users.py

# -*- coding: utf-8 -*-
"""
Created on Wed Sep 24 22:12:20 2014

@author: vikramk3
"""

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import pprint
import re
"""
Your task is to explore the data a bit more.
The first task is a fun one - find out how many unique users
have contributed to the map in this particular area!

The function process_map should return a set of unique user IDs ("uid")
"""

def get_user(element):
    return


def process_map(filename):
    # I added element.clear() after each iteration to avoid memory issues for the iterative parsing
    users = set()
    for _, element in ET.iterparse(filename):
        pass
        new_user=element.get("uid")
        if (new_user not in users) and (new_user != None):
            users.add(element.get("uid"))
        element.clear()

    return users


def test():

    users = process_map('C:\\Users\\vikramk3\\Documents\\Courses\\Data_Wrangling\\austin_texas.osm')
    pprint.pprint(users)
    print "#of unique users= ", len(users)



if __name__ == "__main__":
    test()