def test_filter_unreachable(graph_file, source):
gc.collect()
cu_M = utils.read_csv_file(graph_file)
print("sources size = " + str(len(cu_M)))
print("destinations size = " + str(len(cu_M)))
# cugraph Pagerank Call
G = cugraph.DiGraph()
G.from_cudf_edgelist(cu_M, source="0", destination="1", edge_attr="2")
print("cugraph Solving... ")
t1 = time.time()
df = cugraph.sssp(G, source)
t2 = time.time() - t1
print("Time : " + str(t2))
reachable_df = cugraph.filter_unreachable(df)
if np.issubdtype(df["distance"].dtype, np.integer):
inf = np.iinfo(reachable_df["distance"].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
elif np.issubdtype(df["distance"].dtype, np.inexact):
inf = np.finfo(reachable_df["distance"].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
assert len(reachable_df) != 0
def get_shortest_dists(self, poi: namedtuple) -> None:
"""
Use `cugraph.sssp` to calculate shortest paths from POI to postcodes
First subsets road graph, then finds shortest paths, ensuring all paths are
routed that are known to be important to each POI. Saves to `hdf` to allow
restarts.
Parameters
----------
poi : namedtuple
Single POI created from `df.itertuples()`
"""
if self.buffer:
self.graph = self.create_sub_graph(poi=poi)
shortest_paths: cudf.DataFrame = cugraph.filter_unreachable(
cugraph.sssp(self.graph, source=poi.node_id))
pc_dist = shortest_paths[shortest_paths.vertex.isin(self.postcode_ids)]
self.idx += 1
pc_dist["idx"] = self.idx
if self.log_file.exists():
self.distances = cudf.read_csv(self.log_file).append(pc_dist)
else:
self.distances = pc_dist[["vertex", "distance", "idx"]]
self.distances = (self.distances.sort_values(
"distance").drop_duplicates("vertex").reset_index()[[
"vertex", "distance", "idx"
]])
self.distances.to_csv(self.log_file, index=False)
def test_filter_unreachable(managed, pool, graph_file, source):
gc.collect()
rmm.finalize()
rmm_config.use_managed_memory = managed
rmm_config.use_pool_allocator = pool
rmm_config.initial_pool_size = 2 << 27
rmm.initialize()
assert(rmm.is_initialized())
cu_M = utils.read_csv_file(graph_file)
# Device data
sources = cu_M['0']
destinations = cu_M['1']
print('sources size = ' + str(len(sources)))
print('destinations size = ' + str(len(destinations)))
# cugraph Pagerank Call
G = cugraph.Graph()
G.add_edge_list(sources, destinations)
print('cugraph Solving... ')
t1 = time.time()
df = cugraph.sssp(G, source)
t2 = time.time() - t1
print('Time : '+str(t2))
reachable_df = cugraph.filter_unreachable(df)
if(np.issubdtype(df['distance'].dtype, np.integer)):
inf = np.iinfo(reachable_df['distance'].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
elif(np.issubdtype(df['distance'].dtype, np.inexact)):
inf = np.finfo(reachable_df['distance'].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
assert len(reachable_df) != 0
def test_filter_unreachable(managed, pool, graph_file, source):
gc.collect()
rmm.reinitialize(
managed_memory=managed,
pool_allocator=pool,
initial_pool_size=2 << 27
)
assert(rmm.is_initialized())
cu_M = utils.read_csv_file(graph_file)
print('sources size = ' + str(len(cu_M)))
print('destinations size = ' + str(len(cu_M)))
# cugraph Pagerank Call
G = cugraph.DiGraph()
G.from_cudf_edgelist(cu_M, source='0', destination='1', edge_attr='2')
print('cugraph Solving... ')
t1 = time.time()
df = cugraph.sssp(G, source)
t2 = time.time() - t1
print('Time : '+str(t2))
reachable_df = cugraph.filter_unreachable(df)
if(np.issubdtype(df['distance'].dtype, np.integer)):
inf = np.iinfo(reachable_df['distance'].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
elif(np.issubdtype(df['distance'].dtype, np.inexact)):
inf = np.finfo(reachable_df['distance'].dtype).max # noqa: F841
assert len(reachable_df.query("distance == @inf")) == 0
assert len(reachable_df) != 0