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 = 0, 0
for cl1 in cluster_set.clusters:
update_status((float(opti) + cur_calc) / expected,
"Prob matrix: calc %d, opti %d." % (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 = 0, 0
for cl1 in cluster_set.clusters:
update_status((float(opti) + cur_calc) / expected, "Prob matrix: calc %d, opti %d." % (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,
cluster_set,
last_name="",
cached=[],
use_cache=False,
save_cache=False):
'''
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.
@param last_name: A string which defines the current cluster
of names. It is used only if use_cache or save_cache is true.
@param cached: A list with the bibs, which are not touched
since last save.
'''
self._bib_matrix = self.bib_matrix(cluster_set)
old_matrix = self.bib_matrix()
if use_cache and probability_table_exists():
old_matrix.load(last_name)
elif cached:
raise AssertionError("You cannot have cached"
"results and empty table!")
for cl1 in cluster_set.clusters:
for cl2 in cluster_set.clusters:
if id(cl1) != id(cl2) and cl1.hates(cl2) == False:
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if bib1 in cached and bib2 in cached:
val = old_matrix[bib1, bib2]
if val == None:
val = compare_bibrefrecs(bib1, bib2)
else:
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
if save_cache:
if not probability_table_exists():
create_probability_table()
self._bib_matrix.store(last_name)
def __init__(self, cluster_set, last_name="", cached = [],
use_cache = False, save_cache = False):
'''
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.
@param last_name: A string which defines the current cluster
of names. It is used only if use_cache or save_cache is true.
@param cached: A list with the bibs, which are not touched
since last save.
'''
self._bib_matrix = self.bib_matrix(cluster_set)
old_matrix = self.bib_matrix()
if use_cache and probability_table_exists():
old_matrix.load(last_name)
elif cached:
raise AssertionError("You cannot have cached"
"results and empty table!")
for cl1 in cluster_set.clusters:
for cl2 in cluster_set.clusters:
if id(cl1) != id(cl2) and cl1.hates(cl2) == False:
for bib1 in cl1.bibs:
for bib2 in cl2.bibs:
if bib1 in cached and bib2 in cached:
val = old_matrix[bib1, bib2]
if val == None:
val = compare_bibrefrecs(bib1, bib2)
else:
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
if save_cache:
if not probability_table_exists():
create_probability_table()
self._bib_matrix.store(last_name)
def __init__(self, cluster_set, use_cache=False, save_cache=False):
'''
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.
'''
def check_for_cleaning(cur_calc):
if cur_calc % 10000000 == 0:
clear_comparison_caches()
self._bib_matrix = bib_matrix(cluster_set)
old_matrix = bib_matrix()
ncl = sum(len(cl.bibs) for cl in cluster_set.clusters)
expected = ((ncl * (ncl - 1)) / 2)
if expected == 0:
expected = 1
if use_cache and old_matrix.load(cluster_set.last_name):
cached_bibs = set(filter_modified_record_ids(
old_matrix.get_keys(),
old_matrix.creation_time))
else:
cached_bibs = set()
if save_cache:
creation_time = get_sql_time()
cur_calc, opti = 0, 0
for cl1 in cluster_set.clusters:
update_status((float(opti) + cur_calc) / expected, "Prob matrix: calc %d, opti %d." % (cur_calc, opti))
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 bib1 in cached_bibs and bib2 in cached_bibs:
val = old_matrix[bib1, bib2]
if not val:
cur_calc += 1
check_for_cleaning(cur_calc)
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
check_for_cleaning(cur_calc)
val = compare_bibrefrecs(bib1, bib2)
self._bib_matrix[bib1, bib2] = val
clear_comparison_caches()
if save_cache:
update_status(1., "saving...")
self._bib_matrix.store(cluster_set.last_name, creation_time)
update_status_final("Matrix done. %d calc, %d opt." % (cur_calc, opti))