nerdd-module 0.3.36__tar.gz → 0.3.38__tar.gz

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2023 - present, The Computational Drug Discovery and Design Group (COMP3D)
+Copyright (c) 2023 - present, The Computational Drug Discovery and Design Group (COMP3D), Steffen Hirte
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/PKG-INFO

@@ -1,42 +1,14 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.36
+Version: 0.3.38
 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>
-License: BSD 3-Clause License
-        
-        Copyright (c) 2023 - present, The Computational Drug Discovery and Design Group (COMP3D)
-        
-        Redistribution and use in source and binary forms, with or without
-        modification, are permitted provided that the following conditions are met:
-        
-        1. Redistributions of source code must retain the above copyright notice, this
-           list of conditions and the following disclaimer.
-        
-        2. Redistributions in binary form must reproduce the above copyright notice,
-           this list of conditions and the following disclaimer in the documentation
-           and/or other materials provided with the distribution.
-        
-        3. Neither the name of the copyright holder nor the names of its
-           contributors may be used to endorse or promote products derived from
-           this software without specific prior written permission.
-        
-        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-        AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-        IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-        DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-        FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-        DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-        SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-        CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-        OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-        OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+License-Expression: BSD-3-Clause
 Project-URL: Repository, https://github.com/molinfo-vienna/nerdd-module
 Keywords: science,research,development,nerdd
 Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: BSD License
 Classifier: Programming Language :: Python
 Classifier: Topic :: Software Development
 Classifier: Topic :: Scientific/Engineering

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/cli.py

@@ -56,7 +56,7 @@ def auto_cli(f: Callable[..., Model], *args: Any, **kwargs: Any) -> None:
     input_format_list = "\n".join([f"* {fmt}" for fmt in ["smiles", "sdf", "inchi"]])
 
     help_text = input_description.format(
-        description=model.description, input_format_list=input_format_list
+        description=model.config.description, input_format_list=input_format_list
     )
 
     output_format_list = [
@@ -117,7 +117,7 @@ def auto_cli(f: Callable[..., Model], *args: Any, **kwargs: Any) -> None:
     #
     # Add job parameters
     #
-    for param in model.job_parameters:
+    for param in model.config.job_parameters:
         # convert parameter name to spinal case (e.g. "max_confs" -> "max-confs")
         param_name = spinalcase(param.name)
         main = click.option(

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/config/models.py

@@ -123,7 +123,7 @@ class Module(BaseModel):
         return spinalcase(self.name)
 
     task: Optional[Task] = None
-    rank: Optional[int] = None
+    rank: Optional[float] = None
     name: str
     batch_size: int = 100
     version: Optional[str] = None

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/model/__init__.py

@@ -1,6 +1,6 @@
 from .assign_name_step import *
 from .convert_representations_step import *
 from .model import *
+from .prediction_step import *
 from .read_input_step import *
-from .simple_model import *
 from .write_output_step import *

nerdd_module-0.3.36/nerdd_module/model/simple_model.py → nerdd_module-0.3.38/nerdd_module/model/model.py

@@ -1,4 +1,5 @@
-from abc import abstractmethod
+import logging
+from abc import ABC, abstractmethod
 from functools import cached_property
 from typing import Any, Iterable, List, Optional, Tuple, Union
 
@@ -8,7 +9,6 @@ from ..config import (
     Configuration,
     DefaultConfiguration,
     DictConfiguration,
-    JobParameter,
     MergedConfiguration,
     Module,
     PackageConfiguration,
@@ -17,21 +17,22 @@ from ..config import (
 from ..input import DepthFirstExplorer
 from ..preprocessing import PreprocessingStep
 from ..problem import Problem
-from ..steps import Step
+from ..steps import OutputStep, Step
 from ..util import get_file_path_to_instance
 from .assign_name_step import AssignNameStep
 from .convert_representations_step import ConvertRepresentationsStep
 from .enforce_schema_step import EnforceSchemaStep
-from .model import Model
+from .prediction_step import PredictionStep
 from .read_input_step import ReadInputStep
 from .write_output_step import WriteOutputStep
 
-__all__ = ["SimpleModel"]
+logger = logging.getLogger(__name__)
 
