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
|
"""Hubs and authorities analysis of graph structure.
"""
# Copyright (C) 2008-2012 by
# Aric Hagberg <hagberg@lanl.gov>
# Dan Schult <dschult@colgate.edu>
# Pieter Swart <swart@lanl.gov>
# All rights reserved.
# BSD license.
# NetworkX:http://networkx.lanl.gov/
import networkx as nx
from networkx.exception import NetworkXError
__author__ = """Aric Hagberg (hagberg@lanl.gov)"""
__all__ = ['hits','hits_numpy','hits_scipy','authority_matrix','hub_matrix']
def hits(G,max_iter=100,tol=1.0e-8,nstart=None,normalized=True):
"""Return HITS hubs and authorities values for nodes.
The HITS algorithm computes two numbers for a node.
Authorities estimates the node value based on the incoming links.
Hubs estimates the node value based on outgoing links.
Parameters
----------
G : graph
A NetworkX graph
max_iter : interger, optional
Maximum number of iterations in power method.
tol : float, optional
Error tolerance used to check convergence in power method iteration.
nstart : dictionary, optional
Starting value of each node for power method iteration.
normalized : bool (default=True)
Normalize results by the sum of all of the values.
Returns
-------
(hubs,authorities) : two-tuple of dictionaries
Two dictionaries keyed by node containing the hub and authority
values.
Examples
--------
>>> G=nx.path_graph(4)
>>> h,a=nx.hits(G)
Notes
-----
The eigenvector calculation is done by the power iteration method
and has no guarantee of convergence. The iteration will stop
after max_iter iterations or an error tolerance of
number_of_nodes(G)*tol has been reached.
The HITS algorithm was designed for directed graphs but this
algorithm does not check if the input graph is directed and will
execute on undirected graphs.
References
----------
.. [1] A. Langville and C. Meyer,
"A survey of eigenvector methods of web information retrieval."
http://citeseer.ist.psu.edu/713792.html
.. [2] Jon Kleinberg,
Authoritative sources in a hyperlinked environment
Journal of the ACM 46 (5): 604-32, 1999.
doi:10.1145/324133.324140.
http://www.cs.cornell.edu/home/kleinber/auth.pdf.
"""
if type(G) == nx.MultiGraph or type(G) == nx.MultiDiGraph:
raise Exception("hits() not defined for graphs with multiedges.")
if len(G) == 0:
return {},{}
# choose fixed starting vector if not given
if nstart is None:
h=dict.fromkeys(G,1.0/G.number_of_nodes())
else:
h=nstart
# normalize starting vector
s=1.0/sum(h.values())
for k in h:
h[k]*=s
i=0
while True: # power iteration: make up to max_iter iterations
hlast=h
h=dict.fromkeys(hlast.keys(),0)
a=dict.fromkeys(hlast.keys(),0)
# this "matrix multiply" looks odd because it is
# doing a left multiply a^T=hlast^T*G
for n in h:
for nbr in G[n]:
a[nbr]+=hlast[n]*G[n][nbr].get('weight',1)
# now multiply h=Ga
for n in h:
for nbr in G[n]:
h[n]+=a[nbr]*G[n][nbr].get('weight',1)
# normalize vector
s=1.0/max(h.values())
for n in h: h[n]*=s
# normalize vector
s=1.0/max(a.values())
for n in a: a[n]*=s
# check convergence, l1 norm
err=sum([abs(h[n]-hlast[n]) for n in h])
if err < tol:
break
if i>max_iter:
raise NetworkXError(\
"HITS: power iteration failed to converge in %d iterations."%(i+1))
i+=1
if normalized:
s = 1.0/sum(a.values())
for n in a:
a[n] *= s
s = 1.0/sum(h.values())
for n in h:
h[n] *= s
return h,a
def authority_matrix(G,nodelist=None):
"""Return the HITS authority matrix."""
M=nx.to_numpy_matrix(G,nodelist=nodelist)
return M.T*M
def hub_matrix(G,nodelist=None):
"""Return the HITS hub matrix."""
M=nx.to_numpy_matrix(G,nodelist=nodelist)
return M*M.T
def hits_numpy(G,normalized=True):
"""Return HITS hubs and authorities values for nodes.
The HITS algorithm computes two numbers for a node.
Authorities estimates the node value based on the incoming links.
Hubs estimates the node value based on outgoing links.
Parameters
-----------
G : graph
A NetworkX graph
normalized : bool (default=True)
Normalize results by the sum of all of the values.
Returns
-------
(hubs,authorities) : two-tuple of dictionaries
Two dictionaries keyed by node containing the hub and authority
values.
