def test_add_edge_list_to_adj_list(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())
cu_M = read_csv_file(graph_file + '.csv')
sources = cu_M['0']
destinations = cu_M['1']
M = read_mtx_file(graph_file + '.mtx').tocsr()
if M is None:
raise TypeError('Could not read the input graph')
if M.shape[0] != M.shape[1]:
raise TypeError('Shape is not square')
offsets_exp = M.indptr
indices_exp = M.indices
# cugraph add_egde_list to_adj_list call
G = cugraph.Graph()
G.add_edge_list(sources, destinations, None)
offsets_cu, indices_cu = G.view_adj_list()
assert compare_offsets(offsets_cu, offsets_exp)
assert compare_series(indices_cu, indices_exp)
def test_jaccard_edgevals(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 = read_mtx_file(graph_file)
cu_M = read_csv_file(graph_file + '.csv')
cu_src, cu_dst, cu_coeff = cugraph_call(cu_M, edgevals=True)
nx_src, nx_dst, nx_coeff = networkx_call(M)
# Calculating mismatch
err = 0
tol = 1.0e-06
assert len(cu_coeff) == len(nx_coeff)
for i in range(len(cu_coeff)):
if (abs(cu_coeff[i] - nx_coeff[i]) > tol * 1.1
and cu_src[i] == nx_src[i] and cu_dst[i] == nx_dst[i]):
err += 1
print("Mismatches: %d" % err)
assert err == 0
def test_jaccard_two_hop_edge_vals(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 = read_mtx_file(graph_file)
M = M.tocsr()
Gnx = nx.DiGraph(M).to_undirected()
G = cugraph.Graph()
row_offsets = cudf.Series(M.indptr)
col_indices = cudf.Series(M.indices)
values = cudf.Series(M.data)
G.add_adj_list(row_offsets, col_indices, values)
pairs = G.get_two_hop_neighbors()
nx_pairs = []
for i in range(len(pairs)):
nx_pairs.append((pairs['first'][i], pairs['second'][i]))
preds = nx.jaccard_coefficient(Gnx, nx_pairs)
nx_coeff = []
for u, v, p in preds:
nx_coeff.append(p)
df = cugraph.jaccard(G, pairs['first'], pairs['second'])
assert len(nx_coeff) == len(df)
for i in range(len(df)):
diff = abs(nx_coeff[i] - df['jaccard_coeff'][i])
assert diff < 1.0e-6
def test_pagerank(managed, pool, graph_file, max_iter, tol, alpha,
personalization_perc, has_guess):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
M = read_mtx_file(graph_file + '.mtx')
networkx_pr, networkx_prsn = networkx_call(M, max_iter, tol, alpha,
personalization_perc)
cu_nstart = None
if has_guess == 1:
cu_nstart = cudify(networkx_pr)
max_iter = 5
cu_prsn = cudify(networkx_prsn)
cu_M = read_csv_file(graph_file + '.csv')
cugraph_pr = cugraph_call(cu_M, max_iter, tol, alpha, cu_prsn, cu_nstart)
# Calculating mismatch
networkx_pr = sorted(networkx_pr.items(), key=lambda x: x[0])
err = 0
assert len(cugraph_pr) == len(networkx_pr)
for i in range(len(cugraph_pr)):
if (abs(cugraph_pr[i][1] - networkx_pr[i][1]) > tol * 1.1
and cugraph_pr[i][0] == networkx_pr[i][0]):
err = err + 1
print("Mismatches:", err)
assert err < (0.01 * len(cugraph_pr))
def test_overlap(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 + '.mtx')
M = M.tocsr()
cu_M = utils.read_csv_file(graph_file + '.csv')
row_offsets = cudf.Series(M.indptr)
col_indices = cudf.Series(M.indices)
G = cugraph.Graph()
G.add_adj_list(row_offsets, col_indices, None)
pairs = G.get_two_hop_neighbors()
cu_coeff = cugraph_call(cu_M, pairs['first'], pairs['second'])
cpu_coeff = cpu_call(M, pairs['first'], pairs['second'])
assert len(cu_coeff) == len(cpu_coeff)
for i in range(len(cu_coeff)):
