def parse_od_settings(path_travel_mode: str, path_routing_mode: str,
routing_conf: RoutingConf, orig_lat, orig_lon, dest_lat,
dest_lon, aqi_updater: Union[GraphAqiUpdater,
None]) -> OdSettings:
try:
travel_mode = TravelMode(path_travel_mode)
except Exception:
raise RoutingException(ErrorKey.INVALID_TRAVEL_MODE_PARAM.value)
if path_routing_mode == 'short':
# retain support for legacy path variable 'short'
routing_mode = RoutingMode.FAST
else:
try:
routing_mode = RoutingMode(path_routing_mode)
except Exception:
raise RoutingException(ErrorKey.INVALID_ROUTING_MODE_PARAM.value)
if travel_mode == TravelMode.BIKE and not conf.cycling_enabled:
raise RoutingException(ErrorKey.BIKE_ROUTING_NOT_AVAILABLE.value)
if travel_mode == TravelMode.WALK and not conf.walking_enabled:
raise RoutingException(ErrorKey.WALK_ROUTING_NOT_AVAILABLE.value)
if routing_mode == RoutingMode.GREEN and not conf.gvi_paths_enabled:
raise RoutingException(ErrorKey.GREEN_PATH_ROUTING_NOT_AVAILABLE.value)
if routing_mode == RoutingMode.QUIET and not conf.quiet_paths_enabled:
raise RoutingException(ErrorKey.QUIET_PATH_ROUTING_NOT_AVAILABLE.value)
if routing_mode == RoutingMode.CLEAN:
if not conf.clean_paths_enabled:
raise RoutingException(
ErrorKey.CLEAN_PATH_ROUTING_NOT_AVAILABLE.value)
if not aqi_updater or not aqi_updater.get_aqi_update_status_response(
)['aqi_data_updated']:
raise RoutingException(ErrorKey.NO_REAL_TIME_AQI_AVAILABLE.value)
if travel_mode == TravelMode.WALK and routing_mode == RoutingMode.SAFE:
raise RoutingException(
ErrorKey.SAFE_PATHS_ONLY_AVAILABLE_FOR_BIKE.value)
orig_latLon = {'lat': float(orig_lat), 'lon': float(orig_lon)}
dest_latLon = {'lat': float(dest_lat), 'lon': float(dest_lon)}
orig_point = geom_utils.project_geom(
geom_utils.get_point_from_lat_lon(orig_latLon))
dest_point = geom_utils.project_geom(
geom_utils.get_point_from_lat_lon(dest_latLon))
sens = routing_conf.sensitivities_by_routing_mode[routing_mode]
return OdSettings(orig_point, dest_point, travel_mode, routing_mode, sens)
def get_nodata_zones(wfs_hsy_url: str, layer: str, hma_mask: str,
export_gpkg: str):
"""1) Downloads polygon layer of municipalities of Helsinki Metropolitan Area, 2)
Creates buffered polygons from the boundary lines of these polygons,
3) Exports the boundary-buffers to geopackage.
