nerdd-module 0.3.6__tar.gz → 0.3.8__tar.gz

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nerdd-module
-Version: 0.3.6
+Version: 0.3.8
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/__init__.py

@@ -3,6 +3,7 @@ from .model import *
 from .polyfills import get_entry_points
 from .problem import *
 from .version import *
+from .output import *
 
 for entry_point in get_entry_points("nerdd-module.plugins"):
     entry_point.load()

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/model/model.py

@@ -49,10 +49,6 @@ class Model(ABC):
     def _get_postprocessing_steps(self, output_format: Optional[str], **kwargs: Any) -> List[Step]:
         pass
 
-    @abstractmethod
-    def _get_output_step(self, output_format: Optional[str], **kwargs: Any) -> OutputStep:
-        pass
-
     def predict(
         self,
         input: Any,
@@ -63,14 +59,15 @@ class Model(ABC):
         input_steps = self._get_input_steps(input, input_format, **kwargs)
         preprocessing_steps = self._get_preprocessing_steps(input, input_format, **kwargs)
         postprocessing_steps = self._get_postprocessing_steps(output_format, **kwargs)
-        output_step = self._get_output_step(output_format, **kwargs)
+        output_step = postprocessing_steps[-1]
+
+        assert isinstance(output_step, OutputStep), "The last step must be an OutputStep."
 
         steps = [
             *input_steps,
             *preprocessing_steps,
             PredictionStep(self, batch_size=self.batch_size, **kwargs),
             *postprocessing_steps,
-            output_step,
         ]
 
         # build the pipeline from the list of steps

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/model/simple_model.py

@@ -14,7 +14,7 @@ from ..config import (
 from ..input import DepthFirstExplorer
 from ..preprocessing import PreprocessingStep
 from ..problem import Problem
-from ..steps import OutputStep, Step
+from ..steps import Step
 from ..util import get_file_path_to_instance
 from .assign_mol_id_step import AssignMolIdStep
 from .assign_name_step import AssignNameStep
@@ -66,12 +66,9 @@ class SimpleModel(Model):
             ConvertRepresentationsStep(
                 self.get_config().get("result_properties", []), output_format, **kwargs
             ),
+            WriteOutputStep(output_format, **kwargs),
         ]
 
-    def _get_output_step(self, output_format: Optional[str], **kwargs: Any) -> OutputStep:
-        output_format = output_format or "pandas"
-        return WriteOutputStep(output_format, **kwargs)
-
     def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
         return mol, []
 
@@ -129,9 +126,7 @@ class SimpleModel(Model):
             {"name": "source"},
             {"name": "name", "type": "string"},
             {"name": "input_mol", "type": "mol"},
-            {"name": "input_smiles", "type": "string"},
             {"name": "preprocessed_mol", "type": "mol"},
-            {"name": "preprocessed_smiles", "type": "string"},
         ]
 
         default_properties_end = [

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/model/write_output_step.py

@@ -17,3 +17,6 @@ class WriteOutputStep(OutputStep):
         writer = Writer.get_writer(self._output_format, **self._kawrgs)
         result = writer.write(source)
         return result
+
+    def __repr__(self) -> str:
+        return f"WriteOutputStep(output_format={self._output_format}, kwargs={self._kawrgs})"

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/output/__init__.py

@@ -1,6 +1,7 @@
 from .csv_writer import *
+from .file_writer import *
 from .iterator_writer import *
 from .pandas_writer import *
 from .record_list_writer import *
-from .writer import *
 from .sdf_writer import *
+from .writer import *

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/output/writer.py

@@ -50,5 +50,5 @@ class Writer(ABC):
         return _factories[output_format](kwargs)
 
     @classmethod
-    def get_output_formats(self) -> List[str]:
+    def get_output_formats(cls) -> List[str]:
         return list(_factories.keys())

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/preprocessing/filter_by_element.py

@@ -1,8 +1,8 @@
-from typing import Iterable, List, Optional, Tuple
+from typing import Iterable, List, Optional, Set, Tuple
 
 from rdkit.Chem import Mol
 
-from ..problem import Problem
+from ..problem import InvalidElementsProblem, Problem
 from .preprocessing_step import PreprocessingStep
 
 __all__ = ["FilterByElement", "ORGANIC_SUBSET"]
@@ -37,7 +37,7 @@ class FilterByElement(PreprocessingStep):
         problems = []
         result_mol = mol
 
-        elements = set(atom.GetSymbol() for atom in mol.GetAtoms())
+        elements: Set[str] = set(atom.GetSymbol() for atom in mol.GetAtoms())
         invalid_elements = elements - self.allowed_elements
 
