def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print(prac_heading('Role COMPLETION: %s' % node.frame.actioncore))
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
infstep.executable_plans = []
pngs = {}
for i, db in enumerate(dbs):
# ==================================================================
# Mongo Lookup
# ==================================================================
infstep.indbs.append(db.copy())
db_, missingroles = self.determine_missing_roles(node, db)
if self.prac.verbose > 1:
print()
print(prac_heading('ROLE COMPLETION RESULTS'))
for m in missingroles:
r = node.frame.actionroles.get(m)
if r: print(m, r.type)
# ==================================================================
# Postprocessing
# ==================================================================
infstep.outdbs.append(db_)
for word, actioncore in db.actioncores():
pngs['LookUp - ' + str(i)] = get_query_png(list(missingroles),
dbs,
filename=self.name,
skolemword=word)
infstep.png = pngs
infstep.applied_settings = {
'module': 'missing_roles',
'method': 'DB lookup'
}
return [node]
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print prac_heading('Resolving Coreferences')
preds = list(
node.rdfs(
goaltest=lambda n: isinstance(n, FrameNode) and not n.children,
all=True))[:2]
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
projectpath = os.path.join(pracloc.pracmodules, self.name)
ac = None
pngs = {}
# if not preds: return []
# ======================================================================
# Preprocessing
# ======================================================================
# merge output dbs from senses_and_roles step, containing
# roles inferred from multiple sentences.
if not preds:
# no coreferencing required - forward dbs and settings
# from previous module
infstep.indbs = [db.copy() for db in dbs]
infstep.outdbs = [db.copy() for db in infstep.indbs]
logger.debug(
'%s has no predecessors. Nothing to do here. Passing db...' %
node)
return [node]
# retrieve all words from the dbs to calculate distances.
# Do not use pracinference.instructions as they are not
# annotated by the Stanford parser.
sentences = [db.words() for pred in preds for db in pred.indbs]
infstep.indbs = [db.copy() for db in dbs]
# infstep.outdbs = [db.copy() for db in infstep.indbs]
# query action core to load corresponding project
actioncore = node.frame.actioncore
# clear corefdb and unify current db with the two preceding ones
corefdb = PRACDatabase(self.prac)
corefdb = corefdb.union(dbs, self.prac.mln)
# for s in range(max(0, i - 2), i+1):
# corefdb = corefdb.union(dbs[s], self.prac.mln)
for pred in preds:
logger.debug('unifying with %s' % pred)
for db in pred.indbs:
corefdb = corefdb.union(db, self.prac.mln)
# remove all senses from the databases' domain that are not
# assigned to any word.
for q in corefdb.query('!(EXIST ?w (has_sense(?w,?sense)))'):
corefdb.rmval('sense', q['?sense'])
try:
# preprocessing: adding distance information for each
# word in the instructions
# s = words[max(0, i - 2):i+1]
# snts = list(enumerate(s))
# idx = len(snts) - 1 # idx of current sentence
# for s in snts[:-1]:
# idx2 = s[0]
# for w in s[1]:
# corefdb << 'distance({},DIST{})'.format(w, idx - idx2)
for sidx, s in enumerate(sentences):
for w in s:
cont = True
for q in corefdb.query('distance({}, ?w)'.format(w)):
cont = False
break
if not cont: continue
corefdb << 'distance({},DIST{})'.format(w, sidx)
# print 'distance({},DIST{})'.format(w, sidx)
logger.debug('loading Project: {}'.format(
colorize(actioncore, (None, 'cyan', True), True)))
project = MLNProject.open(
os.path.join(projectpath, '{}.pracmln'.format(actioncore)))
mlntext = project.mlns.get(project.queryconf['mln'], None)
mln = parse_mln(mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=project.queryconf.get('logic', 'FuzzyLogic'),
grammar=project.queryconf.get(
'grammar', 'PRACGrammar'))
except MLNParsingError:
logger.warning(
'Could not use MLN in project {} for coreference resolution'.
