Spaces:
Running
Running
File size: 9,960 Bytes
b200bda |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 |
"""Functions for finding and evaluating cuts in a graph.
"""
from itertools import chain
import networkx as nx
__all__ = [
"boundary_expansion",
"conductance",
"cut_size",
"edge_expansion",
"mixing_expansion",
"node_expansion",
"normalized_cut_size",
"volume",
]
# TODO STILL NEED TO UPDATE ALL THE DOCUMENTATION!
@nx._dispatch(edge_attrs="weight")
def cut_size(G, S, T=None, weight=None):
"""Returns the size of the cut between two sets of nodes.
A *cut* is a partition of the nodes of a graph into two sets. The
*cut size* is the sum of the weights of the edges "between" the two
sets of nodes.
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
T : collection
A collection of nodes in `G`. If not specified, this is taken to
be the set complement of `S`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
Total weight of all edges from nodes in set `S` to nodes in
set `T` (and, in the case of directed graphs, all edges from
nodes in `T` to nodes in `S`).
Examples
--------
In the graph with two cliques joined by a single edges, the natural
bipartition of the graph into two blocks, one for each clique,
yields a cut of weight one::
>>> G = nx.barbell_graph(3, 0)
>>> S = {0, 1, 2}
>>> T = {3, 4, 5}
>>> nx.cut_size(G, S, T)
1
Each parallel edge in a multigraph is counted when determining the
cut size::
>>> G = nx.MultiGraph(["ab", "ab"])
>>> S = {"a"}
>>> T = {"b"}
>>> nx.cut_size(G, S, T)
2
Notes
-----
In a multigraph, the cut size is the total weight of edges including
multiplicity.
"""
edges = nx.edge_boundary(G, S, T, data=weight, default=1)
if G.is_directed():
edges = chain(edges, nx.edge_boundary(G, T, S, data=weight, default=1))
return sum(weight for u, v, weight in edges)
@nx._dispatch(edge_attrs="weight")
def volume(G, S, weight=None):
"""Returns the volume of a set of nodes.
The *volume* of a set *S* is the sum of the (out-)degrees of nodes
in *S* (taking into account parallel edges in multigraphs). [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
The volume of the set of nodes represented by `S` in the graph
`G`.
See also
--------
conductance
cut_size
edge_expansion
edge_boundary
normalized_cut_size
References
----------
.. [1] David Gleich.
*Hierarchical Directed Spectral Graph Partitioning*.
<https://www.cs.purdue.edu/homes/dgleich/publications/Gleich%202005%20-%20hierarchical%20directed%20spectral.pdf>
"""
degree = G.out_degree if G.is_directed() else G.degree
return sum(d for v, d in degree(S, weight=weight))
@nx._dispatch(edge_attrs="weight")
def normalized_cut_size(G, S, T=None, weight=None):
"""Returns the normalized size of the cut between two sets of nodes.
The *normalized cut size* is the cut size times the sum of the
reciprocal sizes of the volumes of the two sets. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
T : collection
A collection of nodes in `G`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
The normalized cut size between the two sets `S` and `T`.
Notes
-----
In a multigraph, the cut size is the total weight of edges including
multiplicity.
See also
--------
conductance
cut_size
edge_expansion
volume
References
----------
.. [1] David Gleich.
*Hierarchical Directed Spectral Graph Partitioning*.
<https://www.cs.purdue.edu/homes/dgleich/publications/Gleich%202005%20-%20hierarchical%20directed%20spectral.pdf>
"""
if T is None:
T = set(G) - set(S)
num_cut_edges = cut_size(G, S, T=T, weight=weight)
volume_S = volume(G, S, weight=weight)
volume_T = volume(G, T, weight=weight)
return num_cut_edges * ((1 / volume_S) + (1 / volume_T))
@nx._dispatch(edge_attrs="weight")
def conductance(G, S, T=None, weight=None):
"""Returns the conductance of two sets of nodes.
The *conductance* is the quotient of the cut size and the smaller of
the volumes of the two sets. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
T : collection
A collection of nodes in `G`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
The conductance between the two sets `S` and `T`.
