nerdd-module 0.3.8__tar.gz → 0.3.9__tar.gz

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nerdd-module
-Version: 0.3.8
+Version: 0.3.9
 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>
@@ -60,12 +60,14 @@ Requires-Dist: decorator>=5.1.1
 Requires-Dist: importlib-resources>=5; python_version < "3.9"
 Requires-Dist: importlib-metadata>=4.6; python_version < "3.10"
 Provides-Extra: dev
-Requires-Dist: mypy; extra == "dev"
-Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy==1.13.0; extra == "dev"
+Requires-Dist: ruff==0.7.1; extra == "dev"
 Requires-Dist: pandas-stubs; extra == "dev"
+Requires-Dist: rdkit-stubs; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-decorator; extra == "dev"
 Requires-Dist: types-setuptools; extra == "dev"
+Requires-Dist: pre-commit==3.5.0; extra == "dev"
 Provides-Extra: rdkit
 Requires-Dist: rdkit>=2022.3.3; extra == "rdkit"
 Provides-Extra: csp
@@ -100,6 +102,7 @@ pip install -U nerdd-module
 ## Contribute
 
 1. Fork and clone the code
-2. Install test dependencies with ` pip install -e .[test,dev,csp]` 
-3. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
-4. Build docs via ` pip install -e .[docs]`  and ` mkdocs serve` 
+2. Install test dependencies with `pip install -e .[test,dev,csp]` 
+3. Install pre-commit hooks `pre-commit install`
+4. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
+5. Build docs via `pip install -e .[docs]`  and `mkdocs serve` 

nerdd_module-0.3.9/README.md

@@ -0,0 +1,19 @@
+# NERDD Module
+
+This package provides the basis to implement molecular prediction modules in the
+NERDD ecosystem.
+
+## Installation
+
+``` bash
+pip install -U nerdd-module
+```
+
+
+## Contribute
+
+1. Fork and clone the code
+2. Install test dependencies with `pip install -e .[test,dev,csp]` 
+3. Install pre-commit hooks `pre-commit install`
+4. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
+5. Build docs via `pip install -e .[docs]`  and `mkdocs serve` 

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/cli.py

@@ -4,7 +4,7 @@ from typing import Any, Callable
 
 import rich_click as click
 from decorator import decorator
-from stringcase import spinalcase  # type: ignore
+from stringcase import spinalcase
 
 from .model import Model
 
@@ -12,7 +12,7 @@ __all__ = ["auto_cli"]
 
 input_description = """{description}
 
-INPUT molecules are provided as file paths or strings. The following formats are 
+INPUT molecules are provided as file paths or strings. The following formats are
 supported:
 
 {input_format_list}
@@ -157,4 +157,4 @@ def auto_cli(f: Callable[..., Model], *args: Any, **kwargs: Any) -> None:
     # show_default=True: default values are shown in the help text
     main = click.command(context_settings={"show_default": True}, help=help_text)(main)
 
-    return main()
+    main()

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/config/configuration.py

@@ -1,6 +1,5 @@
 from abc import ABC, abstractmethod
-from functools import lru_cache
-from typing import List
+from typing import List, Optional
 
 __all__ = ["Configuration"]
 
@@ -30,23 +29,25 @@ def is_visible(result_property: dict, output_format: str) -> bool:
 
 class Configuration(ABC):
     def __init__(self) -> None:
-        pass
+        self._cached_config: Optional[dict] = None
 
-    @lru_cache(1)
     def get_dict(self) -> dict:
-        config = self._get_dict()
+        if self._cached_config is None:
+            config = self._get_dict()
+
+            if "result_properties" not in config:
+                config["result_properties"] = []
 
-        if "result_properties" not in config:
-            config["result_properties"] = []
+            # check that a module can only predict atom or derivative properties, not both
+            num_atom_properties = len(get_property_columns_of_type(config, "atom"))
+            num_derivative_properties = len(get_property_columns_of_type(config, "derivative"))
+            assert (
+                num_atom_properties == 0 or num_derivative_properties == 0
+            ), "A module can only predict atom or derivative properties, not both."
 