 
-class SimpleModel(Model):
+class Model(ABC):
     def __init__(self, preprocessing_steps: Iterable[Step] = []) -> None:
         super().__init__()
+
         assert isinstance(
             preprocessing_steps, Iterable
         ), f"Expected Iterable for argument preprocessing_steps, got {type(preprocessing_steps)}"
@@ -39,8 +40,12 @@ class SimpleModel(Model):
             f"Expected all elements of preprocessing_steps to be of type Step, "
             f"got {[type(step) for step in preprocessing_steps if not isinstance(step, Step)]}"
         )
+
         self._preprocessing_steps = preprocessing_steps
 
+    def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
+        return mol, []
+
     def _get_input_steps(
         self, input: Any, input_format: Optional[str], **kwargs: Any
     ) -> List[Step]:
@@ -59,6 +64,10 @@ class SimpleModel(Model):
             CustomPreprocessingStep(self),
         ]
 
+    @abstractmethod
+    def _predict_mols(self, mols: List[Mol], **kwargs: Any) -> Iterable[dict]:
+        pass
+
     def _get_postprocessing_steps(self, output_format: Optional[str], **kwargs: Any) -> List[Step]:
         output_format = output_format or "pandas"
         return [
@@ -67,13 +76,38 @@ class SimpleModel(Model):
             WriteOutputStep(output_format, config=self.config, **kwargs),
         ]
 
-    def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
-        return mol, []
+    def predict(
+        self,
+        input: Any,
+        input_format: Optional[str] = None,
+        output_format: Optional[str] = None,
+        **kwargs: Any,
+    ) -> Any:
+        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 = postprocessing_steps[-1]
+
+        assert isinstance(output_step, OutputStep), "The last step must be an OutputStep."
+
+        steps = [
+            *input_steps,
+            *preprocessing_steps,
+            PredictionStep(self._predict_mols, batch_size=self.config.batch_size, **kwargs),
+            *postprocessing_steps,
+        ]
 
-    @abstractmethod
-    def _predict_mols(self, mols: List[Mol], **kwargs: Any) -> List[dict]:
-        pass
+        # build the pipeline from the list of steps
+        pipeline = None
+        for t in steps:
+            pipeline = t(pipeline)
+
+        # the last pipeline step holds the result
+        return output_step.get_result()
 
+    #
+    # Configuration
+    #
     def _get_base_config(self) -> Union[Configuration, dict]:
         # get the class of the nerdd module, e.g. <CypstrateModel>
         nerdd_module_class = self.__class__
@@ -192,24 +226,9 @@ class SimpleModel(Model):
     def config(self) -> Module:
         return self._get_config().get_dict()
 
-    def _get_batch_size(self) -> int:
-        default = super()._get_batch_size()
-        return self.config.batch_size or default
-
-    def _get_name(self) -> str:
-        default = super()._get_name()
-        return self.config.name or default
-
-    def _get_description(self) -> str:
-        default = super()._get_description()
-        return self.config.description or default
-
-    def _get_job_parameters(self) -> List[JobParameter]:
-        return super()._get_job_parameters() + self.config.job_parameters
-
 
 class CustomPreprocessingStep(PreprocessingStep):
-    def __init__(self, model: SimpleModel):
+    def __init__(self, model: Model):
         super().__init__()
         self.model = model
 

nerdd_module-0.3.36/nerdd_module/model/model.py → nerdd_module-0.3.38/nerdd_module/model/prediction_step.py

@@ -1,114 +1,22 @@
 import logging
-from abc import ABC, abstractmethod
 from collections import defaultdict
-from typing import Any, Iterable, Iterator, List, Optional, Tuple
+from typing import Any, Callable, Iterator, List, Tuple
 
-from rdkit.Chem import Mol
-from stringcase import snakecase  # type: ignore
-
-from ..config import JobParameter
-from ..problem import Problem
-from ..steps import OutputStep, Step
+from ..problem import IncompletePredictionProblem, UnknownPredictionProblem
+from ..steps import Step
 from ..util import call_with_mappings
 
 logger = logging.getLogger(__name__)
 
