def generate_sets(neighbours, blur_scale, verbose=0):
"""Split the entire dataset into a trainingset and a testset."""
suffix = '_%s_%s' % (blur_scale, neighbours)
learning_set_file = 'learning_set%s.dat' % suffix
test_set_file = 'test_set%s.dat' % suffix
chars = load_characters(neighbours, blur_scale, verbose=verbose)
if verbose:
print 'Going to generate learning set and test set...'
learning_set = []
test_set = []
learned = []
for char in chars:
if learned.count(char.value) == 70:
test_set.append(char)
else:
learning_set.append(char)
learned.append(char.value)
if verbose:
print 'Learning set:', [c.value for c in learning_set]
print '\nTest set:', [c.value for c in test_set]
print '\nSaving learning set...'
fdump(learning_set, learning_set_file)
if verbose:
print 'Saving test set...'
fdump(test_set, test_set_file)
return learning_set, test_set
def load_characters(neighbours, blur_scale, verbose=0):
chars_file = 'characters_%s_%s.dat' % (blur_scale, neighbours)
if exists(chars_file):
print 'Loading characters...'
chars = fload(chars_file)
else:
print 'Going to generate character objects...'
chars = []
for char in sorted(listdir(IMAGES_FOLDER)):
count = 0
for image in sorted(listdir(IMAGES_FOLDER + char)):
image = GrayscaleImage(IMAGES_FOLDER + char + '/' + image)
norm = NormalizedCharacterImage(image, blur=blur_scale, \
height=NORMALIZED_HEIGHT)
character = Character(char, [], norm)
character.get_single_cell_feature_vector(neighbours)
chars.append(character)
count += 1
if verbose:
print 'Loaded character %s %d times' % (char, count)
if verbose:
print 'Saving characters...'
fdump(chars, chars_file)
return chars
