Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 80ba68b

Browse files
authored
Implement google_matrix and binary operators (#62)
* Implement `google_matrix` and binary operators * Also implement `floyd_warshall_numpy` * Remove `floyd_warshall_numpy` from "core" (still in "nxapi")
1 parent 17f19ba commit 80ba68b

File tree

13 files changed

+401
-7
lines changed

13 files changed

+401
-7
lines changed

‎README.md

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -156,8 +156,17 @@ dispatch pattern shown above.
156156
- isolates
157157
- number_of_isolates
158158
- Link Analysis
159+
- google_matrix
159160
- hits
160161
- pagerank
162+
- Operators
163+
- compose
164+
- difference
165+
- disjoint_union
166+
- full_join
167+
- intersection
168+
- symmetric_difference
169+
- union
161170
- Reciprocity
162171
- overall_reciprocity
163172
- reciprocity
@@ -168,6 +177,7 @@ dispatch pattern shown above.
168177
- all_pairs_bellman_ford_path_length
169178
- all_pairs_shortest_path_length
170179
- floyd_warshall
180+
- floyd_warshall_numpy
171181
- floyd_warshall_predecessor_and_distance
172182
- has_path
173183
- negative_edge_cycle

‎graphblas_algorithms/algorithms/__init__.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,7 @@
1010
from .dominating import *
1111
from .isolate import *
1212
from .link_analysis import *
13+
from .operators import *
1314
from .reciprocity import *
1415
from .regular import *
1516
from .shortest_paths import *

‎graphblas_algorithms/algorithms/link_analysis/pagerank_alg.py

Lines changed: 65 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,12 @@
1-
from graphblas import Vector
1+
import numpy as np
2+
from graphblas import Matrix, Vector, binary, monoid
23
from graphblas.semiring import plus_first, plus_times
34

45
from graphblas_algorithms import Graph
56
from graphblas_algorithms.algorithms._helpers import is_converged
67
from graphblas_algorithms.algorithms.exceptions import ConvergenceFailure
78

