def main(input_filename, map_filename, output_filename, column_indices=None):
"""
Get regression targets.
Parameters
----------
input_filename : str
PCBA data filename.
map_filename : str
ID->SMILES map filename.
output_filename : str
Output filename.
column_indices : list, optional
Column indices to include. If None, compounds are classified by
activity.
"""
parser = PcbaParser(input_filename, map_filename,
column_indices=column_indices)
if column_indices is not None:
print "Extracting data from the following columns:"
for col in parser.get_column_names():
print '\t', col
smiles, targets = parser.get_targets()
# print the fraction of valid assay records that were found in the map
total = np.count_nonzero(~np.isnan(parser.read_data().PUBCHEM_CID))
print '{}/{} records matched'.format(len(targets), total)
# save SMILES and targets
write_pickle({'smiles': smiles, 'targets': targets}, output_filename)
def test_read_data(self):
"""
Test Nci60Parser.read_data.
"""
df = self.engine.read_data()
fixed_count = df.count().values.sum() # count excluding NaNs
# use PcbaParser to read data (w/o proper NaN handling)
engine = PcbaParser(self.data_filename, self.map_filename, delimiter="\t", primary_key="NSC", id_prefix="NSC")
df = engine.read_data()
broken_count = df.count().values.sum()
assert fixed_count < broken_count
def test_read_data(self):
"""
Test Nci60Parser.read_data.
"""
df = self.engine.read_data()
fixed_count = df.count().values.sum() # count excluding NaNs
# use PcbaParser to read data (w/o proper NaN handling)
engine = PcbaParser(self.data_filename,
self.map_filename,
delimiter='\t',
primary_key='NSC',
id_prefix='NSC')
df = engine.read_data()
broken_count = df.count().values.sum()
assert fixed_count < broken_count