format(colorize(actioncore, (None, 'cyan', True), True)))
infstep.outdbs = [db.copy(self.prac.mln) for db in dbs]
infstep.png = node.parent.laststep.png
infstep.applied_settings = node.parent.laststep.applied_settings
return [node]
except Exception:
infstep.outdbs = [db.copy(self.prac.mln) for db in dbs]
infstep.png = node.parent.laststep.png
infstep.applied_settings = node.parent.laststep.applied_settings
logger.warning(
'Could not load project "{}". Passing dbs to next module...'.
format(ac))
return [node]
# adding similarities
wnmod = self.prac.module('wn_senses')
newdatabase = wnmod.add_sims(corefdb, mln)
# update queries depending on missing roles
acroles = filter(lambda role: role != 'action_verb',
self.prac.actioncores[actioncore].roles)
missingroles = [
ar for ar in acroles
if len(list(newdatabase.query('{}(?w,{})'.format(ar, actioncore))))
== 0
]
conf = project.queryconf
conf.update({'queries': ','.join(missingroles)})
print colorize('querying for missing roles {}'.format(conf['queries']),
(None, 'green', True), True)
# asserting impossible role-ac combinations, leaving previously
# inferred roles untouched
fulldom = mergedom(mln.domains, newdatabase.domains)
ac_domains = [dom for dom in fulldom if '_ac' in dom]
acs = list(set([v for a in ac_domains for v in fulldom[a]]))
acs = filter(lambda ac_: ac_ != actioncore, acs)
for ac1 in acs:
for r in missingroles:
for w in newdatabase.domains['word']:
# words with no sense are asserted false
if list(
corefdb.query(
'!(EXIST ?sense (has_sense({},?sense)))'.
format(w))):
newdatabase << '!{}({},{})'.format(r, w, actioncore)
# leave previously inferred information roles
# untouched
if list(newdatabase.query('{}({},{})'.format(r, w, ac1))):
continue
else:
newdatabase << '!{}({},{})'.format(r, w, ac1)
try:
# ==========================================================
# Inference
# ==========================================================
infer = self.mlnquery(config=conf,
verbose=self.prac.verbose > 2,
db=newdatabase,
mln=mln)
if self.prac.verbose == 2:
print
print prac_heading('INFERENCE RESULTS')
infer.write()
# ==========================================================
# Postprocessing
# ==========================================================
# merge initial db with results
for db in infstep.indbs:
resultdb = db.copy()
for res in infer.results.keys():
if infer.results[res] != 1.0:
continue
resultdb << str(res)
_, _, args = self.prac.mln.logic.parse_literal(res)
w = args[0]
for q in newdatabase.query(
'has_sense({0},?s) ^ has_pos({0},?pos)'.format(w)):
resultdb << 'has_sense({},{})'.format(w, q['?s'])
resultdb << 'is_a({0},{0})'.format(q['?s'])
resultdb << 'has_pos({},{})'.format(w, q['?pos'])
resultdb = wnmod.add_sims(resultdb, mln)
# enhance the frame data
for mrole in missingroles:
for q in resultdb.query(
'{role}(?w, {actioncore}) ^ has_sense(?w, ?s)'.
format(role=mrole, actioncore=actioncore)):
for p in preds:
if p.frame.object(q['?w']) is not None:
node.frame.actionroles[mrole] = p.frame.object(
q['?w'])
break
infstep.outdbs.append(resultdb)
pprint(node.frame.tojson())
except NoConstraintsError:
logger.debug('No coreferences found. Passing db...')
