File size: 9,327 Bytes
6525fa6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
"""Betweenness centrality measures for subsets of nodes."""
import networkx as nx
from networkx.algorithms.centrality.betweenness import (
_add_edge_keys,
)
from networkx.algorithms.centrality.betweenness import (
_single_source_dijkstra_path_basic as dijkstra,
)
from networkx.algorithms.centrality.betweenness import (
_single_source_shortest_path_basic as shortest_path,
)
__all__ = [
"betweenness_centrality_subset",
"edge_betweenness_centrality_subset",
]
@nx._dispatch(edge_attrs="weight")
def betweenness_centrality_subset(G, sources, targets, normalized=False, weight=None):
r"""Compute betweenness centrality for a subset of nodes.
.. math::
c_B(v) =\sum_{s\in S, t \in T} \frac{\sigma(s, t|v)}{\sigma(s, t)}
where $S$ is the set of sources, $T$ is the set of targets,
$\sigma(s, t)$ is the number of shortest $(s, t)$-paths,
and $\sigma(s, t|v)$ is the number of those paths
passing through some node $v$ other than $s, t$.
If $s = t$, $\sigma(s, t) = 1$,
and if $v \in {s, t}$, $\sigma(s, t|v) = 0$ [2]_.
Parameters
----------
G : graph
A NetworkX graph.
sources: list of nodes
Nodes to use as sources for shortest paths in betweenness
targets: list of nodes
Nodes to use as targets for shortest paths in betweenness
normalized : bool, optional
If True the betweenness values are normalized by $2/((n-1)(n-2))$
for graphs, and $1/((n-1)(n-2))$ for directed graphs where $n$
is the number of nodes in G.
weight : None or string, optional (default=None)
If None, all edge weights are considered equal.
Otherwise holds the name of the edge attribute used as weight.
Weights are used to calculate weighted shortest paths, so they are
interpreted as distances.
Returns
-------
nodes : dictionary
Dictionary of nodes with betweenness centrality as the value.
See Also
--------
edge_betweenness_centrality
load_centrality
Notes
-----
The basic algorithm is from [1]_.
For weighted graphs the edge weights must be greater than zero.
Zero edge weights can produce an infinite number of equal length
paths between pairs of nodes.
The normalization might seem a little strange but it is
designed to make betweenness_centrality(G) be the same as
betweenness_centrality_subset(G,sources=G.nodes(),targets=G.nodes()).
The total number of paths between source and target is counted
differently for directed and undirected graphs. Directed paths
are easy to count. Undirected paths are tricky: should a path
from "u" to "v" count as 1 undirected path or as 2 directed paths?
For betweenness_centrality we report the number of undirected
paths when G is undirected.
For betweenness_centrality_subset the reporting is different.
If the source and target subsets are the same, then we want
to count undirected paths. But if the source and target subsets
differ -- for example, if sources is {0} and targets is {1},
then we are only counting the paths in one direction. They are
undirected paths but we are counting them in a directed way.
To count them as undirected paths, each should count as half a path.
References
----------
.. [1] Ulrik Brandes, A Faster Algorithm for Betweenness Centrality.
Journal of Mathematical Sociology 25(2):163-177, 2001.
https://doi.org/10.1080/0022250X.2001.9990249
.. [2] Ulrik Brandes: On Variants of Shortest-Path Betweenness
Centrality and their Generic Computation.
Social Networks 30(2):136-145, 2008.
https://doi.org/10.1016/j.socnet.2007.11.001
"""
b = dict.fromkeys(G, 0.0) # b[v]=0 for v in G
for s in sources:
# single source shortest paths
if weight is None: # use BFS
S, P, sigma, _ = shortest_path(G, s)
else: # use Dijkstra's algorithm
S, P, sigma, _ = dijkstra(G, s, weight)
b = _accumulate_subset(b, S, P, sigma, s, targets)
b = _rescale(b, len(G), normalized=normalized, directed=G.is_directed())
return b
@nx._dispatch(edge_attrs="weight")
def edge_betweenness_centrality_subset(
G, sources, targets, normalized=False, weight=None
):
r"""Compute betweenness centrality for edges for a subset of nodes.
.. math::
c_B(v) =\sum_{s\in S,t \in T} \frac{\sigma(s, t|e)}{\sigma(s, t)}
where $S$ is the set of sources, $T$ is the set of targets,
$\sigma(s, t)$ is the number of shortest $(s, t)$-paths,
and $\sigma(s, t|e)$ is the number of those paths
passing through edge $e$ [2]_.
