def test_sorensen_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"])
vertex_pair = cu_M[["src_0", "src_1", "dst_0", "dst_1"]]
vertex_pair = vertex_pair[:5]
df_res = cugraph.sorensen(G1, vertex_pair)
G2 = cugraph.Graph()
G2.from_cudf_edgelist(cu_M, source="src_0",
destination="dst_0")
df_exp = cugraph.sorensen(G2, 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["sorensen_coeff"], expected["sorensen_coeff"])
def test_renumber_files_col(graph_file):
gc.collect()
M = utils.read_csv_for_nx(graph_file)
sources = cudf.Series(M["0"])
destinations = cudf.Series(M["1"])
translate = 1000
gdf = cudf.DataFrame()
gdf["src"] = cudf.Series([x + translate for x in sources.values_host])
gdf["dst"] = cudf.Series([x + translate for x in destinations.values_host])
exp_src = cudf.Series([x + translate for x in sources.values_host])
exp_dst = cudf.Series([x + translate for x in destinations.values_host])
renumbered_df, renumber_map = NumberMap.renumber(
gdf, ["src"], ["dst"], preserve_order=True
)
unrenumbered_df = renumber_map.unrenumber(
renumbered_df, renumber_map.renumbered_src_col_name,
preserve_order=True
)
unrenumbered_df = renumber_map.unrenumber(
unrenumbered_df, renumber_map.renumbered_dst_col_name,
preserve_order=True
)
assert_series_equal(exp_src,
unrenumbered_df[renumber_map.renumbered_src_col_name],
check_names=False)
assert_series_equal(exp_dst,
unrenumbered_df[renumber_map.renumbered_dst_col_name],
check_names=False)
def test_series_different_type_cases(dtype, check_exact, check_dtype):
data = [0, 1, 2, 3]
psr1 = pd.Series(data, dtype="uint8")
psr2 = pd.Series(data, dtype=dtype)
sr1 = cudf.from_pandas(psr1)
sr2 = cudf.from_pandas(psr2)
kind = None
try:
pd.testing.assert_series_equal(psr1,
psr2,
check_exact=check_exact,
check_dtype=check_dtype)
except BaseException as e:
kind = type(e)
if kind is not None:
with pytest.raises(kind):
assert_series_equal(sr1,
sr2,
check_exact=check_exact,
check_dtype=check_dtype)
else:
assert_series_equal(sr1,
sr2,
check_exact=check_exact,
check_dtype=check_dtype)
def test_renumber_ips_cols():
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()
renumbered_gdf, renumber_map = NumberMap.renumber(
gdf, ["source_as_int"], ["dest_as_int"], preserve_order=True
)
input_check = renumbered_gdf.merge(gdf, on=["source_list", "dest_list"])
output_check = renumber_map.from_internal_vertex_id(
renumbered_gdf, renumber_map.renumbered_src_col_name,
external_column_names=["check_src"]
)
output_check = renumber_map.from_internal_vertex_id(
output_check, renumber_map.renumbered_dst_col_name,
external_column_names=["check_dst"]
)
merged = output_check.merge(input_check, on=["source_list", "dest_list"])
assert_series_equal(
merged["check_src"], merged["source_as_int"], check_names=False
)
assert_series_equal(
merged["check_dst"], merged["dest_as_int"], check_names=False
)
def test_replicate_cudf_series(input_data_path, dask_client):
gc.collect()
df = cudf.read_csv(
input_data_path,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
for column in df.columns.values:
series = df[column]
worker_to_futures = replication.replicate_cudf_series(series)
for worker in worker_to_futures:
replicated_series = worker_to_futures[worker].result()
assert_series_equal(series, replicated_series, check_names=False)
# FIXME: If we do not clear this dictionary, when comparing
# results for the 2nd column, one of the workers still
# has a value from the 1st column
worker_to_futures = {}
def test_basic_assert_series_equal(
rdata,
rname,
check_names,
check_category_order,
check_categorical,
dtype,
):
p_left = pd.Series([1, 2, 3], name="a", dtype=dtype)
p_right = pd.Series(rdata, name=rname, dtype=dtype)
left = cudf.from_pandas(p_left)