"""
mask_poly: Polygon = geom_utils.project_geom(
gpd.read_file(hma_mask)['geometry'][0]).buffer(500)
municipalities = get_wfs_feature(wfs_hsy_url, layer)
municipalities.to_file(export_gpkg,
layer='hma_municipalities',
driver='GPKG')
boundaries = []
for municipality in municipalities.itertuples():
for poly in municipality.geometry.geoms:
poly = municipality.geometry
boundaries.append(poly.boundary.buffer(22))
dissolved_buffer: Polygon = unary_union(boundaries)
intersected_buffer = dissolved_buffer.intersection(mask_poly)
boundary_gdf = gpd.GeoDataFrame(data=[{
'nodata_zone': 1
}],
geometry=[intersected_buffer],
crs=CRS.from_epsg(3879))
boundary_gdf.to_file(export_gpkg,
layer='municipal_boundaries',
driver='GPKG')
def test_path_set_1_fastest_path_geom(path_set_1):
_, path_fc = path_set_1
s_path = [feat for feat in path_fc['features'] if feat['properties']['type'] == 'fast'][0]
geom = s_path['geometry']
line = LineString(geom['coordinates'])
proj_line = project_geom(line)
assert round(proj_line.length, 2) == 1340.0
def test_data_for_linking_edges_has_right_values(
new_nearest_node: OdNodeData,
new_linking_edge_data: List[dict],
):
assert len(new_linking_edge_data) == 2
link_edge = new_linking_edge_data[0]
assert len(new_nearest_node.link_to_edge_spec.edge) == 28
edge = new_nearest_node.link_to_edge_spec.edge
link_edge_len_ratio = link_edge[E.length.value] / edge[E.length.value]
assert round(link_edge_len_ratio, 2) == 0.1
assert link_edge[E.length.value] == round(
link_edge[E.geometry.value].length, 2)
assert round(
geom_utils.project_geom(link_edge[E.geom_wgs.value]).length,
2) == link_edge[E.length.value]
assert link_edge[E.length.value] == round(
link_edge_len_ratio * edge[E.length.value], 2)
assert link_edge[E.bike_time_cost.value] == round(
link_edge_len_ratio * edge[E.bike_time_cost.value], 2)
assert link_edge[E.bike_safety_cost.value] == round(
link_edge_len_ratio * edge[E.bike_safety_cost.value], 2)
link_edge_total_noise_exp = sum(link_edge[E.noises.value].values())
assert round(link_edge_total_noise_exp, 2) == link_edge[E.length.value]
for key in new_nearest_node.link_to_edge_spec.edge.keys():
if key.startswith('c_') and not key.startswith('c_aq'):
assert round(link_edge[key]) == round(link_edge_len_ratio *
edge[key])
def test_path_set_1_clean_path_geom(path_set_1):
_, path_fc = path_set_1
c_path = [feat for feat in path_fc['features'] if feat['properties']['id'] == path_id][0]
geom = c_path['geometry']
line = LineString(geom['coordinates'])
proj_line = project_geom(line)
assert round(proj_line.length, 2) == 1372.8
def edge_attrs_near_point(lat, lon):
point = geom_utils.project_geom(
geom_utils.get_point_from_lat_lon({
'lat': float(lat),
'lon': float(lon)
}))
edge = G.find_nearest_edge(point)
return jsonify(
G.format_edge_dict_for_debugging(edge.attrs) if edge else None)
def test_func(geometry: dict):
assert geometry['type'] == 'LineString'
coords = geometry['coordinates']
assert isinstance(coords, list)
line = LineString(coords)
assert isinstance(line, LineString)
assert line.is_valid
# test that the length is a positive number
proj_line = project_geom(line)
assert isinstance(proj_line.length, (float, int))
assert proj_line.length >= 0.1
def test_noise_graph_update(self):
in_graph_file = 'data/test_graph.graphml'
out_graph_file = 'temp/test_graph_noises.graphml'
data_extent_file = 'data/HMA.geojson'
noise_csv_dir = 'noise_csv/'
data_extent: Polygon = geom_utils.project_geom(
gpd.read_file(data_extent_file)['geometry'][0])
graph = ig_utils.read_graphml(in_graph_file, log)
noise_graph_update.set_default_and_na_edge_noises(
graph, data_extent, log)
noise_graph_update.noise_graph_update(graph, noise_csv_dir, log)
ig_utils.export_to_graphml(graph, out_graph_file)
graph = ig_utils.read_graphml(out_graph_file)
self.assertEqual(graph.ecount(), 3702)
for edge in graph.es:
attrs = edge.attributes()
# check that edge IDs are correct
self.assertEqual(edge.index, attrs[E.id_ig.value])
if isinstance(attrs[E.geometry.value], LineString):
