coord.py 文件源码

def build_hash_to_coord(paths):
    if os.path.exists("comps/mobike/sol_carl/data/h2c.p") and os.path.exists("comps/mobike/sol_carl/data/c2h.p"):
        return
    h2c,c2h = {},{}
    for path in paths:
        for c,row in enumerate(csv.DictReader(open(path))):
            for tag in ["geohashed_end_loc","geohashed_start_loc"]:
                if tag not in row:
                    continue
                h = row[tag]
                if h not in h2c:
                    coord = str_coord(decode(h))
                    h2c[h] = coord
                    #lat,lon = int(lat+0.5),int(lon+0.5)
                    if coord not in c2h:
                        c2h[coord] = set()
                    c2h[coord].add(h)
            if c>0 and c%100000 == 0:
                print(path,c)
    print(len(h2c),len(c2h))
    pickle.dump(h2c,open("comps/mobike/sol_carl/data/h2c.p","wb"))
    pickle.dump(c2h,open("comps/mobike/sol_carl/data/c2h.p","wb"))