diff = abs(cpu_coeff[i] - cu_coeff[i])
assert diff < 1.0e-6
def test_louvain_with_edgevals(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+'.mtx')
cu_M = utils.read_csv_file(graph_file+'.csv')
cu_parts, cu_mod = cugraph_call(cu_M, edgevals=True)
nx_parts = networkx_call(M)
# Calculating modularity scores for comparison
Gnx = nx.Graph(M)
cu_map = {0: 0}
for i in range(len(cu_parts)):
cu_map[cu_parts['vertex'][i]] = cu_parts['partition'][i]
assert set(nx_parts.keys()) == set(cu_map.keys())
cu_mod_nx = community.modularity(cu_map, Gnx)
nx_mod = community.modularity(nx_parts, Gnx)
assert len(cu_parts) == len(nx_parts)
assert cu_mod > (.82 * nx_mod)
print(cu_mod)
print(cu_mod_nx)
print(nx_mod)
assert abs(cu_mod - cu_mod_nx) < .0001
def test_sssp(managed, pool, graph_file, source):
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 + '.mtx')
cu_M = utils.read_csv_file(graph_file + '.csv')
cu_paths = cugraph_call(cu_M, source)
nx_paths, Gnx = networkx_call(M, source)
# Calculating mismatch
err = 0
for vid in cu_paths:
# Validate vertices that are reachable
# NOTE : If distance type is float64 then cu_paths[vid][0]
# should be compared against np.finfo(np.float64).max)
if (cu_paths[vid][0] != np.finfo(np.float32).max):
if (cu_paths[vid][0] != nx_paths[vid]):
err = err + 1
# check pred dist + 1 = current dist (since unweighted)
pred = cu_paths[vid][1]
if (vid != source and cu_paths[pred][0] + 1 != cu_paths[vid][0]):
err = err + 1
else:
if (vid in nx_paths.keys()):
err = err + 1
assert err == 0
def test_sssp_edgevals(managed, pool, graph_file, source):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
M = read_mtx_file(graph_file + '.mtx')
cu_M = read_csv_file(graph_file + '.csv')
cu_paths = cugraph_call(cu_M, source, edgevals=True)
nx_paths, Gnx = networkx_call(M, source, edgevals=True)
# Calculating mismatch
err = 0
print(cu_paths)
print(nx_paths)
print(len(cu_paths))
for vid in cu_paths:
if (cu_paths[vid][0] != np.finfo(np.float32).max):
if (cu_paths[vid][0] != nx_paths[vid]):
err = err + 1
# check pred dist + edge_weight = current dist
if (vid != source):
pred = cu_paths[vid][1]
edge_weight = Gnx[pred][vid]['weight']
if (cu_paths[pred][0] + edge_weight != cu_paths[vid][0]):
err = err + 1
else:
if (vid in nx_paths.keys()):
err = err + 1
assert err == 0
def test_strong_cc(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 + '.mtx')
netx_labels = networkx_strong_call(M)
cu_M = utils.read_csv_file(graph_file + '.csv')
cugraph_labels = cugraph_strong_call(cu_M)
# NetX returns a list of components, each component being a
# collection (set{}) of vertex indices;
#
# while cugraph returns a component label for each vertex;
nx_n_components = len(netx_labels)
cg_n_components = get_n_uniqs(cugraph_labels)
assert nx_n_components == cg_n_components
lst_nx_components_lens = [len(c) for c in sorted(netx_labels, key=len)]
# get counts of uniques:
#
lst_cg_components_lens = sorted(get_uniq_counts(cugraph_labels))
assert lst_nx_components_lens == lst_cg_components_lens
def test_sssp(managed, pool, graph_file, source):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
M = read_mtx_file(graph_file + '.mtx')
cu_M = read_csv_file(graph_file + '.csv')
cu_paths = cugraph_call(cu_M, source)
nx_paths, Gnx = networkx_call(M, source)
# Calculating mismatch
err = 0
