Last active
July 2, 2018 21:39
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# converts GTFS feed to a CSV sequence of "trip_id,time,lat,lon[,TIMEPOINT]" | |
import datetime | |
import partridge as ptg | |
import numpy | |
day_start = 1522022400; # 03/26/2018 @ 12:00am (UTC) | |
path = '/path/to/gtfs.zip' | |
representative_feed = ptg.get_representative_feed(path) | |
stop_dict = {} | |
for stop in representative_feed.stops.values: | |
stop_dict[stop[0]] = stop | |
trip_stop_times = {} | |
for stop_time in representative_feed.stop_times.values: | |
if not stop_time[0] in trip_stop_times: | |
trip_stop_times[stop_time[0]] = [] | |
trip_stop_times[stop_time[0]].append(stop_time) | |
def print_stop_time(data, stop_time, timepoint): | |
stop = stop_dict[data[3]] | |
output_data = [data[0],str(round((stop_time + day_start) * 1000)), str(stop[4]), str(stop[5])] | |
if timepoint: | |
output_data.append("TIMEPOINT") | |
print(",".join(output_data)) | |
for trip_id in trip_stop_times: | |
trip_stops = trip_stop_times[trip_id] | |
sorted_trip_stop_times = sorted(trip_stops, key=lambda k: k[4]) | |
trip_last_timepoint = 0 | |
non_timepoint_stops = [] | |
for stop_time in sorted_trip_stop_times: | |
if not numpy.isnan(stop_time[1]): | |
current_time = stop_time[1] | |
if len(non_timepoint_stops) > 0: | |
interpolated_time = (current_time - trip_last_timepoint) / (len(non_timepoint_stops) + 1) | |
offset = 1 | |
for ntp_stop in non_timepoint_stops: | |
print_stop_time(ntp_stop, trip_last_timepoint + (interpolated_time * offset), False) | |
offset += 1 | |
non_timepoint_stops = [] | |
trip_last_timepoint = current_time | |
print_stop_time(stop_time, stop_time[1], True) | |
else: | |
non_timepoint_stops.append(stop_time) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment