image for page in train
for image in page.image_templates
if image.name != "NO LABEL"]
grouped_labels = [list_classification(t, train_images)[0]
for t in grouped_test]
predicted_labels = distribute_labels(test.groups,
grouped_labels,
test.num_temps)
real_labels = test.labels
num_right = np.sum([1.0 if predicted_labels[i] == real_labels[i]
else 0.0
for i in range(len(real_labels))])
accuracies.append([num_right/test.num_temps, g_acc])
return accuracies
