Mercurial > bus-service / file comparison
comparison: buses.py
buses.py
- changeset 71
- d2e19670b772
- parent 42
- 0b53b7c70875
- child 72
- 65408ed066b3
equal
deleted
inserted
replaced
| 70:c2fc50748efd | 71:d2e19670b772 |
|---|---|
| 8 | 8 |
| 9 def transform_trip_reference(reference): | 9 def transform_trip_reference(reference): |
| 10 return reference | 10 return reference |
| 11 | 11 |
| 12 class BusTrip: | 12 class BusTrip: |
| 13 def __init__(self, reference, route, service, length): | 13 def __init__(self, reference, route, service, length, block_id): |
| 14 self.reference, self.route, self.service = reference, route, service | 14 self.reference, self.route, self.service, self.block_id = reference, route, service, block_id |
| 15 self.length = length | 15 self.length = length |
| 16 self.schedule = [] | 16 self.schedule = [] |
| 17 self.name = transform_trip_reference(reference) | 17 self.name = transform_trip_reference(reference) |
| 18 def __repr__(self): | 18 def __repr__(self): |
| 19 return 'all_trips[%r]' % self.name | 19 return 'all_trips[%r]' % self.name |
| 27 try: | 27 try: |
| 28 return self.service in services_for_day[day] | 28 return self.service in services_for_day[day] |
| 29 except KeyError: | 29 except KeyError: |
| 30 return False | 30 return False |
| 31 def concise_schedule(self, starting_stop = None): | 31 def concise_schedule(self, starting_stop = None): |
| 32 if starting_stop and starting_stop in self.schedule: | 32 if profile['regions']['use-regions']: |
| 33 schedule = copy(self.schedule) | 33 if starting_stop and starting_stop in self.schedule: |
| 34 schedule = schedule[schedule.index(starting_stop):] | 34 schedule = copy(self.schedule) |
| 35 schedule = schedule[schedule.index(starting_stop):] | |
| 36 else: | |
| 37 schedule = self.schedule | |
| 38 used_areas = set() | |
| 39 result = [] | |
| 40 for halt in schedule: | |
| 41 stop = halt.stop | |
| 42 if stop.region and stop.region not in used_areas: | |
| 43 used_areas.add(stop.region) | |
| 44 result.append(stop.region) | |
| 45 return result | |
| 35 else: | 46 else: |
| 36 schedule = self.schedule | 47 return [halt.stop.name for halt in self.schedule] |
| 37 used_areas = set() | |
| 38 result = [] | |
| 39 for halt in schedule: | |
| 40 stop = halt.stop | |
| 41 if stop.region and stop.region not in used_areas: | |
| 42 used_areas.add(stop.region) | |
| 43 result.append(stop.region) | |
| 44 return result | |
| 45 | 48 |
| 46 class BusRoute: | 49 class BusRoute: |
| 47 def __init__(self, entry): | 50 def __init__(self, entry): |
| 48 self.id = entry['route_id'] | 51 self.id = entry['route_id'] |
| 49 self.reference = entry['route_short_name'] | 52 self.reference = entry['route_short_name'] |
| 128 self.arrival_time, self.departure_time, self.stop, self.trip = arrival_time, departure_time, \ | 131 self.arrival_time, self.departure_time, self.stop, self.trip = arrival_time, departure_time, \ |
| 129 stop, trip | 132 stop, trip |
| 130 self.traveled_distance = traveled_distance | 133 self.traveled_distance = traveled_distance |
| 131 @property | 134 @property |
| 132 def is_arrival(self): | 135 def is_arrival(self): |
| 133 if not hasattr(self, 'cachedIsArrival'): | 136 if profile['regions']['use-regions']: |
| 134 if self.stop.region: | 137 if not hasattr(self, 'cachedIsArrival'): |
| 135 iterator = iter(self.trip.schedule) | 138 if self.stop.region: |
| 136 stop = next(iterator) | 139 iterator = iter(self.trip.schedule) |