right = cudf.from_pandas(p_right)
kind = None
try:
pd.testing.assert_series_equal(
p_left,
p_right,
check_names=check_names,
check_categorical=check_categorical,
check_category_order=check_category_order,
)
except BaseException as e:
kind = type(e)
if kind is not None:
with pytest.raises(kind):
assert_series_equal(
left,
right,
check_names=check_names,
check_categorical=check_categorical,
check_category_order=check_category_order,
)
else:
assert_series_equal(
left,
right,
check_names=check_names,
check_categorical=check_categorical,
check_category_order=check_category_order,
)
def test_dask_mg_degree(dask_client):
gc.collect()
input_data_path = (RAPIDS_DATASET_ROOT_DIR_PATH /
"karate-asymmetric.csv").as_posix()
print(f"dataset={input_data_path}")
chunksize = cugraph.dask.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"],
)
dg = cugraph.DiGraph()
dg.from_dask_cudf_edgelist(ddf, "src", "dst")
g = cugraph.DiGraph()
g.from_cudf_edgelist(df, "src", "dst")
merge_df_in = (dg.in_degree().merge(g.in_degree(),
on="vertex",
suffixes=["_dg", "_g"]).compute())
merge_df_out = (dg.out_degree().merge(g.out_degree(),
on="vertex",
suffixes=["_dg", "_g"]).compute())
assert_series_equal(merge_df_in["degree_dg"],
merge_df_in["degree_g"],
check_names=False)
assert_series_equal(merge_df_out["degree_dg"],
merge_df_out["degree_g"],
check_names=False)
def test_random_walks_coalesced(graph_file, directed):
max_depth = random.randint(2, 10)
df_G = utils.read_csv_file(graph_file)
df_G.rename(columns={"0": "src", "1": "dst", "2": "weight"}, inplace=True)
path_data, seeds = calc_random_walks(graph_file,
directed,
max_depth=max_depth)
check_random_walks(path_data, seeds, df_G)
# Check path query output
df = cugraph.rw_path(len(seeds), path_data[2])
v_offsets = [0] + path_data[2].cumsum()[:-1].to_numpy().tolist()
w_offsets = [0] + (path_data[2] - 1).cumsum()[:-1].to_numpy().tolist()
assert_series_equal(df['weight_sizes'],
path_data[2] - 1,
check_names=False)
assert df['vertex_offsets'].to_numpy().tolist() == v_offsets
assert df['weight_offsets'].to_numpy().tolist() == w_offsets
def test_mg_renumber(graph_file, dask_client):
M = utils.read_csv_for_nx(graph_file)
sources = cudf.Series(M["0"])
destinations = cudf.Series(M["1"])
translate = 1000
gdf = cudf.DataFrame()
gdf["src_old"] = sources
gdf["dst_old"] = destinations
gdf["src"] = sources + translate
gdf["dst"] = destinations + translate
ddf = dask.dataframe.from_pandas(
gdf, npartitions=len(dask_client.scheduler_info()['workers']))
# preserve_order is not supported for MG
renumbered_df, renumber_map = NumberMap.renumber(ddf, ["src", "src_old"],
["dst", "dst_old"],
preserve_order=False)
unrenumbered_df = renumber_map.unrenumber(
renumbered_df,
renumber_map.renumbered_src_col_name,
preserve_order=False)
unrenumbered_df = renumber_map.unrenumber(
unrenumbered_df,
renumber_map.renumbered_dst_col_name,
preserve_order=False)
# sort needed only for comparisons, since preserve_order is False
gdf = gdf.sort_values(by=["src", "src_old", "dst", "dst_old"])
gdf = gdf.reset_index()
unrenumbered_df = unrenumbered_df.compute()
src = renumber_map.renumbered_src_col_name
dst = renumber_map.renumbered_dst_col_name
unrenumbered_df = unrenumbered_df.sort_values(
by=[f"0_{src}", f"1_{src}", f"0_{dst}", f"1_{dst}"])
unrenumbered_df = unrenumbered_df.reset_index()
assert_series_equal(gdf["src"],
unrenumbered_df[f"0_{src}"],
check_names=False)
assert_series_equal(gdf["src_old"],
unrenumbered_df[f"1_{src}"],
check_names=False)
assert_series_equal(gdf["dst"],
unrenumbered_df[f"0_{dst}"],
check_names=False)
assert_series_equal(gdf["dst_old"],
unrenumbered_df[f"1_{dst}"],
check_names=False)