-        # check that a module can only predict atom or derivative properties, not both
-        num_atom_properties = len(get_property_columns_of_type(config, "atom"))
-        num_derivative_properties = len(get_property_columns_of_type(config, "derivative"))
-        assert (
-            num_atom_properties == 0 or num_derivative_properties == 0
-        ), "A module can only predict atom or derivative properties, not both."
+            self._cached_config = config
 
-        return config
+        return self._cached_config
 
     @abstractmethod
     def _get_dict(self) -> dict:

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/config/yaml_configuration.py

@@ -1,4 +1,5 @@
 import base64
+import mimetypes
 import os
 from pathlib import Path
 from typing import IO, Any, Union
@@ -42,9 +43,16 @@ def image_constructor(loader: CustomLoaderLike, node: yaml.Node) -> str:
 
             # determine the file type from the file extension
             kind = filetype.guess(f)
-            assert kind is not None
+            if kind is not None:
+                mime = kind.mime
+            else:
+                # For filetypes without magic headers (e.g. SVG), the filetype library
+                # doesn't work. In these cases, we try the mimetypes library.
+                mime, _ = mimetypes.guess_type(path)
 
-            return f"data:{kind.mime};base64,{encoded}"
+            assert mime is not None, f"Could not determine mime type for {path}"
+
+            return f"data:{mime};base64,{encoded}"
 
 
 class YamlConfiguration(Configuration):

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/depth_first_explorer.py

@@ -15,7 +15,7 @@ class InvalidInputReader(Reader):
         yield MoleculeEntry(
             raw_input=input,
             input_type="unknown",
-            source=tuple(["input"]),
+            source=("input",),
             mol=None,
             errors=[Problem("invalid_input", "Invalid input")],
         )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/explorer.py

@@ -5,9 +5,6 @@ from .reader import MoleculeEntry, Reader
 
 
 class Explorer(ABC):
-    def __init__(self) -> None:
-        pass
-
     @abstractmethod
     def explore(self, input: Any) -> Iterator[MoleculeEntry]:
         pass

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/file_reader.py

@@ -20,8 +20,8 @@ class FileReader(Reader):
         # convert filename to path
         try:
             path = Path(filename)
-        except TypeError:
-            raise ValueError("input must be a valid path")
+        except TypeError as e:
+            raise ValueError("input must be a valid path") from e
 
         # convert to absolute path
         if not path.is_absolute():
@@ -44,7 +44,7 @@ class FileReader(Reader):
                     source: Tuple[str, ...] = tuple()
                 else:
                     source = entry.source
-                yield entry._replace(source=tuple([filename, *source]))
+                yield entry._replace(source=(filename, *source))
 
     def __repr__(self) -> str:
         return f"FileReader(data_dir={self.data_dir})"

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/inchi_reader.py

@@ -48,7 +48,7 @@ class InchiReader(Reader):
                 yield MoleculeEntry(
                     raw_input=line,
                     input_type="inchi",
-                    source=tuple(["raw_input"]),
+                    source=("raw_input",),
                     mol=mol,
                     errors=errors,
                 )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/mol_reader.py

@@ -14,7 +14,7 @@ class MolReader(Reader):
         yield MoleculeEntry(
             raw_input=mol,
             input_type="rdkit_mol",
-            source=tuple(["raw_input"]),
+            source=("raw_input",),
             mol=mol,
             errors=[],
         )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/sdf_reader.py

@@ -61,7 +61,7 @@ class SdfReader(Reader):
                     yield MoleculeEntry(
                         raw_input=mol_block,
                         input_type="mol_block",
-                        source=tuple(["raw_input"]),
+                        source=("raw_input",),
                         mol=mol,
                         errors=errors,
                     )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/smiles_reader.py

@@ -58,7 +58,7 @@ class SmilesReader(Reader):
                 yield MoleculeEntry(
                     raw_input=line,
                     input_type="smiles",
-                    source=tuple(["raw_input"]),
+                    source=("raw_input",),
                     mol=mol,
                     errors=errors,
                 )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/tar_reader.py

@@ -21,7 +21,7 @@ class TarReader(Reader):
                 if not member.isfile():
                     continue
                 for entry in explore(tar.extractfile(member)):
-                    yield entry._replace(source=tuple([member.name, *entry.source]))
+                    yield entry._replace(source=(member.name, *entry.source))
 
     def __repr__(self) -> str:
         return "TarReader()"

