def __call__(self, node):
# ======================================================================
# Initialization
# ======================================================================
if not isinstance(node, NLInstruction):
raise ValueError('Argument must be NLInstruction, got %s' %
type(node).__name__)
if self.prac.verbose > 0:
print(prac_heading('Parsing %s' % node))
infstep = PRACInferenceStep(node, self)
# ======================================================================
# Preprocessing
# ======================================================================
instr = self.compounds(node.instr)
# ======================================================================
# Parsing Instructions
# ======================================================================
if self.prac.verbose > 0:
print(
colorize('Parsing instruction: "%s"',
(None, 'white', True), True) % instr)
dbs = self.parse([instr])
#-----------------------------------------------------------------------
# here come some dirty hacks to catch some very frequent and
# annoying parsing errors:
# 1. "season" is consequently tagged as a noun. We retag it as a verb
for db in dbs:
for q in db.query('has_pos(?w,NN)'):
if q['?w'].lower().startswith('season'):
db['has_pos(%s,NN)' % q['?w']] = 0
db['has_pos(%s,VB)' % q['?w']] = 1
pngs = {}
for i, db in enumerate(dbs):
infstep.outdbs.append(db)
if self.prac.verbose > 1:
print()
print(
colorize('Syntactic evidence:', (None, 'white', True),
True))
db.write(sys.stdout, True)
print()
pngs['NL Parsing - ' + str(i)] = get_cond_prob_png(
','.join([x.name for x in self.mln.predicates[:10]]) + ',...',
str(node.instr),
filename=self.name)
infstep.png = pngs
yield node
def __call__(self, node, **params):
# ======================================================================
# Initialization
# ======================================================================
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
infstep.indbs = [db.copy() for db in dbs]
infstep.outdbs = [db.copy() for db in dbs]
logger.debug('Running {}'.format(self.name))
if self.prac.verbose > 0:
print(prac_heading('Generating CRAM Plan(s)'))
if not hasattr(self.prac.actioncores[node.frame.actioncore], 'plan'):
raise ActionKnowledgeError('I don\'t know how to %s' %
node.frame.sentence)
yield
ac = self.prac.actioncores[node.frame.actioncore]
# fill dictionary with all inferred roles...
acdict = dict([(k, v.type)
for k, v in list(node.frame.actionroles.items())])
# ..and their properties
acdict.update(
dict([('{}_props'.format(k), ' '.join([
'({} {})'.format(pkey, pval)
for pkey, pval in list(v.props.tojson().items())
])) for k, v in list(node.frame.actionroles.items())]))
# update dictionary with missing roles and roles properties
for role in ac.roles:
if acdict.get(role) is None:
acdict[role] = 'Unknown'
acdict['{}_props'.format(role)] = ''
node.plan = ac.parameterize_plan(**acdict)
if self.prac.verbose:
print()
print(prac_heading('PLAN GENERATION RESULTS'))
print(colorize('actioncore:', (None, 'white', True), True),
colorize(ac.name, (None, 'cyan', True), True))
print(colorize('assignments:', (None, 'white', True), True))
for x in acdict:
print('\t{}: {}'.format(
colorize(x, (None, 'white', True), True),
colorize(acdict[x], (None, 'cyan', True), True)))
def write(self, stream=sys.stdout, color=None, bars=True):
'''
Writes this database into the stream in the MLN Database format.
The stream must provide a `write()` method as file objects do.
'''
if color is None:
if stream != sys.stdout:
color = False
else:
color = True
for atom in sorted(self._evidence):
truth = self._evidence[atom]
pred, params = self.mln.logic.parse_atom(atom)
pred = str(pred)
params = map(str, params)
if bars:
bar = barstr(30, truth, color='magenta' if color else None)
else:
bar = ''
if color:
strout = '%s %s\n' % (
bar if bars else colorize('%.6f' % truth,
(None, 'magenta', False), True),
FirstOrderLogic.Lit(False, pred, params,
self.mln).cstr(color))
else:
strout = '%s %s\n' % (bar if bars else '%.6f' % truth,
FirstOrderLogic.Lit(
False, pred, params,
self.mln).cstr(color))
stream.write(strout)
def prac_heading(s, upper=True, color='green'):
'''
Returns a colorized and formatted string for pretty priting module
headings.
