def test_wjaccard_multi_column(graph_file):
gc.collect()
M = utils.read_csv_for_nx(graph_file)
cu_M = cudf.DataFrame()
cu_M["src_0"] = cudf.Series(M["0"])
cu_M["dst_0"] = cudf.Series(M["1"])
cu_M["src_1"] = cu_M["src_0"] + 1000
cu_M["dst_1"] = cu_M["dst_0"] + 1000
G1 = cugraph.Graph()
G1.from_cudf_edgelist(cu_M,
source=["src_0", "src_1"],
destination=["dst_0", "dst_1"])
G2 = cugraph.Graph()
G2.from_cudf_edgelist(cu_M, source="src_0", destination="dst_0")
vertex_pair = cu_M[["src_0", "src_1", "dst_0", "dst_1"]]
vertex_pair = vertex_pair[:5]
weight_arr = cudf.Series(np.ones(G2.number_of_vertices(),
dtype=np.float32))
weights = cudf.DataFrame()
weights['vertex'] = G2.nodes()
weights['vertex_'] = weights['vertex'] + 1000
weights['weight'] = weight_arr
df_res = cugraph.jaccard_w(G1, weights, vertex_pair)
weights = weights[['vertex', 'weight']]
df_exp = cugraph.jaccard_w(G2, weights, vertex_pair[["src_0", "dst_0"]])
# Calculating mismatch
assert df_res["jaccard_coeff"].equals(df_exp["jaccard_coeff"])
def test_wjaccard_multi_column(read_csv):
M, _ = read_csv
cu_M = cudf.DataFrame()
cu_M["src_0"] = cudf.Series(M["0"])
cu_M["dst_0"] = cudf.Series(M["1"])
cu_M["src_1"] = cu_M["src_0"] + 1000
cu_M["dst_1"] = cu_M["dst_0"] + 1000
G1 = cugraph.Graph()
G1.from_cudf_edgelist(cu_M,
source=["src_0", "src_1"],
destination=["dst_0", "dst_1"])
G2 = cugraph.Graph()
G2.from_cudf_edgelist(cu_M, source="src_0", destination="dst_0")
vertex_pair = cu_M[["src_0", "src_1", "dst_0", "dst_1"]]
vertex_pair = vertex_pair[:5]
weight_arr = cudf.Series(np.ones(G2.number_of_vertices(),
dtype=np.float32))
weights = cudf.DataFrame()
weights['vertex'] = G2.nodes()
weights['vertex_'] = weights['vertex'] + 1000
weights['weight'] = weight_arr
df_res = cugraph.jaccard_w(G1, weights, vertex_pair)
weights = weights[['vertex', 'weight']]
df_exp = cugraph.jaccard_w(G2, weights, vertex_pair[["src_0", "dst_0"]])
# Calculating mismatch
actual = df_res.sort_values("0_source").reset_index()
expected = df_exp.sort_values("source").reset_index()
assert_series_equal(actual["jaccard_coeff"], expected["jaccard_coeff"])
def cugraph_call(cu_M):
# Device data
weights_arr = cudf.Series(
np.ones(max(cu_M['0'].max(), cu_M['1'].max()) + 1, dtype=np.float32))
G = cugraph.Graph()
G.from_cudf_edgelist(cu_M, source='0', destination='1')
# cugraph Jaccard Call
t1 = time.time()
df = cugraph.jaccard_w(G, weights_arr)
t2 = time.time() - t1
print('Time : ' + str(t2))
print(df)
return df['jaccard_coeff']
def cugraph_call(cu_M):
# Device data
weights_arr = cudf.Series(
np.ones(max(cu_M["0"].max(), cu_M["1"].max()) + 1, dtype=np.float32))
G = cugraph.Graph()
G.from_cudf_edgelist(cu_M, source="0", destination="1")
# cugraph Jaccard Call
t1 = time.time()
df = cugraph.jaccard_w(G, weights_arr)
t2 = time.time() - t1
print("Time : " + str(t2))
df = df.sort_values(["source", "destination"]).reset_index(drop=True)
return df["jaccard_coeff"]
def cugraph_call(cu_M):
# Device data
sources = cu_M['0']
destinations = cu_M['1']
# values = cudf.Series(np.ones(len(col_indices), dtype=np.float32),
# nan_as_null=False)
weights_arr = cudf.Series(np.ones(max(sources.max(),
destinations.max())+1, dtype=np.float32))
G = cugraph.Graph()
G.add_edge_list(sources, destinations, None)
# cugraph Jaccard Call
t1 = time.time()
df = cugraph.jaccard_w(G, weights_arr)
t2 = time.time() - t1
print('Time : '+str(t2))
return df['jaccard_coeff']
