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
|
import collections
import rdflib
from rdflib import RDF
"""
RDF- and RDFlib-centric Graph utilities.
"""
def graph_to_dot(graph, dot):
"""
Turns graph into dot (graphviz graph drawing format) using pydot.
"""
import pydot
nodes = {}
for s, o in graph.subject_objects():
for i in s, o:
if i not in nodes.keys():
nodes[i] = i
for s, p, o in graph.triples((None, None, None)):
dot.add_edge(pydot.Edge(nodes[s], nodes[o], label=p))
def find_roots(graph, prop, roots=None):
"""
Find the roots in some sort of transitive hierarchy.
find_roots(graph, rdflib.RDFS.subClassOf)
will return a set of all roots of the sub-class hierarchy
Assumes triple of the form (child, prop, parent), i.e. the direction of
RDFS.subClassOf or SKOS.broader
"""
non_roots = set()
if roots is None:
roots = set()
for x, y in graph.subject_objects(prop):
non_roots.add(x)
if x in roots:
roots.remove(x)
if y not in non_roots:
roots.add(y)
return roots
def get_tree(graph,
root,
prop,
mapper=lambda x: x,
sortkey=None,
done=None,
dir='down'):
"""
Return a nested list/tuple structure representing the tree
built by the transitive property given, starting from the root given
i.e.
get_tree(graph,
rdflib.URIRef("http://xmlns.com/foaf/0.1/Person"),
rdflib.RDFS.subClassOf)
will return the structure for the subClassTree below person.
dir='down' assumes triple of the form (child, prop, parent),
i.e. the direction of RDFS.subClassOf or SKOS.broader
Any other dir traverses in the other direction
"""
if done is None:
done = set()
if root in done:
return
done.add(root)
tree = []
if dir == 'down':
branches = graph.subjects(prop, root)
else:
branches = graph.objects(root, prop)
for branch in branches:
t = get_tree(graph, branch, prop, mapper, sortkey, done, dir)
if t:
tree.append(t)
return (mapper(root), sorted(tree, key=sortkey))
VOID = rdflib.Namespace("http://rdfs.org/ns/void#")
DCTERMS = rdflib.Namespace("http://purl.org/dc/terms/")
FOAF = rdflib.Namespace("http://xmlns.com/foaf/0.1/")
def generateVoID(g, dataset=None, res=None, distinctForPartitions=True):
"""
Returns a new graph with a VoID description of the passed dataset
For more info on Vocabulary of Interlinked Datasets (VoID), see:
http://vocab.deri.ie/void
This only makes two passes through the triples (once to detect the types
of things)
The tradeoff is that lots of temporary structures are built up in memory
meaning lots of memory may be consumed :)
I imagine at least a few copies of your original graph.
the distinctForPartitions parameter controls whether
distinctSubjects/objects are tracked for each class/propertyPartition
this requires more memory again
"""
typeMap = collections.defaultdict(set)
classes = collections.defaultdict(set)
for e, c in g.subject_objects(RDF.type):
classes[c].add(e)
typeMap[e].add(c)
triples = 0
subjects = set()
objects = set()
properties = set()
classCount = collections.defaultdict(int)
propCount = collections.defaultdict(int)
classProps = collections.defaultdict(set)
classObjects = collections.defaultdict(set)
propSubjects = collections.defaultdict(set)
propObjects = collections.defaultdict(set)
for s, p, o in g:
triples += 1
subjects.add(s)
properties.add(p)
objects.add(o)
# class partitions
if s in typeMap:
for c in typeMap[s]:
classCount[c] += 1
if distinctForPartitions:
classObjects[c].add(o)
classProps[c].add(p)
# property partitions
propCount[p] += 1
if distinctForPartitions:
propObjects[p].add(o)
propSubjects[p].add(s)
if not dataset:
dataset = rdflib.URIRef("http://example.org/Dataset")
if not res:
res = rdflib.Graph()
res.add((dataset, RDF.type, VOID.Dataset))
# basic stats
res.add((dataset, VOID.triples, rdflib.Literal(triples)))
res.add((dataset, VOID.classes, rdflib.Literal(len(classes))))
res.add((dataset, VOID.distinctObjects, rdflib.Literal(len(objects))))
res.add((dataset, VOID.distinctSubjects, rdflib.Literal(len(subjects))))
res.add((dataset, VOID.properties, rdflib.Literal(len(properties))))
for i, c in enumerate(classes):
part = rdflib.URIRef(dataset + "_class%d" % i)
res.add((dataset, VOID.classPartition, part))
res.add((part, RDF.type, VOID.Dataset))
res.add((part, VOID.triples, rdflib.Literal(classCount[c])))
res.add((part, VOID.classes, rdflib.Literal(1)))
res.add((part, VOID["class"], c))
res.add((part, VOID.entities, rdflib.Literal(len(classes[c]))))
res.add((part, VOID.distinctSubjects, rdflib.Literal(len(classes[c]))))
if distinctForPartitions:
res.add(
(part, VOID.properties, rdflib.Literal(len(classProps[c]))))
res.add((part, VOID.distinctObjects,
rdflib.Literal(len(classObjects[c]))))
for i, p in enumerate(properties):
part = rdflib.URIRef(dataset + "_property%d" % i)
res.add((dataset, VOID.propertyPartition, part))
res.add((part, RDF.type, VOID.Dataset))
res.add((part, VOID.triples, rdflib.Literal(propCount[p])))
res.add((part, VOID.properties, rdflib.Literal(1)))
res.add((part, VOID.property, p))
if distinctForPartitions:
entities = 0
propClasses = set()
for s in propSubjects[p]:
if s in typeMap:
entities += 1
for c in typeMap[s]:
propClasses.add(c)
res.add((part, VOID.entities, rdflib.Literal(entities)))
res.add((part, VOID.classes, rdflib.Literal(len(propClasses))))
res.add((part, VOID.distinctSubjects,
rdflib.Literal(len(propSubjects[p]))))
res.add((part, VOID.distinctObjects,
rdflib.Literal(len(propObjects[p]))))
return res, dataset
|