def cugraph_weak_call(cu_M):
G = cugraph.DiGraph()
G.from_cudf_edgelist(cu_M, source="0", destination="1")
t1 = time.time()
df = cugraph.weakly_connected_components(G)
t2 = time.time() - t1
print("Time : " + str(t2))
label_vertex_dict = defaultdict(list)
for i in range(len(df)):
label_vertex_dict[df["labels"][i]].append(df["vertices"][i])
return label_vertex_dict
def cugraph_weak_call(cu_M):
# cugraph Pagerank Call
G = cugraph.DiGraph()
G.from_cudf_edgelist(cu_M, source='0', destination='1')
t1 = time.time()
df = cugraph.weakly_connected_components(G)
t2 = time.time() - t1
print('Time : '+str(t2))
result = df['labels'].to_array()
labels = sorted(result)
return labels
def cugraph_weak_call(cu_M):
# cugraph Pagerank Call
G = cugraph.DiGraph()
G.from_cudf_edgelist(cu_M, source='0', destination='1')
t1 = time.time()
df = cugraph.weakly_connected_components(G)
t2 = time.time() - t1
print('Time : ' + str(t2))
label_vertex_dict = defaultdict(list)
for i in range(len(df)):
label_vertex_dict[df['labels'][i]].append(df['vertices'][i])
return label_vertex_dict
def cugraph_weak_call(cu_M):
# Device data
sources = cu_M['0']
destinations = cu_M['1']
# cugraph Pagerank Call
G = cugraph.Graph()
G.add_edge_list(sources, destinations, None)
t1 = time.time()
df = cugraph.weakly_connected_components(G)
t2 = time.time() - t1
print('Time : ' + str(t2))
result = df['labels'].to_array()
labels = sorted(result)
return labels
def test_weak_cc_nx(graph_file):
gc.collect()
M = utils.read_csv_for_nx(graph_file)
Gnx = nx.from_pandas_edgelist(
M, source="0", target="1", create_using=nx.DiGraph()
)
nx_wcc = nx.weakly_connected_components(Gnx)
nx_result = sorted(nx_wcc)
cu_wcc = cugraph.weakly_connected_components(Gnx)
pdf = pd.DataFrame.from_dict(cu_wcc, orient='index').reset_index()
pdf.columns = ["vertex", "labels"]
cu_result = pdf["labels"].nunique()
assert len(nx_result) == cu_result
def test_dask_wcc(client_connection):
gc.collect()
# FIXME: update this to allow dataset to be parameterized and have dataset
# part of test param id (see other tests)
input_data_path = r"../datasets/netscience.csv"
print(f"dataset={input_data_path}")
chunksize = dcg.get_chunksize(input_data_path)
ddf = dask_cudf.read_csv(
input_data_path,
chunksize=chunksize,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
df = cudf.read_csv(
input_data_path,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
g = cugraph.DiGraph()
g.from_cudf_edgelist(df, "src", "dst", renumber=True)
dg = cugraph.DiGraph()
dg.from_dask_cudf_edgelist(ddf, "src", "dst")
expected_dist = cugraph.weakly_connected_components(g)
result_dist = dcg.weakly_connected_components(dg)
result_dist = result_dist.compute()
compare_dist = expected_dist.merge(result_dist,
on="vertex",
suffixes=["_local", "_dask"])
unique_local_labels = compare_dist['labels_local'].unique()
for label in unique_local_labels.values.tolist():
dask_labels_df = compare_dist[compare_dist['labels_local'] == label]
dask_labels = dask_labels_df['labels_dask']
assert (dask_labels.iloc[0] == dask_labels).all()
def test_dask_wcc(dask_client):
gc.collect()
input_data_path = (RAPIDS_DATASET_ROOT_DIR_PATH /
"netscience.csv").as_posix()
print(f"dataset={input_data_path}")
chunksize = dcg.get_chunksize(input_data_path)
ddf = dask_cudf.read_csv(
input_data_path,
chunksize=chunksize,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
df = cudf.read_csv(
input_data_path,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
g = cugraph.DiGraph()
g.from_cudf_edgelist(df, "src", "dst", renumber=True)
dg = cugraph.DiGraph()
dg.from_dask_cudf_edgelist(ddf, "src", "dst")
expected_dist = cugraph.weakly_connected_components(g)
result_dist = dcg.weakly_connected_components(dg)
result_dist = result_dist.compute()
compare_dist = expected_dist.merge(result_dist,
on="vertex",
suffixes=["_local", "_dask"])
unique_local_labels = compare_dist['labels_local'].unique()
for label in unique_local_labels.values.tolist():
dask_labels_df = compare_dist[compare_dist['labels_local'] == label]
dask_labels = dask_labels_df['labels_dask']
assert (dask_labels.iloc[0] == dask_labels).all()
def wcc(G):
return cugraph.weakly_connected_components(G)
def connected_components(graph: CuGraph) -> CuDFNodeMap:
series = cugraph.weakly_connected_components(
graph.value).set_index("vertices")["labels"]
return CuDFNodeMap(series)