def wedge(cluster_set, report_cluster_status=False, force_wedge_thrsh=False):
# The lower bound of the edges being processed by the wedge algorithm.
global edge_cut_prob
global wedge_thrsh
if not force_wedge_thrsh:
edge_cut_prob = bconfig.WEDGE_THRESHOLD / 3.
wedge_thrsh = bconfig.WEDGE_THRESHOLD
else:
edge_cut_prob = force_wedge_thrsh / 3.
wedge_thrsh = force_wedge_thrsh
matr = ProbabilityMatrix()
matr.load(cluster_set.last_name)
convert_cluster_set(cluster_set, matr)
del matr # be sure that this is the last reference!
do_wedge(cluster_set)
report = []
if bconfig.DEBUG_WEDGE_PRINT_FINAL_CLUSTER_COMPATIBILITIES or report_cluster_status:
msg = []
for cl1 in cluster_set.clusters:
for cl2 in cluster_set.clusters:
if cl2 > cl1:
id1 = cluster_set.clusters.index(cl1)
id2 = cluster_set.clusters.index(cl2)
c12 = _compare_to(cl1,cl2)
c21 = _compare_to(cl2,cl1)
report.append((id1,id2,c12+c21))
msg.append( ' %s vs %s : %s + %s = %s -- %s' % (id1, id2, c12, c21, c12+c21, cl1.hates(cl2)))
msg = 'Wedge final clusters for %s: \n' % str(wedge_thrsh) + '\n'.join(msg)
if not bconfig.DEBUG_WEDGE_OUTPUT and bconfig.DEBUG_WEDGE_PRINT_FINAL_CLUSTER_COMPATIBILITIES:
print
print msg
print
wedge_print(msg)
restore_cluster_set(cluster_set)
if bconfig.DEBUG_CHECKS:
assert cluster_set._debug_test_hate_relation()
assert cluster_set._debug_duplicated_recs()
if report_cluster_status:
destfile = '/tmp/baistats/cluster_status_report_pid_%s_lastname_%s_thrsh_%s' % (str(PID()),str(cluster_set.last_name),str(wedge_thrsh))
f = open(destfile, 'w')
SER.dump([wedge_thrsh,cluster_set.last_name,report,cluster_set.num_all_bibs],f)
f.close()
gc.collect()
def wedge(cluster_set):
matr = ProbabilityMatrix()
matr.load(cluster_set.last_name)
convert_cluster_set(cluster_set, matr)
del matr # be sure that this is the last reference!
do_wedge(cluster_set)
restore_cluster_set(cluster_set)
if bconfig.DEBUG_CHECKS:
assert cluster_set._debug_test_hate_relation()
assert cluster_set._debug_duplicated_recs()
def wedge(cluster_set):
matr = ProbabilityMatrix()
matr.load(cluster_set.last_name)
convert_cluster_set(cluster_set, matr)
del matr # be sure that this is the last reference!
do_wedge(cluster_set)
restore_cluster_set(cluster_set)
if bconfig.DEBUG_CHECKS:
assert cluster_set._debug_test_hate_relation()
assert cluster_set._debug_duplicated_recs()
