rxn.chemutils.tokenization.tokenize_file

rxn.chemutils.tokenization.tokenize_file(input_file, output_file, fallback_value='')[source]

Tokenize a file containing SMILES strings.

Parameters
  • input_file (Union[str, PathLike]) – file to tokenize.

  • output_file (Union[str, PathLike]) – where to save the tokenized file.

  • fallback_value (str, default: '') – placeholder for strings that cannot be tokenized.

Return type

None