for vid in cu_paths:
if (cu_paths[vid][0] != np.finfo(np.float32).max):
if (cu_paths[vid][0] != nx_paths[vid]):
err = err + 1
# check pred dist + 1 = current dist (since unweighted)
pred = cu_paths[vid][1]
if (vid != source and cu_paths[pred][0] + 1 != cu_paths[vid][0]):
err = err + 1
else:
if (vid in nx_paths.keys()):
err = err + 1
assert err == 0
def test_modularity_clustering(managed, pool, graph_file, partitions):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
# Read in the graph and get a cugraph object
cu_M = read_csv_file(graph_file + '.csv')
sources = cu_M['0']
destinations = cu_M['1']
values = cu_M['2']
G = cugraph.Graph()
G.add_edge_list(sources, destinations, values)
# Get the modularity score for partitioning versus random assignment
cu_score = cugraph_call(G, partitions)
rand_score = random_call(G, partitions)
# Assert that the partitioning has better modularity than the random
# assignment
assert cu_score > rand_score
def test_rmm_modes(managed, pool):
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
array_tester(np.int32, 128)
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 = 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])
G = cugraph.Graph()
src, dst, numbering = G.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_add_adj_list_to_edge_list(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 = read_mtx_file(graph_file + '.mtx').tocsr()
if M is None:
raise TypeError('Could not read the input graph')
if M.shape[0] != M.shape[1]:
raise TypeError('Shape is not square')
offsets = cudf.Series(M.indptr)
indices = cudf.Series(M.indices)
M = M.tocoo()
sources_exp = cudf.Series(M.row)
destinations_exp = cudf.Series(M.col)
# cugraph add_adj_list to_edge_list call
G = cugraph.Graph()
G.add_adj_list(offsets, indices, None)
sources, destinations = G.view_edge_list()
sources_cu = np.array(sources)
destinations_cu = np.array(destinations)
assert compare_series(sources_cu, sources_exp)
assert compare_series(destinations_cu, destinations_exp)
def __init__(self):
self.data_gpu = None
self.back_up_dimension = None
self.dimensions_filters = {}
self.dimensions_filters_response_format = {}
self.group_by_backups = {}
rmm_cfg.use_pool_allocator = True # default is False
rmm.finalize()
rmm.initialize()
def test_rmm_modes(managed, pool):
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert(rmm.is_initialized())
array_tester(np.int32, 128)
def test_grmat_gen(managed, pool):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
vertices, edges, sources, destinations = cugraph.grmat_gen(
'grmat --rmat_scale=2 --rmat_edgefactor=2 --device=0 --normalized'
' --quiet')
def test_networkx_compatibility(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())
# test from_cudf_edgelist()
M = utils.read_mtx_file(graph_file)
df = pd.DataFrame()
df['source'] = pd.Series(M.row)
df['target'] = pd.Series(M.col)
df['weight'] = pd.Series(M.data)
gdf = cudf.from_pandas(df)
# cugraph.Graph() is implicitly a directed graph right at this moment, so
# we should use nx.DiGraph() for comparison.
Gnx = nx.from_pandas_edgelist(df,
source='source',
target='target',
edge_attr=['weight'],
create_using=nx.DiGraph)
G = cugraph.from_cudf_edgelist(gdf,
source='source',
target='target',
weight='weight')
assert compare_graphs(Gnx, G)
Gnx.clear()
G.clear()