infstep.outdbs.append(db)
except Exception:
logger.error('Something went wrong')
traceback.print_exc()
pngs['Coref - ' + str(node)] = get_cond_prob_png(project.queryconf.get(
'queries', ''),
dbs,
filename=self.name)
infstep.png = pngs
infstep.applied_settings = project.queryconf.config
return [node]
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print(prac_heading('Recognizing Action Cores'))
if params.get('project', None) is None:
# load default project
projectpath = os.path.join(pracloc.pracmodules, self.name,
self.defproject)
ac_project = MLNProject.open(projectpath)
else:
logger.info(
colorize('Loading Project from params', (None, 'cyan', True),
True))
projectpath = os.path.join(
params.get('projectpath', None)
or os.path.join(pracloc.pracmodules, self.name),
params.get('project').name)
ac_project = params.get('project')
dbs = node.outdbs
mlntext = ac_project.mlns.get(ac_project.queryconf['mln'], None)
mln = parse_mln(mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=ac_project.queryconf.get('logic',
'FirstOrderLogic'),
grammar=ac_project.queryconf.get(
'grammar', 'PRACGrammar'))
known_concepts = mln.domains.get('concept', [])
infstep = PRACInferenceStep(node, self)
wnmod = self.prac.module('wn_senses')
pngs = {}
nlinstr = node.nlinstr()
sidx = nlinstr.idx()
sentence = nlinstr.instr
for db_ in dbs:
# ==================================================================
# Preprocessing
# ==================================================================
db = wnmod.get_senses_and_similarities(db_, known_concepts)
tmp_union_db = db.union(db_, mln=self.prac.mln)
infstep.indbs.append(tmp_union_db)
# ==================================================================
# Inference
# ==================================================================
infer = self.mlnquery(config=ac_project.queryconf,
verbose=self.prac.verbose > 2,
db=tmp_union_db,
mln=mln)
resultdb = infer.resultdb
if self.prac.verbose == 2:
print()
print(prac_heading('INFERENCE RESULTS'))
infer.write()
# ==================================================================
# Postprocessing
# ==================================================================
unified_db = resultdb.union(tmp_union_db, mln=self.prac.mln)
# infstep.outdbs
infstep.outdbs.extend(
self.extract_multiple_action_cores(self.prac, unified_db,
wnmod, known_concepts))
pngs[unified_db.domains.get('actioncore',
[None])[0]] = get_cond_prob_png(
ac_project.queryconf.get(
'queries', ''),
dbs,
filename=self.name)
infstep.png = pngs
infstep.applied_settings = ac_project.queryconf.config
pred = None
for outdb in infstep.outdbs:
# out('in ac rec:')
# for w, ac in outdb.actioncores():
# out(w, ac)
for frame in node.pracinfer.buildframes(outdb, sidx, sentence):
node_ = FrameNode(node.pracinfer,
frame,
node,
pred,
indbs=[outdb],
prevmod=self.name)
pred = node_
yield node_
break
else:
logger.error('no actioncore recognized in %s' % node)
raise Exception('no actioncore recognized in %s' % node)
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print prac_heading('Update roles based on Action Core Refinement')
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
# planlist = self.getPlanList()
# out(node.parent.frame, '->', node.frame)
pngs = {}
for i, db_ in enumerate(dbs):
# db = db_.copy()
# db = PRACDatabase(self.prac)
# ==================================================================
# Preprocessing
# ==================================================================
actioncore = node.frame.actioncore
logger.debug('Action core: {}'.format(actioncore))
if params.get('project', None) is None:
logger.debug('Loading Project: {}.pracmln'.format(
colorize(actioncore, (None, 'cyan', True), True)))
projectpath = os.path.join(
pracloc.pracmodules, self.name,
'{}Transformation.pracmln'.format(actioncore))
project = MLNProject.open(projectpath)
else:
logger.debug(