-
-# an unknown prediction problem indicates that the model raised an exception during
-# prediction
-def UnknownPredictionProblem() -> Problem:
-    return Problem("unknown_prediction_error", "An unknown error occured during prediction.")
-
-
-# an incomplete prediction problem indicates that the model successfully returns
-# predictions, but part of the input molecules are missing in the results
-def IncompletePredictionProblem() -> Problem:
-    return Problem("incomplete_prediction_error", "The model couldn't process the molecule.")
-
-
-class Model(ABC):
-    def __init__(self) -> None:
-        super().__init__()
-
-    @abstractmethod
-    def _predict_mols(self, mols: List[Mol], **kwargs: Any) -> Iterable[dict]:
-        pass
-
-    @abstractmethod
-    def _get_input_steps(
-        self, input: Any, input_format: Optional[str], **kwargs: Any
-    ) -> List[Step]:
-        pass
-
-    @abstractmethod
-    def _get_preprocessing_steps(
-        self, input: Any, input_format: Optional[str], **kwargs: Any
-    ) -> List[Step]:
-        pass
-
-    @abstractmethod
-    def _get_postprocessing_steps(self, output_format: Optional[str], **kwargs: Any) -> List[Step]:
-        pass
-
-    def predict(
-        self,
-        input: Any,
-        input_format: Optional[str] = None,
-        output_format: Optional[str] = None,
-        **kwargs: Any,
-    ) -> Any:
-        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 = 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,
-        ]
-
-        # build the pipeline from the list of steps
-        pipeline = None
-        for t in steps:
-            pipeline = t(pipeline)
-
-        # the last pipeline step holds the result
-        return output_step.get_result()
-
-    #
-    # Properties
-    #
-    def _get_batch_size(self) -> int:
-        return 1
-
-    batch_size = property(fget=lambda self: self._get_batch_size())
-
-    def _get_name(self) -> str:
-        return snakecase(self.__class__.__name__)
-
-    name = property(fget=lambda self: self._get_name())
-
-    def _get_description(self) -> str:
-        return ""
-
-    description = property(fget=lambda self: self._get_description())
-
-    def _get_job_parameters(self) -> List[JobParameter]:
-        return []
-
-    job_parameters = property(fget=lambda self: self._get_job_parameters())
+__all__ = ["PredictionStep"]
 
 
 class PredictionStep(Step):
-    def __init__(self, model: Model, batch_size: int, **kwargs: Any) -> None:
+    def __init__(self, predict_fn: Callable, batch_size: int, **kwargs: Any) -> None:
         super().__init__()
-        self.model = model
-        self.batch_size = batch_size
-        self.kwargs = kwargs
+        self._predict_fn = predict_fn
+        self._batch_size = batch_size
+        self._kwargs = kwargs
 
     def _run(self, source: Iterator[dict]) -> Iterator[dict]:
         # We need to process the molecules in batches, because most ML models perform
@@ -131,7 +39,7 @@ class PredictionStep(Step):
             if len(batch) > 0 or len(none_batch) > 0:
                 yield batch, none_batch
 
-        for batch, none_batch in _batch_and_filter(source, self.batch_size):
+        for batch, none_batch in _batch_and_filter(source, self._batch_size):
             # return the records where mols are None
             yield from none_batch
 
@@ -151,8 +59,8 @@ class PredictionStep(Step):
             if len(batch) > 0:
                 predictions = list(
                     call_with_mappings(
-                        self.model._predict_mols,
-                        {**self.kwargs, "mols": mols},
+                        self._predict_fn,
+                        {**self._kwargs, "mols": mols},
                     )
                 )
             else:

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/problem.py

@@ -2,6 +2,8 @@ from typing import Iterable, NamedTuple
 
 __all__ = [
     "Problem",
+    "UnknownPredictionProblem",
+    "IncompletePredictionProblem",
     "InvalidSmiles",
     "UnknownProblem",
     "InvalidWeightProblem",
@@ -14,6 +16,18 @@ class Problem(NamedTuple):
     message: str
 
 
+# an unknown prediction problem indicates that the model raised an exception during
+# prediction
+def UnknownPredictionProblem() -> Problem:
+    return Problem("unknown_prediction_error", "An unknown error occured during prediction.")
+
+
+# an incomplete prediction problem indicates that the model successfully returns
+# predictions, but part of the input molecules are missing in the results
+def IncompletePredictionProblem() -> Problem:
+    return Problem("incomplete_prediction_error", "The model couldn't process the molecule.")
+
+
 def InvalidSmiles() -> Problem:
     return Problem(type="invalid_smiles", message="Invalid SMILES string")
 

