File: 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 (314 lines) | stat: -rw-r--r-- 8,553 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
# -*- coding: utf-8 -*-
"""
**************
Adjacency List
**************
Read and write NetworkX graphs as adjacency lists.

Adjacency list format is useful for graphs without data associated
with nodes or edges and for nodes that can be meaningfully represented 
as strings.

Format
------
The adjacency list format consists of lines with node labels.  The
first label in a line is the source node.  Further labels in the line
are considered target nodes and are added to the graph along with an edge
between the source node and target node.

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):: 

     a b c # source target target
     d 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_adjlist',
           'write_adjlist',
           'parse_adjlist',
           'read_adjlist']

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


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

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

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

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

    See Also
    --------
    write_adjlist, read_adjlist

    """
    directed=G.is_directed()
    seen=set()
    for s,nbrs in G.adjacency_iter():
        line = make_str(s)+delimiter
        for t,data in nbrs.items():
            if not directed and t in seen:
                continue
            if G.is_multigraph():
                for d in data.values():
                    line += make_str(t) + delimiter
            else:
                line += make_str(t) + delimiter
        if not directed:
            seen.add(s)
        yield line

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


    Parameters
    ----------
    G : NetworkX graph
    
    path : string or file
       Filename or file handle for data output.
       Filenames ending in .gz or .bz2 will be compressed.

    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_adjlist(G,"test.adjlist")

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

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

    Notes
    -----
    This format does not store graph, node, or edge data.

    See Also
    --------
    read_adjlist, generate_adjlist
    """
    import sys
    import time
    pargs=comments + " ".join(sys.argv) + '\n'
    header = (pargs
             + comments + " GMT %s\n" % (time.asctime(time.gmtime()))
             + comments + " %s\n" % (G.name))
    path.write(header.encode(encoding))

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


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

    Parameters
    ----------
    lines : list or iterator of strings
        Input data in 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 adjacency list format.

    Examples
    --------
    >>> lines = ['1 2 5',
    ...          '2 3 4',
    ...          '3 5',
    ...          '4',
    ...          '5']
    >>> G = nx.parse_adjlist(lines, nodetype = int)
    >>> G.nodes()
    [1, 2, 3, 4, 5]
    >>> G.edges()
    [(1, 2), (1, 5), (2, 3), (2, 4), (3, 5)]

    See Also
    --------
    read_adjlist
    
    """
    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 len(line):
            continue
        vlist=line.strip().split(delimiter)
        u=vlist.pop(0)
        # convert types
        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)
        if nodetype is not None:
            try:
                vlist=map(nodetype,vlist)
            except:
                raise TypeError("Failed to convert nodes (%s) to type %s"\
                                    %(','.join(vlist),nodetype))
        G.add_edges_from([(u, v) for v in vlist])
    return G

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

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

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

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

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

    >>> nx.write_adjlist(G,"test.adjlist.gz")
    >>> G=nx.read_adjlist("test.adjlist.gz")

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

    For example

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

    will attempt to convert all nodes to integer type.

    Since nodes must be hashable, the function nodetype must return hashable
    types (e.g. int, float, str, frozenset - or tuples of those, etc.) 

    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_adjlist("test.adjlist", create_using=nx.DiGraph())

    Notes
    -----
    This format does not store graph or node data.

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

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