         # special case: hydrogens are not recognized by mol.GetAtoms()
@@ -52,16 +52,6 @@ class FilterByElement(PreprocessingStep):
             if self.remove_invalid_molecules:
                 result_mol = None
 
-            if len(invalid_elements) > 3:
-                invalid_elements_str = ", ".join(list(invalid_elements)[:3]) + "..."
-            else:
-                invalid_elements_str = ", ".join(list(invalid_elements))
-
-            problems.append(
-                Problem(
-                    "invalid_elements",
-                    f"Molecule contains invalid elements {invalid_elements_str}",
-                )
-            )
+            problems.append(InvalidElementsProblem(invalid_elements))
 
         return result_mol, problems

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/preprocessing/filter_by_weight.py

@@ -3,7 +3,7 @@ from typing import List, Optional, Tuple
 from rdkit.Chem import Mol
 from rdkit.Chem.rdMolDescriptors import CalcExactMolWt
 
-from ..problem import Problem
+from ..problem import InvalidWeightProblem, Problem
 from .preprocessing_step import PreprocessingStep
 
 
@@ -27,14 +27,6 @@ class FilterByWeight(PreprocessingStep):
         if weight < self.min_weight or weight > self.max_weight:
             if self.remove_invalid_molecules:
                 result_mol = None
-            problems.append(
-                Problem(
-                    type="invalid_weight",
-                    message=(
-                        f"Molecular weight {weight:.2f} out of range "
-                        f"[{self.min_weight}, {self.max_weight}]"
-                    ),
-                )
-            )
+            problems.append(InvalidWeightProblem(weight, self.min_weight, self.max_weight))
 
         return result_mol, problems

nerdd_module-0.3.8/nerdd_module/problem.py

@@ -0,0 +1,42 @@
+from typing import Iterable, NamedTuple
+
+__all__ = [
+    "Problem",
+    "InvalidSmiles",
+    "UnknownProblem",
+    "InvalidWeightProblem",
+    "InvalidElementsProblem",
+]
+
+
+class Problem(NamedTuple):
+    type: str
+    message: str
+
+
+def InvalidSmiles() -> Problem:
+    return Problem(type="invalid_smiles", message="Invalid SMILES string")
+
+
+def UnknownProblem() -> Problem:
+    return Problem(type="unknown", message="Unknown error occurred")
+
+
+def InvalidWeightProblem(weight: float, min_weight: float, max_weight: float) -> Problem:
+    return Problem(
+        type="invalid_weight",
+        message=(f"Molecular weight {weight:.2f} out of range " f"[{min_weight}, {max_weight}]"),
+    )
+
+
+def InvalidElementsProblem(invalid_elements: Iterable[str]) -> Problem:
+    invalid_element_list = list(invalid_elements)
+    if len(invalid_element_list) > 3:
+        invalid_elements_str = ", ".join(invalid_element_list[:3]) + "..."
+    else:
+        invalid_elements_str = ", ".join(invalid_element_list)
+
+    return Problem(
+        "invalid_elements",
+        f"Molecule contains invalid elements {invalid_elements_str}",
+    )

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/tests/models/AtomicMassModel.py

@@ -56,6 +56,7 @@ class AtomicMassModel(SimpleModel):
     def _get_base_config(self):
         return {
             "name": "atomic_mass_model",
+            "version": "0.1",
             "job_parameters": [
                 {"name": "multiplier", "type": "float"},
             ],

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module/tests/models/MolWeightModel.py

@@ -39,6 +39,7 @@ class MolWeightModel(SimpleModel):
     def _get_base_config(self):
         return {
             "name": "mol_scale",
+            "version": "0.1",
             "description": "Computes the molecular weight of a molecule",
             "job_parameters": [
                 {"name": "multiplier", "type": "float"},

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/nerdd_module.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nerdd-module
-Version: 0.3.6
+Version: 0.3.8
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.6 → nerdd_module-0.3.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.6"
+version = "0.3.8"
 description = "Base package to create NERDD modules"
 readme = "README.md"
 license = { file = "LICENSE" }

nerdd_module-0.3.6/nerdd_module/problem.py

@@ -1,16 +0,0 @@
-from typing import NamedTuple
-
-__all__ = ["Problem", "InvalidSmiles", "UnknownProblem"]
-
-
-class Problem(NamedTuple):
-    type: str
-    message: str
-
-
-def InvalidSmiles() -> Problem:
-    return Problem(type="invalid_smiles", message="Invalid SMILES string")
-
-
-def UnknownProblem() -> Problem:
-    return Problem(type="unknown", message="Unknown error occurred")