File: multiline_adjlist.py

package info (click to toggle)
python-networkx 1.7~rc1-3
  • links: PTS, VCS
  • area: main
  • in suites: wheezy
  • size: 4,128 kB
  • sloc: python: 44,557; makefile: 135
file content (393 lines) | stat: -rw-r--r-- 12,138 bytes parent folder | download
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
# -*- coding: utf-8 -*-
"""
*************************
Multi-line Adjacency List
*************************
Read and write NetworkX graphs as multi-line adjacency lists.

The multi-line adjacency list format is useful for graphs with 
nodes that can be meaningfully represented as strings.  With this format 
simple edge data can be stored but node or graph data is not. 

Format
------
The first label in a line is the source node label followed by the node degree
d.  The next d lines are target node labels and optional edge data.
That pattern repeats for all nodes in the graph.

The graph with edges a-b, a-c, d-e can be represented as the following 
adjacency list (anything following the # in a line is a comment):: 

     # example.multiline-adjlist
     a 2
     b
     c
     d 1
     e
"""
__author__ = '\n'.join(['Aric Hagberg <hagberg@lanl.gov>',
                        'Dan Schult <dschult@colgate.edu>',
                        'Loïc Séguin-C. <loicseguin@gmail.com>'])
#    Copyright (C) 2004-2010 by 
#    Aric Hagberg <hagberg@lanl.gov>
#    Dan Schult <dschult@colgate.edu>
#    Pieter Swart <swart@lanl.gov>
#    All rights reserved.
#    BSD license.

__all__ = ['generate_multiline_adjlist',
           'write_multiline_adjlist',
           'parse_multiline_adjlist',
           'read_multiline_adjlist']

from networkx.utils import make_str, open_file
import networkx as nx

def generate_multiline_adjlist(G, delimiter = ' '):
    """Generate a single line of the graph G in multiline adjacency list format.

    Parameters
    ----------
    G : NetworkX graph
    
    delimiter : string, optional
       Separator for node labels 

    Returns
    -------
    lines : string
        Lines of data in multiline adjlist format.

    Examples
    --------
    >>> G = nx.lollipop_graph(4, 3)
    >>> for line in nx.generate_multiline_adjlist(G):
    ...     print(line)    
    0 3
    1 {}
    2 {}
    3 {}
    1 2
    2 {}
    3 {}
    2 1
    3 {}
    3 1
    4 {}
    4 1
    5 {}
    5 1
    6 {}
    6 0

    See Also
    --------
    write_multiline_adjlist, read_multiline_adjlist
    """
    if G.is_directed():
        if G.is_multigraph():
            for s,nbrs in G.adjacency_iter():
                nbr_edges=[ (u,data) 
                            for u,datadict in nbrs.items() 
                            for key,data in datadict.items()]
                deg=len(nbr_edges)
                yield make_str(s)+delimiter+"%i"%(deg)
                for u,d in nbr_edges:
                    if d is None:
                        yield make_str(u)
                    else:
                        yield make_str(u)+delimiter+make_str(d)
        else: # directed single edges
            for s,nbrs in G.adjacency_iter():
                deg=len(nbrs)
                yield make_str(s)+delimiter+"%i"%(deg)
                for u,d in nbrs.items():
                   if d is None:    
                       yield make_str(u)
                   else:   
                       yield make_str(u)+delimiter+make_str(d)
    else: # undirected
        if G.is_multigraph():
            seen=set()  # helper dict used to avoid duplicate edges
            for s,nbrs in G.adjacency_iter():
                nbr_edges=[ (u,data) 
                            for u,datadict in nbrs.items() 
                            if u not in seen
                            for key,data in datadict.items()]
                deg=len(nbr_edges)
                yield make_str(s)+delimiter+"%i"%(deg)
                for u,d in nbr_edges:
                    if d is None:    
                        yield make_str(u)
                    else:   
                        yield make_str(u)+delimiter+make_str(d)
                seen.add(s)
        else: # undirected single edges
            seen=set()  # helper dict used to avoid duplicate edges
            for s,nbrs in G.adjacency_iter():
                nbr_edges=[ (u,d) for u,d in nbrs.items() if u not in seen]
                deg=len(nbr_edges)
                yield  make_str(s)+delimiter+"%i"%(deg)
                for u,d in nbr_edges:
                    if d is None:    
                        yield make_str(u)
                    else:   
                        yield make_str(u)+delimiter+make_str(d)
                seen.add(s)

