def __init__(self,
logic='FirstOrderLogic',
grammar='PRACGrammar',
mlnfile=None):
# instantiate the logic and grammar
logic_str = '%s("%s", self)' % (logic, grammar)
self.logic = eval(logic_str)
logger.debug('Creating MLN with %s syntax and %s semantics' %
(grammar, logic))
self._predicates = {
} # maps from predicate name to the predicate instance
self.domains = {} # maps from domain names to list of values
self._formulas = [] # list of MLNFormula instances
self.domain_decls = []
self.weights = []
self.fixweights = []
self.vars = {}
self._unique_templvars = []
self._probreqs = []
self._materialized = False
self.fuzzypreds = [
] # for saving fuzzy predicates that have been converted to binary preds
if mlnfile is not None:
MLN.load(mlnfile, logic=logic, grammar=grammar, mln=self)
return
self.closedWorldPreds = []
self.formulaGroups = []
self.templateIdx2GroupIdx = {}
self.posteriorProbReqs = []
self.watch = StopWatch()
def __init__(self, logic='FirstOrderLogic', grammar='PRACGrammar', mlnfile=None):
# instantiate the logic and grammar
logic_str = '%s("%s", self)' % (logic, grammar)
self.logic = eval(logic_str)
logger.debug('Creating MLN with %s syntax and %s semantics' % (grammar, logic))
self._predicates = {} # maps from predicate name to the predicate instance
self.domains = {} # maps from domain names to list of values
self._formulas = [] # list of MLNFormula instances
self.domain_decls = []
self.weights = []
self.fixweights = []
self.vars = {}
self._unique_templvars = []
self._probreqs = []
self._materialized = False
self.fuzzypreds = [] # for saving fuzzy predicates that have been converted to binary preds
if mlnfile is not None:
MLN.load(mlnfile, logic=logic, grammar=grammar, mln=self)
return
self.closedWorldPreds = []
self.formulaGroups = []
self.templateIdx2GroupIdx = {}
self.posteriorProbReqs = []
# self.parameterType = parameterType
# self.probabilityFittingInferenceMethod = InferenceMethods.Exact
# self.probabilityFittingThreshold = 0.002 # maximum difference between desired and computed probability
# self.probabilityFittingMaxSteps = 20 # maximum number of steps to run iterative proportional fitting
# self.defaultInferenceMethod = defaultInferenceMethod
# self.allSoft = False
self.watch = StopWatch()
def __init__(self, mln_, dbs, method, **params):
'''
:param dbs: list of :class:`mln.database.Database` objects to
be used for learning.
:param mln_: the MLN object to be used for learning
:param method: the algorithm to be used for learning. Must be a
class provided by
:class:`mln.methods.LearningMethods`.
:param **params: additional parameters handed over to the base
learners.
'''
self.dbs = dbs
self._params = edict(params)
if not mln_._materialized:
self.mln = mln_.materialize(*dbs)
else:
self.mln = mln_
self.watch = StopWatch()
self.learners = [None] * len(dbs)
self.watch.tag('setup learners', verbose=self.verbose)
if self.verbose:
bar = ProgressBar(steps=len(dbs), color='green')
if self.multicore:
pool = Pool(maxtasksperchild=1)
logger.debug(
'Setting up multi-core processing for {} cores'.format(
pool._processes))
try:
for i, learner in pool.imap(with_tracing(_setup_learner),
self._iterdbs(method)):
self.learners[i] = learner
if self.verbose:
bar.label('Database %d, %s' % ((i + 1), learner.name))
bar.inc()
except Exception as e:
logger.error('Error in child process. Terminating pool...')