# cugraph.Graph() is implicitly a directed graph right at this moment, so
# we should use nx.DiGraph() for comparison.
Gnx = nx.from_pandas_edgelist(df,
source='source',
target='target',
create_using=nx.DiGraph)
G = cugraph.from_cudf_edgelist(gdf, source='source', target='target')
assert compare_graphs(Gnx, G)
Gnx.clear()
G.clear()
def test_triangles_edge_vals(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 = read_mtx_file(graph_file)
cu_count = cugraph_call(M, edgevals=True)
nx_count = networkx_call(M)
assert cu_count == nx_count
def test_add_edge_or_adj_list_after_add_edge_or_adj_list(
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 = read_mtx_file(graph_file)
sources = cudf.Series(M.row)
destinations = cudf.Series(M.col)
M = M.tocsr()
if M is None:
raise TypeError('Could not read the input graph')
if M.shape[0] != M.shape[1]:
raise TypeError('Shape is not square')
offsets = cudf.Series(M.indptr)
indices = cudf.Series(M.indices)
G = cugraph.Graph()
# If cugraph has at least one graph representation, adding a new graph
# should fail to prevent a single graph object storing two different
# graphs.
# If cugraph has a graph edge list, adding a new graph should fail.
G.add_edge_list(sources, destinations, None)
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.add_edge_list(sources, destinations, None)
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.add_adj_list(offsets, indices, None)
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
G.delete_edge_list()
# If cugraph has a graph adjacency list, adding a new graph should fail.
G.add_adj_list(sources, destinations, None)
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.add_edge_list(sources, destinations, None)
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.add_adj_list(offsets, indices, None)
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
G.delete_adj_list()
def test_subgraph_extraction(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)
verts = np.zeros(3, dtype=np.int32)
verts[0] = 0
verts[1] = 1
verts[2] = 17
cu_sg = cugraph_call(M, verts)
nx_sg = nx_call(M, verts)
assert compare_edges(cu_sg, nx_sg, verts)
def test_wjaccard(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+'.mtx')
cu_M = utils.read_csv_file(graph_file+'.csv')
# suppress F841 (local variable is assigned but never used) in flake8
# no networkX equivalent to compare cu_coeff against...
cu_coeff = cugraph_call(cu_M) # noqa: F841
nx_coeff = networkx_call(M)
for i in range(len(cu_coeff)):
diff = abs(nx_coeff[i] - cu_coeff[i])
assert diff < 1.0e-6
def test_degree_functionality(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 = read_mtx_file(graph_file + '.mtx')
cu_M = read_csv_file(graph_file + '.csv')
sources = cu_M['0']
destinations = cu_M['1']
values = cu_M['2']
G = cugraph.Graph()
G.add_edge_list(sources, destinations, values)
Gnx = nx.DiGraph(M)
df_in_degree = G.in_degree()
df_out_degree = G.out_degree()
df_degree = G.degree()
nx_in_degree = Gnx.in_degree()
nx_out_degree = Gnx.out_degree()
nx_degree = Gnx.degree()
err_in_degree = 0
err_out_degree = 0
err_degree = 0
for i in range(len(df_degree)):
if (df_in_degree['degree'][i] != nx_in_degree[i]):
err_in_degree = err_in_degree + 1
if (df_out_degree['degree'][i] != nx_out_degree[i]):
err_out_degree = err_out_degree + 1
if (df_degree['degree'][i] != nx_degree[i]):
err_degree = err_degree + 1
assert err_in_degree == 0
assert err_out_degree == 0
assert err_degree == 0
def test_transpose_from_adj_list(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 = read_mtx_file(graph_file + '.mtx').tocsr()
offsets = cudf.Series(M.indptr)
indices = cudf.Series(M.indices)
G = cugraph.Graph()
G.add_adj_list(offsets, indices, None)
G.add_transposed_adj_list()
Mt = M.transpose().tocsr()
toff, tind = G.view_transposed_adj_list()
assert compare_series(tind, Mt.indices)
assert compare_offsets(toff, Mt.indptr)
def test_view_edge_list_from_adj_list(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 = read_mtx_file(graph_file + '.mtx').tocsr()
