def spectralBalancedCutClustering(G,
num_clusters,
num_eigen_vects=2,
evs_tolerance=.00001,
evs_max_iter=100,
kmean_tolerance=.00001,
kmean_max_iter=100):
"""
Compute a clustering/partitioning of the given graph using the spectral
balanced cut method.
Parameters
----------
G : cugraph.Graph
cuGraph graph descriptor
num_clusters : integer
Specifies the number of clusters to find
num_eigen_vects : integer
Specifies the number of eigenvectors to use. Must be lower or equal to
num_clusters.
evs_tolerance: float
Specifies the tolerance to use in the eigensolver
Default is 0.00001
evs_max_iter: integer
Specifies the maximum number of iterations for the eigensolver
Default is 100
kmean_tolerance: float
Specifies the tolerance to use in the k-means solver
Default is 0.00001
kmean_max_iter: integer
Specifies the maximum number of iterations for the k-means solver
Default is 100
Returns
-------
df : cudf.DataFrame
GPU data frame containing two cudf.Series of size V: the vertex
identifiers and the corresponding cluster assignments.
df['vertex'] : cudf.Series
contains the vertex identifiers
df['cluster'] : cudf.Series
contains the cluster assignments
Examples
--------
>>> M = cudf.read_csv('datasets/karate.csv',
delimiter = ' ',
dtype=['int32', 'int32', 'float32'],
header=None)
>>> G = cugraph.Graph()
>>> G.from_cudf_edgelist(M, source='0', destination='1')
>>> df = cugraph.spectralBalancedCutClustering(G, 5)
"""
df = spectral_clustering_wrapper.spectralBalancedCutClustering(
G, num_clusters, num_eigen_vects, evs_tolerance, evs_max_iter,
kmean_tolerance, kmean_max_iter)
return df
def spectralBalancedCutClustering(
G,
num_clusters,
num_eigen_vects=2,
evs_tolerance=0.00001,
evs_max_iter=100,
kmean_tolerance=0.00001,
kmean_max_iter=100,
):
"""
Compute a clustering/partitioning of the given graph using the spectral
balanced cut method.
Parameters
----------
G : cugraph.Graph or networkx.Graph
Graph descriptor
num_clusters : integer
Specifies the number of clusters to find, must be greater than 1
num_eigen_vects : integer, optional
Specifies the number of eigenvectors to use. Must be lower or equal to
num_clusters. Default is 2
evs_tolerance: float, optional
Specifies the tolerance to use in the eigensolver.
Default is 0.00001
evs_max_iter: integer, optional
Specifies the maximum number of iterations for the eigensolver.
Default is 100
kmean_tolerance: float, optional
Specifies the tolerance to use in the k-means solver.
Default is 0.00001
kmean_max_iter: integer, optional
Specifies the maximum number of iterations for the k-means solver.
Default is 100
Returns
-------
df : cudf.DataFrame
GPU data frame containing two cudf.Series of size V: the vertex
identifiers and the corresponding cluster assignments.
df['vertex'] : cudf.Series
contains the vertex identifiers
df['cluster'] : cudf.Series
contains the cluster assignments
Examples
--------
>>> M = cudf.read_csv(datasets_path / 'karate.csv',
... delimiter = ' ',
... dtype=['int32', 'int32', 'float32'],
... header=None)
>>> G = cugraph.Graph()
>>> G.from_cudf_edgelist(M, source='0', destination='1')
>>> df = cugraph.spectralBalancedCutClustering(G, 5)
"""
# Error checking in C++ code
G, isNx = ensure_cugraph_obj_for_nx(G)
df = spectral_clustering_wrapper.spectralBalancedCutClustering(
G,
num_clusters,
num_eigen_vects,
evs_tolerance,
evs_max_iter,
kmean_tolerance,
kmean_max_iter,
)
if G.renumbered:
df = G.unrenumber(df, "vertex")
if isNx is True:
df = df_score_to_dictionary(df, "cluster")
return df