:param s: the string to be formatted
:param upper: (bool) if string should be converted to uppercase. default
is true
:param color: the color in which the heading should be printed. default
is green
:return: the colorized and formatted string
'''
b = colorize('+{}+'.format(''.ljust(len(s) + 2, '=')), (None, color, True),
True)
t = colorize('| {} |'.format(s.upper() if upper else s),
(None, color, True), True)
return '\n{}\n{}\n{}\n'.format(b, t, b)
def printListAndTick(l, t):
if type(t) is str:
t = l.index(t)
for idx, item in enumerate(l):
print(' [{}] {}'.format(
'X' if t == idx else ' ',
colorize(item, (None, {
True: 'yellow',
False: 'white'
}[t == idx], True), True)))
def write(self, stream=sys.stdout, color=None):
'''
Writes the MLN to the given stream.
The default stream is `sys.stdout`. In order to print the MLN to the console, a simple
call of `mln.write()` is sufficient. If color is not specified (is None), then the
output to the console will be colored and uncolored for every other stream.
:param stream: the stream to write the MLN to.
:param color: whether or not output should be colorized.
'''
if color is None:
if stream != sys.stdout:
color = False
else:
color = True
if 'learnwts_message' in dir(self):
stream.write("/*\n%s*/\n\n" % self.learnwts_message)
# domain declarations
if self.domain_decls:
stream.write(
colorize("// domain declarations\n", comment_color, color))
for d in self.domain_decls:
stream.write("%s\n" % d)
stream.write('\n')
# variable definitions
if self.vars:
stream.write(
colorize('// variable definitions\n', comment_color, color))
for var, val in self.vars.iteritems():
stream.write('%s = %s' % (var, val))
stream.write('\n')
stream.write(
colorize("\n// predicate declarations\n", comment_color, color))
for predicate in self.iterpreds():
if isinstance(predicate,
FuzzyPredicate) or predicate.name in self.fuzzypreds:
stream.write('#fuzzy\n')
stream.write("%s(%s)\n" % (colorize(
predicate.name, predicate_color, color), predicate.argstr()))
stream.write(colorize("\n// formulas\n", comment_color, color))
for idx, formula in self.iterformulas():
if self._unique_templvars[idx]:
stream.write('#unique{%s}\n' %
','.join(self._unique_templvars[idx]))
if formula.weight == HARD:
stream.write("%s.\n" % fstr(formula.cstr(color)))
else:
try:
w = colorize("%-10.6f", weight_color, color) % float(
eval(str(formula.weight)))
except:
w = colorize(str(formula.weight), weight_color, color)
stream.write("%s %s\n" % (w, fstr(formula.cstr(color))))
def write(self, stream=sys.stdout, color=None):
'''
Writes the MLN to the given stream.
The default stream is `sys.stdout`. In order to print the MLN to the console, a simple
call of `mln.write()` is sufficient. If color is not specified (is None), then the
output to the console will be colored and uncolored for every other stream.
:param stream: the stream to write the MLN to.
:param color: whether or not output should be colorized.
'''
if color is None:
if stream != sys.stdout:
color = False
else: color = True
if 'learnwts_message' in dir(self):
stream.write("/*\n%s*/\n\n" % self.learnwts_message)
# domain declarations
if self.domain_decls: stream.write(colorize("// domain declarations\n", comment_color, color))
for d in self.domain_decls:
stream.write("%s\n" % d)
stream.write('\n')
# variable definitions
if self.vars: stream.write(colorize('// variable definitions\n', comment_color, color))
for var, val in self.vars.iteritems():
stream.write('%s = %s' % (var, val))
stream.write('\n')
stream.write(colorize("\n// predicate declarations\n", comment_color, color))
for predicate in self.iterpreds():
if isinstance(predicate, FuzzyPredicate) or predicate.name in self.fuzzypreds:
stream.write('#fuzzy\n')
stream.write("%s(%s)\n" % (colorize(predicate.name, predicate_color, color), predicate.argstr()))
stream.write(colorize("\n// formulas\n", comment_color, color))
for idx, formula in self.iterformulas():
if self._unique_templvars[idx]:
stream.write('#unique{%s}\n' % ','.join(self._unique_templvars[idx]))
if formula.weight == HARD:
stream.write("%s.\n" % fstr(formula.cstr(color)))
else:
try:
w = colorize("%-10.6f", weight_color, color) % float(eval(str(formula.weight)))
except:
w = colorize(str(formula.weight), weight_color, color)
stream.write("%s %s\n" % (w, fstr(formula.cstr(color))))
def write(self, stream=sys.stdout, color=None, bars=True):
'''
Writes this database into the stream in the MLN Database format.