| 137 while stop is not self: | |
| 138 stop = next(iterator) | 140 stop = next(iterator) |
| 139 for stop in iterator: | 141 while stop is not self: |
| 140 if stop.stop.region != self.stop.region: | 142 stop = next(iterator) |
| 141 self.cachedIsArrival = False | 143 for stop in iterator: |
| 142 break | 144 if stop.stop.region != self.stop.region: |
| 145 self.cachedIsArrival = False | |
| 146 break | |
| 147 else: | |
| 148 self.cachedIsArrival = True | |
| 143 else: | 149 else: |
| 144 self.cachedIsArrival = True | 150 self.cachedIsArrival = False |
| 145 else: | 151 return self.cachedIsArrival |
| 146 self.cachedIsArrival = False | 152 else: |
| 147 return self.cachedIsArrival | 153 return self == self.trip.schedule[-1] |
| 148 def __repr__(self): | 154 def __repr__(self): |
| 149 return 'BusHalt(%r, %r, %r, %r)' % (self.arrival_time, self.departure_time, self.stop, self.trip) | 155 return 'BusHalt(%r, %r, %r, %r)' % (self.arrival_time, self.departure_time, self.stop, self.trip) |
| 156 def sign(self, long = False): | |
| 157 from busroute import reduce_schedule | |
| 158 return reduce_schedule( | |
| 159 route = self.trip.concise_schedule(self), | |
| 160 trip_length = self.trip.length - self.traveled_distance, | |
| 161 long = long, | |
| 162 ) | |
| 150 | 163 |
| 151 routes = {} | 164 routes = {} |
| 152 routes_per_id = {} | 165 routes_per_id = {} |
| 153 all_trips = {} | 166 all_trips = {} |
| 154 services = {} | 167 services = {} |
| 156 all_clusters = set() | 169 all_clusters = set() |
| 157 viimeinen_käyttöpäivä = None | 170 viimeinen_käyttöpäivä = None |
| 158 clusters_by_name = {} | 171 clusters_by_name = {} |
| 159 services_for_day = {} | 172 services_for_day = {} |
| 160 | 173 |
| 161 def load_buses(gtfs_zip_path, profile): | 174 def load_buses(gtfs_zip_path): |
| 162 global viimeinen_käyttöpäivä | 175 global viimeinen_käyttöpäivä |
| 163 from zipfile import ZipFile | 176 from zipfile import ZipFile |
| 164 with ZipFile(gtfs_zip_path) as gtfs_zip: | 177 with ZipFile(gtfs_zip_path) as gtfs_zip: |
| 165 print('Ladataan linjat... ', file = stderr, end = '', flush = True) | 178 print('Ladataan linjat... ', file = stderr, end = '', flush = True) |
| 166 with gtfs_zip.open('routes.txt') as file: | 179 with gtfs_zip.open('routes.txt') as file: |
| 171 print('%d linjaa' % len(routes), file = stderr) | 184 print('%d linjaa' % len(routes), file = stderr) |
| 172 | 185 |
| 173 print('Ladataan ajovuorot... ', file = stderr, end = '', flush = True) | 186 print('Ladataan ajovuorot... ', file = stderr, end = '', flush = True) |
| 174 | 187 |
| 175 shape_distances = {} | 188 shape_distances = {} |
| 176 with gtfs_zip.open('shapes.txt') as file: | 189 try: |
| 177 for row in read_csv(map(bytes.decode, file)): | 190 with gtfs_zip.open('shapes.txt') as file: |
| 178 shape_distances[row['shape_id']] = max(shape_distances.get(row['shape_id'], 0), float(row['shape_dist_traveled'])) | 191 for row in read_csv(map(bytes.decode, file)): |
| 192 shape_distances[row['shape_id']] = max(shape_distances.get(row['shape_id'], 0), float(row['shape_dist_traveled'])) | |
| 193 except KeyError: | |
| 194 pass | |
| 179 | 195 |
| 180 with gtfs_zip.open('trips.txt') as file: | 196 with gtfs_zip.open('trips.txt') as file: |
| 181 for row in read_csv(map(bytes.decode, file)): | 197 for row in read_csv(map(bytes.decode, file)): |
| 182 if row['service_id'] not in services: | 198 if row['service_id'] not in services: |