8-
__all__ = ["pagerank"]
9+
__all__ = ["pagerank", "google_matrix"]
910

1011

1112
def pagerank(
@@ -98,3 +99,65 @@ def pagerank(
9899
x.name = name
99100
return x
100101
raise ConvergenceFailure(max_iter)
102+
103+
104+
def google_matrix(
105+
G: Graph,
106+
alpha=0.85,
107+
personalization=None,
108+
nodelist=None,
109+
dangling=None,
110+
name="google_matrix",
111+
) -> Matrix:
112+
A = G._A
113+
ids = G.list_to_ids(nodelist)
114+
if ids is not None:
115+
ids = np.array(ids, np.uint64)
116+
A = A[ids, ids].new(float, name=name)
117+
else:
118+
A = A.dup(float, name=name)
119+
N = A.nrows
120+
if N == 0:
121+
return A
122+
123+
# Personalization vector or scalar
124+
if personalization is None:
125+
p = 1.0 / N
126+
else:
127+
if ids is not None:
128+
personalization = personalization[ids].new(name="personalization")
129+
denom = personalization.reduce().get(0)
130+
if denom == 0:
131+
raise ZeroDivisionError("personalization sums to 0")
132+
p = (personalization / denom).new(mask=personalization.V, name="p")
133+
134+
if ids is None or len(ids) == len(G):
135+
nonempty_rows = G.get_property("any_rowwise+") # XXX: What about self-edges?
136+
else:
137+
nonempty_rows = A.reduce_rowwise(monoid.any).new(name="nonempty_rows")
138+
139+
is_dangling = nonempty_rows.nvals < N
140+
if is_dangling:
141+
empty_rows = (~nonempty_rows.S).new(name="empty_rows")
142+
if dangling is not None:
143+
if ids is not None:
144+
dangling = dangling[ids].new(name="dangling")
145+
dangling_weights = (1.0 / dangling.reduce().get(0) * dangling).new(
146+
mask=dangling.V, name="dangling_weights"
147+
)
148+
A << binary.first(empty_rows.outer(dangling_weights) | A)
149+
elif personalization is None:
150+
A << binary.first((p * empty_rows) | A)
151+
else:
152+
A << binary.first(empty_rows.outer(p) | A)
153+
154+
scale = A.reduce_rowwise(monoid.plus).new(float)
155+
scale << alpha / scale
156+
A << scale * A
157+
p *= 1 - alpha
158+
if personalization is None:
159+
# Add a scalar everywhere, which makes A dense
160+
A(binary.plus)[:, :] = p
161+
else:
162+
A << A + p
163+
return A
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
from .binary import *
Lines changed: 156 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,156 @@
1+
import numpy as np
2+
from graphblas import Matrix, binary, dtypes, unary
3+
4+
from ..exceptions import GraphBlasAlgorithmException
5+
6+
__all__ = [
7+
"compose",
8+
"difference",
9+
"disjoint_union",
10+
"full_join",
11+
"intersection",
12+
"symmetric_difference",
13+
"union",
14+
]
15+
16+
17+
def union(G, H, rename=(), *, name="union"):
18+
if G.is_multigraph() != H.is_multigraph():
19+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
20+
if G.is_multigraph():
21+
raise NotImplementedError("Not yet implemented for multigraphs")
22+
if rename:
23+
prefix = rename[0]
24+
if prefix is not None:
25+
G = type(G)(
26+
G._A, key_to_id={f"{prefix}{key}": val for key, val in G._key_to_id.items()}
27+
)
28+
if len(rename) > 1:
29+
prefix = rename[1]
30+
if prefix is not None:
31+
H = type(H)(
32+
H._A, key_to_id={f"{prefix}{key}": val for key, val in H._key_to_id.items()}
33+
)
34+
A = G._A
35+
B = H._A
36+
if not G._key_to_id.keys().isdisjoint(H._key_to_id.keys()):
37+
raise GraphBlasAlgorithmException("The node sets of the graphs are not disjoint.")
38+
C = Matrix(dtypes.unify(A.dtype, B.dtype), A.nrows + B.nrows, A.ncols + B.ncols, name=name)
39+
C[: A.nrows, : A.ncols] = A
40+
C[A.nrows :, A.ncols :] = B
41+
offset = A.nrows
42+
key_to_id = {key: val + offset for key, val in H._key_to_id.items()}
43+
key_to_id.update(G._key_to_id)
44+
return type(G)(C, key_to_id=key_to_id)
45+
46+
47+
def disjoint_union(G, H, *, name="disjoint_union"):
48+
if G.is_multigraph() != H.is_multigraph():
49+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
50+
if G.is_multigraph():
51+
raise NotImplementedError("Not yet implemented for multigraphs")
52+
A = G._A
53+
B = H._A
54+
C = Matrix(dtypes.unify(A.dtype, B.dtype), A.nrows + B.nrows, A.ncols + B.ncols, name=name)
55+
C[: A.nrows, : A.ncols] = A
56+
C[A.nrows :, A.ncols :] = B
57+
return type(G)(C)
58+
59+
60+
def intersection(G, H, *, name="intersection"):
61+
if G.is_multigraph() != H.is_multigraph():
62+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
63+
if G.is_multigraph():
64+
raise NotImplementedError("Not yet implemented for multigraphs")
65+
keys = sorted(G._key_to_id.keys() & H._key_to_id.keys(), key=G._key_to_id.__getitem__)
66+
ids = np.array(G.list_to_ids(keys), np.uint64)
67+
A = G._A[ids, ids].new()
68+
ids = np.array(H.list_to_ids(keys), np.uint64)
69+
B = H._A[ids, ids].new(dtypes.unify(A.dtype, H._A.dtype), mask=A.S, name=name)
70+
B << unary.one(B)
71+
return type(G)(B, key_to_id=dict(zip(keys, range(len(keys)))))
72+
73+
74+
def difference(G, H, *, name="difference"):
75+
if G.is_multigraph() != H.is_multigraph():
76+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
77+
if G.is_multigraph():
78+
raise NotImplementedError("Not yet implemented for multigraphs")
79+
if G._key_to_id.keys() != H._key_to_id.keys():
80+
raise GraphBlasAlgorithmException("Node sets of graphs not equal")
81+
A = G._A
82+
if G._key_to_id == H._key_to_id:
83+
B = H._A
84+
else:
85+
# Need to perform a permutation
86+
keys = sorted(G._key_to_id, key=G._key_to_id.__getitem__)
87+
ids = np.array(H.list_to_ids(keys), np.uint64)
88+
B = H._A[ids, ids].new()
89+
C = unary.one(A).new(mask=~B.S, name=name)
90+
return type(G)(C, key_to_id=G._key_to_id)
91+
92+
93+
def symmetric_difference(G, H, *, name="symmetric_difference"):
94+
if G.is_multigraph() != H.is_multigraph():
95+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
96+
if G.is_multigraph():
97+
raise NotImplementedError("Not yet implemented for multigraphs")
98+
if G._key_to_id.keys() != H._key_to_id.keys():
99+
raise GraphBlasAlgorithmException("Node sets of graphs not equal")
100+
A = G._A
101+
if G._key_to_id == H._key_to_id:
102+
B = H._A
103+
else:
104+
# Need to perform a permutation
105+
keys = sorted(G._key_to_id, key=G._key_to_id.__getitem__)
106+
ids = np.array(H.list_to_ids(keys), np.uint64)
107+
B = H._A[ids, ids].new()
108+
Mask = binary.pair[bool](A & B).new(name="mask")
109+
C = binary.pair(A | B, left_default=True, right_default=True).new(mask=~Mask.S, name=name)
110+
return type(G)(C, key_to_id=G._key_to_id)
111+
112+
113+
def compose(G, H, *, name="compose"):
114+
if G.is_multigraph() != H.is_multigraph():
115+
raise GraphBlasAlgorithmException("All graphs must be graphs or multigraphs.")
116+
if G.is_multigraph():
117+
raise NotImplementedError("Not yet implemented for multigraphs")
118+
A = G._A
119+
B = H._A
120+
if G._key_to_id.keys() == H._key_to_id.keys():
121+
if G._key_to_id != H._key_to_id:
122+
# Need to perform a permutation
123+
keys = sorted(G._key_to_id, key=G._key_to_id.__getitem__)
124+
ids = np.array(H.list_to_ids(keys), np.uint64)
125+
B = B[ids, ids].new()
126+
C = binary.second(A | B).new(name=name)
127+
key_to_id = G._key_to_id
128+
else:
129+
keys = sorted(G._key_to_id.keys() & H._key_to_id.keys(), key=G._key_to_id.__getitem__)
130+
B = H._A
131+
C = Matrix(
132+
dtypes.unify(A.dtype, B.dtype),
133+
A.nrows + B.nrows - len(keys),
134+
A.ncols + B.ncols - len(keys),
135+
name=name,
136+
)
137+
C[: A.nrows, : A.ncols] = A
138+
ids1 = np.array(G.list_to_ids(keys), np.uint64)
139+
ids2 = np.array(H.list_to_ids(keys), np.uint64)
140+
C[ids1, ids1] = B[ids2, ids2]
141+
newkeys = sorted(H._key_to_id.keys() - G._key_to_id.keys(), key=H._key_to_id.__getitem__)
142+
ids = np.array(H.list_to_ids(newkeys), np.uint64)
143+
C[A.nrows :, A.ncols :] = B[ids, ids]
144+
# Now make new `key_to_id`
145+
ids += A.nrows
146+
key_to_id = dict(zip(newkeys, ids.tolist()))
147+
key_to_id.update(G._key_to_id)
148+
return type(G)(C, key_to_id=key_to_id)
149+
150+
151+
def full_join(G, H, rename=(), *, name="full_join"):
152+
rv = union(G, H, rename, name=name)
153+
nrows, ncols = G._A.shape
154+
rv._A[:nrows, ncols:] = True
155+
rv._A[nrows:, :ncols] = True
156+
return rv

