def main():
parser = argparse.ArgumentParser()
parser.add_argument('-d', type=int, action='store',
dest='data_num', help='choose which data set to use')
if len(sys.argv) != 3:
print 'Command e.g.: python findNearPlace.py -d 0(1,2)'
sys.exit(1)
para = parser.parse_args()
if para.data_num == 0:
location_infile = settings["ROOT_PATH"] + settings["SRC_DATA_FILE1_1"]
nearplace_outfile = settings["ROOT_PATH"] + settings["NEAR_PLACE_FILE1"]
elif para.data_num == 1:
location_infile = settings["ROOT_PATH"] + settings["SRC_DATA_FILE2_1"]
nearplace_outfile = settings["ROOT_PATH"] + settings["NEAR_PLACE_FILE2"]
elif para.data_num == 2:
location_infile = settings["ROOT_PATH"] + settings["SRC_DATA_FILE3_3"]
nearplace_outfile = settings["ROOT_PATH"] + settings["NEAR_PLACE_FILE3"]
else:
print 'Invalid choice of data set'
sys.exit(1)
loc_latlng = {}
try:
for entry in csv.reader(open(location_infile, 'rU')):
pid, lat, lng = int(entry[0]), float(entry[2]), float(entry[3])
loc_latlng[pid] = (lat, lng)
except:
print entry
sys.exit(1)
# directly scanning all POIs to get answer, which is too slow
'''writer = csv.writer(open(nearplace_outfile, "w"), lineterminator="\r\n")
pids = loc_latlng.keys()
for i in xrange(len(pids)):
pid1 = pids[i]
near_place = []
for j in xrange(len(pids)):
pid2 = pids[j]
dis = distance.distance(loc_latlng[pid1], loc_latlng[pid2]).miles
if dis < settings["DISTANCE_THRESHOLD"]:
near_place.append(pid2)
writer.writerow([pid1] + near_place)
print i'''
# quad tree
index_extent = (-90, -180, 90, 180)
index = Quadtree(index_extent)
for pid in loc_latlng:
index.add(pid, loc_latlng[pid])
for pid in loc_latlng:
start_time = time.clock()
pid_set = findNearPlaceByQuadtree(loc_latlng,
loc_latlng[pid],
index.struct(),
settings["DISTANCE_THRESHOLD"])
end_time = time.clock()
print "Time Cost: %f(s)" % (end_time-start_time)
raw_input()
print len(pid_set)
raw_input()