# note: this will fail if some of the edges are outside the noise data extent
self.assertNotEqual(edge[E.noises.value], None)
self.assertIsInstance(edge[E.noises.value], dict)
self.assertNotEqual(edge[E.noise_source.value], None)
self.assertIsInstance(edge[E.noise_source.value], str)
else:
# for edges without geometry the noise attributes should be nodata
self.assertEqual(edge[E.noises.value], None)
self.assertEqual(edge[E.noise_source.value], None)
# if edge noises are nodata then also noise source must be nodata
if edge[E.noises.value] == None:
self.assertEqual(edge[E.noise_source.value], None)
# if edge noises are not nodata but {} then noise source must also be just '' (not nodata)
if edge[E.noises.value] == {}:
self.assertEqual(edge[E.noise_source.value], '')
# if edge has noises it must also have noise source
if edge[E.noises.value]:
self.assertNotEqual(edge[E.noise_source.value], '')
self.assertNotEqual(edge[E.noise_source.value], None)
# if edge has noise source it must have also noises
if edge[E.noise_source.value]:
self.assertNotEqual(edge[E.noises.value], '')
self.assertNotEqual(edge[E.noises.value], None)
def test_path_set_1_quiet_path_geom(path_set_1):
data = path_set_1
path_fc = data['path_FC']
q_path = [
feat for feat in path_fc['features']
if feat['properties']['id'] == path_id
][0]
geom = q_path['geometry']
line = LineString(geom['coordinates'])
proj_line = project_geom(line)
assert round(proj_line.length, 2) == 1475.14
def main(conf: GraphNoiseJoinConf):
data_extent: Polygon = geom_utils.project_geom(
gpd.read_file(conf.noise_data_extent_fp)['geometry'][0])
graph = ig_utils.read_graphml(conf.graph_in_fp, log)
set_default_and_na_edge_noises(graph, data_extent)
noise_graph_update(graph, conf.noise_data_csv_dir)
ig_utils.export_to_graphml(graph, conf.graph_out_fp)
log.info(f'exported graph of {graph.ecount()} edges')
log.info('all done')
def test_updates_noises_from_csv_to_graph():
in_graph_file = f'{base_dir}/data/test_graph.graphml'
out_graph_file = f'{base_dir}/temp/test_graph_noises.graphml'
data_extent_file = f'{base_dir}/data/HMA.geojson'
noise_csv_dir = f'{base_dir}/noise_csv/'
data_extent: Polygon = geom_utils.project_geom(gpd.read_file(data_extent_file)['geometry'][0])
graph = ig_utils.read_graphml(in_graph_file)
noise_graph_update.set_default_and_na_edge_noises(graph, data_extent)
noise_graph_update.noise_graph_update(graph, noise_csv_dir)
ig_utils.export_to_graphml(graph, out_graph_file)
graph = ig_utils.read_graphml(out_graph_file)
assert graph.ecount() == 3702
for edge in graph.es:
attrs = edge.attributes()
# check that edge IDs are correct
assert edge.index == attrs[E.id_ig.value]
if isinstance(attrs[E.geometry.value], LineString):
# note: this will fail if some of the edges are outside the noise data extent
assert edge[E.noises.value] is not None
assert isinstance(edge[E.noises.value], dict)
assert edge[E.noise_source.value] is not None
assert isinstance(edge[E.noise_source.value], str)
else:
# for edges without geometry the noise attributes should be nodata
assert edge[E.noises.value] is None
assert edge[E.noise_source.value] is None
# if edge noises are nodata then also noise source must be nodata
if edge[E.noises.value] is None:
assert edge[E.noise_source.value] is None
# if edge noises are not nodata but {} then noise source must also be just '' (not nodata)
if edge[E.noises.value] == {}:
assert edge[E.noise_source.value] == ''
# if edge has noises it must also have noise source
if edge[E.noises.value]:
assert edge[E.noise_source.value] != ''
assert edge[E.noise_source.value] is not None
# if edge has noise source it must have also noises
if edge[E.noise_source.value]:
assert edge[E.noises.value] != ''
assert edge[E.noises.value] is not None
def test_routes_quiet_paths_on_same_street(quiet_paths_on_one_street,
test_line_geometry,
test_fast_path_prop_types,
test_edge_props):
"""Tests that if origin and destination are on the same street, the resultsets are still as expected."""
