def read(feed_path: str) -> TransitNetwork:
"""
Read GTFS feed from folder and TransitNetwork object
Args:
feed_path: where to read transit network files from
Returns: a TransitNetwork object.
"""
config = default_config()
feed = ptg.load_feed(feed_path, config=config)
WranglerLogger.info("Read in transit feed from: {}".format(feed_path))
updated_config = TransitNetwork.validate_feed(feed, config)
# Read in each feed so we can write over them
editable_feed = DotDict()
for node in updated_config.nodes.keys():
# Load (initiate Partridge's lazy load)
editable_feed[node.replace(".txt", "")] = feed.get(node)
transit_network = TransitNetwork(feed=editable_feed,
config=updated_config)
transit_network.feed_path = feed_path
return transit_network
def __init__(self, path, config=None, view=None, encoding=None):
self.path = path
self.is_dir = os.path.isdir(self.path)
self.config = default_config() if config is None else config
self.view = {} if view is None else view
self.zmap = {}
self.encoding = encoding
print(encoding)
assert os.path.isfile(self.path) or self.is_dir, \
'File or path not found: {}'.format(self.path)
assert nx.is_directed_acyclic_graph(self.config), \
'Config must be a DAG'
roots = {n for n, d in self.config.out_degree() if d == 0}
for filename, param in self.view.items():
assert filename in roots, \
'Filter param given for a non-root node ' \
'of the config graph: {} {}'.format(filename, param)
if self.is_dir:
self._verify_folder_contents()
else:
self._verify_zip_contents()
def test_bad_edge_config():
config = default_config()
# Remove the `dependencies` key from an edge config
config.edges["stop_times.txt", "trips.txt"].pop("dependencies")
feed = Feed(fixture("caltrain-2017-07-24"), config=config)
with pytest.raises(ValueError, message="Edge missing `dependencies` attribute"):
feed.stop_times
def read_feed(feed_path: str = None) -> Tuple[nx.DiGraph, Feed]:
"""
Read GTFS feed from folder and return a config and Partridge Feed object
"""
config = geo_config()
config.nodes["shapes.txt"]["required_columns"] = config.nodes[
"shapes.txt"]["required_columns"] + ("A", "B", "LINK_ID")
try:
feed = ptg.load_feed(feed_path, config=config)
TransitNetwork.validate_feed(feed, config)
except KeyError:
config = default_config()
config.nodes["shapes.txt"]["required_columns"] = (
"shape_id",
"A",
"B",
"LINK_ID",
)
WranglerLogger.warning(
"Reducing data requirements for shapes.txt to:",
config.nodes["shapes.txt"]["required_columns"],
)
feed = ptg.load_feed(feed_path, config=config)
TransitNetwork.validate_feed(feed, config)
## todo should be read in as a schema
WranglerLogger.info(
"Read %s agencies from %s" %
(feed.agency.size, os.path.join(feed_path, "agency.txt")))
WranglerLogger.info("Read %s frequencies from %s" %
(feed.frequencies.size,
os.path.join(feed_path, "frequencies.txt")))
WranglerLogger.info(
"Read %s routes from %s" %
(feed.routes.size, os.path.join(feed_path, "routes.txt")))
WranglerLogger.info(
"Read %s shapes from %s" %
(feed.shapes.size, os.path.join(feed_path, "shapes.txt")))
WranglerLogger.info(
"Read %s stops from %s" %
(feed.stops.size, os.path.join(feed_path, "stops.txt")))
WranglerLogger.info(
"Read %s transfers from %s" %
(feed.transfers.size, os.path.join(feed_path, "transfers.txt")))
WranglerLogger.info(
"Read %s trips from %s" %
(feed.trips.size, os.path.join(feed_path, "transfers.txt")))
return config, feed
def get_filtered_feed(path, filters, config=None):
'''
Multi-file feed filtering
'''
filter_config = default_config() if config is None else config.copy()
filter_config = remove_node_attributes(filter_config, 'converters')
trip_ids = set(raw_feed(path).trips.trip_id)
for filename, column_filters in filters.items():
feed = mkfeed(path,
config=reroot_graph(filter_config, filename),
view={filename: column_filters})
trip_ids &= set(feed.trips.trip_id)
return mkfeed(path, config, {'trips.txt': {'trip_id': trip_ids}})
def read(feed_path: str, fast: bool = False) -> TransitNetwork:
"""
Read GTFS feed from folder and TransitNetwork object
"""
config = default_config()
feed = ptg.load_feed(feed_path, config=config)
WranglerLogger.info("Read in transit feed from: {}".format(feed_path))
updated_config = TransitNetwork.validate_feed(feed, config)
# Read in each feed so we can write over them
new_feed = DotDict()
for node in updated_config.nodes.keys():
# Load (initiate Partridge's lazy load)
new_feed[node.replace(".txt", "")] = feed.get(node)
transit_network = TransitNetwork(feed=new_feed, config=updated_config)
transit_network.feed_path = feed_path
return transit_network