def induce(self,
b,
filestem='default',
examples=None,
pos=None,
neg=None,
cn2sd=True):
"""
Generate features and find subgroups.
@param filestem The base name of this experiment.
@param examples Classified examples; can be used instead of separate pos / neg files below.
@param pos String of positive examples.
@param neg String of negative examples.
@param b String with background knowledge.
@param cn2sd Find subgroups after feature construction?
Returns a tuple (features, weka, rules), where:
- features is a set of prolog clauses of generated features,
- weka is the propositional form of the input data,
- rules is a set of generated cn2sd subgroup descriptions;
this will be an empty string if cn2sd is set to False.
"""
# Write the inputs
self.__prepare(filestem, b, examples=examples, pos=pos, neg=neg)
# Write scripts
self.__scripts(filestem)
# Run the script
logger.info("Running RSD...")
try:
for script in RSD.SCRIPTS:
# Skip subgroup discovery part?
if script == RSD.SUBGROUPS and not cn2sd:
continue
p = SafePopen(['yap', '-s50000', '-h200000', '-L', script],
cwd=self.tmpdir,
stdout=PIPE).safe_run()
stdout_str, stderr_str = p.communicate()
logger.debug(stdout_str)
logger.debug(stderr_str)
logger.info("Done.")
# Return the rules written in the output file.
features = open('%s/%s' %
(self.tmpdir, filestem + '_frs.pl')).read()
weka = open('%s/%s' % (self.tmpdir, filestem + '.arff')).read()
rules = open(
'%s/%s' %
(self.tmpdir, filestem + '.rules')).read() if cn2sd else ''
self.__cleanup()
return (features, weka, rules)
except OSError:
raise RuntimeError(
"Yap compiler could not be loaded! (see http://www.dcc.fc.up.pt/~vsc/Yap/)."
)
def induce(self, b, filestem='default',
examples=None,
pos=None,
neg=None,
cn2sd=True,
printOutput=False):
"""
Generate features and find subgroups.
@param filestem The base name of this experiment.
@param examples Classified examples; can be used instead of separate pos / neg files below.
@param pos String of positive examples.
@param neg String of negative examples.
@param b String with background knowledge.
@param cn2sd Find subgroups after feature construction?
Returns a tuple (features, weka, rules), where:
- features is a set of prolog clauses of generated features,
- weka is the propositional form of the input data,
- rules is a set of generated cn2sd subgroup descriptions;
this will be an empty string if cn2sd is set to False.
"""
# Write the inputs
self.__prepare(filestem, b, examples=examples, pos=pos, neg=neg)
# Write scripts
self.__scripts(filestem)
dumpFile = None
if not printOutput:
dumpFile = tempfile.TemporaryFile()
# Run the script
logger.info("Running RSD...")
try:
for script in RSD.SCRIPTS:
# Skip subgroup discovery part?
if script == RSD.SUBGROUPS and not cn2sd:
continue
p = SafePopen(['yap', '-s50000', '-h200000', '-L', script],
cwd=self.tmpdir,
stdout=dumpFile,
stderr=dumpFile).safe_run()
stdout_str, stderr_str = p.communicate()
logger.debug(stdout_str)
logger.debug(stderr_str)
logger.info("Done.")
# Return the rules written in the output file.
features = open('%s/%s' % (self.tmpdir, filestem + '_frs.pl')).read()
weka = open('%s/%s' % (self.tmpdir, filestem + '.arff')).read()
rules = open('%s/%s' % (self.tmpdir, filestem + '.rules')).read() if cn2sd else ''
self.__cleanup()
return (features, weka, rules)
except OSError:
raise RuntimeError("Yap compiler could not be loaded! (see http://www.dcc.fc.up.pt/~vsc/Yap/).")
def induce(self, mode, pos, neg, b, filestem='default', printOutput=False):
"""
Induce a theory or features in 'mode'.
:param filestem: The base name of this experiment.
:param mode: In which mode to induce rules/features.
:param pos: String of positive examples.
:param neg: String of negative examples.
:param b: String of background knowledge.
:return: The theory as a string or an arff dataset in induce_features mode.