edge_fc, path_fc = quiet_paths_on_one_street
# edges
assert len(edge_fc['features']) == 1
test_line_geometry(edge_fc['features'][0]['geometry'])
test_edge_props(edge_fc['features'][0]['properties'])
# paths
assert len(path_fc['features']) == 1
test_line_geometry(path_fc['features'][0]['geometry'])
test_fast_path_prop_types(path_fc['features'][0]['properties'])
# geom length
coords = path_fc['features'][0]['geometry']['coordinates']
line = LineString(coords)
line_proj = project_geom(line)
assert round(line_proj.length, 2) == 82.73
def get_link_edge_data(new_node_id: int, link_to_edge_spec: LinkToEdgeSpec,
create_inbound_links: bool,
create_outbound_links: bool) -> Tuple[dict]:
"""
Returns complete edge attribute dictionaries for new linking edges.
Args:
new_node_id: An identifier of the new node.
split_point: A point geometry of the new node (on an existing edge).
edge: All attributes of the edge on which the new node was created.
create_inbound_links: A boolean variable indicating whether links should be inbound.
create_outbound_links: A boolean variable indicating whether links should be outbound.
"""
e_node_from = link_to_edge_spec.edge[E.uv.value][0]
e_node_to = link_to_edge_spec.edge[E.uv.value][1]
# create geometry objects for the links
link1, link2 = geom_utils.split_line_at_point(
link_to_edge_spec.edge[E.geometry.value], link_to_edge_spec.snap_point)
link1_wgs, link2_wgs = tuple(
geom_utils.project_geom(
link, geom_epsg=gp_conf.proj_crs_epsg, to_epsg=4326)
for link in (link1, link2))
link1_rev, link1_wgs_rev, link2_rev, link2_wgs_rev = (LineString(
link.coords[::-1]) for link in (link1, link1_wgs, link2, link2_wgs))
outbound_links = tuple(
__project_link_edge_attrs(u, v, geom, geom_wgs, link_to_edge_spec.edge)
for u, v, geom, geom_wgs in (
(new_node_id, e_node_from, link1_rev, link1_wgs_rev),
(new_node_id, e_node_to, link2, link2_wgs),
)) if create_outbound_links else ()
inbound_links = tuple(
__project_link_edge_attrs(u, v, geom, geom_wgs, link_to_edge_spec.edge)
for u, v, geom, geom_wgs in (
(e_node_from, new_node_id, link1,
link1_wgs), (e_node_to, new_node_id, link2_rev,
link2_wgs_rev))) if create_inbound_links else ()
return outbound_links + inbound_links
def get_noise_data(
hel_wfs_download: bool = False,
process_hel: bool = False,
process_espoo: bool = False,
process_syke: bool = False,
mask_poly_file: str = None,
noise_layer_info_csv: str = None,
noise_data_hel_gpkg: str = None,
processed_data_gpkg: str = None,
wfs_hki_url: str = None,
) -> None:
if None in [noise_data_hel_gpkg, processed_data_gpkg]:
raise ValueError(
'Arguments noise_data_hel_gpkg and processed_data_gpkg must be specified'
)
try:
noise_layer_info = pd.read_csv(noise_layer_info_csv).to_dict('records')
except Exception:
log.error('Missing or invalid argument noise_layer_info_csv')
log.error(traceback.format_exc())
if os.path.exists(processed_data_gpkg):
log.info(
f'Removing previously processed data in {processed_data_gpkg}')
try:
os.remove(processed_data_gpkg)
except Exception:
log.error('Error in removing data')
mask_poly = geom_utils.project_geom(
gpd.read_file(mask_poly_file)['geometry'][0]).buffer(500)
if hel_wfs_download:
log.info('Starting to download noise data from Helsinki (WFS)')
