Adds logic to handle isolated vertices at python layer

python/cugraph/cugraph/community/louvain.py

@@ -12,6 +12,7 @@
 # limitations under the License.
 
 from cugraph.utilities import (
+    is_nx_graph_type,
     ensure_cugraph_obj_for_nx,
     df_score_to_dictionary,
 )
@@ -21,6 +22,9 @@
 from pylibcugraph import louvain as pylibcugraph_louvain
 from pylibcugraph import ResourceHandle
 
+VERTEX_COL_NAME = "vertex"
+CLUSTER_ID_COL_NAME = "partition"
+
 
 # FIXME: max_level should default to 100 once max_iter is removed
 def louvain(G, max_level=None, max_iter=None, resolution=1.0, threshold=1e-7):
@@ -72,9 +76,9 @@ def louvain(G, max_level=None, max_iter=None, resolution=1.0, threshold=1e-7):
         GPU data frame of size V containing two columns the vertex id and the
         partition id it is assigned to.
 
-        df['vertex'] : cudf.Series
+        result_df[VERTEX_COL_NAME] : cudf.Series
             Contains the vertex identifiers
-        df['partition'] : cudf.Series
+        result_df[CLUSTER_ID_COL_NAME] : cudf.Series
             Contains the partition assigned to the vertices
 
     modularity_score : float
@@ -89,6 +93,17 @@ def louvain(G, max_level=None, max_iter=None, resolution=1.0, threshold=1e-7):
 
     """
 
+    # FIXME: Onece the graph construction calls support isolated vertices through
+    #  the C API (the C++ interface already supports this) then there will be
+    # no need to compute isolated vertices here.
+
+    isolated_vertices = list()
+    if is_nx_graph_type(type(G)):
+        isolated_vertices = [v for v in range(G.number_of_nodes()) if G.degree[v] == 0]
+    else:
+        # FIXME: Gather isolated vertices of G
+        pass
+
     G, isNx = ensure_cugraph_obj_for_nx(G)
 
     if G.is_directed():
@@ -112,6 +127,9 @@ def louvain(G, max_level=None, max_iter=None, resolution=1.0, threshold=1e-7):
     if max_level is None:
         max_level = 100
 
+    if max_level > 1000:
+        max_level = 1000
+
     vertex, partition, mod_score = pylibcugraph_louvain(
         resource_handle=ResourceHandle(),
         graph=G._plc_graph,
@@ -121,14 +139,27 @@ def louvain(G, max_level=None, max_iter=None, resolution=1.0, threshold=1e-7):
         do_expensive_check=False,
     )
 
-    df = cudf.DataFrame()
-    df["vertex"] = vertex
-    df["partition"] = partition
+    result_df = cudf.DataFrame()
+    result_df[VERTEX_COL_NAME] = vertex
+    result_df[CLUSTER_ID_COL_NAME] = partition
+
+    if isNx and len(isolated_vertices) > 0:
+        unique_cids = result_df[CLUSTER_ID_COL_NAME].unique()
+        max_cluster_id = -1 if len(result_df) == 0 else unique_cids.max()
+
+        isolated_vtx_and_cids = cudf.DataFrame()
+        isolated_vtx_and_cids[VERTEX_COL_NAME] = isolated_vertices
+        isolated_vtx_and_cids[CLUSTER_ID_COL_NAME] = [
+            (max_cluster_id + i + 1) for i in range(len(isolated_vertices))
+        ]
+        result_df = cudf.concat(
+            [result_df, isolated_vtx_and_cids], ignore_index=True, sort=False
+        )
 
     if G.renumbered:
-        df = G.unrenumber(df, "vertex")
+        result_df = G.unrenumber(result_df, VERTEX_COL_NAME)
 
     if isNx is True:
-        df = df_score_to_dictionary(df, "partition")
+        result_df = df_score_to_dictionary(result_df, CLUSTER_ID_COL_NAME)
 
-    return df, mod_score
+    return result_df, mod_score

python/cugraph/cugraph/utilities/utils.py

@@ -364,8 +364,8 @@ def is_matrix_type(m):
     return is_cp_matrix_type(m) or is_sp_matrix_type(m)
 
 
-def is_nx_graph_type(g):
-    return g in __nx_graph_types
+def is_nx_graph_type(graph_type):
+    return graph_type in __nx_graph_types
 
 
 def is_cugraph_graph_type(g):