colorize('Loading Project from params',
(None, 'cyan', True), True))
projectpath = os.path.join(
params.get('projectpath', None)
or os.path.join(pracloc.pracmodules, self.name),
params.get('project').name)
project = params.get('project')
mlntext = project.mlns.get(project.queryconf['mln'], None)
mln = parse_mln(
mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=project.queryconf.get('logic', 'FirstOrderLogic'),
grammar=project.queryconf.get('grammar', 'PRACGrammar'))
result_db = None
for pdb in node.parent.outdbs:
db = pdb.copy()
db = db.union(db_)
objs = {o.id for o in node.parent.frame.actionroles.values()}
for w in set(db.domains['word']):
if w not in objs:
db.rmval('word', w)
infstep.indbs.append(db)
ac = node.parent.frame.actioncore
db << 'achieved_by(%s, %s)' % (ac, actioncore)
for role, object_ in node.parent.frame.actionroles.iteritems():
db << '%s(%s, %s)' % (role, object_.id, ac)
try:
# ==========================================================
# Inference
# ==========================================================
infer = self.mlnquery(config=project.queryconf,
db=db,
verbose=self.prac.verbose > 2,
mln=mln)
result_db = infer.resultdb
if self.prac.verbose == 2:
print
print prac_heading('INFERENCE RESULTS')
print
infer.write()
except NoConstraintsError:
logger.error(
'no constraints in role transformation: %s -> %s' %
(node.parent.frame, node.frame))
result_db = db
# ==============================================================
# Postprocessing
# ==============================================================
r_db = PRACDatabase(self.prac)
roles = self.prac.actioncores[actioncore].roles
for atom, truth in sorted(result_db.evidence.iteritems()):
if any(r in atom for r in roles):
_, predname, args = self.prac.mln.logic.parse_literal(atom)
word, ac = args
if ac == actioncore:
r_db << (atom, truth)
if truth:
sense = pdb.sense(word)
props = pdb.properties(word)
obj = Object(self.prac,
id_=word,
type_=sense,
props=props,
syntax=node.pracinfer.buildword(
pdb, word))
node.frame.actionroles[predname] = obj
# out('->', node.frame)
unified_db = db.union(r_db, mln=self.prac.mln)
r_db_ = PRACDatabase(self.prac)
# It will be assumed that there is only one true action_
# c1ore predicate per database
# for actionverb, actioncore in unified_db.actioncores(): break
for atom, truth in sorted(unified_db.evidence.iteritems()):
if 'action_core' in atom: continue
r_db_ << (atom, truth)
infstep.outdbs.append(r_db_)
pngs['RolesTransformation - ' + str(i)] = get_cond_prob_png(
project.queryconf.get('queries', ''), dbs, filename=self.name)
infstep.png = pngs
infstep.applied_settings = project.queryconf.config
return [node]
def __call__(self, pracinference, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print(prac_heading('Recognizing Control Structures'))
if params.get('project', None) is None:
# load default project
projectpath = os.path.join(pracloc.pracmodules, self.name,
self.defproject)
ac_project = MLNProject.open(projectpath)
else:
logger.info(
colorize('Loading Project from params', (None, 'cyan', True),
True))
projectpath = os.path.join(
params.get('projectpath', None)
or os.path.join(pracloc.pracmodules, self.name),
params.get('project').name)
ac_project = params.get('project')
dbs = pracinference.inference_steps[-1].output_dbs
mlntext = ac_project.mlns.get(ac_project.queryconf['mln'], None)
mln = parse_mln(mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=ac_project.queryconf.get('logic',
'FirstOrderLogic'),
grammar=ac_project.queryconf.get(
'grammar', 'PRACGrammar'))
inf_step = PRACInferenceStep(pracinference, self)
pngs = {}
for i, db in enumerate(dbs):
db_ = db.copy()
# ======================================================================
# Inference
# ======================================================================
infer = self.mlnquery(config=ac_project.queryconf, db=db, mln=mln)
