def get_representative_feed(file_loc: str,
day_type: str='busiest') -> ptg.gtfs.Feed:
"""
Given a filepath, extract a partridge feed object, holding a \
representative set of schedule patterns, extracted from the GTFS zip \
file, as a set of pandas DataFrames.
Parameters
----------
file_loc : str
The location (filepath) of the GTFS zip file.
day_type : str
The name of the type of representative feed desired. Currently, only \
one type is supported, busiest. This extracts the schedule pattern \
for a day that has the most service on it. This is determined by the \
day with the most trips on it.
Returns
-------
feed : ptg.gtfs.Feed
A partridge feed object, holding related schedule information as \
pandas DataFrames for the busiest day in the available schedule.
"""
# Extract service ids and then trip counts by those dates
try:
service_ids_by_date = ptg.read_service_ids_by_date(file_loc)
trip_counts_by_date = ptg.read_trip_counts_by_date(file_loc)
# Raised by partridge if no valid dates returned
except AssertionError:
# Make sure we have some valid values returned in trips
raise InvalidGTFS('No valid trip counts by date '
'were identified in GTFS.')
# TODO: Due to partridge's assertion error being raised, this
# check may no longer be needed.
if not len(trip_counts_by_date.items()):
# Otherwise, error out
raise InvalidGTFS('No valid trip counts by date '
'were identified in GTFS.')
# At this point, different methods can be implemented to help select how
# to pick which date/schedule id to use
if day_type == 'busiest':
# Choose the service id that has the most trips associated with it
(selected_date,
trip_count) = max(trip_counts_by_date.items(), key=lambda p: p[1])
else:
raise NotImplementedError('Unsupported day type string supplied.')
log('Selected_date: {}'.format(selected_date))
log('Number of trips on that date: {}'.format(trip_count))
all_service_ids = '\n\t'.join(service_ids_by_date[selected_date])
log('\nAll related service IDs: \n\t{}'.format(all_service_ids))
sub = service_ids_by_date[selected_date]
feed_query = {'trips.txt': {'service_id': sub}}
return ptg.load_feed(file_loc, view=feed_query)
def get_representative_feed(file_loc: str, day_type: str = 'busiest'):
# Extract service ids and then trip counts by those dates
service_ids_by_date = ptg.read_service_ids_by_date(file_loc)
trip_counts_by_date = ptg.read_trip_counts_by_date(file_loc)
# Make sure we have some valid values returned in trips
if not len(trip_counts_by_date.items()):
# Otherwise, error out
raise InvalidGTFS('No valid trip counts by date '
'were identified in GTFS.')
# At this point, different methods can be implemented to help select how
# to pick which date/schedule id to use
if day_type == 'busiest':
# Choose the service id that has the most trips associated with it
(selected_date, trip_count) = max(trip_counts_by_date.items(),
key=lambda p: p[1])
else:
raise NotImplementedError('Unsupported day type string supplied.')
log('Selected_date: {}'.format(selected_date))
log('Number of trips on that date: {}'.format(trip_count))
all_service_ids = '\n\t'.join(service_ids_by_date[selected_date])
log('\nAll related service IDs: \n\t{}'.format(all_service_ids))
sub = service_ids_by_date[selected_date]
feed_query = {'trips.txt': {'service_id': sub}}
return ptg.feed(file_loc, view=feed_query)
def test_trip_counts_by_date(path):
trip_counts_by_date = ptg.read_trip_counts_by_date(path)
assert trip_counts_by_date == {
datetime.date(2017, 8, 1): 442,
datetime.date(2017, 8, 2): 442,
datetime.date(2017, 8, 3): 442,
datetime.date(2017, 8, 4): 442,
datetime.date(2017, 8, 5): 1,
datetime.date(2017, 8, 7): 442,
}
def get_representative_feed(self,file_loc: str, the_date: str):
year, month, day = map(int, the_date.split("/"))
selected_date = date(year, month, day)
# Extract service ids and then trip counts by those dates
service_ids_by_date = ptg.read_service_ids_by_date(file_loc)
trip_counts_by_date = ptg.read_trip_counts_by_date(file_loc)
# Make sure we have some valid values returned in trips
if not len(trip_counts_by_date.items()):
# Otherwise, error out
raise InvalidGTFS('No valid trip counts by date '
'were identified in GTFS.')
sub = service_ids_by_date[selected_date]
feed_query = {'trips.txt': {'service_id': sub}}
feeds=ptg.load_feed(file_loc, view=feed_query)
return feeds