log.info(f'Initializing WFS connection to {wfs_hki_url}')
wfs_hki = WebFeatureService(url=wfs_hki_url)
log.info(
f'Initialized WFS connection with name: {wfs_hki.identification.title}'
f'and version: {wfs_hki.version}')
log.info(
f'Found available methods: {[operation.name for operation in wfs_hki.operations]}'
)
for layer in noise_layer_info:
if layer[L.source.name] == 'hel':
try:
log.info(
f'Downloading WFS layer from {wfs_hki.identification.title}: {layer["name"]}'
)
noise_features = get_wfs_feature(wfs_hki_url,
layer['name'])
noise_features.to_file(noise_data_hel_gpkg,
layer=layer['export_name'],
driver='GPKG')
log.info(
f'Exported features to file: {layer["export_name"]}')
except Exception:
log.error(traceback.format_exc())
log.info('Noise data from Helsinki downloaded (WFS)')
else:
log.info('Skipping noise data download from Helsinki WFS')
log.info('Starting to process noise data')
for layer in noise_layer_info:
read_data = False
if layer[L.source.name] == 'hel' and process_hel:
log.info(
f'Processing layer from {layer["source"]}: {layer["name"]}')
gdf = gpd.read_file(noise_data_hel_gpkg,
layer=layer['export_name'])
read_data = True
if layer[L.source.name] == 'espoo' and process_espoo:
log.info(
f'Processing layer from {layer["source"]}: {layer["name"]}')
gdf = gpd.read_file(layer['name'])
read_data = True
if layer[L.source.name] == 'syke' and process_syke:
log.info(
f'Processing layer from {layer["source"]}: {layer["name"]}')
gdf = gpd.read_file(layer['name'])
gdf = filter_out_features_outside_mask(
gdf,
geom_utils.project_geom(mask_poly,
geom_epsg=3879,
to_epsg=3047))
gdf = gdf.to_crs(epsg=3879)
# extract db low from strings like '55-60' and '>70'
gdf[layer['noise_attr']] = [
int(db[-2:]) if (len(db) == 3) else int(db[:2])
for db in gdf[layer['noise_attr']]
]
read_data = True
if read_data:
gdf = explode_multipolygons_to_polygons(gdf)
gdf = gdf.rename(columns={layer['noise_attr']: L.db_low.name})
gdf[['geometry',
L.db_low.name]].to_file(processed_data_gpkg,
layer=layer['export_name'],
driver='GPKG')
log.info('All data processed')
def new_nearest_node(graph_handler: GraphHandler) -> OdNodeData:
point = geom_utils.project_geom(Point(24.97086446863051,
60.21352729760156))
yield od_handler.get_nearest_node(graph_handler,
point,
avoid_node_creation=False)
log.info(
f'found {real_edge_count - len(edges_within)} edges of {real_edge_count} outside noise data extent'
)
# set noise attributes of edges within the data extent to default values (no noise)
for edge in edges_within.itertuples():
graph.es[getattr(edge, E.id_ig.name)][E.noises.value] = {}
graph.es[getattr(edge, E.id_ig.name)][E.noise_source.value] = ''
if (__name__ == '__main__'):
log = Logger(printing=True,
log_file='noise_graph_update.log',
level='debug')
in_graph_file = 'data/hma.graphml'
out_graph_file = 'out_graph/hma.graphml'
data_extent_file = 'data/HMA.geojson'
noise_csv_dir = 'out_csv/'
data_extent: Polygon = geom_utils.project_geom(
gpd.read_file(data_extent_file)['geometry'][0])
graph = ig_utils.read_graphml(in_graph_file, log)
set_default_and_na_edge_noises(graph, data_extent, log)
noise_graph_update(graph, noise_csv_dir, log)
ig_utils.export_to_graphml(graph, out_graph_file)