pool.close()
raise e
finally:
pool.terminate()
pool.join()
# as MLNs and formulas have been copied to the separate processes,
# the mln pointers of the formulas now point to the MLNs in these child processes
# we have to copy the materialized weight back to our parent process
self.mln.weights = list(first(self.learners).mrf.mln.weights)
else:
for i, db in enumerate(self.dbs):
_, learner = _setup_learner(
(i, self.mln, db, method, self._params + {
'multicore': False
}))
self.learners[i] = learner
if self.verbose:
bar.label('Database %d, %s' % ((i + 1), learner.name))
bar.inc()
if self.verbose:
print 'set up', self.name
self.watch.finish('setup learners')
def __init__(self, mrf, queries=ALL, **params):
self.mrf = mrf
self.mln = mrf.mln
self._params = edict(params)
if not queries:
self.queries = [
self.mln.logic.gnd_lit(ga, negated=False, mln=self.mln)
for ga in self.mrf.gndatoms
if self.mrf.evidence[ga.idx] is None
]
else:
# check for single/multiple query and expand
if type(queries) is not list:
queries = [queries]
self.queries = self._expand_queries(queries)
# fill in the missing truth values of variables that have only one remaining value
for variable in self.mrf.variables:
if variable.valuecount(self.mrf.evidence_dicti(
)) == 1: # the var is fully determined by the evidence
for _, value in variable.itervalues(self.mrf.evidence):
break
self.mrf.set_evidence(variable.value2dict(value), erase=False)
# apply the closed world assumptions to the explicitly specified predicates
if self.cwpreds:
for pred in self.cwpreds:
if isinstance(self.mln.predicate(pred),
SoftFunctionalPredicate):
if self.verbose:
logger.warning(
'Closed world assumption will be applied to soft functional predicate %s'
% pred)
elif isinstance(self.mln.predicate(pred), FunctionalPredicate):
raise Exception(
'Closed world assumption is inapplicable to functional predicate %s'
% pred)
for gndatom in self.mrf.gndatoms:
if gndatom.predname != pred: continue
if self.mrf.evidence[gndatom.idx] is None:
self.mrf.evidence[gndatom.idx] = 0
# apply the closed world assumption to all remaining ground atoms that are not in the queries
if self.closedworld:
qpreds = set()
for q in self.queries:
qpreds.update(q.prednames())
for gndatom in self.mrf.gndatoms:
if isinstance(self.mln.predicate(gndatom.predname), FunctionalPredicate) \
or isinstance(self.mln.predicate(gndatom.predname), SoftFunctionalPredicate):
continue
if gndatom.predname not in qpreds and self.mrf.evidence[
gndatom.idx] is None:
self.mrf.evidence[gndatom.idx] = 0
for var in self.mrf.variables:
if isinstance(var, FuzzyVariable):
var.consistent(self.mrf.evidence, strict=True)
self._watch = StopWatch()
def __init__(self, mln_, dbs, method, **params):
'''
:param dbs: list of :class:`mln.database.Database` objects to be used for learning.
:param mln_: the MLN object to be used for learning
:param method: the algorithm to be used for learning. Must be a class provided by :class:`mln.methods.LearningMethods`.
:param **params: additional parameters handed over to the base learners.
'''
self.dbs = dbs
self._params = edict(params)
if not mln_._materialized:
self.mln = mln_.materialize(*dbs)
else:
self.mln = mln_
self.watch = StopWatch()
self.learners = [None] * len(dbs)
self.watch.tag('setup learners', verbose=self.verbose)
if self.verbose:
bar = ProgressBar(width=100, steps=len(dbs), color='green')
if self.multicore:
pool = Pool(maxtasksperchild=1)
logger.debug('Setting up multi-core processing for %d cores' %
pool._processes)
for i, learner in pool.imap(with_tracing(_setup_learner),
self._iterdbs(method)):
self.learners[i] = learner
if self.verbose:
bar.label('Database %d, %s' % ((i + 1), learner.name))
bar.inc()
pool.close()
pool.join()
else:
for i, db in enumerate(self.dbs):
_, learner = _setup_learner(
(i, self.mln, db, method, self._params + {
'multicore': False
}))
self.learners[i] = learner
if self.verbose:
bar.label('Database %d, %s' % ((i + 1), learner.name))
bar.inc()
if self.verbose:
print 'set up', self.name
self.watch.finish('setup learners')
def __init__(self,
mrf,
simplify=False,
unsatfailure=False,
formulas=None,
cache=auto,
**params):
self.mrf = mrf
self.formulas = ifNone(formulas, list(self.mrf.formulas))
self.total_gf = 0
for f in self.formulas:
self.total_gf += f.countgroundings(self.mrf)
self.grounder = None
self._cachesize = CACHE_SIZE if cache is auto else cache
self._cache = None
self.__cacheinit = False
self.__cachecomplete = False
self._params = params
self.watch = StopWatch()
self.simplify = simplify
self.unsatfailure = unsatfailure
def run(self):
'''
Run the MLN learning with the given parameters.