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/tests/models/AtomicMassModel.py

@@ -1,4 +1,4 @@
-from nerdd_module import SimpleModel
+from nerdd_module import Model
 from nerdd_module.preprocessing import Sanitize
 
 __all__ = ["AtomicMassModel"]
@@ -7,7 +7,7 @@ __all__ = ["AtomicMassModel"]
 allowed_versions = ["mol_ids", "mols", "iterator", "error"]
 
 
-class AtomicMassModel(SimpleModel):
+class AtomicMassModel(Model):
     def __init__(self, preprocessing_steps=[Sanitize()], version="mol_ids", **kwargs):
         assert (
             version in allowed_versions

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module/tests/models/MolWeightModel.py

@@ -1,6 +1,6 @@
 from rdkit.Chem.rdMolDescriptors import CalcExactMolWt
 
-from nerdd_module import SimpleModel
+from nerdd_module import Model
 from nerdd_module.preprocessing import Sanitize
 
 __all__ = ["MolWeightModel"]
@@ -8,7 +8,7 @@ __all__ = ["MolWeightModel"]
 allowed_versions = ["order_based", "mol_ids", "mols", "iterator", "error"]
 
 
-class MolWeightModel(SimpleModel):
+class MolWeightModel(Model):
     def __init__(self, preprocessing_steps=[Sanitize()], version="order_based", **kwargs):
         assert (
             version in allowed_versions

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module.egg-info/PKG-INFO

@@ -1,42 +1,14 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.36
+Version: 0.3.38
 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>
-License: BSD 3-Clause License
-        
-        Copyright (c) 2023 - present, The Computational Drug Discovery and Design Group (COMP3D)
-        
-        Redistribution and use in source and binary forms, with or without
-        modification, are permitted provided that the following conditions are met:
-        
-        1. Redistributions of source code must retain the above copyright notice, this
-           list of conditions and the following disclaimer.
-        
-        2. Redistributions in binary form must reproduce the above copyright notice,
-           this list of conditions and the following disclaimer in the documentation
-           and/or other materials provided with the distribution.
-        
-        3. Neither the name of the copyright holder nor the names of its
-           contributors may be used to endorse or promote products derived from
-           this software without specific prior written permission.
-        
-        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-        AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-        IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-        DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-        FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-        DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-        SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-        CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-        OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-        OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+License-Expression: BSD-3-Clause
 Project-URL: Repository, https://github.com/molinfo-vienna/nerdd-module
 Keywords: science,research,development,nerdd
 Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: BSD License
 Classifier: Programming Language :: Python
 Classifier: Topic :: Software Development
 Classifier: Topic :: Scientific/Engineering

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/nerdd_module.egg-info/SOURCES.txt

@@ -49,8 +49,8 @@ nerdd_module/model/assign_name_step.py
 nerdd_module/model/convert_representations_step.py
 nerdd_module/model/enforce_schema_step.py
 nerdd_module/model/model.py
+nerdd_module/model/prediction_step.py
 nerdd_module/model/read_input_step.py
-nerdd_module/model/simple_model.py
 nerdd_module/model/write_output_step.py
 nerdd_module/output/__init__.py
 nerdd_module/output/csv_writer.py

{nerdd_module-0.3.36 → nerdd_module-0.3.38}/pyproject.toml

@@ -4,10 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.36"
+version = "0.3.38"
 description = "Base package to create NERDD modules"
 readme = "README.md"
-license = { file = "LICENSE" }
+license = "BSD-3-Clause"
+license-files = ["LICENSE"]
 authors = [{ name = "Steffen Hirte", email = "steffen.hirte@univie.ac.at" }]
 maintainers = [{ name = "Steffen Hirte", email = "steffen.hirte@univie.ac.at" }]
 dependencies = [
@@ -29,8 +30,6 @@ classifiers = [
     # audience
     "Intended Audience :: Science/Research",
     "Intended Audience :: Developers",
-    # license
-    "License :: OSI Approved :: BSD License",
     # programming language
     "Programming Language :: Python",
     # topics