gauravbansal98

# load clean descriptions into memory
def load_clean_descriptions(filename, dataset):
	# load document
	doc = load_doc(filename)
	descriptions = dict()
	for line in doc.split('\n'):
		# split line by white space
		tokens = line.split()
		# split id from description
		image_id, image_desc = tokens[0], tokens[1:]

gauravbansal98

# 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

gauravbansal98

2252123185_487f21e336 bunch on people are seated in stadium
2252123185_487f21e336 crowded stadium is full of people watching an event
2252123185_487f21e336 crowd of people fill up packed stadium
2252123185_487f21e336 crowd sitting in an indoor stadium
2252123185_487f21e336 stadium full of people watch game
...

gauravbansal98

# save descriptions to file, one per line
def save_descriptions(descriptions, filename):
	lines = list()
	for key, desc_list in descriptions.items():
		for desc in desc_list:
			lines.append(key + ' ' + desc)
	data = '\n'.join(lines)
	file = open(filename, 'w')
	file.write(data)
	file.close()

gauravbansal98

# convert the loaded descriptions into a vocabulary of words
def to_vocabulary(descriptions):
	# build a list of all description strings
	all_desc = set()
	for key in descriptions.keys():
		[all_desc.update(d.split()) for d in descriptions[key]]
	return all_desc

# summarize vocabulary
vocabulary = to_vocabulary(descriptions)

gauravbansal98

import string

def clean_descriptions(descriptions):
	# prepare translation table for removing punctuation
	table = str.maketrans('', '', string.punctuation)
	for key, desc_list in descriptions.items():
		for i in range(len(desc_list)):
			desc = desc_list[i]
			# tokenize
			desc = desc.split()

gauravbansal98

# extract descriptions for images
def load_descriptions(doc):
	mapping = dict()
	# process lines
	for line in doc.split('\n'):
		# split line by white space
		tokens = line.split()
		if len(line) < 2:
			continue
		# take the first token as the image id, the rest as the description

gauravbansal98

3
4
5
6
7
8
9
10
11

gauravbansal98

# 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
 

gauravbansal98

3
4
5
6
7
8
9
10
11