:rtype: str
"""
# Write the inputs to appropriate files.
self.__prepare(filestem, pos, neg, b)
# Make a script to run aleph (with appropriate settings).
self.__script(mode, filestem)
logger.info("Running aleph...")
dumpFile = None
if not printOutput:
dumpFile = tempfile.TemporaryFile()
# Run the aleph script.
p = SafePopen(['yap', '-s50000', '-h200000', '-L', Aleph.SCRIPT],
cwd=self.tmpdir,
stdout=dumpFile,
stderr=dumpFile).safe_run()
stdout_str, stderr_str = p.communicate()
logger.info("Done.")
result = None
if mode != 'induce_features':
# Return the rules written in the output file.
rules_fn = filestem + Aleph.RULES_SUFFIX
result = open('%s/%s' % (self.tmpdir, rules_fn)).read()
features = None
else:
features_fn = filestem + Aleph.FEATURES_SUFFIX
features = open('%s/%s' % (self.tmpdir, features_fn)).read()
dataset_fn = filestem + Aleph.PROP_DATASET_SUFFIX
pl_dataset = open('%s/%s' % (self.tmpdir, dataset_fn)).read()
result = self.__to_arff(features, pl_dataset, filestem)
# Cleanup.
self.__cleanup()
return (result, features)
def induce(self, mode, pos, neg, b, filestem='default', printOutput=False):
"""
Induce a theory or features in 'mode'.
@param filestem The base name of this experiment.
@param mode In which mode to induce rules/features.
@param pos String of positive examples.
@param neg String of negative examples.
@param b String with background knowledge.
@return The theory as a string or an arff dataset in induce_features mode.
"""
# Write the inputs to appropriate files.
self.__prepare(filestem, pos, neg, b)
# Make a script to run aleph (with appropriate settings).
self.__script(mode, filestem)
logger.info("Running aleph...")
dumpFile = None
if not printOutput:
dumpFile = tempfile.TemporaryFile()
# Run the aleph script.
p = SafePopen(['yap', '-s50000', '-h200000', '-L', Aleph.SCRIPT],
cwd=self.tmpdir,
stdout=dumpFile,
stderr=dumpFile
).safe_run()
stdout_str, stderr_str = p.communicate()
logger.info("Done.")
result = None
if mode != 'induce_features':
# Return the rules written in the output file.
rules_fn = filestem + Aleph.RULES_SUFFIX
result = open('%s/%s' % (self.tmpdir, rules_fn)).read()
features = None
else:
features_fn = filestem + Aleph.FEATURES_SUFFIX
features = open('%s/%s' % (self.tmpdir, features_fn)).read()
dataset_fn = filestem + Aleph.PROP_DATASET_SUFFIX
pl_dataset = open('%s/%s' % (self.tmpdir, dataset_fn)).read()
result = self.__to_arff(features, pl_dataset, filestem)
# Cleanup.
self.__cleanup()
return (result, features)
def induce(self, mode, pos, neg, b, filestem='default'):
"""
Induce a theory in 'mode'.
@param filestem The base name of this experiment.
@param mode In which mode to induce rules.
@param pos String of positive examples.
@param neg String of negative examples.
@param b String with background knowledge.
"""
# Write the inputs to appropriate files.
self.__prepare(filestem, pos, neg, b)
# Make a script to run aleph (with appropriate settings, stack/heap sizes, ...).
self.__script(mode, filestem)
logger.info("Running aleph...")
# Run the aleph script.
p = SafePopen(['yap', '-s50000', '-h200000', '-L', Aleph.SCRIPT], cwd=self.tmpdir, stdout=PIPE).safe_run()
stdout_str, stderr_str = p.communicate()
logger.debug(stdout_str)
logger.debug(stderr_str)
logger.info("Done.")
# Return the rules written in the output file.
rules = open('%s/%s' % (self.tmpdir, filestem + Aleph.RULES_SUFFIX)).read()
#shutil.copy('%s/%s.py' % (self.tmpdir, filestem), '/home/anzev/programiranje/sdm/results/')
# Cleanup.
self.__cleanup()
return rules