log.info(f'exported graph of {graph.ecount()} edges')
log.info('all done')
def convert_otp_graph_to_igraph(
node_csv_file: str,
edge_csv_file: str,
hma_poly_file: str,
igraph_out_file: str,
b_export_otp_data_to_gpkg: bool = False,
b_export_decomposed_igraphs_to_gpkg: bool = False,
b_export_final_graph_to_gpkg: bool = False,
debug_otp_graph_gpkg: str = 'debug/otp_graph_features.gpkg',
debug_igraph_gpkg: str = 'debug/otp2igraph_features.gpkg',
) -> ig.Graph:
hma_poly = geom_utils.project_geom(gpd.read_file(hma_poly_file)['geometry'][0])
# 1) read nodes nodes from CSV
n = pd.read_csv(node_csv_file, sep=';')
log.info(f'read {len(n.index)} nodes')
log.debug(f'node column types: {n.dtypes}')
log.debug(f'nodes head: {n.head()}')
log.info('creating node gdf')
n[Node.geometry.name] = [
shapely.wkt.loads(geom) if isinstance(geom, str) else Point() for geom in n[Node.geometry.name]
]
n[Node.geom_wgs.name] = n[Node.geometry.name]
n = gpd.GeoDataFrame(n, geometry=Node.geometry.name, crs=CRS.from_epsg(4326))
log.info('reprojecting nodes to etrs')
n = n.to_crs(epsg=gp_conf.proj_crs_epsg)
log.debug(f'nodes head: {n.head()}')
# 2) read edges from CSV
e = pd.read_csv(edge_csv_file, sep=';')
log.info(f'read {len(e.index)} edges')
log.debug(f'edge column types: {e.dtypes}')
log.debug(f'edges head: {e.head()}')
log.info('creating edge gdf')
e[Edge.geometry.name] = [
shapely.wkt.loads(geom) if isinstance(geom, str) else LineString() for geom in e[Edge.geometry.name]
]
e[Edge.geom_wgs.name] = e[Edge.geometry.name]
e = gpd.GeoDataFrame(e, geometry=Edge.geometry.name, crs=CRS.from_epsg(4326))
log.info('reprojecting edges to etrs')
e = e.to_crs(epsg=gp_conf.proj_crs_epsg)
log.debug(f'edges head: {e.head()}')
# 3) export graph data to gpkg
if b_export_otp_data_to_gpkg:
log.info('writing otp graph data to gpkg')
e.drop(columns=[Edge.geom_wgs.name]).to_file(debug_otp_graph_gpkg, layer='edges', driver='GPKG')
log.info(f'exported edges to {debug_otp_graph_gpkg} (layer=edges)')
n.drop(columns=[Edge.geom_wgs.name]).to_file(debug_otp_graph_gpkg, layer='nodes', driver='GPKG')
log.info(f'exported nodes to {debug_otp_graph_gpkg} (layer=nodes)')
# 4) filter out edges that are unsuitable for both walking and cycling
def filter_df_by_query(df: pd.DataFrame, query: str, name: str = 'rows'):
count_before = len(df.index)
df_filt = df.query(query).copy()
filt_ratio = (count_before-len(df_filt.index)) / count_before
log.info(f'filtered out {count_before-len(df_filt.index)} {name} ({round(filt_ratio * 100, 1)} %) by {query}')
return df_filt
e_filt = filter_df_by_query(e, f'{Edge.allows_walking.name} == True or {Edge.allows_biking.name} == True', name='edges')
e_filt = filter_df_by_query(e_filt, f'{Edge.is_no_thru_traffic.name} == False', name='edges')
# 5) create a dictionaries for converting otp ids to ig ids and vice versa
log.debug('create maps for converting otp ids to ig ids')
n[Node.id_ig.name] = np.arange(len(n.index))
ids_otp_ig = {}
ids_ig_otp = {}
for node in n.itertuples():
ids_otp_ig[getattr(node, Node.id_otp.name)] = getattr(node, Node.id_ig.name)
ids_ig_otp[getattr(node, Node.id_ig.name)] = getattr(node, Node.id_otp.name)
# 6) add nodes to graph
log.info('adding nodes to graph')
G = ig.Graph(directed=True)
