def analyzeClustering_modularity(G, n_clusters, clustering):
"""
Compute the modularity score for a partitioning/clustering
Parameters
----------
G : cugraph.Graph
cuGraph graph descriptor. This graph should have edge weights.
n_clusters : integer
Specifies the number of clusters in the given clustering
clustering : cudf.Series
The cluster assignment to analyze.
Returns
-------
score : float
The computed modularity score
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', edge_attr='2')
>>> df = cugraph.spectralBalancedCutClustering(G, 5)
>>> score = cugraph.analyzeClustering_modularity(G, 5, df['cluster'])
"""
score = spectral_clustering_wrapper.analyzeClustering_modularity(
G, n_clusters, clustering)
return score
def analyzeClustering_modularity(G,
n_clusters,
clustering,
vertex_col_name='vertex',
cluster_col_name='cluster'):
"""
Compute the modularity score for a partitioning/clustering
Parameters
----------
G : cugraph.Graph
cuGraph graph descriptor. This graph should have edge weights.
n_clusters : integer
Specifies the number of clusters in the given clustering
clustering : cudf.DataFrame
The cluster assignment to analyze.
vertex_col_name : str
The name of the column in the clustering dataframe identifying
the external vertex id
cluster_col_name : str
The name of the column in the clustering dataframe identifying
the cluster id
Returns
-------
score : float
The computed modularity score
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', edge_attr='2')
>>> df = cugraph.spectralBalancedCutClustering(G, 5)
>>> score = cugraph.analyzeClustering_modularity(G, 5, df,
>>> 'vertex', 'cluster')
"""
if G.renumbered:
clustering = G.add_internal_vertex_id(clustering,
vertex_col_name,
vertex_col_name,
drop=True)
clustering = clustering.sort_values(vertex_col_name)
score = spectral_clustering_wrapper.analyzeClustering_modularity(
G, n_clusters, clustering[cluster_col_name])
return score
def analyzeClustering_modularity(G, n_clusters, clustering,
vertex_col_name='vertex',
cluster_col_name='cluster'):
"""
Compute the modularity score for a given partitioning/clustering.
The assumption is that “clustering” is the results from a call
from a special clustering algorithm and contains columns named
“vertex” and “cluster”.
Parameters
----------
G : cugraph.Graph or networkx.Graph
graph descriptor. This graph should have edge weights.
n_clusters : integer
Specifies the number of clusters in the given clustering
clustering : cudf.DataFrame
The cluster assignment to analyze.
vertex_col_name : str or list of str, optional (default='vertex')
The names of the column in the clustering dataframe identifying
the external vertex id
cluster_col_name : str, optional (default='cluster')
The name of the column in the clustering dataframe identifying
the cluster id
Returns
-------
score : float
The computed modularity score
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', edge_attr='2')
>>> df = cugraph.spectralBalancedCutClustering(G, 5)
>>> score = cugraph.analyzeClustering_modularity(G, 5, df)
"""
if type(vertex_col_name) is list:
if not all(isinstance(name, str) for name in vertex_col_name):
raise Exception("vertex_col_name must be list of string")
elif type(vertex_col_name) is not str:
raise Exception("vertex_col_name must be a string")
if type(cluster_col_name) is not str:
raise Exception("cluster_col_name must be a string")
G, isNx = ensure_cugraph_obj_for_nx(G)
if G.renumbered:
clustering = G.add_internal_vertex_id(clustering,
'vertex',
vertex_col_name,
drop=True)
clustering = clustering.sort_values('vertex')
score = spectral_clustering_wrapper.analyzeClustering_modularity(
G, n_clusters, clustering[cluster_col_name]
)
return score