@open_file(1,mode='wb')
def write_multiline_adjlist(G, path, delimiter=' ', 
                            comments='#', encoding = 'utf-8'):
    """ Write the graph G in multiline adjacency list format to path

    Parameters
    ----------
    G : NetworkX graph
    
    comments : string, optional
       Marker for comment lines

    delimiter : string, optional
       Separator for node labels 

    encoding : string, optional
       Text encoding. 

    Examples
    --------
    >>> G=nx.path_graph(4)
    >>> nx.write_multiline_adjlist(G,"test.adjlist")

    The path can be a file handle or a string with the name of the file. If a
    file handle is provided, it has to be opened in 'wb' mode.

    >>> fh=open("test.adjlist",'wb')
    >>> nx.write_multiline_adjlist(G,fh)

    Filenames ending in .gz or .bz2 will be compressed.

    >>> nx.write_multiline_adjlist(G,"test.adjlist.gz")

    See Also
    --------
    read_multiline_adjlist
    """
    import sys
    import time

    pargs=comments+" ".join(sys.argv)
    header = ("%s\n" % (pargs)
             + comments + " GMT %s\n" % (time.asctime(time.gmtime()))
             + comments + " %s\n" % (G.name))
    path.write(header.encode(encoding))

    for multiline in generate_multiline_adjlist(G, delimiter):
        multiline+='\n'
        path.write(multiline.encode(encoding))

def parse_multiline_adjlist(lines, comments = '#', delimiter = None,
                            create_using = None, nodetype = None,
                            edgetype = None):
    """Parse lines of a multiline adjacency list representation of a graph.

    Parameters
    ----------
    lines : list or iterator of strings
        Input data in multiline adjlist format

    create_using: NetworkX graph container       
       Use given NetworkX graph for holding nodes or edges.

    nodetype : Python type, optional
       Convert nodes to this type.  
       
    comments : string, optional
       Marker for comment lines

    delimiter : string, optional
       Separator for node labels.  The default is whitespace. 

    create_using: NetworkX graph container       
       Use given NetworkX graph for holding nodes or edges.


    Returns
    -------
    G: NetworkX graph
        The graph corresponding to the lines in multiline adjacency list format.

    Examples
    --------
    >>> lines = ['1 2',
    ...          "2 {'weight':3, 'name': 'Frodo'}",
    ...          "3 {}",
    ...          "2 1",
    ...          "5 {'weight':6, 'name': 'Saruman'}"]
    >>> G = nx.parse_multiline_adjlist(iter(lines), nodetype = int)
    >>> G.nodes()
    [1, 2, 3, 5]
    >>> G.edges(data = True)
    [(1, 2, {'name': 'Frodo', 'weight': 3}), (1, 3, {}), (2, 5, {'name': 'Saruman', 'weight': 6})]
    