G.add_vertices(len(n.index))
for attr in Node:
if attr.name in n.columns:
G.vs[attr.value] = list(n[attr.name])
else:
log.warning(f'node column {attr.name} not present in dataframe')
# 7) add edges to graph
log.info('adding edges to graph')
# get edge lengths by projected geometry
e_filt[Edge.length.name] = [
round(geom.length, 4) if isinstance(geom, LineString) else 0.0 for geom in e_filt[Edge.geometry.name]
]
def get_ig_uv(edge):
return (ids_otp_ig[edge['node_orig_id']], ids_otp_ig[edge['node_dest_id']])
e_filt['uv_ig'] = e_filt.apply(lambda row: get_ig_uv(row), axis=1)
e_filt[Edge.id_ig.name] = np.arange(len(e_filt.index))
G.add_edges(list(e_filt['uv_ig']))
for attr in Edge:
if attr.name in e_filt.columns:
G.es[attr.value] = list(e_filt[attr.name])
else:
log.warning(f'edge column {attr.name} not present in dataframe')
# 8) delete edges outside Helsinki Metropolitan Area (HMA)
hma_buffered = hma_poly.buffer(100)
def intersects_hma(geom: Union[LineString, None]):
if not geom or geom.is_empty:
return True
return geom.intersects(hma_buffered)
e_gdf = ig_utils.get_edge_gdf(G)
log.info('finding edges that intersect with HMA')
e_gdf['in_hma'] = [intersects_hma(line) for line in e_gdf[Edge.geometry.name]]
e_gdf_del = e_gdf.query('in_hma == False').copy()
out_ratio = round(100 * len(e_gdf_del.index)/len(e_gdf.index), 1)
log.info(f'found {len(e_gdf_del.index)} ({out_ratio} %) edges outside HMA')
log.info('deleting edges')
before_count = G.ecount()
G.delete_edges(e_gdf_del.index.tolist())
after_count = G.ecount()
log.info(f'deleted {before_count-after_count} edges')
# check if id_ig:s need to be updated to edge attributes
mismatch_count = len(
[edge.index for edge in G.es if edge.attributes()[Edge.id_ig.value] != edge.index]
)
log.info(f'invalid edge ids: {mismatch_count}')
# reassign igraph indexes to edge and node attributes
G.es[Edge.id_ig.value] = [e.index for e in G.es]
G.vs[Node.id_ig.value] = [v.index for v in G.vs]
# check if id_ig:s need to be updated to edge attributes
mismatch_count = len(
[edge.index for edge in G.es if edge.attributes()[Edge.id_ig.value] != edge.index]
)
log.info(f'invalid edge ids: {mismatch_count} (after re-indexing)')
# 9) find and inspect subgraphs by decomposing the graph
sub_graphs = G.decompose(mode='STRONG')
log.info(f'found {len(sub_graphs)} subgraphs')
graph_sizes = [graph.ecount() for graph in sub_graphs]
log.info(f'subgraphs with more than 10 edges: {len([s for s in graph_sizes if s > 10])}')
log.info(f'subgraphs with more than 50 edges: {len([s for s in graph_sizes if s > 50])}')
log.info(f'subgraphs with more than 100 edges: {len([s for s in graph_sizes if s > 100])}')
log.info(f'subgraphs with more than 500 edges: {len([s for s in graph_sizes if s > 500])}')
log.info(f'subgraphs with more than 10000 edges: {len([s for s in graph_sizes if s > 10000])}')
small_graphs = [graph for graph in sub_graphs if graph.ecount() <= 15]
medium_graphs = [graph for graph in sub_graphs if (graph.ecount() > 15 and graph.ecount() <= 500)]
big_graphs = [graph for graph in sub_graphs if graph.ecount() > 500]
small_graph_edges = []
for graph_id, graph in enumerate(small_graphs):
edges = ig_utils.get_edge_dicts(graph, attrs=[Edge.id_otp, Edge.id_ig, Edge.geometry])
