penwings 0.1.3.dev1__tar.gz → 0.2.0__tar.gz

{penwings-0.1.3.dev1/src/penwings.egg-info → penwings-0.2.0}/PKG-INFO

@@ -1,27 +1,43 @@
 Metadata-Version: 2.4
 Name: penwings
-Version: 0.1.3.dev1
+Version: 0.2.0
 Summary: Lightweight library to handle data and reproduce workflows
-Author-email: Raf Blanckaert <R.Blanckaert@outlook.com>
-License: LICENSE
+Author-email: Raf Blanckaert <r.blanckaert@outlook.com>
+License-Expression: MIT
 Project-URL: Homepage, https://github.com/Frissie/penwings
 Project-URL: Repository, https://github.com/Frissie/penwings
 Project-URL: Issues, https://github.com/Frissie/penwings/issues
+Keywords: data,workflow,reproducibility,sql,analytics
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: sqlalchemy<3.0.0,>=2.0.46
-Requires-Dist: pyodbc<6.0.0,>=5.3.0
-Requires-Dist: pandas<4.0.0,>=3.0.0
-Requires-Dist: numpy<3.0.0,>=2.4.1
+Requires-Dist: sqlalchemy<3.0,>=2.0
+Requires-Dist: pyodbc<6.0,>=5.0
+Requires-Dist: pandas<4.0,>=2.2
+Requires-Dist: numpy<3.0,>=1.26
+Provides-Extra: excel
+Requires-Dist: openpyxl<4.0,>=3.1; extra == "excel"
+Provides-Extra: ml
+Requires-Dist: scikit-learn<2.0,>=1.4; extra == "ml"
 Provides-Extra: scipy
-Requires-Dist: scipy<2.0.0,>=1.17.0; extra == "scipy"
-Provides-Extra: sklearn
-Requires-Dist: scikit-learn<2.0.0,>=1.8.0; extra == "sklearn"
+Requires-Dist: scipy<2.0,>=1.11; extra == "scipy"
 Provides-Extra: optuna
-Requires-Dist: optuna<5.0.0,>=4.7.0; extra == "optuna"
+Requires-Dist: optuna<5.0,>=3.5; extra == "optuna"
 Provides-Extra: all
-Requires-Dist: openpyxl<4.0.0,>=3.1.5; extra == "all"
+Requires-Dist: openpyxl<4.0,>=3.1; extra == "all"
+Requires-Dist: scikit-learn<2.0,>=1.4; extra == "all"
+Requires-Dist: scipy<2.0,>=1.11; extra == "all"
+Requires-Dist: optuna<5.0,>=3.5; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: ruff>=0.3; extra == "dev"
+Requires-Dist: mypy>=1.8; extra == "dev"
 Dynamic: license-file
 
 # Penwings

penwings-0.2.0/pyproject.toml

@@ -0,0 +1,70 @@
+[build-system]
+requires = ["setuptools>=68", "setuptools-scm>=8"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "penwings"
+version = "v0.2.0"
+description = "Lightweight library to handle data and reproduce workflows"
+readme = { file = "README.md", content-type = "text/markdown" }
+license = "MIT"
+authors = [
+    { name = "Raf Blanckaert", email = "r.blanckaert@outlook.com" }
+]
+requires-python = ">=3.11"
+
+keywords = ["data", "workflow", "reproducibility", "sql", "analytics"]
+
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Operating System :: OS Independent",
+]
+
+dependencies = [
+    "sqlalchemy>=2.0,<3.0",
+    "pyodbc>=5.0,<6.0",
+    "pandas>=2.2,<4.0",
+    "numpy>=1.26,<3.0",
+]
+
+[project.optional-dependencies]
+excel = ["openpyxl>=3.1,<4.0"]
+ml = ["scikit-learn>=1.4,<2.0"]
+scipy = ["scipy>=1.11,<2.0"]
+optuna = ["optuna>=3.5,<5.0"]
+all = [
+    "openpyxl>=3.1,<4.0",
+    "scikit-learn>=1.4,<2.0",
+    "scipy>=1.11,<2.0",
+    "optuna>=3.5,<5.0",
+]
+
+dev = [
+    "pytest>=8.0",
+    "ruff>=0.3",
+    "mypy>=1.8",
+]
+
+[project.urls]
+Homepage = "https://github.com/Frissie/penwings"
+Repository = "https://github.com/Frissie/penwings"
+Issues = "https://github.com/Frissie/penwings/issues"
+
+# setuptools config
+[tool.setuptools]
+package-dir = { "" = "src" }
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["penwings*"]
+
+# Versioning via SCM
+[tool.setuptools_scm]
+version_scheme = "guess-next-dev"
+local_scheme = "no-local-version"
+tag_regex = "^v(?P<version>.*)$"
+write_to = "src/penwings/_version.py"