‎graphblas_algorithms/algorithms/shortest_paths/dense.py

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,18 @@
11
from graphblas import Matrix, Vector, binary, indexunary, replace, select
22
from graphblas.semiring import any_plus, any_second
33

4+
from ..exceptions import GraphBlasAlgorithmException
5+
46
__all__ = ["floyd_warshall", "floyd_warshall_predecessor_and_distance"]
57

68

79
def floyd_warshall(G, is_weighted=False):
810
return floyd_warshall_predecessor_and_distance(G, is_weighted, compute_predecessors=False)[1]
911

1012

11-
def floyd_warshall_predecessor_and_distance(G, is_weighted=False, *, compute_predecessors=True):
13+
def floyd_warshall_predecessor_and_distance(
14+
G, is_weighted=False, *, compute_predecessors=True, permutation=None
15+
):
1216
# By using `offdiag` instead of `G._A`, we ensure that D will not become dense.
1317
# Dense D may be better at times, but not including the diagonal will result in less work.
1418
# Typically, Floyd-Warshall algorithms sets the diagonal of D to 0 at the beginning.
@@ -19,6 +23,13 @@ def floyd_warshall_predecessor_and_distance(G, is_weighted=False, *, compute_pre
1923
nonempty_nodes = binary.pair(row_degrees & column_degrees).new(name="nonempty_nodes")
2024
else:
2125
A, nonempty_nodes = G.get_properties("U- degrees-")
26+
if permutation is not None:
27+
if len(permutation) != nonempty_nodes.size:
28+
raise GraphBlasAlgorithmException(
29+
"permutation must contain every node in G with no repeats."
30+
)
31+
A = A[permutation, permutation].new()
32+
nonempty_nodes = nonempty_nodes[permutation].new(name="nonempty_nodes")
2233

