def test_dump_to_csv(tmpdir):
f = tmpdir.join('out.csv')
matrix, attributes = preprocess.to_matrix(fx.data(),
do_binarize=True,
bins=4)
preprocess.dump_to_csv(matrix, attributes, str(f))
df = pd.read_csv(f, sep=';')
assert len(df) == 10
assert list(df.columns) == [
'id', '2.6429less_than=lefthippocampusless_than2.850575',
'2.850575less_than=lefthippocampusless_than3.05825',
'3.05825less_than=lefthippocampusless_than3.2659249999999997',
'3.2659249999999997less_than=lefthippocampusless_than3.4736',
'63.0less_than=subjectageyearsless_than67.0',
'67.0less_than=subjectageyearsless_than71.0',
'71.0less_than=subjectageyearsless_than75.0',
'75.0less_than=subjectageyearsless_than79.0', 'alzheimerbroadcategory'
]
def main(clean_files=False):
"""
:param clean_files: if True, clean files afterwards
"""
# Read inputs
inputs = io_helper.fetch_data()
data = inputs["data"]
beam = parameters.get_parameter('beam', int, 10)
support = parameters.get_parameter('support', float, '0.00001')
out_file = 'input.csv'
rules_out_file = 'rules.txt'
matrix, attributes = preprocess.to_matrix(data)
preprocess.dump_to_csv(matrix, attributes, out_file)
# Call hedwig with sensible defaults
examples_file = out_file
empty_bk = tempfile.mkdtemp()
call([
'python', '-m'
'hedwig.__main__', empty_bk, examples_file, '--beam',
str(beam), '--support',
str(support), '-f', 'csv', '-l', '-o', rules_out_file, '--nocache'
])
with open(rules_out_file) as f:
results = f.read()
if clean_files:
os.remove(out_file)
os.remove(rules_out_file)
io_helper.save_results(results.replace('less_than', '<'),
shapes.Shapes.TEXT)
DEFAULT_DOCKER_IMAGE = 'python-hedwig'
if __name__ == '__main__':
# Configure logging
logging.basicConfig(level=logging.INFO)
# Read inputs
inputs = io_helper.fetch_data()
data = inputs["data"]
out_file = 'input.csv'
rules_out_file = 'rules.txt'
matrix, attributes = preprocess.to_matrix(data)
preprocess.dump_to_csv(matrix, attributes, out_file)
# Call hedwig with sensible defaults
examples_file = out_file
empty_bk = tempfile.mkdtemp()
call([
'python', '-m', 'hedwig', empty_bk, examples_file, '-f', 'csv', '-l',
'-o', rules_out_file, '--nocache'
])
results = ''
with open(rules_out_file) as f:
results = f.read()
io_helper.save_results(results, '', 'text/plain')