Spaces:
Running
Running
File size: 8,690 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 |
"""
*****
Pajek
*****
Read graphs in Pajek format.
This implementation handles directed and undirected graphs including
those with self loops and parallel edges.
Format
------
See http://vlado.fmf.uni-lj.si/pub/networks/pajek/doc/draweps.htm
for format information.
"""
import warnings
import networkx as nx
from networkx.utils import open_file
__all__ = ["read_pajek", "parse_pajek", "generate_pajek", "write_pajek"]
def generate_pajek(G):
"""Generate lines in Pajek graph format.
Parameters
----------
G : graph
A Networkx graph
References
----------
See http://vlado.fmf.uni-lj.si/pub/networks/pajek/doc/draweps.htm
for format information.
"""
if G.name == "":
name = "NetworkX"
else:
name = G.name
# Apparently many Pajek format readers can't process this line
# So we'll leave it out for now.
# yield '*network %s'%name
# write nodes with attributes
yield f"*vertices {G.order()}"
nodes = list(G)
# make dictionary mapping nodes to integers
nodenumber = dict(zip(nodes, range(1, len(nodes) + 1)))
for n in nodes:
# copy node attributes and pop mandatory attributes
# to avoid duplication.
na = G.nodes.get(n, {}).copy()
x = na.pop("x", 0.0)
y = na.pop("y", 0.0)
try:
id = int(na.pop("id", nodenumber[n]))
except ValueError as err:
err.args += (
(
"Pajek format requires 'id' to be an int()."
" Refer to the 'Relabeling nodes' section."
),
)
raise
nodenumber[n] = id
shape = na.pop("shape", "ellipse")
s = " ".join(map(make_qstr, (id, n, x, y, shape)))
# only optional attributes are left in na.
for k, v in na.items():
if isinstance(v, str) and v.strip() != "":
s += f" {make_qstr(k)} {make_qstr(v)}"
else:
warnings.warn(
f"Node attribute {k} is not processed. {('Empty attribute' if isinstance(v, str) else 'Non-string attribute')}."
)
yield s
# write edges with attributes
if G.is_directed():
yield "*arcs"
else:
yield "*edges"
for u, v, edgedata in G.edges(data=True):
d = edgedata.copy()
value = d.pop("weight", 1.0) # use 1 as default edge value
s = " ".join(map(make_qstr, (nodenumber[u], nodenumber[v], value)))
for k, v in d.items():
if isinstance(v, str) and v.strip() != "":
s += f" {make_qstr(k)} {make_qstr(v)}"
else:
warnings.warn(
f"Edge attribute {k} is not processed. {('Empty attribute' if isinstance(v, str) else 'Non-string attribute')}."
)
yield s
@open_file(1, mode="wb")
def write_pajek(G, path, encoding="UTF-8"):
"""Write graph in Pajek format to path.
Parameters
----------
G : graph
A Networkx graph
path : file or string
File or filename to write.
Filenames ending in .gz or .bz2 will be compressed.
Examples
--------
>>> G = nx.path_graph(4)
>>> nx.write_pajek(G, "test.net")
Warnings
--------
Optional node attributes and edge attributes must be non-empty strings.
Otherwise it will not be written into the file. You will need to
convert those attributes to strings if you want to keep them.
References
----------
See http://vlado.fmf.uni-lj.si/pub/networks/pajek/doc/draweps.htm
for format information.
"""
for line in generate_pajek(G):
line += "\n"
path.write(line.encode(encoding))
@open_file(0, mode="rb")
@nx._dispatch(graphs=None)
def read_pajek(path, encoding="UTF-8"):
"""Read graph in Pajek format from path.
Parameters
----------
path : file or string
File or filename to write.
Filenames ending in .gz or .bz2 will be uncompressed.
Returns
-------
G : NetworkX MultiGraph or MultiDiGraph.
Examples
--------
>>> G = nx.path_graph(4)
>>> nx.write_pajek(G, "test.net")
>>> G = nx.read_pajek("test.net")
To create a Graph instead of a MultiGraph use
>>> G1 = nx.Graph(G)
References
----------
See http://vlado.fmf.uni-lj.si/pub/networks/pajek/doc/draweps.htm
for format information.
"""
lines = (line.decode(encoding) for line in path)
return parse_pajek(lines)
@nx._dispatch(graphs=None)
def parse_pajek(lines):
"""Parse Pajek format graph from string or iterable.
Parameters
----------
lines : string or iterable
Data in Pajek format.
Returns
-------
G : NetworkX graph
See Also
--------
read_pajek
"""
import shlex
# multigraph=False
if isinstance(lines, str):
lines = iter(lines.split("\n"))
lines = iter([line.rstrip("\n") for line in lines])
G = nx.MultiDiGraph() # are multiedges allowed in Pajek? assume yes
labels = [] # in the order of the file, needed for matrix
while lines:
try:
l = next(lines)
except: # EOF
break
if l.lower().startswith("*network"):
try:
label, name = l.split(None, 1)
except ValueError:
# Line was not of the form: *network NAME
pass
else:
G.graph["name"] = name
elif l.lower().startswith("*vertices"):
nodelabels = {}
l, nnodes = l.split()
for i in range(int(nnodes)):
l = next(lines)
try:
splitline = [
x.decode("utf-8") for x in shlex.split(str(l).encode("utf-8"))
]
except AttributeError:
splitline = shlex.split(str(l))
id, label = splitline[0:2]
labels.append(label)
G.add_node(label)
nodelabels[id] = label
G.nodes[label]["id"] = id
try:
x, y, shape = splitline[2:5]
G.nodes[label].update(
{"x": float(x), "y": float(y), "shape": shape}
)
except:
pass
extra_attr = zip(splitline[5::2], splitline[6::2])
G.nodes[label].update(extra_attr)
elif l.lower().startswith("*edges") or l.lower().startswith("*arcs"):
if l.lower().startswith("*edge"):
# switch from multidigraph to multigraph
G = nx.MultiGraph(G)
if l.lower().startswith("*arcs"):
# switch to directed with multiple arcs for each existing edge
G = G.to_directed()
for l in lines:
try:
splitline = [
x.decode("utf-8") for x in shlex.split(str(l).encode("utf-8"))
]
except AttributeError:
splitline = shlex.split(str(l))
if len(splitline) < 2:
continue
ui, vi = splitline[0:2]
u = nodelabels.get(ui, ui)
v = nodelabels.get(vi, vi)
# parse the data attached to this edge and put in a dictionary
edge_data = {}
try:
# there should always be a single value on the edge?
w = splitline[2:3]
edge_data.update({"weight": float(w[0])})
except:
pass
# if there isn't, just assign a 1
# edge_data.update({'value':1})
extra_attr = zip(splitline[3::2], splitline[4::2])
edge_data.update(extra_attr)
# if G.has_edge(u,v):
# multigraph=True
G.add_edge(u, v, **edge_data)
elif l.lower().startswith("*matrix"):
G = nx.DiGraph(G)
adj_list = (
(labels[row], labels[col], {"weight": int(data)})
for (row, line) in enumerate(lines)
for (col, data) in enumerate(line.split())
if int(data) != 0
)
G.add_edges_from(adj_list)
return G
def make_qstr(t):
"""Returns the string representation of t.
Add outer double-quotes if the string has a space.
"""
if not isinstance(t, str):
t = str(t)
if " " in t:
t = f'"{t}"'
return t
|