The stream must provide a `write()` method as file objects do.
'''
if color is None:
if stream != sys.stdout:
color = False
else: color = True
for atom in sorted(self._evidence):
truth = self._evidence[atom]
pred, params = self.mln.logic.parse_atom(atom)
pred = str(pred)
params = map(str, params)
if bars:
bar = barstr(30, truth, color='magenta' if color else None)
else:
bar = ''
if color:
strout = '%s %s\n' % (bar if bars else colorize('%.6f' % truth, (None, 'magenta', False), True),
FirstOrderLogic.Lit(False, pred, params, self.mln).cstr(color))
else:
strout = '%s %s\n' % (bar if bars else '%.6f' % truth, FirstOrderLogic.Lit(False, pred, params, self.mln).cstr(color))
stream.write(strout)
def printWordSenses(self, synsets, tick):
'''
Prints the list of synsets or synset ids and ticks the one specified
by the given index.
tick may be either the index or the sense id itself or the synset
instance.
'''
if type(tick) is str:
tick = self.prac.wordnet.synset(tick)
synsets_ = []
for idx, sense in enumerate(synsets):
if isinstance(sense, str):
sense = self.prac.wordnet.synset(sense)
synsets_.append(sense)
if isinstance(tick, Synset):
tick = synsets_.index(tick)
for idx, sense in enumerate(synsets_):
print ' [{}] {}: {} ({})'.format(
'X' if tick == idx else ' ',
colorize(sense.name(), (None, {
True: 'yellow',
False: 'white'
}[tick == idx], True), True), sense.definition(),
';'.join(sense.examples()))
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('Refining Actioncores'))
dbs = node.outdbs
infstep = PRACInferenceStep(node, self)
# if node.previous_module == 'achieved_by':
# raise ActionKnowledgeError('I don\'t know how to %s' % node.frame.sentence)
# ======================================================================
# Preprocessing
# ======================================================================
for olddb in dbs:
infstep.indbs.append(olddb.copy())
#To handle multiple acs in one task, we have to check if the single
# dbs contain achieved_bys which representing already plans
pngs = {}
actioncore = node.frame.actioncore
mod = self.prac.module('complex_achieved_by')
newnodes = list(mod(node))
n = None
parentframes = [
p.frame for p in node.parentspath()
if isinstance(p, FrameNode)
]
if any(n.frame in parentframes for n in newnodes):
logger.error(
'aborting reasoning because of infinite loop. (%s)' %
node.frame)
node.children = []
else:
for n in newnodes:
yield n
if n is not None: return
if n is None:
# This list is used to avoid an infinite loop during the
# achieved by inference.
# To avoid this infinite loop, the list contains the pracmlns
# which were inferenced during the process.
# Every pracmln should be used only once during the process
# because the evidence for the inference will always remain
# the same.
# So if the pracmln hadnt inferenced a plan in the first time,
# it will never do it.
# Need to remove possible achieved_by predicates from
# previous achieved_by inferences
db_ = PRACDatabase(self.prac)
for atom, truth in sorted(olddb.evidence.items()):
if 'achieved_by' in atom: continue
db_ << (atom, truth)
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))
if os.path.exists(projectpath):
project = MLNProject.open(projectpath)
else:
infstep.outdbs.append(olddb)
logger.error(actioncore + ".pracmln does not exist.")
