def update_config(self):
out('update_config')
self.config = PRACMLNConfig()
self.config['mln'] = self.mln_container.selected_file.get().strip().lstrip('*')
self.config["db"] = self.db_container.selected_file.get().strip().lstrip('*')
self.config["output_filename"] = self.output_filename.get()
self.config["params"] = self.params.get().strip()
self.config["method"] = LearningMethods.id(self.selected_method.get().strip())
self.config["pattern"] = self.pattern.get()
self.config["use_prior"] = int(self.use_prior.get())
self.config["prior_mean"] = self.priorMean.get()
self.config["prior_stdev"] = self.priorStdDev.get()
self.config["incremental"] = int(self.incremental.get())
self.config["shuffle"] = int(self.shuffle.get())
self.config["use_initial_weights"] = int(self.use_initial_weights.get())
self.config["qpreds"] = self.queryPreds.get().strip()
self.config["epreds"] = self.evidencePreds.get().strip()
self.config["discr_preds"] = self.discrPredicates.get()
self.config['logic'] = self.selected_logic.get()
self.config['grammar'] = self.selected_grammar.get()
self.config['multicore'] = self.multicore.get()
self.config['profile'] = self.profile.get()
self.config['verbose'] = self.verbose.get()
self.config['ignore_unknown_preds'] = self.ignore_unknown_preds.get()
self.config['ignore_zero_weight_formulas'] = self.ignore_zero_weight_formulas.get()
self.config['save'] = self.save.get()
self.config["output_filename"] = self.output_filename.get().strip()
self.project.learnconf = PRACMLNConfig()
self.project.learnconf.update(self.config.config.copy())
def print_gndatoms(self, stream=sys.stdout):
'''
Prints the alphabetically sorted list of ground atoms in this MRF to the given `stream`.
'''
out('=== GROUND ATOMS ===', tb=2)
l = self._gndatoms.keys()
for ga in sorted(l):
stream.write(str(ga) + '\n')
def print_world_vars(self, world, stream=sys.stdout, tb=2):
'''
Prints the given world `world` as a readable string of the MRF variables to the given stream.
'''
out('=== WORLD VARIABLES ===', tb=tb)
for var in self.variables:
stream.write(repr(var) + '\n')
for i, v in enumerate(var.evidence_value(world)):
vstr = '%.3f' % v if v is not None else '? '
stream.write(' %s %s\n' % (vstr, var.gndatoms[i]))
def loaddb(self, mln, config, db=None):
if db is None:
if config == 'query': config = self.queryconf
elif config == 'learn': config = self.learnconf
else: raise Exception('Need a database name or config.')
from pracmln.mln.database import parse_db
path = self.path if hasattr(self, 'path') else None
out(db)
out(self.dbs[db])
return parse_db(mln, self.dbs[ifNone(db, config['db'])], ignore_unknown_preds=config['ignore_unknown_preds'], projectpath=path)
def eval(self, mln, dbs):
'''
Returns a confusion matrix for the given (learned) MLN evaluated on
the databases given in dbs.