| 183 services[row['service_id']] = BusService(row['service_id']) | 199 services[row['service_id']] = BusService(row['service_id']) |
| 184 route = routes_per_id[row['route_id']] | 200 route = routes_per_id[row['route_id']] |
| 185 trip = BusTrip( | 201 trip = BusTrip( |
| 186 reference = row['trip_id'], | 202 reference = row['trip_id'], |
| 187 route = route, | 203 route = route, |
| 188 service = services[row['service_id']], | 204 service = services[row['service_id']], |
| 189 length = shape_distances[row['shape_id']] * float(profile['metrics']['shape-modifier']) | 205 length = shape_distances.get(row.get('shape_id'), 1) * float(profile['metrics']['shape-modifier']), |
| 206 block_id = row['block_id'], | |
| 190 ) | 207 ) |
| 191 route.trips.add(trip) | 208 route.trips.add(trip) |
| 192 assert trip.name not in all_trips | 209 if trip.name in all_trips: |
| 193 all_trips[trip.name] = trip | 210 print('Trip %s already exists' % trip.name) |
| 211 else: | |
| 212 all_trips[trip.name] = trip | |
| 194 print('%d ajoa' % len(all_trips), file = stderr) | 213 print('%d ajoa' % len(all_trips), file = stderr) |
| 195 | 214 |
| 196 def read_date(teksti): | 215 def read_date(teksti): |
| 197 return date(int(teksti[:4]), int(teksti[4:6]), int(teksti[6:])) | 216 return date(int(teksti[:4]), int(teksti[4:6]), int(teksti[6:])) |
| 198 | 217 |
| 251 location = Sijainti(float(row['stop_lat']), float(row['stop_lon'])) | 270 location = Sijainti(float(row['stop_lat']), float(row['stop_lon'])) |
| 252 stop = BusStop( | 271 stop = BusStop( |
| 253 reference = row['stop_id'], | 272 reference = row['stop_id'], |
| 254 name = row['stop_name'], | 273 name = row['stop_name'], |
| 255 location = location, | 274 location = location, |
| 256 code = row['stop_code'], | 275 code = row.get('stop_code', row['stop_id']), |
| 257 ) | 276 ) |
| 258 bus_stops[stop.reference] = stop | 277 bus_stops[stop.reference] = stop |
| 259 with open('regions-per-stop.json') as file: | 278 if profile['regions']['use-regions']: |
| 260 for stop_reference, region in json.load(file).items(): | 279 with open('regions-per-stop.json') as file: |
| 261 bus_stops[stop_reference].region = region | 280 for stop_reference, region in json.load(file).items(): |
| 281 try: | |
| 282 bus_stops[stop_reference].region = region | |
| 283 except KeyError: | |
| 284 pass | |
| 262 print('%d pysäkkiä' % len(bus_stops), file = stderr) | 285 print('%d pysäkkiä' % len(bus_stops), file = stderr) |
| 263 | 286 |
| 264 | 287 |
| 265 class BusStopCluster: | 288 class BusStopCluster: |
| 266 def __init__(self): | 289 def __init__(self): |
| 365 for name, clusters in clusters_per_name.items(): | 388 for name, clusters in clusters_per_name.items(): |
| 366 if len(clusters) == 1: | 389 if len(clusters) == 1: |
| 367 # Ryhmä on ainoa jolla on varaus tälle nimelle. Sen kuin vaan. | 390 # Ryhmä on ainoa jolla on varaus tälle nimelle. Sen kuin vaan. |
| 368 next(iter(clusters)).name = name | 391 next(iter(clusters)).name = name |
| 369 else: | 392 else: |
| 370 # Olisiko kaikki klusterit eri alueilla? | 393 if profile['regions']['use-regions']: |
| 371 common_regions = shared_elements_in_n_sets({stop.region for stop in cluster.stops} for cluster in clusters) | 394 # Olisiko kaikki klusterit eri alueilla? |
| 372 # Esitys: ryhmä -> ne alueet jotka ovat tälle ryhmälle ainutlaatuisia | 395 common_regions = shared_elements_in_n_sets({stop.region for stop in cluster.stops} for cluster in clusters) |
