opening 3 files to convert matrix indexes to int from string hash

read index.py

#!/usr/bin/python #http://labrosa.ee.columbia.edu/millionsong/sites/default/files/challenge/train_triplets.txt.zip
songs_file = open('songs.txt', 'r')
users_file = open('users.txt', 'r')
dataset_file = open('train_triplets.txt', 'r')
#dataset_file = open('a.txt', 'r')
songs_count = 0 
users_count = 0
dataset_count = 0

users_dict = dict()
songs_dict = dict()	

# reading songs into a dictionary object
lines = songs_file.readlines()
for line in lines:
	line = line.strip()
	songs_dict[line] = songs_count
	songs_count = songs_count + 1
		
#print songs_count
#print songs_dict
songs_file.close()

# reading users into a dictionary object
lines = users_file.readlines()
for line in lines:
	line = line.strip()
	users_dict[line] = users_count
	users_count = users_count + 1
		
#print users_count
#print users_dict.values()
users_file.close()

#reading dataset
# reading songs into a dictionary object

while 1:
	lines = dataset_file.readlines(1000000)
	if not lines:
		break
	for line in lines:
		line = line.strip()
		(user, song, freq) = line.split()
		user = user.strip()
		if (users_dict.haskey(user) == False):
			users_dict[user] = users_count + 1;
		song = song.strip()
		if (songs_dict.haskey(song) == False):
			songs_dict[song] = songss_count + 1;
		freq = freq.strip()
		print users_dict[user], songs_dict[song], freq
	
dataset_file.close()