for edge in edges:
edge['graph_id'] = graph_id
small_graph_edges.extend(edges)
medium_graph_edges = []
for graph_id, graph in enumerate(medium_graphs):
edges = ig_utils.get_edge_dicts(graph, attrs=[Edge.id_otp, Edge.id_ig, Edge.geometry])
for edge in edges:
edge['graph_id'] = graph_id
medium_graph_edges.extend(edges)
big_graph_edges = []
for graph_id, graph in enumerate(big_graphs):
edges = ig_utils.get_edge_dicts(graph, attrs=[Edge.id_otp, Edge.id_ig, Edge.geometry])
for edge in edges:
edge['graph_id'] = graph_id
big_graph_edges.extend(edges)
if b_export_decomposed_igraphs_to_gpkg:
log.info('exporting subgraphs to gpkg')
# graphs with <= 15 edges
small_graph_edges_gdf = gpd.GeoDataFrame(small_graph_edges, crs=CRS.from_epsg(gp_conf.proj_crs_epsg))
small_graph_edges_gdf.to_file(debug_igraph_gpkg, layer='small_graph_edges', driver='GPKG')
# graphs with 15–500 edges
medium_graph_edges_gdf = gpd.GeoDataFrame(medium_graph_edges, crs=CRS.from_epsg(gp_conf.proj_crs_epsg))
medium_graph_edges_gdf.to_file(debug_igraph_gpkg, layer='medium_graph_edges', driver='GPKG')
# graphs with > 500 edges
big_graph_edges_gdf = gpd.GeoDataFrame(big_graph_edges, crs=CRS.from_epsg(gp_conf.proj_crs_epsg))
big_graph_edges_gdf.to_file(debug_igraph_gpkg, layer='big_graph_edges', driver='GPKG')
log.info('graphs exported')
# 10) delete smallest subgraphs from the graph
del_edge_ids = [edge[Edge.id_ig.name] for edge in small_graph_edges]
log.info(f'deleting {len(del_edge_ids)} isolated edges')
before_count = G.ecount()
G.delete_edges(del_edge_ids)
after_count = G.ecount()
del_ratio = round(100 * (before_count-after_count) / before_count, 1)
log.info(f'deleted {before_count-after_count} ({del_ratio} %) edges')
# 11) delete isolated nodes from the graph
del_node_ids = [v.index for v in G.vs.select(_degree_eq=0)]
log.info(f'deleting {len(del_node_ids)} isolated nodes')
before_count = G.vcount()
G.delete_vertices(del_node_ids)
after_count = G.vcount()
del_ratio = round(100 * (before_count-after_count) / before_count, 1)
log.info(f'deleted {before_count-after_count} ({del_ratio} %) nodes')
# check if id_ig:s need to be updated to edge attributes
mismatch_count = len([edge.index for edge in G.es if edge.attributes()[Edge.id_ig.value] != edge.index])
log.info(f'invalid edge ids: {mismatch_count}')
# reassign igraph indexes to edge and node attributes
G.es[Edge.id_ig.value] = [e.index for e in G.es]
G.vs[Node.id_ig.value] = [v.index for v in G.vs]
# check if id_ig:s need to be updated to edge attributes
mismatch_count = len([edge.index for edge in G.es if edge.attributes()[Edge.id_ig.value] != edge.index])
log.info(f'invalid edge ids: {mismatch_count} (after re-indexing)')
# 12) export graph data to GeoDataFrames fro debugging
if b_export_final_graph_to_gpkg:
log.info(f'exporting final graph to {debug_igraph_gpkg} for debugging')
e_gdf = ig_utils.get_edge_gdf(G, attrs=[Edge.id_otp, Edge.id_ig], ig_attrs=['source', 'target'])
n_gdf = ig_utils.get_node_gdf(G, ig_attrs=['index'])
e_gdf.to_file(debug_igraph_gpkg, layer='final_graph_edges', driver='GPKG')
n_gdf.to_file(debug_igraph_gpkg, layer='final_graph_nodes', driver='GPKG')
if igraph_out_file:
ig_utils.export_to_graphml(G, igraph_out_file)
return G
