Branch 22.06 MNMG bug work and support for Undirected Graphs

python/cugraph/cugraph/dask/traversal/bfs.py

@@ -66,10 +66,10 @@ def bfs(input_graph,
 
     Parameters
     ----------
-    input_graph : directed cugraph.Graph
+    input_graph : cugraph.Graph
         cuGraph graph instance, should contain the connectivity information
         as dask cudf edge list dataframe(edge weights are not used for this
-        algorithm). Undirected Graph not currently supported.
+        algorithm).
 
     start : Integer
         Specify starting vertex for breadth-first search; this function

python/cugraph/cugraph/link_prediction/jaccard.py

@@ -12,7 +12,6 @@
 # limitations under the License.
 
 import cudf
-from cugraph.structure.graph_classes import Graph
 from cugraph.link_prediction import jaccard_wrapper
 from cugraph.utilities import (ensure_cugraph_obj_for_nx,
                                df_edge_score_to_dictionary,
@@ -108,9 +107,8 @@ def jaccard(input_graph, vertex_pair=None):
     >>> df = cugraph.jaccard(G)
 
     """
-    if type(input_graph) is not Graph:
-        raise TypeError("input graph must a Graph")
-
+    if input_graph.is_directed():
+        raise TypeError("Input must an undirected Graph.")
     if type(vertex_pair) == cudf.DataFrame:
         vertex_pair = renumber_vertex_pair(input_graph, vertex_pair)
     elif vertex_pair is not None:

python/cugraph/cugraph/structure/graph_implementation/simpleDistributedGraph.py

@@ -64,8 +64,6 @@ def __from_edgelist(
     ):
         if not isinstance(input_ddf, dask_cudf.DataFrame):
             raise TypeError("input should be a dask_cudf dataFrame")
-        if self.properties.directed is False:
-            raise TypeError("Undirected distributed graph not supported")
 
         s_col = source
         d_col = destination

python/cugraph/cugraph/tests/dask/test_mg_bfs.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2021, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -25,7 +25,6 @@
     is_single_gpu(), reason="skipping MG testing on Single GPU system"
 )
 def test_dask_bfs(dask_client):
-    gc.collect()
 
     input_data_path = (RAPIDS_DATASET_ROOT_DIR_PATH /
                        "netscience.csv").as_posix()
@@ -85,6 +84,70 @@ def modify_dataset(df):
     assert err == 0
 
 
+@pytest.mark.skipif(
+    is_single_gpu(), reason="skipping MG testing on Single GPU system"
+)
+def test_dask_bfs_undirected(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"],
+    )
+
+    def modify_dataset(df):
+        temp_df = cudf.DataFrame()
+        temp_df['src'] = df['src']+1000
+        temp_df['dst'] = df['dst']+1000
+        temp_df['value'] = df['value']
+        return cudf.concat([df, temp_df])
+
+    meta = ddf._meta
+    ddf = ddf.map_partitions(modify_dataset, meta=meta)
+
+    df = cudf.read_csv(
+        input_data_path,
+        delimiter=" ",
+        names=["src", "dst", "value"],
+        dtype=["int32", "int32", "float32"],
+    )
+
+    df = modify_dataset(df)
+
+    g = cugraph.Graph(directed=False)
+    g.from_cudf_edgelist(df, "src", "dst")
+
+    dg = cugraph.Graph(directed=False)
+    dg.from_dask_cudf_edgelist(ddf, "src", "dst")
+    expected_dist = cugraph.bfs(g, [0, 1000])
+    result_dist = dcg.bfs(dg, [0, 1000])
+    result_dist = result_dist.compute()
+
+    compare_dist = expected_dist.merge(
+        result_dist, on="vertex", suffixes=["_local", "_dask"]
+    )
+
+    err = 0
+
+    for i in range(len(compare_dist)):
+        if (
+            compare_dist["distance_local"].iloc[i]
+            != compare_dist["distance_dask"].iloc[i]
+        ):
+            err = err + 1
+    assert err == 0
+    assert not dg.is_directed()
+
+
 @pytest.mark.skipif(
     is_single_gpu(), reason="skipping MG testing on Single GPU system"
 )

python/cugraph/cugraph/tests/test_jaccard.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2021, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -155,6 +155,25 @@ def test_jaccard(read_csv, gpubenchmark):
     assert err == 0
 
 
+def test_directed_graph_check(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(directed=True)
+    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]
+    with pytest.raises(TypeError):
+        df_res = cugraph.jaccard(G1, vertex_pair)
+        print(df_res)
+
+
 def test_nx_jaccard_time(read_csv, gpubenchmark):
 
     M, _ = read_csv