def test_graph2(): sym = True adj = np.array([ [0, 1, 0, 16], [2, 4, 0, 14], [4, 5, 0, 4], [0, 2, 1, 13], [2, 1, 1, 4], [3, 5, 1, 20], [1, 3, 2, 12], [3, 2, 2, 9], [4, 3, 2, 7] ]) shape = (6, 6, 3) G = make_graph(adj[:,:3], shape, values=adj[:,3], sym=sym, display=False) G.sources = np.repeat(np.arange(G.N), np.diff(G.csr.indptr)) G.targets = G.csr.indices % G.N cost_vec = G.indeg_vec print "Original graph:\n", G # Successive shortest path algorithm s, p, o = 0, 2, 5 expect = 2.88888888889 mincostflow = succ_shortest_path(G, cost_vec, s, p, o) print mincostflow assert np.allclose(mincostflow.flow, expect) print 'Recovered max-flow edges (i, j, r, flow)..' adj = np.zeros((len(mincostflow.edges), 4)) for i, (k, v) in enumerate(mincostflow.edges.iteritems()): adj[i, :] = np.array([k[0], k[1], k[2], v]) adj = adj[np.lexsort((adj[:,2], adj[:,1], adj[:,0])),:] print adj print ''
def test_graph1():
sym = True
adj = np.array([[0, 2, 0, 10], [1, 2, 0, 30], [0, 1, 1, 20], [1, 3, 1, 10],
[2, 3, 1, 20]])
shape = (4, 4, 2)
G = make_graph(adj[:, :3], shape, values=adj[:, 3], sym=sym, display=False)
G.sources = np.repeat(np.arange(G.N), np.diff(G.csr.indptr))
G.targets = G.csr.indices % G.N
cost_vec = G.indeg_vec
print("Original graph:\n", G)
# Successive shortest path algorithm
s, p, o = 0, 1, 3
expect = 6.42857142857
mincostflow = succ_shortest_path(G, cost_vec, s, p, o)
print(mincostflow)
assert np.allclose(mincostflow.flow, expect)
print('Recovered max-flow edges (i, j, r, flow)..')
adj = np.zeros((len(mincostflow.edges), 4))
for i, (k, v) in enumerate(mincostflow.edges.items()):
adj[i, :] = np.array([k[0], k[1], k[2], v])
adj = adj[np.lexsort((adj[:, 2], adj[:, 1], adj[:, 0])), :]
print(adj)
print('')
def test_dbpedia():
dirpath = abspath(expanduser('./data/kg/_undir/'))
shape = (6060993, 6060993, 663)
G = Graph.reconstruct(dirpath, shape, sym=True)
cost_vec = np.log(G.indeg_vec)
s, p, o = 2145431, 178, 459128 # Gravity, Alfonso Cuarón
mincostflow = succ_shortest_path(G, cost_vec, s, p, o)
print mincostflow
def compute_mincostflow(G, relsim, subs, preds, objs, flowfile):
"""
Parameters:
-----------
G: rgraph
See `datastructures`.
relsim: ndarray
A square matrix containing relational similarity scores.
subs, preds, objs: sequence
Sequences representing the subject, predicate and object of
input triples.
flowfile: str
Absolute path of the file where flow will be stored as JSON,
one line per triple.
Returns:
--------
mincostflows: sequence
A sequence containing total flow for each triple.
times: sequence
Times taken to compute stream of each triple.
"""
# take graph backup
G_bak = {
'data': G.csr.data.copy(),
'indices': G.csr.indices.copy(),
'indptr': G.csr.indptr.copy()
}
cost_vec_bak = np.log(G.indeg_vec).copy()
# some set up
G.sources = np.repeat(np.arange(G.N), np.diff(G.csr.indptr))
G.targets = G.csr.indices % G.N
cost_vec = cost_vec_bak.copy()
indegsim = weighted_degree(G.indeg_vec, weight=WTFN)
specificity_wt = indegsim[G.targets] # specificity
relations = (G.csr.indices - G.targets) / G.N
mincostflows, times = [], []
with open(flowfile, 'w', 0) as ff:
for idx, (s, p, o) in enumerate(zip(subs, preds, objs)):
s, p, o = [int(x) for x in (s, p, o)]
ts = time()
print '{}. Working on {} .. '.format(idx + 1, (s, p, o)),
sys.stdout.flush()
# set weights
relsimvec = np.array(relsim[p, :]) # specific to predicate p
relsim_wt = relsimvec[relations]
G.csr.data = np.multiply(relsim_wt, specificity_wt)
# compute
mcflow = succ_shortest_path(G,
cost_vec,
s,
p,
o,
return_flow=False,
npaths=5)
mincostflows.append(mcflow.flow)
ff.write(json.dumps(mcflow.stream) + '\n')
tend = time()
times.append(tend - ts)
print 'mincostflow: {:.5f}, #paths: {}, time: {:.2f}s.'.format(
mcflow.flow, len(mcflow.stream['paths']), tend - ts)
# reset state of the graph
np.copyto(G.csr.data, G_bak['data'])
np.copyto(G.csr.indices, G_bak['indices'])
np.copyto(G.csr.indptr, G_bak['indptr'])
np.copyto(cost_vec, cost_vec_bak)
return mincostflows, times