'''
querypred = self.params.querypred
# query_dom = self.params.query_dom
# sig = ['?arg%d' % i for i, _ in enumerate(mln.predicates[query_pred])]
# querytempl = '%s(%s)' % (query_pred, ','.join(sig))
# dbs = map(lambda db: db.copy(mln), dbs)
for db_ in dbs:
# save and remove the query predicates from the evidence
db = db_.copy()
gndtruth = mln.ground(db)
gndtruth.apply_cw()
for atom, _ in db.gndatoms(querypred):
out('removing evidence', repr(atom))
del db.evidence[atom]
db.write()
stop()
try:
resultdb = MLNQuery(config=self.params.queryconf, mln=mln, method=InferenceMethods.WCSPInference, db=db,
cw_preds=[p.name for p in mln.predicates if p.name != self.params.querypred], multicore=False).run().resultdb
result = mln.ground(db)
result.set_evidence(resultdb)
for variable in result.variables:
if variable.predicate.name != querypred: continue
pvalue = variable.evidence_value()
tvalue = variable.evidence_value()
prediction = [a for a, v in variable.atomvalues(pvalue) if v == 1]
truth = [a for a, v in variable.atomvalues(tvalue) if v == 1]
prediction = str(prediction[0]) if prediction else None
truth = str(truth[0]) if truth else None
self.confmat.addClassificationResult(prediction, truth)
# sig2 = list(sig)
# entityIdx = mln.predicates[query_pred].argdoms.index(query_dom)
# for entity in db.domains[]:
# sig2[entityIdx] = entity
# query = '%s(%s)' % (queryPred, ','.join(sig2))
# for truth in trueDB.query(query):
# truth = truth.values().pop()
# for pred in resultDB.query(query):
# pred = pred.values().pop()
# self.confMatrix.addClassificationResult(pred, truth)
# for e, v in trueDB.evidence.iteritems():
# if v is not None:
# db.addGroundAtom('%s%s' % ('' if v is True else '!', e))
except:
logger.critical(''.join(traceback.format_exception(*sys.exc_info())))
def loaddb(self, mln, config, db=None):
if db is None:
if config == 'query': config = self.queryconf
elif config == 'learn': config = self.learnconf
else: raise Exception('Need a database name or config.')
from pracmln.mln.database import parse_db
path = self.path if hasattr(self, 'path') else None
out(db)
out(self.dbs[db])
return parse_db(mln,
self.dbs[ifNone(db, config['db'])],
ignore_unknown_preds=config['ignore_unknown_preds'],
projectpath=path)
def delete_file(self):
fname = self.selected_file.get().strip()
# remove element from project mlns and buffer
if fname in self.file_buffer:
del self.file_buffer[fname]
if self.delete_hook is not None:
self.delete_hook(fname)
f = self.update_file_choices()
out(f)
# select first element from remaining list
if f: self.list_files['menu'].invoke(0)
else:
self.selected_file.set('')
self.editor.delete("1.0", END)
self.dirty = True
def delete_file(self):
fname = self.selected_file.get().strip()
# remove element from project mlns and buffer
if fname in self.file_buffer:
del self.file_buffer[fname]
if self.delete_hook is not None:
self.delete_hook(fname)
f = self.update_file_choices()
out(f)
# select first element from remaining list
if f: self.list_files['menu'].invoke(0)
else:
self.selected_file.set('')
self.editor.delete("1.0", END)
self.dirty = True
def print_domains(self):
out('=== MRF DOMAINS ==', tb=2)
for dom, values in self.domains.iteritems():
print dom, '=', ','.join(values)
def learn(self, savegeometry=True, options={}, *args):
mln_content = self.mln_container.editor.get("1.0", END).encode('utf8').strip()
db_content = self.db_container.editor.get("1.0", END).encode('utf8').strip()
# create conf from current gui settings
self.update_config()
# write gui settings
self.write_gconfig(savegeometry=savegeometry)
# hide gui
self.master.withdraw()
try:
print headline('PRAC LEARNING TOOL')
print
if options.get('mlnarg') is not None:
mlnobj = MLN(mlnfile=os.path.abspath(options.get('mlnarg')),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
else:
mlnobj = parse_mln(mln_content, searchpaths=[self.project_dir],
projectpath=os.path.join(self.project_dir, self.project.name),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
if options.get('dbarg') is not None:
dbobj = Database.load(mlnobj, dbfiles=[options.get('dbarg')], ignore_unknown_preds=self.config.get('ignore_unknown_preds', True))
else:
if self.config.get('pattern'):
local, dblist = self.get_training_db_paths(self.config.get('pattern').strip())
dbobj = []
# build database list from project dbs
if local:
for dbname in dblist:
dbobj.extend(parse_db(mlnobj, self.project.dbs[dbname].strip(),
ignore_unknown_preds=self.config.get('ignore_unknown_preds', True),
projectpath=os.path.join(self.dir, self.project.name)))
out(dbobj)
# build database list from filesystem dbs
else:
for dbpath in dblist:
dbobj.extend(Database.load(mlnobj, dbpath, ignore_unknown_preds= self.config.get('ignore_unknown_preds', True)))
# build single db from currently selected db
else:
dbobj = parse_db(mlnobj, db_content, projectpath=os.path.join(self.dir, self.project.name), dirs=[self.dir])
learning = MLNLearn(config=self.config, mln=mlnobj, db=dbobj)
result = learning.run()
# write to file if run from commandline, otherwise save result
# to project results
if options.get('outputfile') is not None:
output = StringIO.StringIO()
result.write(output)
with open(os.path.abspath(options.get('outputfile')), 'w') as f:
f.write(output.getvalue())
logger.info('saved result to {}'.format(os.path.abspath(options.get('outputfile'))))
elif self.save.get():
output = StringIO.StringIO()
result.write(output)
self.project.add_mln(self.output_filename.get(), output.getvalue())
self.mln_container.update_file_choices()
self.project.save(dirpath=self.project_dir)
logger.info('saved result to file mln/{} in project {}'.format(self.output_filename.get(), self.project.name))
else:
logger.debug("No output file given - results have not been saved.")
