def domain_map(features, feature_format, train_context, test_context,
intervals={},
format='arff',
positive_class=None):
dataset = None
if feature_format in ['rsd', 'aleph']:
train_rsd = RSDConverter(train_context)
test_rsd = RSDConverter(test_context, discr_intervals=intervals)
mapper_target_name = train_context.target_table + '_mapper'
train_examples = train_rsd.all_examples(pred_name=mapper_target_name)
test_examples = test_rsd.all_examples(pred_name=mapper_target_name)
if feature_format == 'aleph':
features = aleph_to_rsd_features(features)
prolog_bk = '\n'.join([
_example_ids('testExampleIDs', test_examples),
'%% test examples',
test_examples,
'%% train examples',
train_examples,
'%% train background knowledge',
train_rsd.background_knowledge(),
'%% test background knowledge',
test_rsd.background_knowledge(),
_feature_numbers(features),
'%% features',
features,
])
THIS_DIR = os.path.dirname(__file__) if os.path.dirname(__file__) else '.'
f = tempfile.NamedTemporaryFile(delete=False)
f.write(prolog_bk)
f.close()
cmd_args = ['yap', '-L', '--', '%s/mapper.pl' % THIS_DIR, f.name, mapper_target_name]
evaluations = subprocess.check_output(cmd_args)
dataset = dump_dataset(features, feature_format, evaluations,
train_context,
format=format,
positive_class=positive_class)
# Cleanup
os.remove(f.name)
elif feature_format == 'treeliker':
# We provide treeliker with the test dataset
# since it has a built-in ability to evaluate features
treeliker_test = TreeLikerConverter(test_context,
discr_intervals=intervals)
treeliker = features
treeliker.test_dataset = treeliker_test.dataset()
_, test_dataset = treeliker.run()
if format == 'arff':
dataset = test_dataset
else:
return 'unsupported format'
return dataset
def domain_map(features,
feature_format,
train_context,
test_context,
intervals={},
format='arff',
positive_class=None):
'''
Use the features returned by a propositionalization method to map
unseen test examples into the new feature space.
:param features: string of features as returned by rsd, aleph or treeliker
:param feature_format: 'rsd', 'aleph', 'treeliker'
:param train_context: DBContext with training examples
:param test_context: DBContext with test examples
:param intervals: discretization intervals (optional)
:param format: output format (only arff is used atm)
:param positive_class: required for aleph
:return: returns the test examples in propositional form
:rtype: str
:Example:
>>> test_arff = mapper.domain_map(features, 'rsd', train_context, test_context)
'''
dataset = None
if feature_format in ['rsd', 'aleph']:
train_rsd = RSDConverter(train_context)
test_rsd = RSDConverter(test_context, discr_intervals=intervals)
mapper_target_name = train_context.target_table + '_mapper'
train_examples = train_rsd.all_examples(pred_name=mapper_target_name)
test_examples = test_rsd.all_examples(pred_name=mapper_target_name)
if feature_format == 'aleph':
features = aleph_to_rsd_features(features)
prolog_bk = '\n'.join([
_example_ids('testExampleIDs', test_examples),
'%% test examples',
test_examples,
'%% train examples',
train_examples,
'%% train background knowledge',
train_rsd.background_knowledge(),
'%% test background knowledge',
test_rsd.background_knowledge(),
_feature_numbers(features),
'%% features',
features,
])
THIS_DIR = os.path.dirname(__file__) if os.path.dirname(
__file__) else '.'
f = tempfile.NamedTemporaryFile(delete=False)
f.write(prolog_bk)
f.close()
cmd_args = [
'yap', '-L', '--',
'%s/mapper.pl' % THIS_DIR, f.name, mapper_target_name
]
evaluations = subprocess.check_output(cmd_args)
dataset = dump_dataset(features,
feature_format,
evaluations,
train_context,
format=format,
positive_class=positive_class)
# Cleanup
os.remove(f.name)
elif feature_format == 'treeliker':
# We provide treeliker with the test dataset
# since it has a built-in ability to evaluate features
treeliker_test = TreeLikerConverter(test_context,
discr_intervals=intervals)
treeliker = features
treeliker.test_dataset = treeliker_test.dataset()
_, test_dataset = treeliker.run()
if format == 'arff':
dataset = test_dataset
else:
return 'unsupported format'
return dataset
def database_rsd_converter(input_dict):
dump = input_dict['dump'] == 'true'
rsd = RSDConverter(input_dict['context'], discr_intervals=input_dict['discr_intervals'] or {})
return {'examples' : rsd.all_examples(), 'bk' : rsd.background_knowledge()}
