def recalculate(self, cluster_set):
'''
Constructs probability matrix. If use_cache is true, it will
try to load old computations from the database. If save cache
is true it will save the current results into the database.
@param cluster_set: A cluster set object, used to initialize
the matrix.
'''
last_cleaned = 0
old_matrix = self._bib_matrix
cached_bibs = self.__get_up_to_date_bibs()
have_cached_bibs = bool(cached_bibs)
self._bib_matrix = Bib_matrix(cluster_set)
ncl = cluster_set.num_all_bibs
expected = ((ncl * (ncl - 1)) / 2)
if expected == 0:
expected = 1
cur_calc, opti, prints_counter = 0, 0, 0
for cl1 in cluster_set.clusters:
if cur_calc + opti - prints_counter > 100000:
update_status(
(float(opti) + cur_calc) / expected,
"Prob matrix: calc %d, opti %d." % (cur_calc, opti))
prints_counter = cur_calc + opti
#clean caches
if cur_calc - last_cleaned > 2000000:
clear_comparison_caches()
last_cleaned = cur_calc
for cl2 in cluster_set.clusters:
if id(cl1) < id(cl2) and not cl1.hates(cl2):
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if have_cached_bibs and bib1 in cached_bibs and bib2 in cached_bibs:
val = old_matrix[bib1, bib2]
if not val:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
else:
opti += 1
if bconfig.DEBUG_CHECKS:
assert _debug_is_eq_v(
val,
compare_bibrefrecs(bib1, bib2))
else:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
clear_comparison_caches()
update_status_final("Matrix done. %d calc, %d opt." % (cur_calc, opti))
def recalculate(self, cluster_set):
'''
Constructs probability matrix. If use_cache is true, it will
try to load old computations from the database. If save cache
is true it will save the current results into the database.
@param cluster_set: A cluster set object, used to initialize
the matrix.
'''
last_cleaned = 0
old_matrix = self._bib_matrix
cached_bibs = self.__get_up_to_date_bibs()
have_cached_bibs = bool(cached_bibs)
self._bib_matrix = Bib_matrix(cluster_set)
ncl = cluster_set.num_all_bibs
expected = ((ncl * (ncl - 1)) / 2)
if expected == 0:
expected = 1
cur_calc, opti, prints_counter = 0, 0, 0
for cl1 in cluster_set.clusters:
if cur_calc+opti - prints_counter > 100000:
update_status((float(opti) + cur_calc) / expected, "Prob matrix: calc %d, opti %d." % (cur_calc, opti))
prints_counter = cur_calc+opti
#clean caches
if cur_calc - last_cleaned > 2000000:
clear_comparison_caches()
last_cleaned = cur_calc
for cl2 in cluster_set.clusters:
if id(cl1) < id(cl2) and not cl1.hates(cl2):
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if have_cached_bibs and bib1 in cached_bibs and bib2 in cached_bibs:
val = old_matrix[bib1, bib2]
if not val:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
else:
opti += 1
if bconfig.DEBUG_CHECKS:
assert _debug_is_eq_v(val, compare_bibrefrecs(bib1, bib2))
else:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
clear_comparison_caches()
update_status_final("Matrix done. %d calc, %d opt." % (cur_calc, opti))
def __init__(self):
self._bib_matrix = Bib_matrix()
class ProbabilityMatrix(object):
'''
This class contains and maintains the comparison
between all virtual authors. It is able to write
and read from the database and update the results.
'''
def __init__(self):
self._bib_matrix = Bib_matrix()
def load(self, lname, load_map=True, load_matrix=True):
update_status(0., "Loading probability matrix...")
self._bib_matrix.load(lname, load_map, load_matrix)
update_status_final("Probability matrix loaded.")
def store(self, name):
update_status(0., "Saving probability matrix...")
self._bib_matrix.store(name)
update_status_final("Probability matrix saved.")
def __getitem__(self, bibs):
return self._bib_matrix[bibs[0], bibs[1]]
def __get_up_to_date_bibs(self):
return frozenset(
filter_modified_record_ids(self._bib_matrix.get_keys(),
self._bib_matrix.creation_time))
def is_up_to_date(self, cluster_set):
return self.__get_up_to_date_bibs() >= frozenset(
cluster_set.all_bibs())
def recalculate(self, cluster_set):
'''
Constructs probability matrix. If use_cache is true, it will
try to load old computations from the database. If save cache
is true it will save the current results into the database.