result_db = infer.resultdb
if self.prac.verbose == 2:
print()
print(prac_heading('INFERENCE RESULTS'))
infer.write()
# ==========================================================
# Postprocessing
# ==========================================================
for q in result_db.query('event(?w,?ac)'):
db_ << 'event({},{})'.format(q['?w'], q['?ac'])
for q in result_db.query('condition(?w)'):
db_ << 'condition({})'.format(q['?w'])
inf_step.output_dbs.append(db_)
pngs['CS' + str(i)] = get_cond_prob_png(ac_project.queryconf.get(
'queries', ''),
dbs,
filename=self.name)
inf_step.png = pngs
inf_step.applied_settings = ac_project.queryconf.config
return inf_step
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print(prac_heading('Property Extraction'))
if params.get('project', None) is None:
# load default project
projectpath = os.path.join(pracloc.pracmodules, self.name,
self.defproject)
project = MLNProject.open(projectpath)
else:
# load project from params
projectpath = os.path.join(
params.get('projectpath', None)
or os.path.join(pracloc.pracmodules, self.name),
params.get('project').name)
project = params.get('project')
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
mlntext = project.mlns.get(project.queryconf['mln'], None)
mln = parse_mln(mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=project.queryconf.get('logic', 'FuzzyLogic'),
grammar=project.queryconf.get('grammar',
'PRACGrammar'))
wnmod = self.prac.module('wn_senses')
pngs = {}
for i, db in enumerate(dbs):
# ==================================================================
# Preprocessing
# ==================================================================
db_ = wnmod.add_sims(db, mln)
infstep.indbs.append(db_)
try:
# ==============================================================
# Inference
# ==============================================================
infer = self.mlnquery(config=project.queryconf,
verbose=self.prac.verbose > 2,
db=db_,
mln=mln)
result_db = infer.resultdb
if self.prac.verbose == 2:
print()
print(prac_heading('INFERENCE RESULTS'))
print()
infer.write()
# ==============================================================
# Postprocessing
# ==============================================================
unified_db = db.copy(self.prac.mln)
props = [
p for p in project.queryconf.get('queries', '').split(',')
if p != 'has_sense'
]
for p in props:
for q in result_db.query(
'{}(?w1,?w2) ^ has_sense(?w2,?s2)'.format(p)):
unified_db << '{}({},{})'.format(p, q['?w1'], q['?w2'])
unified_db << 'has_sense({},{})'.format(
q['?w2'], q['?s2'])
infstep.outdbs.append(unified_db)
except NoConstraintsError:
logger.debug('No properties found. Passing db...')
infstep.outdbs.append(db.copy())
except Exception:
logger.error('Something went wrong')
traceback.print_exc()
pngs['PropExtraction - ' + str(i)] = get_cond_prob_png(
project.queryconf.get('queries', ''),
infstep.indbs,
filename=self.name)
infstep.png = pngs
infstep.applied_settings = project.queryconf.config
return [node]
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
logger.debug('inference on {}'.format(self.name))
if self.prac.verbose > 0:
print prac_heading('Recognizing {} Roles'.format({
True: 'MISSING',
False: 'GIVEN'
}[params.get('missing', False)]))
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
queries = ''
wnmod = self.prac.module('wn_senses')
actionroles = defaultdict(list)
pngs = {}
for n, olddb in enumerate(dbs):
db_copy = olddb.copy(mln=self.prac.mln)
actioncore = node.frame.actioncore
logger.debug(actioncore)
if params.get('project', None) is None:
logger.debug('Loading Project: {}.pracmln'.format(
colorize(actioncore, (None, 'cyan', True), True)))
projectpath = os.path.join(pracloc.pracmodules, self.name,
'{}.pracmln'.format(actioncore))
project = MLNProject.open(projectpath)
else:
logger.debug(
colorize('Loading Project from params',
(None, 'cyan', True), True))
