zerodivision error in bondtypefeaturizer

[kjappelbaum]

concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/process.py", line 246, in _process_worker
    r = call_item.fn(*call_item.args, **call_item.kwargs)
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/process.py", line 205, in _process_chunk
    return [fn(*args) for args in chunk]
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/process.py", line 205, in <listcomp>
    return [fn(*args) for args in chunk]
  File "/Users/kevinmaikjablonka/git/openbioml/chemnlp/data/tabular/inverse_1/transform.py", line 69, in featurize_smiles
    return FEATURIZER.featurize(molecule)
  File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/base.py", line 247, in featurize
    features = [
  File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/base.py", line 248, in <listcomp>
    feature for f in self.featurizers for feature in f.featurize(molecule).flatten()
  File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/bonds.py", line 448, in featurize
    return np.array(self._get_bond_distribution(molecule=molecule)).reshape(1, -1)
  File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/bonds.py", line 434, in _get_bond_distribution
    bond_proportion = [count / total_bond_count for count in num_bonds]
  File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/bonds.py", line 434, in <listcomp>
    bond_proportion = [count / total_bond_count for count in num_bonds]
ZeroDivisionError: division by zero
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/kevinmaikjablonka/git/openbioml/chemnlp/data/tabular/inverse_1/transform.py", line 96, in <module>
    transform()
  File "/Users/kevinmaikjablonka/git/openbioml/chemnlp/data/tabular/inverse_1/transform.py", line 83, in transform
    for feature in executor.map(featurize_smiles, merged["SMILES"]):
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/process.py", line 562, in _chain_from_iterable_of_lists
    for element in iterable:
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/_base.py", line 609, in result_iterator
    yield fs.pop().result()
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/_base.py", line 439, in result
    return self.__get_result()
  File "/Users/kevinmaikjablonka/miniconda3/envs/chemnlp3.9/lib/python3.9/concurrent/futures/_base.py", line 391, in __get_result
    raise self._exception
ZeroDivisionError: division by zero

[Harkhymadhe]

Just seeing this now. This should be fixed already in my new PR.

[Harkhymadhe]

Just in case, did you check if the issue persists for all SMILES or for selected SMILES?

[kjappelbaum]

Just seeing this now. This should be fixed already in my new PR.

do we also have a test for that?

[Harkhymadhe]

Just seeing this now. This should be fixed already in my new PR.

do we also have a test for that?

There are no specific tests for this except to run the regression test suite, which I have, and all is well.

File "/Users/kevinmaikjablonka/git/lamalab-org/chem-caption/src/chemcaption/featurize/bonds.py", line 434, in
bond_proportion = [count / total_bond_count for count in num_bonds]
ZeroDivisionError: division by zero

The only way we'd get a bug of this nature is for the total_bond_count to be zero, which should not be possible. Is a trivial bug that I probably just fixed in passing.