def test_renumber_ips():
source_list = ['192.168.1.1',
'172.217.5.238',
'216.228.121.209',
'192.16.31.23']
dest_list = ['172.217.5.238',
'216.228.121.209',
'192.16.31.23',
'192.168.1.1']
pdf = pd.DataFrame({
'source_list': source_list,
'dest_list': dest_list
})
gdf = cudf.from_pandas(pdf)
gdf['source_as_int'] = gdf['source_list'].str.ip2int()
gdf['dest_as_int'] = gdf['dest_list'].str.ip2int()
src, dst, numbering = cugraph.renumber(gdf['source_as_int'],
gdf['dest_as_int'])
for i in range(len(gdf)):
assert numbering[src[i]] == gdf['source_as_int'][i]
assert numbering[dst[i]] == gdf['dest_as_int'][i]
def test_renumber_files(managed, pool, graph_file):
gc.collect()
rmm.reinitialize(
managed_memory=managed,
pool_allocator=pool,
initial_pool_size=2 << 27
)
assert(rmm.is_initialized())
M = utils.read_csv_for_nx(graph_file)
sources = cudf.Series(M['0'])
destinations = cudf.Series(M['1'])
translate = 1000
source_translated = cudf.Series([x + translate for x in sources])
dest_translated = cudf.Series([x + translate for x in destinations])
src, dst, numbering = cugraph.renumber(source_translated, dest_translated)
for i in range(len(sources)):
assert sources[i] == (numbering[src[i]] - translate)
assert destinations[i] == (numbering[dst[i]] - translate)
def test_renumber_negative():
source_list = [4, 6, 8, -20, 1]
dest_list = [1, 29, 35, 0, 77]
df = pd.DataFrame({
'source_list': source_list,
'dest_list': dest_list,
})
gdf = cudf.DataFrame.from_pandas(df[['source_list', 'dest_list']])
src, dst, numbering = cugraph.renumber(gdf['source_list'],
gdf['dest_list'])
for i in range(len(source_list)):
assert source_list[i] == numbering[src[i]]
assert dest_list[i] == numbering[dst[i]]
def test_renumber_files(graph_file):
gc.collect()
M = utils.read_csv_for_nx(graph_file)
sources = cudf.Series(M['0'])
destinations = cudf.Series(M['1'])
translate = 1000
source_translated = cudf.Series([x + translate for x in sources])
dest_translated = cudf.Series([x + translate for x in destinations])
src, dst, numbering = cugraph.renumber(source_translated, dest_translated)
for i in range(len(sources)):
assert sources[i] == (numbering[src[i]] - translate)
assert destinations[i] == (numbering[dst[i]] - translate)
def load_cugraph(lang,
year,
usecols=[0, 2],
dtype=["int32", "str", "int32", "str"]):
import cugraph
import cudf
G = cugraph.DiGraph()
file_name = generate_file_name(lang, year)
gdf = cudf.read_csv(file_name, usecols=usecols, dtype=dtype, sep="\t")
sources = cudf.Series(gdf["page_id_from"])
destinations = cudf.Series(gdf["page_id_to"])
source_col, dest_col, renumbering_map = cugraph.renumber(
sources, destinations)
edge_df = cudf.DataFrame()
edge_df.add_column("src", source_col)
edge_df.add_column("dst", dest_col)
G.from_cudf_edgelist(edge_df, source="src", target="dst")
return G, renumbering_map
def test_renumber_files(managed, pool, graph_file):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
M = utils.read_mtx_file(graph_file)
sources = cudf.Series(M.row)
destinations = cudf.Series(M.col)
translate = 1000
source_translated = cudf.Series([x + translate for x in sources])
dest_translated = cudf.Series([x + translate for x in destinations])
src, dst, numbering = cugraph.renumber(source_translated, dest_translated)
for i in range(len(sources)):
assert sources[i] == (numbering[src[i]] - translate)
assert destinations[i] == (numbering[dst[i]] - translate)