offsets = cudf.Series(M.indptr)
indices = cudf.Series(M.indices)
G = cugraph.Graph()
G.add_adj_list(offsets, indices, None)
src2, dst2 = G.view_edge_list()
M = M.tocoo()
src1 = M.row
dst1 = M.col
assert compare_series(src1, src2)
assert compare_series(dst1, dst2)
def test_modularity_clustering(managed, pool, graph_file, partitions):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
# Read in the graph and get a cugraph object
M = utils.read_mtx_file(graph_file + '.mtx').tocsr()
cu_M = utils.read_csv_file(graph_file + '.csv', read_weights_in_sp=False)
row_offsets = cudf.Series(M.indptr)
col_indices = cudf.Series(M.indices)
sources = cu_M['0']
destinations = cu_M['1']
G_adj = cugraph.Graph()
G_adj.add_adj_list(row_offsets, col_indices)
G_edge = cugraph.Graph()
G_edge.add_edge_list(sources, destinations)
# Get the modularity score for partitioning versus random assignment
cu_vid, cu_score = cugraph_call(G_adj, partitions)
rand_vid, rand_score = random_call(G_adj, partitions)
# Assert that the partitioning has better modularity than the random
# assignment
assert cu_score < rand_score
# Get the modularity score for partitioning versus random assignment
cu_vid, cu_score = cugraph_call(G_edge, partitions)
rand_vid, rand_score = random_call(G_edge, partitions)
# Assert that the partitioning has better modularity than the random
# assignment
assert cu_score < rand_score
def test_filter_unreachable(managed, pool, graph_file, source):
gc.collect()
rmm.finalize()
rmm_cfg.use_managed_memory = managed
rmm_cfg.use_pool_allocator = pool
rmm.initialize()
assert (rmm.is_initialized())
cu_M = utils.read_csv_file(graph_file + '.csv')
# 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_number_of_vertices(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())
cu_M = utils.read_csv_file(graph_file + '.csv')
sources = cu_M['0']
destinations = cu_M['1']
M = utils.read_mtx_file(graph_file + '.mtx')
if M is None:
raise TypeError('Could not read the input graph')
# cugraph add_edge_list
G = cugraph.Graph()
G.add_edge_list(sources, destinations, None)
assert (G.number_of_vertices() == M.shape[0])
def test_bfs(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 = read_mtx_file(graph_file + '.mtx')
cu_M = read_csv_file(graph_file + '.csv')
base_vid, base_dist = base_call(M, 0)
cugraph_vid, cugraph_dist = cugraph_call(cu_M, 0)
# Calculating mismatch
assert len(base_dist) == len(cugraph_dist)
for i in range(len(cugraph_dist)):
assert base_vid[i] == cugraph_vid[i]
assert base_dist[i] == cugraph_dist[i]
def test_two_hop_neighbors(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())
cu_M = read_csv_file(graph_file + '.csv')
sources = cu_M['0']
destinations = cu_M['1']
values = cu_M['2']
G = cugraph.Graph()
G.add_edge_list(sources, destinations, values)
df = G.get_two_hop_neighbors()
M = read_mtx_file(graph_file + '.mtx').tocsr()
find_two_paths(df, M)
check_all_two_hops(df, M)
def test_delete_edge_list_delete_adj_list(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 = read_mtx_file(graph_file + '.mtx')
sources = cudf.Series(M.row)
destinations = cudf.Series(M.col)
M = M.tocsr()
if M is None:
raise TypeError('Could not read the input graph')
if M.shape[0] != M.shape[1]:
raise TypeError('Shape is not square')
offsets = cudf.Series(M.indptr)
indices = cudf.Series(M.indices)
# cugraph delete_adj_list delete_edge_list call
G = cugraph.Graph()
G.add_edge_list(sources, destinations, None)
G.delete_edge_list()
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.view_adj_list()
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
G.add_adj_list(offsets, indices, None)
G.delete_adj_list()
with pytest.raises(cudf.bindings.GDFError.GDFError) as excinfo:
G.view_edge_list()
assert excinfo.value.errcode.decode() == 'GDF_INVALID_API_CALL'
def test_uninitialized():
rmm.finalize()
assert(not rmm.is_initialized())
rmm.initialize() # so further tests will pass