def ilp_hedwig(input_dict):
import hedwig
format = input_dict['format']
suffix = '.' + format
bk_suffix = suffix
if format == 'csv':
bk_suffix = '.tsv'
# Writes examples file
data_file = tempfile.NamedTemporaryFile(delete=False, suffix=format)
data_file.write(input_dict['examples'])
data_file.close()
# Write BK files to BK dir
bk_dir = tempfile.mkdtemp()
if format == 'csv':
suffix = 'tsv'
for bk_file in input_dict['bk_file']:
tmp_bk_file = tempfile.NamedTemporaryFile(delete=False,
dir=bk_dir,
suffix=bk_suffix)
tmp_bk_file.write(bk_file)
tmp_bk_file.close()
output_file = tempfile.NamedTemporaryFile(delete=False)
hedwig.run({
'bk_dir': bk_dir,
'data': data_file.name,
'format': format,
'output': output_file.name,
'mode': 'subgroups',
'target': input_dict['target'] if 'target' in input_dict else None,
'score': input_dict['score'],
'negations': input_dict['negations'] == 'true',
'alpha': float(input_dict['alpha']),
'adjust': input_dict['adjust'],
'FDR': float(input_dict['fdr']),
'leaves': input_dict['leaves'] == 'true',
'learner': 'heuristic',
'optimalsubclass': input_dict['optimalsubclass'] == 'true',
'uris': input_dict['uris'] == 'true',
'beam': int(input_dict['beam']),
'support': float(input_dict['support']),
'depth': int(input_dict['depth']),
'nocache': True,
'covered': None
})
rules = open(output_file.name).read()
return {'rules': rules}
def ilp_hedwig(input_dict):
import hedwig
format = input_dict['format']
suffix = '.' + format
bk_suffix = suffix
if format == 'csv':
bk_suffix = '.tsv'
# Writes examples file
data_file = tempfile.NamedTemporaryFile(delete=False, suffix=format)
data_file.write(input_dict['examples'])
data_file.close()
# Write BK files to BK dir
bk_dir = tempfile.mkdtemp()
if format == 'csv':
suffix = 'tsv'
for bk_file in input_dict['bk_file']:
tmp_bk_file = tempfile.NamedTemporaryFile(delete=False, dir=bk_dir, suffix=bk_suffix)
tmp_bk_file.write(bk_file)
tmp_bk_file.close()
output_file = tempfile.NamedTemporaryFile(delete=False)
hedwig.run({
'bk_dir': bk_dir,
'data': data_file.name,
'format': format,
'output': output_file.name,
'mode': 'subgroups',
'target': input_dict['target'] if 'target' in input_dict else None,
'score': input_dict['score'],
'negations': input_dict['negations'] == 'true',
'alpha': float(input_dict['alpha']),
'adjust': input_dict['adjust'],
'FDR': float(input_dict['fdr']),
'leaves': input_dict['leaves'] == 'true',
'learner': 'heuristic',
'optimalsubclass': input_dict['optimalsubclass'] == 'true',
'uris': input_dict['uris'] == 'true',
'beam': int(input_dict['beam']),
'support': float(input_dict['support']),
'depth': int(input_dict['depth']),
'nocache': True,
'covered': None
})
rules = open(output_file.name).read()
return {'rules': rules}
def ilp_hedwig(input_dict):
import hedwig
format = input_dict['format']
ont_format = '.tsv' if format == 'csv' else '.' + format
examples_file = tempfile.NamedTemporaryFile(suffix='.' + format,
delete=False)
examples_file.write(input_dict['examples'])
examples_file.close()
bk_dir = tempfile.mkdtemp()
for bk in input_dict['bk']:
f = tempfile.NamedTemporaryFile(suffix=ont_format,
delete=False,
dir=bk_dir)
f.write(bk)
f.close()
result = hedwig.run({
'data': examples_file.name,
'bk_dir': bk_dir,
'adjust': input_dict['adjust'],
'FDR': float(input_dict['fdr']),
'format': format,
'support': float(input_dict['sup']),
'learner': input_dict['learner'],
'depth': int(input_dict['depth']),
'optimalsubclass': input_dict['optimal'] == "true",
'beam': int(input_dict['beam']),
'alpha': float(input_dict['alpha']),
'score': input_dict['score_fun'],
'uris': input_dict['uris'],
'negations': input_dict['negations'] == "true",
# Presets
'leaves': True,
'covered': None,
'target': None,
'mode': 'subgroups',
'output': 'foo.txt',
'verbose': False,
'nocache': True
})
return {'rules': result}
def ilp_hedwig(input_dict):
import hedwig
format = input_dict['format']
ont_format = '.tsv' if format == 'csv' else '.' + format
examples_file = tempfile.NamedTemporaryFile(suffix='.' + format, delete=False)
examples_file.write(input_dict['examples'])
examples_file.close()
bk_dir = tempfile.mkdtemp()
for bk in input_dict['bk']:
f = tempfile.NamedTemporaryFile(suffix=ont_format, delete=False, dir=bk_dir)
f.write(bk)
f.close()
result = hedwig.run({
'data': examples_file.name,
'bk_dir': bk_dir,
'adjust': input_dict['adjust'],
'FDR': float(input_dict['fdr']),
'format': format,
'support': float(input_dict['sup']),
'learner': input_dict['learner'],
'depth': int(input_dict['depth']),
'optimalsubclass': input_dict['optimal'] == "true",
'beam': int(input_dict['beam']),
'alpha': float(input_dict['alpha']),
'score': input_dict['score_fun'],
'uris': input_dict['uris'],
'negations': input_dict['negations'] == "true",
# Presets
'leaves': True,
'covered': None,
'target': None,
'mode': 'subgroups',
'output': 'foo.txt',
'verbose': False,
'nocache': True
})
return {'rules': result}
parser.add_argument('-b',
'--beam',
default=Defaults.BEAM_SIZE,
type=int,
help='Beam size.')
parser.add_argument('-S',
'--support',
default=Defaults.SUPPORT,
type=float,
help='Minimum support.')
parser.add_argument('-d',
'--depth',
default=Defaults.DEPTH,
type=int,
help='Maximum number of conjunctions.')
parser.add_argument('-C',
'--nocache',
action='store_true',
help='Don\'t cache background knowledge graph files.')
parser.add_argument("-v",
"--verbose",
help="Increase output verbosity.",
action="store_true")
args = parser.parse_args()
hedwig.run(args.__dict__, cli=True)
help='Max false discovery rate; applies only if \
"--adjust fdr" is used.',
)
parser.add_argument("-l", "--leaves", action="store_true", help="Use instance names in rule conjunctions.")
parser.add_argument(
"-L", "--learner", choices=["heuristic", "optimal"], default="heuristic", help="Type of learner to use."
)
parser.add_argument(
"-O",
"--optimalsubclass",
action="store_true",
help="In each step the full hierarchy under a particular \
concept is searched",
)
parser.add_argument("-u", "--uris", action="store_true", help="Show URIs in rule conjunctions.")
parser.add_argument("-b", "--beam", default="20", type=int, help="Beam size.")
parser.add_argument("-S", "--support", default="0.1", type=float, help="Minimum support.")
parser.add_argument("-d", "--depth", default="5", type=int, help="Maximum number of conjunctions.")
parser.add_argument("-v", "--verbose", help="Increase output verbosity.", action="store_true")
args = parser.parse_args()
hedwig.run(args.__dict__, cli=True)