except:
traceback.print_exc()
# restore gui
sys.stdout.flush()
self.master.deiconify()
def infer(self, savegeometry=True, options={}, *args):
mln_content = self.mln_container.editor.get(
"1.0", END).encode('utf8').strip()
db_content = self.db_container.editor.get("1.0",
END).encode('utf8').strip()
# create conf from current gui settings
self.update_config()
# write gui settings
self.write_gconfig(savegeometry=savegeometry)
# hide gui
self.master.withdraw()
try:
print headline('PRACMLN QUERY TOOL')
print
if options.get('mlnarg') is not None:
mlnobj = MLN(mlnfile=os.path.abspath(options.get('mlnarg')),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
else:
mlnobj = parse_mln(
mln_content,
searchpaths=[self.dir],
projectpath=os.path.join(self.dir, self.project.name),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
if options.get('emlnarg') is not None:
emln_content = mlnpath(options.get('emlnarg')).content
else:
emln_content = self.emln_container.editor.get(
"1.0", END).encode('utf8').strip()
if options.get('dbarg') is not None:
dbobj = Database.load(mlnobj,
dbfiles=[options.get('dbarg')],
ignore_unknown_preds=self.config.get(
'ignore_unknown_preds', True))
else:
out(self.config.get('ignore_unknown_preds', True))
dbobj = parse_db(mlnobj,
db_content,
ignore_unknown_preds=self.config.get(
'ignore_unknown_preds', True))
if options.get('queryarg') is not None:
self.config["queries"] = options.get('queryarg')
infer = MLNQuery(config=self.config,
mln=mlnobj,
db=dbobj,
emln=emln_content)
result = infer.run()
# write to file if run from commandline, otherwise save result to project results
if options.get('outputfile') is not None:
output = StringIO.StringIO()
result.write(output)
with open(os.path.abspath(options.get('outputfile')),
'w') as f:
f.write(output.getvalue())
logger.info('saved result to {}'.format(
os.path.abspath(options.get('outputfile'))))
elif self.save.get():
output = StringIO.StringIO()
result.write(output)
fname = self.output_filename.get()
self.project.add_result(fname, output.getvalue())
self.project.save(dirpath=self.dir)
logger.info(
'saved result to file results/{} in project {}'.format(
fname, self.project.name))
else:
logger.debug(
'No output file given - results have not been saved.')
except:
traceback.print_exc()
# restore main window
sys.stdout.flush()
self.master.deiconify()
def eval(self, mln, dbs):
'''
Returns a confusion matrix for the given (learned) MLN evaluated on
the databases given in dbs.
