factrainer-base 0.1.0__tar.gz

factrainer_base-0.1.0/.gitignore

@@ -0,0 +1,173 @@
+notebooks/
+
+# pytest-profiling
+prof/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

factrainer_base-0.1.0/PKG-INFO

@@ -0,0 +1,8 @@
+Metadata-Version: 2.4
+Name: factrainer-base
+Version: 0.1.0
+Summary: Add your description here
+Author-email: ritsuki1227 <ritsuki1227@gmail.com>
+Requires-Python: >=3.12
+Requires-Dist: pydantic>=2.11.2
+Requires-Dist: scikit-learn>=1.6.1

factrainer_base-0.1.0/pyproject.toml

@@ -0,0 +1,18 @@
+[project]
+name = "factrainer-base"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+authors = [{ name = "ritsuki1227", email = "ritsuki1227@gmail.com" }]
+requires-python = ">=3.12"
+dependencies = [
+    "pydantic>=2.11.2",
+    "scikit-learn>=1.6.1",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/factrainer"]

factrainer_base-0.1.0/src/factrainer/base/config.py

@@ -0,0 +1,52 @@
+from abc import ABC, abstractmethod
+from typing import Self
+
+from pydantic import BaseModel, ConfigDict
+
+from .dataset import BaseDataset, Prediction
+from .raw_model import RawModel
+
+
+class BaseTrainConfig(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+
+class BasePredictConfig(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+
+class BaseLearner[T: BaseDataset, U: RawModel, V: BaseTrainConfig](ABC):
+    @abstractmethod
+    def train(self, train_dataset: T, val_dataset: T | None, config: V) -> U:
+        raise NotImplementedError
+
+
+class BasePredictor[T: BaseDataset, U: RawModel, W: BasePredictConfig](ABC):
+    @abstractmethod
+    def predict(self, dataset: T, raw_model: U, config: W | None) -> Prediction:
+        raise NotImplementedError
+
+
+class BaseMlModelConfig[
+    T: BaseDataset,
+    U: RawModel,
+    V: BaseTrainConfig,
+    W: BasePredictConfig,
+](BaseModel):
+    learner: BaseLearner[T, U, V]
+    predictor: BasePredictor[T, U, W]
+    train_config: V
+    pred_config: W | None = None
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+
+class MlModelConfig[
+    T: BaseDataset,
+    U: RawModel,
+    V: BaseTrainConfig,
+    W: BasePredictConfig,
+](BaseMlModelConfig[T, U, V, W], ABC):
+    @classmethod
+    @abstractmethod
+    def create(cls, train_config: V, pred_config: W | None = None) -> Self:
+        raise NotImplementedError

factrainer_base-0.1.0/src/factrainer/base/dataset.py

@@ -0,0 +1,43 @@
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+from typing import Any, Generator, Self
+
+import numpy as np
+import numpy.typing as npt
+from pydantic import BaseModel, ConfigDict
+from sklearn.model_selection._split import _BaseKFold
+
+# type Prediction = npt.NDArray[Any] | scipy.sparse.spmatrix | list[scipy.sparse.spmatrix]
+type Prediction = npt.NDArray[np.number[Any]]
+type RowIndex = list[int]
+type RowIndices = Sequence[RowIndex]
+type Rows = int | slice | RowIndex
+type RowsAndColumns = Rows | tuple[Rows, ...]
+
+
+class BaseDataset(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+
+class IndexableDataset(BaseDataset):
+    @abstractmethod
+    def __getitem__(self, index: RowsAndColumns) -> Self:
+        raise NotImplementedError
+
+    @abstractmethod
+    def get_index(
+        self, k_fold: _BaseKFold
+    ) -> Generator[tuple[RowIndex, RowIndex], None, None]:
+        raise NotImplementedError
+
+
+class BaseDatasetEqualityChecker[T](ABC):
+    @abstractmethod
+    def check(self, left: T, right: T) -> bool:
+        raise NotImplementedError
+
+
+class BaseDatasetSlicer[T](ABC):
+    @abstractmethod
+    def slice(self, data: T, index: RowIndex) -> T:
+        raise NotImplementedError

factrainer_base-0.1.0/src/factrainer/base/raw_model.py

@@ -0,0 +1,5 @@
+from pydantic import BaseModel, ConfigDict
+
+
+class RawModel(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)