Tutorial week 12 question 5

distance_from_unsw.py

from os import scandir
from sys import argv
from math import radians, cos, sin, asin, sqrt

def iterate_users(dataset_path):
    l = []
    for user in scandir(dataset_path):
        for f in scandir(user.path):
            if f.name == "user.txt":
                l.append(parse_file(f.path))
    return l
                
def parse_file(filename):
    my_lat, my_lon = -33.9172238, 151.2302268
    d = {}
    for line in open(filename):
        name, data = line.strip().split("=", 1)
        d[name] = data
    d["distance"] = haversine(float(d.get("home_longitude", 0)), float(d.get("home_latitude", 0)), my_lon, my_lat)
    return d
    
for user in sorted(iterate_users(argv[1]), key = lambda x: x["distance"]):
    if user["distance"]:
        print("{} lives at {} {} in {}".format(user["zid"], user["home_latitude"], user["home_longitude"], user["home_suburb"]))

def haversine(lon1, lat1, lon2, lat2):
    """
    Calculate the great circle distance between two points 
    on the earth (specified in decimal degrees)
    """
    # convert decimal degrees to radians 
    lon1, lat1, lon2, lat2 = map(radians, [lon1, lat1, lon2, lat2])

    # haversine formula 
    dlon = lon2 - lon1 
    dlat = lat2 - lat1 
    a = sin(dlat/2)**2 + cos(lat1) * cos(lat2) * sin(dlon/2)**2
    c = 2 * asin(sqrt(a)) 
    r = 6371 # Radius of earth in kilometers. Use 3956 for miles
    if lon1 and lat1:
        return c * r
    else:
        return 0