Examples
--------
>>> G=nx.path_graph(4)
>>> h,a=nx.hits(G)
Notes
-----
The eigenvector calculation uses NumPy's interface to LAPACK.
The HITS algorithm was designed for directed graphs but this
algorithm does not check if the input graph is directed and will
execute on undirected graphs.
References
----------
.. [1] A. Langville and C. Meyer,
"A survey of eigenvector methods of web information retrieval."
http://citeseer.ist.psu.edu/713792.html
.. [2] Jon Kleinberg,
Authoritative sources in a hyperlinked environment
Journal of the ACM 46 (5): 604-32, 1999.
doi:10.1145/324133.324140.
http://www.cs.cornell.edu/home/kleinber/auth.pdf.
"""
try:
import numpy as np
except ImportError:
raise ImportError(\
"hits_numpy() requires NumPy: http://scipy.org/")
if len(G) == 0:
return {},{}
H=nx.hub_matrix(G,G.nodes())
e,ev=np.linalg.eig(H)
m=e.argsort()[-1] # index of maximum eigenvalue
h=np.array(ev[:,m]).flatten()
A=nx.authority_matrix(G,G.nodes())
e,ev=np.linalg.eig(A)
m=e.argsort()[-1] # index of maximum eigenvalue
a=np.array(ev[:,m]).flatten()
if normalized:
h = h/h.sum()
a = a/a.sum()
else:
h = h/h.max()
a = a/a.max()
hubs=dict(zip(G.nodes(),map(float,h)))
authorities=dict(zip(G.nodes(),map(float,a)))
return hubs,authorities
def hits_scipy(G,max_iter=100,tol=1.0e-6,normalized=True):
"""Return HITS hubs and authorities values for nodes.
The HITS algorithm computes two numbers for a node.
Authorities estimates the node value based on the incoming links.
Hubs estimates the node value based on outgoing links.
Parameters
-----------
G : graph
A NetworkX graph
max_iter : interger, optional
Maximum number of iterations in power method.
tol : float, optional
Error tolerance used to check convergence in power method iteration.
nstart : dictionary, optional
Starting value of each node for power method iteration.
normalized : bool (default=True)
Normalize results by the sum of all of the values.
Returns
-------
(hubs,authorities) : two-tuple of dictionaries
Two dictionaries keyed by node containing the hub and authority
values.
Examples
--------
>>> G=nx.path_graph(4)
>>> h,a=nx.hits(G)
Notes
-----
This implementation uses SciPy sparse matrices.
The eigenvector calculation is done by the power iteration method
and has no guarantee of convergence. The iteration will stop
after max_iter iterations or an error tolerance of
number_of_nodes(G)*tol has been reached.
The HITS algorithm was designed for directed graphs but this
algorithm does not check if the input graph is directed and will
execute on undirected graphs.
References
----------
.. [1] A. Langville and C. Meyer,
"A survey of eigenvector methods of web information retrieval."
http://citeseer.ist.psu.edu/713792.html
.. [2] Jon Kleinberg,
Authoritative sources in a hyperlinked environment
Journal of the ACM 46 (5): 604-632, 1999.
doi:10.1145/324133.324140.
http://www.cs.cornell.edu/home/kleinber/auth.pdf.
"""
try:
import scipy.sparse
import numpy as np
except ImportError:
raise ImportError(\
"hits_scipy() requires SciPy: http://scipy.org/")
if len(G) == 0:
return {},{}
M=nx.to_scipy_sparse_matrix(G,nodelist=G.nodes())
(n,m)=M.shape # should be square
A=M.T*M # authority matrix
x=scipy.ones((n,1))/n # initial guess
# power iteration on authority matrix
i=0
while True:
xlast=x
x=A*x
x=x/x.max()
# check convergence, l1 norm
err=scipy.absolute(x-xlast).sum()
if err < tol:
break
if i>max_iter:
raise NetworkXError(\
"HITS: power iteration failed to converge in %d iterations."%(i+1))
i+=1
a=np.asarray(x).flatten()
# h=M*a
h=np.asarray(M*a).flatten()
if normalized:
h = h/h.sum()
a = a/a.sum()
hubs=dict(zip(G.nodes(),map(float,h)))
authorities=dict(zip(G.nodes(),map(float,a)))
return hubs,authorities
# fixture for nose tests
def setup_module(module):
from nose import SkipTest
try:
import numpy
except:
raise SkipTest("NumPy not available")
try:
import scipy
except:
raise SkipTest("SciPy not available")
|