See also
--------
cut_size
edge_expansion
normalized_cut_size
volume
References
----------
.. [1] David Gleich.
*Hierarchical Directed Spectral Graph Partitioning*.
<https://www.cs.purdue.edu/homes/dgleich/publications/Gleich%202005%20-%20hierarchical%20directed%20spectral.pdf>
"""
if T is None:
T = set(G) - set(S)
num_cut_edges = cut_size(G, S, T, weight=weight)
volume_S = volume(G, S, weight=weight)
volume_T = volume(G, T, weight=weight)
return num_cut_edges / min(volume_S, volume_T)
@nx._dispatch(edge_attrs="weight")
def edge_expansion(G, S, T=None, weight=None):
"""Returns the edge expansion between two node sets.
The *edge expansion* is the quotient of the cut size and the smaller
of the cardinalities of the two sets. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
T : collection
A collection of nodes in `G`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
The edge expansion between the two sets `S` and `T`.
See also
--------
boundary_expansion
mixing_expansion
node_expansion
References
----------
.. [1] Fan Chung.
*Spectral Graph Theory*.
(CBMS Regional Conference Series in Mathematics, No. 92),
American Mathematical Society, 1997, ISBN 0-8218-0315-8
<http://www.math.ucsd.edu/~fan/research/revised.html>
"""
if T is None:
T = set(G) - set(S)
num_cut_edges = cut_size(G, S, T=T, weight=weight)
return num_cut_edges / min(len(S), len(T))
@nx._dispatch(edge_attrs="weight")
def mixing_expansion(G, S, T=None, weight=None):
"""Returns the mixing expansion between two node sets.
The *mixing expansion* is the quotient of the cut size and twice the
number of edges in the graph. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
T : collection
A collection of nodes in `G`.
weight : object
Edge attribute key to use as weight. If not specified, edges
have weight one.
Returns
-------
number
The mixing expansion between the two sets `S` and `T`.
See also
--------
boundary_expansion
edge_expansion
node_expansion
References
----------
.. [1] Vadhan, Salil P.
"Pseudorandomness."
*Foundations and Trends
in Theoretical Computer Science* 7.1–3 (2011): 1–336.
<https://doi.org/10.1561/0400000010>
"""
num_cut_edges = cut_size(G, S, T=T, weight=weight)
num_total_edges = G.number_of_edges()
return num_cut_edges / (2 * num_total_edges)
# TODO What is the generalization to two arguments, S and T? Does the
# denominator become `min(len(S), len(T))`?
@nx._dispatch
def node_expansion(G, S):
"""Returns the node expansion of the set `S`.
The *node expansion* is the quotient of the size of the node
boundary of *S* and the cardinality of *S*. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
Returns
-------
number
The node expansion of the set `S`.
See also
--------
boundary_expansion
edge_expansion
mixing_expansion
References
----------
.. [1] Vadhan, Salil P.
"Pseudorandomness."
*Foundations and Trends
in Theoretical Computer Science* 7.1–3 (2011): 1–336.
<https://doi.org/10.1561/0400000010>
"""
neighborhood = set(chain.from_iterable(G.neighbors(v) for v in S))
return len(neighborhood) / len(S)
# TODO What is the generalization to two arguments, S and T? Does the
# denominator become `min(len(S), len(T))`?
@nx._dispatch
def boundary_expansion(G, S):
"""Returns the boundary expansion of the set `S`.
The *boundary expansion* is the quotient of the size
of the node boundary and the cardinality of *S*. [1]
Parameters
----------
G : NetworkX graph
S : collection
A collection of nodes in `G`.
Returns
-------
number
The boundary expansion of the set `S`.
See also
--------
edge_expansion
mixing_expansion
node_expansion
References
----------
.. [1] Vadhan, Salil P.
"Pseudorandomness."
*Foundations and Trends in Theoretical Computer Science*
7.1–3 (2011): 1–336.
<https://doi.org/10.1561/0400000010>
"""
return len(nx.node_boundary(G, S)) / len(S)
|