Parameters
----------
G : graph
A networkx graph.
sources: list of nodes
Nodes to use as sources for shortest paths in betweenness
targets: list of nodes
Nodes to use as targets for shortest paths in betweenness
normalized : bool, optional
If True the betweenness values are normalized by `2/(n(n-1))`
for graphs, and `1/(n(n-1))` for directed graphs where `n`
is the number of nodes in G.
weight : None or string, optional (default=None)
If None, all edge weights are considered equal.
Otherwise holds the name of the edge attribute used as weight.
Weights are used to calculate weighted shortest paths, so they are
interpreted as distances.
Returns
-------
edges : dictionary
Dictionary of edges with Betweenness centrality as the value.
See Also
--------
betweenness_centrality
edge_load
Notes
-----
The basic algorithm is from [1]_.
For weighted graphs the edge weights must be greater than zero.
Zero edge weights can produce an infinite number of equal length
paths between pairs of nodes.
The normalization might seem a little strange but it is the same
as in edge_betweenness_centrality() and is designed to make
edge_betweenness_centrality(G) be the same as
edge_betweenness_centrality_subset(G,sources=G.nodes(),targets=G.nodes()).
References
----------
.. [1] Ulrik Brandes, A Faster Algorithm for Betweenness Centrality.
Journal of Mathematical Sociology 25(2):163-177, 2001.
https://doi.org/10.1080/0022250X.2001.9990249
.. [2] Ulrik Brandes: On Variants of Shortest-Path Betweenness
Centrality and their Generic Computation.
Social Networks 30(2):136-145, 2008.
https://doi.org/10.1016/j.socnet.2007.11.001
"""
b = dict.fromkeys(G, 0.0) # b[v]=0 for v in G
b.update(dict.fromkeys(G.edges(), 0.0)) # b[e] for e in G.edges()
for s in sources:
# single source shortest paths
if weight is None: # use BFS
S, P, sigma, _ = shortest_path(G, s)
else: # use Dijkstra's algorithm
S, P, sigma, _ = dijkstra(G, s, weight)
b = _accumulate_edges_subset(b, S, P, sigma, s, targets)
for n in G: # remove nodes to only return edges
del b[n]
b = _rescale_e(b, len(G), normalized=normalized, directed=G.is_directed())
if G.is_multigraph():
b = _add_edge_keys(G, b, weight=weight)
return b
def _accumulate_subset(betweenness, S, P, sigma, s, targets):
delta = dict.fromkeys(S, 0.0)
target_set = set(targets) - {s}
while S:
w = S.pop()
if w in target_set:
coeff = (delta[w] + 1.0) / sigma[w]
else:
coeff = delta[w] / sigma[w]
for v in P[w]:
delta[v] += sigma[v] * coeff
if w != s:
betweenness[w] += delta[w]
return betweenness
def _accumulate_edges_subset(betweenness, S, P, sigma, s, targets):
"""edge_betweenness_centrality_subset helper."""
delta = dict.fromkeys(S, 0)
target_set = set(targets)
while S:
w = S.pop()
for v in P[w]:
if w in target_set:
c = (sigma[v] / sigma[w]) * (1.0 + delta[w])
else:
c = delta[w] / len(P[w])
if (v, w) not in betweenness:
betweenness[(w, v)] += c
else:
betweenness[(v, w)] += c
delta[v] += c
if w != s:
betweenness[w] += delta[w]
return betweenness
def _rescale(betweenness, n, normalized, directed=False):
"""betweenness_centrality_subset helper."""
if normalized:
if n <= 2:
scale = None # no normalization b=0 for all nodes
else:
scale = 1.0 / ((n - 1) * (n - 2))
else: # rescale by 2 for undirected graphs
if not directed:
scale = 0.5
else:
scale = None
if scale is not None:
for v in betweenness:
betweenness[v] *= scale
return betweenness
def _rescale_e(betweenness, n, normalized, directed=False):
"""edge_betweenness_centrality_subset helper."""
if normalized:
if n <= 1:
scale = None # no normalization b=0 for all nodes
else:
scale = 1.0 / (n * (n - 1))
else: # rescale by 2 for undirected graphs
if not directed:
scale = 0.5
else:
scale = None
if scale is not None:
for v in betweenness:
betweenness[v] *= scale
return betweenness
|