def test_datetime_like_compaibility(rdata, check_datetimelike_compat):
psr1 = pd.Series([0, 1, 2, 3], dtype="datetime64[ns]")
psr2 = pd.Series(rdata, dtype="datetime64[ns]").astype("str")
sr1 = cudf.from_pandas(psr1)
sr2 = cudf.from_pandas(psr2)
kind = None
try:
pd.testing.assert_series_equal(
psr1, psr2, check_datetimelike_compat=check_datetimelike_compat)
except BaseException as e:
kind = type(e)
if kind is not None:
with pytest.raises(kind):
assert_series_equal(
sr1, sr2, check_datetimelike_compat=check_datetimelike_compat)
else:
assert_series_equal(
sr1, sr2, check_datetimelike_compat=check_datetimelike_compat)
def test_enable_batch_adjlist_replication_weights(graph_file, directed,
dask_client):
gc.collect()
df = cudf.read_csv(
graph_file,
delimiter=" ",
names=["src", "dst", "value"],
dtype=["int32", "int32", "float32"],
)
G = cugraph.DiGraph() if directed else cugraph.Graph()
G.from_cudf_edgelist(df,
source="src",
destination="dst",
edge_attr="value")
G.enable_batch()
G.view_adj_list()
adjlist = G.adjlist
offsets = adjlist.offsets
indices = adjlist.indices
weights = adjlist.weights
for worker in G.batch_adjlists:
(rep_offsets, rep_indices, rep_weights) = G.batch_adjlists[worker]
assert_series_equal(offsets, rep_offsets.result(), check_names=False)
assert_series_equal(indices, rep_indices.result(), check_names=False)
assert_series_equal(weights, rep_weights.result(), check_names=False)
def test_woverlap_multi_column(graph_file):
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.overlap_w(G1, weights, vertex_pair)
weights = weights[['vertex', 'weight']]
df_exp = cugraph.overlap_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["overlap_coeff"], expected["overlap_coeff"])
def test_renumber_negative_col():
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"]])
gdf["original_src"] = gdf["source_list"]
gdf["original_dst"] = gdf["dest_list"]
renumbered_gdf, renumber_map = NumberMap.renumber(
gdf, ["source_list"], ["dest_list"], preserve_order=True
)
input_check = renumbered_gdf.merge(
gdf, on=["original_src", "original_dst"]
)
output_check = renumber_map.from_internal_vertex_id(
renumbered_gdf, renumber_map.renumbered_src_col_name,
external_column_names=["check_src"]
)
output_check = renumber_map.from_internal_vertex_id(
output_check, renumber_map.renumbered_dst_col_name,
external_column_names=["check_dst"]
)
merged = output_check.merge(
input_check, on=["original_src", "original_dst"]
)
assert_series_equal(
merged["check_src"], merged["original_src"], check_names=False
)
assert_series_equal(
merged["check_dst"], merged["original_dst"], check_names=False
)
def test_renumber_files_multi_col(graph_file):
gc.collect()
M = utils.read_csv_for_nx(graph_file)
sources = cudf.Series(M["0"])
destinations = cudf.Series(M["1"])
translate = 1000
gdf = cudf.DataFrame()
gdf["src_old"] = sources
gdf["dst_old"] = destinations
gdf["src"] = sources + translate
gdf["dst"] = destinations + translate
renumbered_df, renumber_map = NumberMap.renumber(
gdf, ["src", "src_old"], ["dst", "dst_old"], preserve_order=True
)
unrenumbered_df = renumber_map.unrenumber(
renumbered_df, renumber_map.renumbered_src_col_name,
preserve_order=True
)
unrenumbered_df = renumber_map.unrenumber(
unrenumbered_df, renumber_map.renumbered_dst_col_name,
preserve_order=True
)
src = renumber_map.renumbered_src_col_name
dst = renumber_map.renumbered_dst_col_name
assert_series_equal(
gdf["src"], unrenumbered_df[f"0_{src}"], check_names=False
)
assert_series_equal(
gdf["src_old"], unrenumbered_df[f"1_{src}"], check_names=False
)
assert_series_equal(
gdf["dst"], unrenumbered_df[f"0_{dst}"], check_names=False
)
assert_series_equal(
gdf["dst_old"], unrenumbered_df[f"1_{dst}"], check_names=False
)