| 373 proposal = { | 396 # Esitys: ryhmä -> ne alueet jotka ovat tälle ryhmälle ainutlaatuisia |
| 374 cluster: {stop.region for stop in cluster.stops} - common_regions - {None} | 397 proposal = { |
| 398 cluster: {stop.region for stop in cluster.stops} - common_regions - {None} | |
| 399 for cluster in clusters | |
| 400 } | |
| 401 # Jos enintään yksi klusteri tässä esityksessä on kokonaan ilman omaa aluetta, jolla se voisi eritellä, | |
| 402 # niin nimetään klusterit näiden alueiden mukaan. | |
| 403 # Se klusteri jolla ei ole omaa aluetta (jos on) jätetään ilman aluepäätettä. | |
| 404 if sum([1 for unique_areas in proposal.values() if not unique_areas]) <= 1: | |
| 405 for cluster, unique_areas in proposal.items(): | |
| 406 individual_cluster_name = name | |
| 407 if unique_areas: | |
| 408 individual_cluster_name += ' (' + min(unique_areas) + ')' | |
| 409 cluster.name = individual_cluster_name | |
| 410 break | |
| 411 # Typerä reunatapaus. Indeksoidaan numeroin... | |
| 412 for n, (_, cluster) in enumerate(sorted( | |
| 413 min((stop.reference.lower(), cluster) for stop in cluster.stops) | |
| 375 for cluster in clusters | 414 for cluster in clusters |
| 376 } | 415 ), 1): |
| 377 # Jos enintään yksi klusteri tässä esityksessä on kokonaan ilman omaa aluetta, jolla se voisi eritellä, | 416 individual_cluster_name = name + '-' + str(n) |
| 378 # niin nimetään klusterit näiden alueiden mukaan. | 417 cluster.name = individual_cluster_name |
| 379 # Se klusteri jolla ei ole omaa aluetta (jos on) jätetään ilman aluepäätettä. | |
| 380 if sum([1 for unique_areas in proposal.values() if not unique_areas]) <= 1: | |
| 381 for cluster, unique_areas in proposal.items(): | |
| 382 individual_cluster_name = name | |
| 383 if unique_areas: | |
| 384 individual_cluster_name += ' (' + min(unique_areas) + ')' | |
| 385 cluster.name = individual_cluster_name | |
| 386 else: | |
| 387 # Typerä reunatapaus. Indeksoidaan numeroin... | |
| 388 for n, (_, cluster) in enumerate(sorted( | |
| 389 min((stop.reference.lower(), cluster) for stop in cluster.stops) | |
| 390 for cluster in clusters | |
| 391 ), 1): | |
| 392 individual_cluster_name = name + '-' + str(n) | |
| 393 cluster.name = individual_cluster_name | |
| 394 | 418 |
| 395 print('Ryhmitellään pysäkit...') | 419 print('Ryhmitellään pysäkit...') |
| 396 cluster_bus_stops() | 420 cluster_bus_stops() |
| 397 name_clusters() | 421 name_clusters() |
| 398 | 422 |
| 406 with gtfs_zip.open('stop_times.txt') as file: | 430 with gtfs_zip.open('stop_times.txt') as file: |
| 407 row_count = sum(line.count(b'\n') for line in file) | 431 row_count = sum(line.count(b'\n') for line in file) |
| 408 with gtfs_zip.open('stop_times.txt') as file: | 432 with gtfs_zip.open('stop_times.txt') as file: |
| 409 progress = 0 | 433 progress = 0 |
| 410 for row in read_csv(map(bytes.decode, file)): | 434 for row in read_csv(map(bytes.decode, file)): |
| 435 if int(row.get('pickup_type', 0)) and int(row.get('drop_off_type', 0)): | |
| 436 continue | |
| 411 trip = all_trips[transform_trip_reference(row['trip_id'])] | 437 trip = all_trips[transform_trip_reference(row['trip_id'])] |
| 412 arrival_time = read_time(row['arrival_time']) | 438 arrival_time = read_time(row['arrival_time']) |
| 413 departure_time = read_time(row['departure_time']) | 439 departure_time = read_time(row['departure_time']) |
| 414 stop = bus_stops[row['stop_id']] | 440 stop = bus_stops[row['stop_id']] |