2334
if A.dtype == bool or not is_weighted:
2435
dtype = int

‎graphblas_algorithms/interface.py

Lines changed: 34 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,16 @@ class Dispatcher:
5151
number_of_isolates = nxapi.isolate.number_of_isolates
5252
# Link Analysis
5353
hits = nxapi.link_analysis.hits_alg.hits
54+
google_matrix = nxapi.link_analysis.pagerank_alg.google_matrix
5455
pagerank = nxapi.link_analysis.pagerank_alg.pagerank
56+
# Operators
57+
compose = nxapi.operators.binary.compose
58+
difference = nxapi.operators.binary.difference
59+
disjoint_union = nxapi.operators.binary.disjoint_union
60+
full_join = nxapi.operators.binary.full_join
61+
intersection = nxapi.operators.binary.intersection
62+
symmetric_difference = nxapi.operators.binary.symmetric_difference
63+
union = nxapi.operators.binary.union
5564
# Reciprocity
5665
overall_reciprocity = nxapi.overall_reciprocity
5766
reciprocity = nxapi.reciprocity
@@ -60,6 +69,7 @@ class Dispatcher:
6069
is_regular = nxapi.regular.is_regular
6170
# Shortest Paths
6271
floyd_warshall = nxapi.shortest_paths.dense.floyd_warshall
72+
floyd_warshall_numpy = nxapi.shortest_paths.dense.floyd_warshall_numpy
6373
floyd_warshall_predecessor_and_distance = (
6474
nxapi.shortest_paths.dense.floyd_warshall_predecessor_and_distance
6575
)
@@ -112,10 +122,14 @@ def convert_from_nx(graph, weight=None, *, name=None):
112122

113123
@staticmethod
114124
def convert_to_nx(obj, *, name=None):
125+
from graphblas import Matrix
126+
115127
from .classes import Graph
116128

117129
if isinstance(obj, Graph):
118130
obj = obj.to_networkx()
131+
elif isinstance(obj, Matrix):
132+
obj = obj.to_dense(fill_value=False)
119133
return obj
120134

121135
@staticmethod
@@ -127,8 +141,11 @@ def on_start_tests(items):
127141

128142
def key(testpath):
129143
filename, path = testpath.split(":")
130-
classname, testname = path.split(".")
131-
return (testname, frozenset({classname, filename}))
144+
*names, testname = path.split(".")
145+
if names:
146+
[classname] = names
147+
return (testname, frozenset({classname, filename}))
148+
return (testname, frozenset({filename}))
132149

133150
# Reasons to skip tests
134151
multi_attributed = "unable to handle multi-attributed graphs"
@@ -140,7 +157,22 @@ def key(testpath):
140157
key("test_mst.py:TestBoruvka.test_attributes"): multi_attributed,
141158
key("test_mst.py:TestBoruvka.test_weight_attribute"): multi_attributed,
142159
key("test_dense.py:TestFloyd.test_zero_weight"): multidigraph,
160+
key("test_dense_numpy.py:test_zero_weight"): multidigraph,
143161
key("test_weighted.py:TestBellmanFordAndGoldbergRadzik.test_multigraph"): multigraph,
162+
key("test_binary.py:test_compose_multigraph"): multigraph,
163+
key("test_binary.py:test_difference_multigraph_attributes"): multigraph,
164+
key("test_binary.py:test_disjoint_union_multigraph"): multigraph,
165+
key("test_binary.py:test_full_join_multigraph"): multigraph,
166+
key("test_binary.py:test_intersection_multigraph_attributes"): multigraph,
167+
key(
168+
"test_binary.py:test_intersection_multigraph_attributes_node_set_different"
169+
): multigraph,
170+
key("test_binary.py:test_symmetric_difference_multigraph"): multigraph,
171+
key("test_binary.py:test_union_attributes"): multi_attributed,
172+
# TODO: move failing assertion from `test_union_and_compose`
173+
key("test_binary.py:test_union_and_compose"): multi_attributed,
174+
key("test_binary.py:test_union_multigraph"): multigraph,
175+
key("test_vf2pp.py:test_custom_multigraph4_different_labels"): multigraph,
144176
}
145177
for item in items:
146178
kset = set(item.keywords)

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /