def __init__(self,
name,
configuration_dict,
non_ids=None,
display_synonyms=None,
kv_separator='__',
kvsv_separator='=',
nested_separator='\"\"',
sorted_by_key=True,
first_ks=None,
last_ks=None,
length_limit=255):
super(Configuration, self).__init__()
self.name = name
self.dict = configuration_dict
self.sorted_by_key = sorted_by_key
self.kv_separator = kv_separator
self.kvsv_separator = kvsv_separator
self.nested_separator = nested_separator
self.length_limit = length_limit
self.display_synonyms = display_synonyms if display_synonyms else {}
self.first_ks = first_ks if first_ks else []
self.last_ks = last_ks if last_ks else []
#Keys here won't make it to the configuration string
if not non_ids:
self.non_ids = set()
elif is_iterable(non_ids):
self.non_ids = set(non_ids)
else:
raise Exception('non_ids must be None or an iterable')
def assign_feature(self, substructures):
if not is_iterable(substructures):
substructures = (substructures,)
features = self.hash(substructures) % self.fold_size
if self._save_map:
for feature, key in izip(features, substructures):
self._features[feature].add(key)
return features
def molids2mols(self, molids):
"""Returns a list of rdkit molecules (None also possible) for the molids."""
if not is_iterable(molids):
molids = (molids,)
return list(map(self.molid2mol, molids))