    """
    from ast import literal_eval
    if create_using is None:
        G=nx.Graph()
    else:
        try:
            G=create_using
            G.clear()
        except:
            raise TypeError("Input graph is not a networkx graph type")

    for line in lines:
        p=line.find(comments)
        if p>=0:
            line = line[:p]
        if not line: continue
        try:
            (u,deg)=line.strip().split(delimiter)
            deg=int(deg)
        except:
            raise TypeError("Failed to read node and degree on line (%s)"%line)
        if nodetype is not None:
            try:
                u=nodetype(u)
            except:
                raise TypeError("Failed to convert node (%s) to type %s"\
                      %(u,nodetype))
        G.add_node(u)
        for i in range(deg):
            while True:
                try:
                    line = next(lines)
                except StopIteration:
                    msg = "Failed to find neighbor for node (%s)" % (u,)
                    raise TypeError(msg)
                p=line.find(comments)
                if p>=0:
                    line = line[:p]
                if line: break
            vlist=line.strip().split(delimiter)
            numb=len(vlist)
            if numb<1:
                continue # isolated node
            v=vlist.pop(0)
            data=''.join(vlist)
            if nodetype is not None:
                try:
                    v=nodetype(v)
                except:
                    raise TypeError(
                            "Failed to convert node (%s) to type %s"\
                                       %(v,nodetype))
            if edgetype is not None:
                try:
                    edgedata={'weight':edgetype(data)}
                except:
                    raise TypeError(
                            "Failed to convert edge data (%s) to type %s"\
                                    %(data, edgetype))
            else:
                try: # try to evaluate 
                    edgedata=literal_eval(data)
                except:
                    edgedata={}
            G.add_edge(u,v,attr_dict=edgedata)

    return G

@open_file(0,mode='rb')
def read_multiline_adjlist(path, comments="#", delimiter=None,
                           create_using=None,
                           nodetype=None, edgetype=None,
                           encoding = 'utf-8'):
    """Read graph in multi-line adjacency list format from path.

    Parameters
    ----------
    path : string or file
       Filename or file handle to read.
       Filenames ending in .gz or .bz2 will be uncompressed.

    create_using: NetworkX graph container       
       Use given NetworkX graph for holding nodes or edges.

    nodetype : Python type, optional
       Convert nodes to this type.  
       
    edgetype : Python type, optional
       Convert edge data to this type.

    comments : string, optional
       Marker for comment lines

    delimiter : string, optional
       Separator for node labels.  The default is whitespace. 

    create_using: NetworkX graph container       
       Use given NetworkX graph for holding nodes or edges.


    Returns
    -------
    G: NetworkX graph

    Examples
    --------
    >>> G=nx.path_graph(4)
    >>> nx.write_multiline_adjlist(G,"test.adjlist")
    >>> G=nx.read_multiline_adjlist("test.adjlist")

    The path can be a file or a string with the name of the file. If a
    file s provided, it has to be opened in 'rb' mode.

    >>> fh=open("test.adjlist", 'rb')
    >>> G=nx.read_multiline_adjlist(fh)

    Filenames ending in .gz or .bz2 will be compressed.

    >>> nx.write_multiline_adjlist(G,"test.adjlist.gz")
    >>> G=nx.read_multiline_adjlist("test.adjlist.gz")

    The optional nodetype is a function to convert node strings to nodetype.

    For example

    >>> G=nx.read_multiline_adjlist("test.adjlist", nodetype=int)

    will attempt to convert all nodes to integer type.

    The optional edgetype is a function to convert edge data strings to 
    edgetype.  

    >>> G=nx.read_multiline_adjlist("test.adjlist")

    The optional create_using parameter is a NetworkX graph container.
    The default is Graph(), an undirected graph.  To read the data as 
    a directed graph use

    >>> G=nx.read_multiline_adjlist("test.adjlist", create_using=nx.DiGraph())
    
    Notes
    -----
    This format does not store graph, node, or edge data.

    See Also
    --------
    write_multiline_adjlist
    """
    lines = (line.decode(encoding) for line in path)
    return parse_multiline_adjlist(lines, 
                                   comments = comments,
                                   delimiter = delimiter,
                                   create_using = create_using,
                                   nodetype = nodetype,
                                   edgetype = edgetype)


# fixture for nose tests
def teardown_module(module):
    import os
    os.unlink('test.adjlist')
    os.unlink('test.adjlist.gz')