@param cluster_set: A cluster set object, used to initialize
the matrix.
'''
last_cleaned = 0
old_matrix = self._bib_matrix
cached_bibs = self.__get_up_to_date_bibs()
have_cached_bibs = bool(cached_bibs)
self._bib_matrix = Bib_matrix(cluster_set)
ncl = cluster_set.num_all_bibs
expected = ((ncl * (ncl - 1)) / 2)
if expected == 0:
expected = 1
cur_calc, opti, prints_counter = 0, 0, 0
for cl1 in cluster_set.clusters:
if cur_calc + opti - prints_counter > 100000:
update_status(
(float(opti) + cur_calc) / expected,
"Prob matrix: calc %d, opti %d." % (cur_calc, opti))
prints_counter = cur_calc + opti
#clean caches
if cur_calc - last_cleaned > 2000000:
clear_comparison_caches()
last_cleaned = cur_calc
for cl2 in cluster_set.clusters:
if id(cl1) < id(cl2) and not cl1.hates(cl2):
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if have_cached_bibs and bib1 in cached_bibs and bib2 in cached_bibs:
val = old_matrix[bib1, bib2]
if not val:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
else:
opti += 1
if bconfig.DEBUG_CHECKS:
assert _debug_is_eq_v(
val,
compare_bibrefrecs(bib1, bib2))
else:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
clear_comparison_caches()
update_status_final("Matrix done. %d calc, %d opt." % (cur_calc, opti))
def __init__(self):
self._bib_matrix = Bib_matrix()
class ProbabilityMatrix(object):
'''
This class contains and maintains the comparison
between all virtual authors. It is able to write
and read from the database and update the results.
'''
def __init__(self):
self._bib_matrix = Bib_matrix()
def load(self, lname, load_map=True, load_matrix=True):
update_status(0., "Loading probability matrix...")
self._bib_matrix.load(lname, load_map, load_matrix)
update_status_final("Probability matrix loaded.")
def store(self, name):
update_status(0., "Saving probability matrix...")
self._bib_matrix.store(name)
update_status_final("Probability matrix saved.")
def __getitem__(self, bibs):
return self._bib_matrix[bibs[0], bibs[1]]
def __get_up_to_date_bibs(self):
return frozenset(filter_modified_record_ids(
self._bib_matrix.get_keys(),
self._bib_matrix.creation_time))
def is_up_to_date(self, cluster_set):
return self.__get_up_to_date_bibs() >= frozenset(cluster_set.all_bibs())
def recalculate(self, cluster_set):
'''
Constructs probability matrix. If use_cache is true, it will
try to load old computations from the database. If save cache
is true it will save the current results into the database.
@param cluster_set: A cluster set object, used to initialize
the matrix.
'''
last_cleaned = 0
old_matrix = self._bib_matrix
cached_bibs = self.__get_up_to_date_bibs()
have_cached_bibs = bool(cached_bibs)
self._bib_matrix = Bib_matrix(cluster_set)
ncl = cluster_set.num_all_bibs
expected = ((ncl * (ncl - 1)) / 2)
if expected == 0:
expected = 1
cur_calc, opti, prints_counter = 0, 0, 0
for cl1 in cluster_set.clusters:
if cur_calc+opti - prints_counter > 100000:
update_status((float(opti) + cur_calc) / expected, "Prob matrix: calc %d, opti %d." % (cur_calc, opti))
prints_counter = cur_calc+opti
#clean caches
if cur_calc - last_cleaned > 2000000:
clear_comparison_caches()
last_cleaned = cur_calc
for cl2 in cluster_set.clusters:
if id(cl1) < id(cl2) and not cl1.hates(cl2):
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if have_cached_bibs and bib1 in cached_bibs and bib2 in cached_bibs:
val = old_matrix[bib1, bib2]
if not val:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
else:
opti += 1
if bconfig.DEBUG_CHECKS:
assert _debug_is_eq_v(val, compare_bibrefrecs(bib1, bib2))
else:
cur_calc += 1
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
clear_comparison_caches()
update_status_final("Matrix done. %d calc, %d opt." % (cur_calc, opti))