load_set

# load doc into memory
def load_doc(filename):
	# open the file as read only
	file = open(filename, 'r')
	# read all text
	text = file.read()
	# close the file
	file.close()
	return text

# load a pre-defined list of photo identifiers
def load_set(filename):
	doc = load_doc(filename)
	dataset = list()
	# process line by line
	for line in doc.split('\n'):
		# skip empty lines
		if len(line) < 1:
			continue
		# get the image identifier
		identifier = line.split('.')[0]
		dataset.append(identifier)
	return set(dataset)