'''
querypred = self.params.querypred
# query_dom = self.params.query_dom
# sig = ['?arg%d' % i for i, _ in enumerate(mln.predicates[query_pred])]
# querytempl = '%s(%s)' % (query_pred, ','.join(sig))
# dbs = map(lambda db: db.copy(mln), dbs)
for db_ in dbs:
# save and remove the query predicates from the evidence
db = db_.copy()
gndtruth = mln.ground(db)
gndtruth.apply_cw()
for atom, _ in db.gndatoms(querypred):
out('removing evidence', repr(atom))
del db.evidence[atom]
db.write()
stop()
try:
resultdb = MLNQuery(config=self.params.queryconf,
mln=mln,
method=InferenceMethods.WCSPInference,
db=db,
cw_preds=[
p.name for p in mln.predicates
if p.name != self.params.querypred
],
multicore=False).run().resultdb
result = mln.ground(db)
result.set_evidence(resultdb)
for variable in result.variables:
if variable.predicate.name != querypred: continue
pvalue = variable.evidence_value()
tvalue = variable.evidence_value()
prediction = [
a for a, v in variable.atomvalues(pvalue) if v == 1
]
truth = [
a for a, v in variable.atomvalues(tvalue) if v == 1
]
prediction = str(prediction[0]) if prediction else None
truth = str(truth[0]) if truth else None
self.confmat.addClassificationResult(prediction, truth)
# sig2 = list(sig)
# entityIdx = mln.predicates[query_pred].argdoms.index(query_dom)
# for entity in db.domains[]:
# sig2[entityIdx] = entity
# query = '%s(%s)' % (queryPred, ','.join(sig2))
# for truth in trueDB.query(query):
# truth = truth.values().pop()
# for pred in resultDB.query(query):
# pred = pred.values().pop()
# self.confMatrix.addClassificationResult(pred, truth)
# for e, v in trueDB.evidence.iteritems():
# if v is not None:
# db.addGroundAtom('%s%s' % ('' if v is True else '!', e))
except:
logger.critical(''.join(
traceback.format_exception(*sys.exc_info())))
def infer(self, savegeometry=True, options={}, *args):
mln_content = self.mln_container.editor.get("1.0", END).encode('utf8').strip()
db_content = self.db_container.editor.get("1.0", END).encode('utf8').strip()
# create conf from current gui settings
self.update_config()
# write gui settings
self.write_gconfig(savegeometry=savegeometry)
# hide gui
self.master.withdraw()
try:
print headline('PRACMLN QUERY TOOL')
print
if options.get('mlnarg') is not None:
mlnobj = MLN(mlnfile=os.path.abspath(options.get('mlnarg')),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
else:
mlnobj = parse_mln(mln_content, searchpaths=[self.dir],
projectpath=os.path.join(self.dir, self.project.name),
logic=self.config.get('logic', 'FirstOrderLogic'),
grammar=self.config.get('grammar', 'PRACGrammar'))
if options.get('emlnarg') is not None:
emln_content = mlnpath(options.get('emlnarg')).content
else:
emln_content = self.emln_container.editor.get("1.0", END).encode('utf8').strip()
if options.get('dbarg') is not None:
dbobj = Database.load(mlnobj, dbfiles=[options.get('dbarg')], ignore_unknown_preds=self.config.get('ignore_unknown_preds', True))
else:
out(self.config.get('ignore_unknown_preds', True))
dbobj = parse_db(mlnobj, db_content, ignore_unknown_preds=self.config.get('ignore_unknown_preds', True))
if options.get('queryarg') is not None:
self.config["queries"] = options.get('queryarg')
infer = MLNQuery(config=self.config, mln=mlnobj, db=dbobj, emln=emln_content)
result = infer.run()
# write to file if run from commandline, otherwise save result to project results
if options.get('outputfile') is not None:
output = StringIO.StringIO()
result.write(output)
with open(os.path.abspath(options.get('outputfile')), 'w') as f:
f.write(output.getvalue())
logger.info('saved result to {}'.format(os.path.abspath(options.get('outputfile'))))
elif self.save.get():
output = StringIO.StringIO()
result.write(output)
fname = self.output_filename.get()
self.project.add_result(fname, output.getvalue())
self.project.save(dirpath=self.dir)
logger.info('saved result to file results/{} in project {}'.format(fname, self.project.name))
else:
logger.debug('No output file given - results have not been saved.')
except:
traceback.print_exc()
# restore main window
sys.stdout.flush()
self.master.deiconify()
def _print_unsatisfied_constraints(self):
out(" %d unsatisfied: %s" % (len(self.unsatisfied), map(str, [self.clauses[i] for i in self.unsatisfied])), tb=2)