projectpath = os.path.join(
params.get('projectpath', None)
or os.path.join(pracloc.pracmodules, self.name),
params.get('project').name)
project = params.get('project')
queries = project.queryconf.get('queries', '')
mlntext = project.mlns.get(project.queryconf['mln'], None)
mln = parse_mln(mlntext,
searchpaths=[self.module_path],
projectpath=projectpath,
logic=project.queryconf.get('logic', 'FuzzyLogic'),
grammar=project.queryconf.get(
'grammar', 'PRACGrammar'))
known_concepts = mln.domains.get('concept', [])
# ==============================================================
# Preprocessing
# ==============================================================
# adding senses and similarities. might be obsolete as it has
# already been performed in ac recognition
logger.debug('adding senses. concepts={}'.format(known_concepts))
db = wnmod.get_senses_and_similarities(db_copy, known_concepts)
# we need senses and similarities as well as original evidence
tmp_union_db = db.union(db_copy, mln=self.prac.mln)
# ignore roles of false ac's
new_tmp_union_db = tmp_union_db.copy(mln=self.prac.mln)
roles = self.prac.actioncores[actioncore].roles
for ac in tmp_union_db.domains['actioncore']:
if ac == actioncore: continue
for r in roles:
for w in new_tmp_union_db.words():
new_tmp_union_db << ('{}({},{})'.format(r, w, ac), 0)
infstep.indbs.append(new_tmp_union_db)
# ==============================================================
# Inference
# ==============================================================
infer = self.mlnquery(config=project.queryconf,
verbose=self.prac.verbose > 2,
db=new_tmp_union_db,
mln=mln)
resultdb = infer.resultdb
if self.prac.verbose == 2:
print
print prac_heading('INFERENCE RESULTS')
infer.write()
# ==============================================================
# Postprocessing
# ==============================================================
# get query roles for given actioncore and add inference results
# for them to final output db. ignore 0-truth results.
unified_db = new_tmp_union_db.union(resultdb, mln=self.prac.mln)
# node.frame.actionroles = defaultdict(list)
for role, word in unified_db.rolesw(actioncore):
sense = unified_db.sense(word)
props = dict(unified_db.properties(word))
obj = Object(self.prac,
id_=word,
type_=sense,
props=props,
syntax=node.pracinfer.buildword(unified_db, word))
actionroles[role].append(obj)
# argdoms = kb.query_mln.predicate(role).argdoms
roles = self.prac.actioncores[actioncore].roles
new_result = PRACDatabase(self.prac)
for atom, truth in unified_db.evidence.iteritems():
if any(r in atom for r in roles):
(_, predname,
args) = self.prac.mln.logic.parse_literal(atom)
if not args[-1] == actioncore:
continue
new_result << (atom, truth)
for q in unified_db.query('has_sense(?w, ?s)'):
# TODO Add additional formulas to avoid the using of null values
if self.prac.verbose > 1:
print colorize(' WORD:', (None, 'white', True),
True), q['?w']
print colorize(' SENSE:', (None, 'white', True),
True), q['?s']
wnmod.printWordSenses(
wnmod.get_possible_meanings_of_word(
unified_db, q['?w']), q['?s'])
print
infstep.outdbs.append(new_result)
pngs['Recognizing {} roles - {}'.format(
'given', str(n))] = get_cond_prob_png(queries,
infstep.indbs,
filename=self.name)
infstep.png = pngs
if 'project' not in locals():
raise Exception('no actioncore in database: %s' % olddb)
infstep.applied_settings = project.queryconf.config
# pprint(actionroles)
newframes = splitd(actionroles)
pred = None
for newframe in newframes:
# pprint(newframe)
f = Frame(self.prac,
node.frame.sidx,
node.frame.sentence,
syntax=list(olddb.syntax()),
words=node.frame.words,
actioncore=node.frame.actioncore,
actionroles=newframe)
logger.debug('created new frame %s' % f)
# for db in infstep.outdbs:
# out(db.syntax())
pred = FrameNode(node.pracinfer,
f,
node,
pred,
indbs=infstep.outdbs,
prevmod=self.name)
yield pred