def from_cudf_edgelist(df,
source='source',
destination='destination',
edge_attr=None,
create_using=Graph,
renumber=True):
"""
Return a new graph created from the edge list representaion. This function
is added for NetworkX compatibility (this function is a RAPIDS version of
NetworkX's from_pandas_edge_list()). This function does not support
multiple source or destination columns. But does support renumbering
Parameters
----------
df : cudf.DataFrame
This cudf.DataFrame contains columns storing edge source vertices,
destination (or target following NetworkX's terminology) vertices, and
(optional) weights.
source : string or integer, optional (default='source')
This is used to index the source column.
destination : string or integer, optional (default='destination')
This is used to index the destination (or target following NetworkX's
terminology) column.
edge_attr : string or integer, optional (default=None)
This pointer can be ``None``. If not, this is used to index the weight
column.
create_using : cuGraph.Graph, optional (default=cugraph.Graph)
Specify the type of Graph to create.
renumber : bool, optional (default=True)
If source and destination indices are not in range 0 to V where V
is number of vertices, renumber argument should be True.
Examples
--------
>>> M = cudf.read_csv(datasets_path / 'karate.csv', delimiter=' ',
... dtype=['int32', 'int32', 'float32'], header=None)
>>> G = cugraph.Graph()
>>> G = cugraph.from_cudf_edgelist(M, source='0', destination='1',
... edge_attr='2')
"""
if create_using is Graph:
G = Graph()
elif create_using is DiGraph:
G = DiGraph()
else:
raise Exception("create_using supports Graph and DiGraph")
G.from_cudf_edgelist(df,
source=source,
destination=destination,
edge_attr=edge_attr,
renumber=renumber)
return G
def _minimum_spanning_tree_subgraph(G):
mst_subgraph = Graph()
if type(G) is not Graph:
raise Exception("input graph must be undirected")
mst_df = minimum_spanning_tree_wrapper.minimum_spanning_tree(G)
if G.renumbered:
mst_df = G.unrenumber(mst_df, "src")
mst_df = G.unrenumber(mst_df, "dst")
mst_subgraph.from_cudf_edgelist(
mst_df, source="src", destination="dst", edge_attr="weight"
)
return mst_subgraph
def _maximum_spanning_tree_subgraph(G):
mst_subgraph = Graph()
if type(G) is not Graph:
raise Exception("input graph must be undirected")
if G.adjlist.weights is not None:
G.adjlist.weights = G.adjlist.weights.mul(-1)
mst_df = minimum_spanning_tree_wrapper.minimum_spanning_tree(G)
# revert to original weights
if G.adjlist.weights is not None:
G.adjlist.weights = G.adjlist.weights.mul(-1)
mst_df["weight"] = mst_df["weight"].mul(-1)
if G.renumbered:
mst_df = G.unrenumber(mst_df, "src")
mst_df = G.unrenumber(mst_df, "dst")
mst_subgraph.from_cudf_edgelist(
mst_df, source="src", destination="dst", edge_attr="weight"
)
return mst_subgraph
def ktruss_subgraph(G, k, use_weights=True):
"""
Returns the K-Truss subgraph of a graph for a specific k.
The k-truss of a graph is a subgraph where each edge is part of at least
(k−2) triangles. K-trusses are used for finding tighlty knit groups of
vertices in a graph. A k-truss is a relaxation of a k-clique in the graph
and was define in [1]. Finding cliques is computationally demanding and
finding the maximal k-clique is known to be NP-Hard.
In contrast, finding a k-truss is computationally tractable as its
key building block, namely triangle counting counting, can be executed
in polnymomial time.Typically, it takes many iterations of triangle
counting to find the k-truss of a graph. Yet these iterations operate
on a weakly monotonically shrinking graph.
Therefore, finding the k-truss of a graph can be done in a fairly
reasonable amount of time. The solution in cuGraph is based on a
GPU algorithm first shown in [2] and uses the triangle counting algorithm
from [3].
[1] Cohen, J.,
"Trusses: Cohesive subgraphs for social network analysis"
National security agency technical report, 2008
[2] O. Green, J. Fox, E. Kim, F. Busato, et al.
“Quickly Finding a Truss in a Haystack”
IEEE High Performance Extreme Computing Conference (HPEC), 2017
https://doi.org/10.1109/HPEC.2017.8091038
[3] O. Green, P. Yalamanchili, L.M. Munguia,
“Fast Triangle Counting on GPU”
Irregular Applications: Architectures and Algorithms (IA3), 2014
Parameters
----------
G : cuGraph.Graph
cuGraph graph descriptor with connectivity information. k-Trusses are
defined for only undirected graphs as they are defined for
undirected triangle in a graph.
k : int
The desired k to be used for extracting the k-truss subgraph.
use_weights : Bool
whether the output should contain the edge weights if G has them
Returns
-------
G_truss : cuGraph.Graph
A cugraph graph descriptor with the k-truss subgraph for the given k.
Examples
--------
>>> gdf = cudf.read_csv('datasets/karate.csv', delimiter=' ',
>>> dtype=['int32', 'int32', 'float32'], header=None)
>>> G = cugraph.Graph()
>>> G.from_cudf_edgelist(gdf, source='0', destination='1')
>>> k_subgraph = cugraph.ktruss_subgraph(G, 3)
"""
KTrussSubgraph = Graph()
if type(G) is not Graph:
raise Exception("input graph must be undirected")
subgraph_df = ktruss_subgraph_wrapper.ktruss_subgraph(G, k, use_weights)
if G.renumbered:
subgraph_df = G.unrenumber(subgraph_df, "src")
subgraph_df = G.unrenumber(subgraph_df, "dst")
if G.edgelist.weights:
KTrussSubgraph.from_cudf_edgelist(subgraph_df,
source="src",
destination="dst",
edge_attr="weight")
else:
KTrussSubgraph.from_cudf_edgelist(subgraph_df,
source="src",
destination="dst")
return KTrussSubgraph