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/input/zip_reader.py

@@ -23,7 +23,7 @@ class ZipReader(Reader):
                     continue
                 with zipf.open(member, "r") as f:
                     for entry in explore(f):
-                        yield entry._replace(source=tuple([member, *entry.source]))
+                        yield entry._replace(source=(member, *entry.source))
 
     def __repr__(self) -> str:
         return "ZipReader()"

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/model/enforce_schema_step.py

@@ -16,9 +16,9 @@ class EnforceSchemaStep(Step):
 
         # check that properties are unique
         if len(self._property_names) != len(set(self._property_names)):
-            duplicate_properties = set(
-                [x for x in self._property_names if self._property_names.count(x) > 1]
-            )
+            duplicate_properties = {
+                x for x in self._property_names if self._property_names.count(x) > 1
+            }
             logger.warning(
                 f"Duplicate properties in result_properties: " f"{', '.join(duplicate_properties)}"
             )

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/output/writer.py

@@ -24,9 +24,6 @@ _factories: Dict[str, WriterFactory] = {}
 class Writer(ABC):
     """Abstract class for writers."""
 
-    def __init__(self) -> None:
-        pass
-
     @classmethod
     def __init_subclass__(
         cls,

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/preprocessing/chembl_structure_pipeline.py

@@ -18,8 +18,7 @@ try:
     # importing chembl_structure_pipeline already logs messages
     # --> suppress them temporarily
     with BlockLogs():
-        from chembl_structure_pipeline import get_parent_mol  # type: ignore
-        from chembl_structure_pipeline import standardize_mol  # type: ignore
+        from chembl_structure_pipeline import get_parent_mol, standardize_mol
 
     import_error = None
 except ImportError as e:
@@ -38,7 +37,7 @@ class StandardizeWithCsp(PreprocessingStep):
             raise import_error
 
     def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
-        problems = []
+        problems: List[Problem] = []
 
         # chembl structure pipeline cannot handle molecules with 3D coordinates
         # --> delete conformers

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/preprocessing/filter_by_element.py

@@ -29,7 +29,7 @@ class FilterByElement(PreprocessingStep):
         self, allowed_elements: Iterable[str], remove_invalid_molecules: bool = False
     ) -> None:
         super().__init__()
-        self.allowed_elements = set([a[0].upper() + a[1:] for a in allowed_elements])
+        self.allowed_elements = {a[0].upper() + a[1:] for a in allowed_elements}
         self.hydrogen_in_allowed_elements = "H" in self.allowed_elements
         self.remove_invalid_molecules = remove_invalid_molecules
 
@@ -37,7 +37,7 @@ class FilterByElement(PreprocessingStep):
         problems = []
         result_mol = mol
 
-        elements: Set[str] = set(atom.GetSymbol() for atom in mol.GetAtoms())
+        elements: Set[str] = {atom.GetSymbol() for atom in mol.GetAtoms()}
         invalid_elements = elements - self.allowed_elements
 
         # special case: hydrogens are not recognized by mol.GetAtoms()

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/util/call_with_mappings.py

@@ -1,5 +1,5 @@
 import inspect
-from typing import Callable, Dict, Tuple, Type, TypeVar, Union
+from typing import Callable, Dict, Optional, Tuple, Type, TypeVar, Union
 
 __all__ = ["call_with_mappings"]
 
@@ -10,8 +10,11 @@ def call_with_mappings(
     class_or_function: Union[Type[T], Callable[..., T]],
     config: dict,
     args_mapping: Tuple[str, ...] = (),
-    kwargs_mapping: Dict[str, str] = {},
+    kwargs_mapping: Optional[Dict[str, str]] = None,
 ) -> T:
+    if kwargs_mapping is None:
+        kwargs_mapping = {}
+
     # translate all args
     translated_args = tuple(config.get(arg) for arg in args_mapping)
     # translate all kwargs