return
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'))
known_concepts = mln.domains.get('concept', [])
wnmod = self.prac.module('wn_senses')
#Merge domains of db and given mln to avoid errors due to role inference and the resulting missing fuzzy perdicates
known_concepts = list(
set(known_concepts).union(
set(db_.domains.get('concept', []))))
db = wnmod.get_senses_and_similarities(db_, known_concepts)
unified_db = db_.union(db)
dbnew = wnmod.add_sims(unified_db, unified_db)
# Inference achieved_by predicate
db_ = self.extendDBWithAchievedByEvidence(
dbnew, mln, actioncore)
# ==============================================================
# Inference
# ==============================================================
# db_.write()
try:
infer = self.mlnquery(config=project.queryconf,
verbose=self.prac.verbose > 2,
db=db_,
mln=mln)
except NoConstraintsError:
logger.error(
'achieved_by inference failed due to NoConstraintsError: %s'
% node.frame)
return
result_db = infer.resultdb
if self.prac.verbose == 2:
print()
print(prac_heading('INFERENCE RESULTS'))
infer.write()
# ==============================================================
# Postprocessing
# ==============================================================
# unified_db = result_db.union(kb.query_mln, db_)
# only add inferred achieved_by atoms, leave out
# 0-evidence atoms
for qa in result_db.query('achieved_by(?ac1,?ac2)'):
if qa['?ac2'] == 'Complex': continue
unified_db << 'achieved_by({},{})'.format(
qa['?ac1'], qa['?ac2'])
pngs[qa['?ac2']] = get_cond_prob_png(project.queryconf.get(
'queries', ''),
dbs,
filename=self.name)
newframe = Frame(self.prac,
node.frame.sidx,
'',
words=[],
syntax=[],
actioncore=qa['?ac2'],
actionroles={})
# out('->', newframe)
infstep.outdbs.append(unified_db)
yield FrameNode(node.pracinfer,
newframe,
node,
pred=None,
indbs=[unified_db],
prevmod=self.name)
return
infstep.outdbs.append(unified_db)
# raise ActionKnowledgeError('I don\'t know how to %s' % node.frame.sentence)
def main():
headline("Running main...")
usage = 'PRAC Object Recognition tool'
parser = argparse.ArgumentParser(description=usage)
parser.add_argument(
"-i",
"--interactive",
dest="interactive",
default=False,
action='store_true',
help="Starts PRAC object recognition with an interactive "
"GUI tool.")
parser.add_argument(
"-t",
"--train",
dest="trainMLN",
nargs=1,
default=None,
help=
"Train given MLN with inference results from argument. Example: pracobjrec -t orange.n.01 'It is a yellow "
"or orange fruit.'")
parser.add_argument(
"-r",
"--regular",
dest="regular",
default=False,
action='store_true',
help="Runs regular inference pipeline. Arguments: mlnName")
parser.add_argument("-f",
"--onthefly",
dest="onthefly",
default=False,
action='store_true',
help="Generate MLN on the fly")
parser.add_argument(
"-m",
"--mln",
nargs=2,
dest='mln',
default=None,
help="Runs regular inference pipeline. Arguments: mlnName")
args = parser.parse_args()
opts_ = vars(args)
interactive = args.interactive
regular = args.regular
sentences = args
prac = PRAC()
prac.wordnet = WordNet(concepts=None)
infer = PRACInference(prac, sentences)
# in case we have natural-language parameters, parse them
if len(infer.instructions) > 0:
parser = prac.module('nl_parsing')
prac.run(infer, parser)
if interactive: # use the GUI
logger.info('Entering interactive mode')
gui = PRACQueryGUI(infer)
gui.open()
elif args.trainMLN: # training with property inference output
logger.info(
'Training MLN {} with result from property inference'.format(
args.trainMLN))
# property inference from parsed input
propExtract = prac.module('prop_extraction')
prac.run(infer, propExtract)
objRecog = prac.module('obj_recognition')
praclearn = PRACLearning(prac)
praclearn.otherParams['mln'] = args.mln[0]
praclearn.otherParams['logic'] = args.mln[1]
praclearn.otherParams['concept'] = args.trainMLN
praclearn.otherParams['onthefly'] = args.onthefly
praclearn.training_dbs = infer.inference_steps[-1].output_dbs
objRecog.train(praclearn)
sys.exit(0)
else: # regular PRAC pipeline
logger.info('Entering regular inference pipeline')
# property inference from parsed input
propExtract = prac.module('prop_extraction')