'''
# load the MLN
if isinstance(self.mln, MLN):
mln = self.mln
else:
raise Exception('No MLN specified')
# load the training databases
if type(self.db) is list and all(
[isinstance(e, Database) for e in self.db]):
dbs = self.db
elif isinstance(self.db, Database):
dbs = [self.db]
elif isinstance(self.db, str):
db = self.db
if db is None or not db:
raise Exception('no trainig data given!')
dbpaths = [os.path.join(self.directory, 'db', db)]
dbs = []
for p in dbpaths:
dbs.extend(Database.load(mln, p, self.ignore_unknown_preds))
else:
raise Exception(
'Unexpected type of training databases: %s' % type(self.db))
if self.verbose:
print(('loaded %d database(s).' % len(dbs)))
watch = StopWatch()
if self.verbose:
confg = dict(self._config)
confg.update(eval("dict(%s)" % self.params))
if type(confg.get('db', None)) is list:
confg['db'] = '%d Databases' % len(confg['db'])
print((tabulate(
sorted(list(confg.items()), key=lambda key_v: str(key_v[0])),
headers=('Parameter:', 'Value:'))))
params = dict([(k, getattr(self, k)) for k in (
'multicore', 'verbose', 'profile', 'ignore_zero_weight_formulas')])
# for discriminative learning
if issubclass(self.method, DiscriminativeLearner):
if self.discr_preds == QUERY_PREDS: # use query preds
params['qpreds'] = self.qpreds
elif self.discr_preds == EVIDENCE_PREDS: # use evidence preds
params['epreds'] = self.epreds
# gaussian prior settings
if self.use_prior:
params['prior_mean'] = self.prior_mean
params['prior_stdev'] = self.prior_stdev
# expand the parameters
params.update(self.params)
if self.profile:
prof = Profile()
print('starting profiler...')
prof.enable()
else:
prof = None
# set the debug level
olddebug = logger.level
logger.level = eval('logs.%s' % params.get('debug', 'WARNING').upper())
mlnlearnt = None
try:
# run the learner
mlnlearnt = mln.learn(dbs, self.method, **params)
if self.verbose:
print()
print(headline('LEARNT MARKOV LOGIC NETWORK'))
print()
mlnlearnt.write()
except SystemExit:
print('Cancelled...')
finally:
if self.profile:
prof.disable()
print(headline('PROFILER STATISTICS'))
ps = pstats.Stats(prof, stream=sys.stdout).sort_stats(
'cumulative')
ps.print_stats()
# reset the debug level
logger.level = olddebug
print()
watch.finish()
watch.printSteps()
return mlnlearnt
def run(self):
watch = StopWatch()
watch.tag('inference', self.verbose)
# load the MLN
if isinstance(self.mln, MLN):
mln = self.mln
else:
raise Exception('No MLN specified')
if self.use_emln and self.emln is not None:
mlnstrio = io.StringIO()
mln.write(mlnstrio)
mlnstr = mlnstrio.getvalue()
mlnstrio.close()
emln = self.emln
mln = parse_mln(mlnstr + emln,
grammar=self.grammar,
logic=self.logic)
# load the database
if isinstance(self.db, Database):
db = self.db
elif isinstance(self.db, list) and len(self.db) == 1:
db = self.db[0]
elif isinstance(self.db, list) and len(self.db) == 0:
db = Database(mln)
elif isinstance(self.db, list):
raise Exception(
'Got {} dbs. Can only handle one for inference.'.format(
len(self.db)))
else:
raise Exception('DB of invalid format {}'.format(type(self.db)))
# expand the
# parameters
params = dict(self._config)
if 'params' in params:
params.update(eval("dict(%s)" % params['params']))
del params['params']
params['verbose'] = self.verbose
if self.verbose:
print((tabulate(sorted(list(params.items()),
key=lambda k_v: str(k_v[0])),
headers=('Parameter:', 'Value:'))))
if type(db) is list and len(db) > 1:
raise Exception('Inference can only handle one database at a time')
elif type(db) is list:
db = db[0]
params['cw_preds'] = [x for x in self.cw_preds if bool(x)]
# extract and remove all non-algorithm
for s in GUI_SETTINGS:
if s in params: del params[s]
if self.profile:
prof = Profile()
print('starting profiler...')