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nerdd-module
-Version: 0.3.8
+Version: 0.3.9
 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>
@@ -60,12 +60,14 @@ Requires-Dist: decorator>=5.1.1
 Requires-Dist: importlib-resources>=5; python_version < "3.9"
 Requires-Dist: importlib-metadata>=4.6; python_version < "3.10"
 Provides-Extra: dev
-Requires-Dist: mypy; extra == "dev"
-Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy==1.13.0; extra == "dev"
+Requires-Dist: ruff==0.7.1; extra == "dev"
 Requires-Dist: pandas-stubs; extra == "dev"
+Requires-Dist: rdkit-stubs; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-decorator; extra == "dev"
 Requires-Dist: types-setuptools; extra == "dev"
+Requires-Dist: pre-commit==3.5.0; extra == "dev"
 Provides-Extra: rdkit
 Requires-Dist: rdkit>=2022.3.3; extra == "rdkit"
 Provides-Extra: csp
@@ -100,6 +102,7 @@ pip install -U nerdd-module
 ## Contribute
 
 1. Fork and clone the code
-2. Install test dependencies with ` pip install -e .[test,dev,csp]` 
-3. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
-4. Build docs via ` pip install -e .[docs]`  and ` mkdocs serve` 
+2. Install test dependencies with `pip install -e .[test,dev,csp]` 
+3. Install pre-commit hooks `pre-commit install`
+4. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
+5. Build docs via `pip install -e .[docs]`  and `mkdocs serve` 

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module.egg-info/requires.txt

@@ -15,12 +15,14 @@ importlib-resources>=5
 chembl_structure_pipeline>=1.0.0
 
 [dev]
-mypy
-ruff
+mypy==1.13.0
+ruff==0.7.1
 pandas-stubs
+rdkit-stubs
 types-PyYAML
 types-decorator
 types-setuptools
+pre-commit==3.5.0
 
 [docs]
 mkdocs

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.8"
+version = "0.3.9"
 description = "Base package to create NERDD modules"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -48,12 +48,14 @@ classifiers = [
 
 [project.optional-dependencies]
 dev = [
-    "mypy",
-    "ruff",
+    "mypy==1.13.0",
+    "ruff==0.7.1",
     "pandas-stubs",
+    "rdkit-stubs",
     "types-PyYAML",
     "types-decorator",
     "types-setuptools",
+    "pre-commit==3.5.0",
 ]
 rdkit = [
     # Some old RDKit versions are not recognized by setuptools. For that reason,
@@ -98,7 +100,7 @@ nerdd_module = ["py.typed"]
 [tool.pytest.ini_options]
 log_cli = 1
 log_cli_level = "INFO"
-addopts = "-x -s --cov-report term --cov=nerdd_module"
+addopts = "-x --cov-report term --cov=nerdd_module"
 
 [tool.pytest-watcher]
 patterns = ["*.py", "*.feature", "pyproject.toml"]
@@ -108,12 +110,23 @@ line-length = 100
 extend-exclude = ["tests", "nerdd_module/tests"]
 
 [tool.ruff.lint]
-# F403: 'from module import *' used; unable to detect undefined names
-#       (but we need this for the __init__ files in submodules)
-ignore = ["F403"]
-extend-select = ["T20"]
+select = [
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # pyflakes
+    "I",  # isort
+    "B",  # flake8-bugbear
+    "C4",  # flake8-comprehensions
+    "T20"  # no print statements
+]
+ignore = [
+    "F403", # I often use 'from .submodule import *' in __init__.py files
+    "C408"  # I prefer dict(a=5) over {'a': 5}
+]
 
 [tool.mypy]
+mypy_path="typings"
+# strict=true
 disallow_untyped_defs = true
 # no_implicit_optional = True
 # check_untyped_defs = True

nerdd_module-0.3.8/README.md

@@ -1,18 +0,0 @@
-# NERDD Module
-
-This package provides the basis to implement molecular prediction modules in the
-NERDD ecosystem.
-
-## Installation
-
-``` bash
-pip install -U nerdd-module
-```
-
-
-## Contribute
-
-1. Fork and clone the code
-2. Install test dependencies with ` pip install -e .[test,dev,csp]` 
-3. Run tests via `pytest` or `pytest-watch` (short: `ptw`)
-4. Build docs via ` pip install -e .[docs]`  and ` mkdocs serve` 

{nerdd_module-0.3.8 → nerdd_module-0.3.9}/nerdd_module/__init__.py

@@ -1,9 +1,9 @@
 from .cli import *
 from .model import *
+from .output 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()