prac.run(infer, propExtract)
objRecog = prac.module('obj_recognition')
# object inference based on inferred properties
prac.run(infer, objRecog)
step = infer.inference_steps[-1]
print()
print(prac_heading('PRAC INFERENCE RESULTS'))
print()
print('Object description: {}'.format(
colorize(''.join(sentences), (None, 'white', True), True)))
print()
for db in step.output_dbs:
print('Inferred properties:')
for ek in sorted(db.evidence):
e = db.evidence[ek]
if e == 1.0 and any(
ek.startswith(p) for p in [
'color', 'size', 'shape', 'hypernym', 'hasa',
'dimension', 'consistency', 'material'
]):
print('{}({}, {}'.format(
colorize(ek.split('(')[0], (None, 'white', True), True),
colorize(
ek.split('(')[1].split(',')[0],
(None, 'magenta', True), True),
colorize(
ek.split('(')[1].split(',')[1], (None, 'green', True),
True)))
for db in step.output_dbs:
print()
print('Inferred possible concepts:')
for ek in sorted(db.evidence, key=db.evidence.get, reverse=True):
e = db.evidence[ek]
if e > 0.001 and ek.startswith('object'):
print('{} {}({}, {})'.format(
colorize('{:.4f}'.format(e), (None, 'cyan', True), True),
colorize('object', (None, 'white', True), True),
colorize(
ek.split(',')[0].split('(')[1],
(None, 'magenta', True), True),
colorize(
ek.split(',')[1].split(')')[0], (None, 'yellow', True),
True)))
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 _run(self):
"""
verbose: whether to print results (or anything at all, in fact)
details: (given that verbose is true) whether to output additional
status information
debug: (given that verbose is true) if true, outputs debug
information, in particular the distribution over possible
worlds
debugLevel: level of detail for debug mode
"""
# check consistency with hard constraints:
self._watch.tag('check hard constraints', verbose=self.verbose)
hcgrounder = FastConjunctionGrounding(self.mrf, simplify=False, unsatfailure=True,
formulas=[f for f in self.mrf.formulas if f.weight == HARD],
**(self._params + {'multicore': False, 'verbose': False}))
for gf in hcgrounder.itergroundings():
if isinstance(gf, Logic.TrueFalse) and gf.truth() == .0:
raise SatisfiabilityException('MLN is unsatisfiable due to hard constraint violation by evidence: {} ({})'.format(str(gf), str(self.mln.formula(gf.idx))))
self._watch.finish('check hard constraints')
# compute number of possible worlds
worlds = 1
for variable in self.mrf.variables:
values = variable.valuecount(self.mrf.evidence)
worlds *= values
numerators = [0.0 for i in range(len(self.queries))]
denominator = 0.
# start summing
logger.debug("Summing over %d possible worlds..." % worlds)
if worlds > 500000 and self.verbose:
print colorize('!!! %d WORLDS WILL BE ENUMERATED !!!' % worlds, (None, 'red', True), True)
k = 0
self._watch.tag('enumerating worlds', verbose=self.verbose)
global global_enumAsk
global_enumAsk = self
bar = None
if self.verbose:
bar = ProgressBar(width=100, steps=worlds, color='green')
if self.multicore:
pool = Pool()
logger.debug('Using multiprocessing on {} core(s)...'.format(pool._processes))
try:
for num, denum in pool.imap(with_tracing(eval_queries), self.mrf.worlds()):
denominator += denum
k += 1
for i, v in enumerate(num):
numerators[i] += v
if self.verbose: bar.inc()
except Exception as e:
logger.error('Error in child process. Terminating pool...')
pool.close()
raise e
finally:
pool.terminate()
pool.join()
else: # do it single core
for world in self.mrf.worlds():
# compute exp. sum of weights for this world
num, denom = eval_queries(world)
denominator += denom
for i, _ in enumerate(self.queries):
numerators[i] += num[i]
k += 1
if self.verbose:
bar.update(float(k) / worlds)
logger.debug("%d worlds enumerated" % k)
self._watch.finish('enumerating worlds')
if 'grounding' in self.grounder.watch.tags:
self._watch.tags['grounding'] = self.grounder.watch['grounding']
if denominator == 0:
raise SatisfiabilityException(
'MLN is unsatisfiable. All probability masses returned 0.')
# normalize answers
dist = map(lambda x: float(x) / denominator, numerators)
result = {}
for q, p in zip(self.queries, dist):
result[str(q)] = p
return result
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