prof.enable()
# set the debug level
olddebug = logger.level
logger.level = (eval('logs.%s' %
params.get('debug', 'WARNING').upper()))
result = None
try:
mln_ = mln.materialize(db)
mrf = mln_.ground(db)
inference = self.method(mrf, self.queries, **params)
if self.verbose:
print()
print((headline('EVIDENCE VARIABLES')))
print()
mrf.print_evidence_vars()
result = inference.run()
if self.verbose:
print()
print((headline('INFERENCE RESULTS')))
print()
inference.write()
if self.verbose:
print()
inference.write_elapsed_time()
except SystemExit:
traceback.print_exc()
print('Cancelled...')
finally:
if self.profile:
prof.disable()
print((headline('PROFILER STATISTICS')))
ps = pstats.Stats(prof,
stream=sys.stdout).sort_stats('cumulative')
ps.print_stats()
# reset the debug level
logger.level = olddebug
if self.verbose:
print()
watch.finish()
watch.printSteps()
return result
def run(self):
watch = StopWatch()
watch.tag('inference', self.verbose)
# load the MLN
if isinstance(self.mln, MLN):
mln = self.mln
else:
raise Exception('No MLN specified')
if self.use_emln and self.emln is not None:
mlnstr = StringIO.StringIO()
mln.write(mlnstr)
mlnstr.close()
mlnstr = str(mlnstr)
emln = self.emln
mln = parse_mln(mlnstr + emln,
grammar=self.grammar,
logic=self.logic)
# load the database
if isinstance(self.db, Database):
db = self.db
elif isinstance(self.db, list) and len(self.db) == 1:
db = self.db[0]
elif isinstance(self.db, list):
raise Exception(
'Got {} dbs. Can only handle one for inference.'.format(
len(self.db)))
else:
raise Exception('DB of invalid format {}'.format(type(self.db)))
# expand the
# parameters
params = dict(self._config)
if 'params' in params:
params.update(eval("dict(%s)" % params['params']))
del params['params']
if self.verbose:
print tabulate(sorted(list(params.viewitems()),
key=lambda (k, v): str(k)),
headers=('Parameter:', 'Value:'))
# create the MLN and evidence database and the parse the queries
# mln = parse_mln(modelstr, searchPath=self.dir.get(), logic=self.config['logic'], grammar=self.config['grammar'])
# db = parse_db(mln, db_content, ignore_unknown_preds=params.get('ignore_unknown_preds', False))
if type(db) is list and len(db) > 1:
raise Exception('Inference can only handle one database at a time')
elif type(db) is list:
db = db[0]
# parse non-atomic params
# if type(self.queries) is not list:
# queries = parse_queries(mln, str(self.queries))
params['cw_preds'] = filter(lambda x: bool(x), self.cw_preds)
# extract and remove all non-algorithm
for s in GUI_SETTINGS:
if s in params: del params[s]
if self.profile:
prof = Profile()
print 'starting profiler...'
prof.enable()
# set the debug level
olddebug = praclog.level()
praclog.level(
eval('logging.%s' % params.get('debug', 'WARNING').upper()))
result = None
try:
mln_ = mln.materialize(db)
mrf = mln_.ground(db)
inference = self.method(mrf, self.queries, **params)
if self.verbose:
print
print headline('EVIDENCE VARIABLES')
print
mrf.print_evidence_vars()
result = inference.run()
if self.verbose:
print
print headline('INFERENCE RESULTS')
print
inference.write()
if self.verbose:
print
inference.write_elapsed_time()
except SystemExit:
print 'Cancelled...'
finally:
if self.profile:
prof.disable()
print headline('PROFILER STATISTICS')
ps = pstats.Stats(prof,
stream=sys.stdout).sort_stats('cumulative')
ps.print_stats()
# reset the debug level
praclog.level(olddebug)
if self.verbose:
print
watch.finish()
watch.printSteps()
return result