| 415 traveled_distance = float(row['shape_dist_traveled']) * float(profile['metrics']['shape-modifier']) | 441 traveled_distance = float(row.get('shape_dist_traveled', 1)) * float(profile['metrics']['shape-modifier']) |
| 416 trip.schedule.append(BusHalt(arrival_time, departure_time, stop, trip, traveled_distance)) | 442 trip.schedule.append(BusHalt(arrival_time, departure_time, stop, trip, traveled_distance)) |
| 417 stop.involved_trips.add(trip) | 443 stop.involved_trips.add(trip) |
| 418 progress += 1 | 444 progress += 1 |
| 419 if progress % 1000 == 0: | 445 if progress % 1000 == 0: |
| 420 print('\rLadataan aikataulut... %.1f%%' % (progress * 100 / row_count), end = ' ', file = stderr) | 446 print('\rLadataan aikataulut... %.1f%%' % (progress * 100 / row_count), end = ' ', file = stderr) |
| 448 try: | 474 try: |
| 449 most_common_route = tally.most_common(1)[0][0] | 475 most_common_route = tally.most_common(1)[0][0] |
| 450 route.description = simplify_name(most_common_route[0]) + ' - ' + simplify_name(most_common_route[-1]) | 476 route.description = simplify_name(most_common_route[0]) + ' - ' + simplify_name(most_common_route[-1]) |
| 451 except: | 477 except: |
| 452 route.description = '' | 478 route.description = '' |
| 453 route.trips = sorted(route.trips, key = lambda trip: trip.schedule[0].departure_time) | 479 route.trips = sorted(route.trips, key = lambda trip: trip.schedule and trip.schedule[0].departure_time or timedelta()) |
| 454 | 480 |
| 455 # Fölin datassa on jotain tosi kummaa. Ilmeisesti ajovuoron viimeisen pysähdyksen saapumisaika on ihan täysin | 481 # Fölin datassa on jotain tosi kummaa. Ilmeisesti ajovuoron viimeisen pysähdyksen saapumisaika on ihan täysin |
| 456 # väärin. Arvaan että se on seuraavan lähdön aika, mutta joka tapauksessa se on väärin. | 482 # väärin. Arvaan että se on seuraavan lähdön aika, mutta joka tapauksessa se on väärin. |
| 457 # Arvataan mikä se todellinen saapumisaika on. Se ei voi mennä kauhean paljon pahemmin vikaan kuin alkuperäinen | 483 # Arvataan mikä se todellinen saapumisaika on. Se ei voi mennä kauhean paljon pahemmin vikaan kuin alkuperäinen |
| 458 # väärin oleva data. | 484 # väärin oleva data. |
| 459 for trip in all_trips.values(): | 485 for trip in all_trips.values(): |
| 460 bus_speed_coefficient = 750 # metriä minuutissa | 486 if len(trip.schedule) >= 2: |
| 461 last_leg_distance = trip.schedule[-1].traveled_distance - trip.schedule[-2].traveled_distance | 487 bus_speed_coefficient = 750 # metriä minuutissa |
| 462 trip.schedule[-1].arrival_time = trip.schedule[-2].departure_time + timedelta(minutes = last_leg_distance / bus_speed_coefficient) | 488 last_leg_distance = trip.schedule[-1].traveled_distance - trip.schedule[-2].traveled_distance |
| 489 trip.schedule[-1].arrival_time = trip.schedule[-2].departure_time + timedelta(minutes = last_leg_distance / bus_speed_coefficient) | |
| 490 | |
| 491 global trips_by_vehicle_info | |
| 492 trips_by_vehicle_info = {} | |
| 493 for trip in all_trips.values(): | |
| 494 trips_by_vehicle_info[(trip.block_id, trip.schedule[0].arrival_time)] = trip | |
| 463 | 495 |
| 464 if __name__ == '__main__': | 496 if __name__ == '__main__': |
| 465 from configparser import ConfigParser | |
| 466 profile = ConfigParser() | |
| 467 profile.read('profiles/föli.ini') | 497 profile.read('profiles/föli.ini') |
| 468 load_buses('gtfs.zip', profile) | 498 load_buses('gtfs.zip') |