{penwings-0.1.3.dev1 → penwings-0.2.0}/src/penwings/__init__.py

@@ -1,9 +1,8 @@
 from .io.cache import SQLParquetCache
-from .paths import input_dir, output_dir, model_dir
+from .paths import input_dir, output_dir
 
 __all__ = [
     "SQLParquetCache",
     "input_dir",
     "output_dir",
-    "model_dir",
 ]

penwings-0.2.0/src/penwings/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.2.1.dev0'
+__version_tuple__ = version_tuple = (0, 2, 1, 'dev0')
+
+__commit_id__ = commit_id = 'g96cf35c66'

penwings-0.2.0/src/penwings/io/cache.py

@@ -0,0 +1,198 @@
+import pandas as pd
+
+from sqlalchemy import Engine
+from pathlib import Path
+from datetime import datetime, timedelta
+from typing import Unpack, Optional
+from .._utils._typing import SQLParquetKwargs
+from .._utils._decorators import timing_sql
+
+
+class SQLParquetCache:
+    """
+    Cache SQL query results locally as Parquet files.
+
+    This class executes SQL queries using a SQLAlchemy engine and caches
+    the results as Parquet files in a specified directory. On subsequent
+    calls, the cached Parquet file is returned if it is considered "fresh"
+    according to a configurable refresh window.
+
+    The query can either be provided directly as a SQL string or as a path
+    to a ``.sql`` file. If a Parquet file already exists and is within the
+    refresh window, it will be loaded instead of re-executing the query,
+    unless ``force=True`` is specified.
+
+    Parameters
+    ----------
+    parquet_dir : str or pathlib.Path
+        Directory where Parquet cache files will be stored.
+    conn : sqlalchemy.engine.Engine
+        SQLAlchemy engine used to execute SQL queries.
+    sql_dir : str or pathlib.Path, optional
+        Directory containing ``.sql`` files. Required when passing a
+        filename instead of a raw SQL string.
+    refresh_days : int, default 0
+        Number of days for which a cached Parquet file is considered fresh.
+        If 0, refresh checking is disabled and existing Parquet files are
+        always used unless ``force=True``.
+    verbose : bool, default True
+        Whether to enable verbose output (if used by decorators or
+        extended implementations).
+    **kwargs : dict
+        Additional keyword arguments passed to ``pandas.read_sql``.
+        These are stored globally and merged with per-call arguments
+        in :meth:`get`.
+
+    Notes
+    -----
+    - Cached Parquet filenames are derived from the SQL filename stem
+      or from the provided ``parquet_name``.
+    - If a raw SQL string is provided, ``parquet_name`` must be specified.
+    - The cache directory is created automatically if it does not exist.
+    - The method :meth:`get` returns both the DataFrame and the source
+      ("SQL" or "Parquet") used to obtain the data.
+    """
+
+    def __init__(
+        self,
+        parquet_dir: Path | str,
+        conn: Engine,
+        sql_dir: Optional[Path | str] = None,
+        refresh_days: int = 0,  # zero disables refresh when force == false
+        verbose: bool = True,
+        **kwargs: Unpack[SQLParquetKwargs],
+    ):
+
+        if sql_dir is not None:
+            self.sql_dir: Path = Path(sql_dir)
+        self.parquet_dir: Path = Path(parquet_dir)
+        self.refresh_days = refresh_days
+        self.conn = conn
+        self.global_kwargs = kwargs
+
+        self.verbose = verbose
+
+    def set_params(self, **params):
+        for key, value in params.items():
+            if not hasattr(self, key):
+                raise ValueError(f"Invalid parameter: {key}")
+            setattr(self, key, value)
+        return self
+
+    def _sql_path(self, sql_file: str) -> Path:
+        if not hasattr(self, "sql_dir"):
+            raise ValueError("sql_dir must be set when passing a .sql filename.")
+        return self.sql_dir / sql_file
+
+    def _parquet_path(self, parquet_name: str) -> Path:
+        return self.parquet_dir / f"{parquet_name}.parquet"
+
+    def _is_fresh(self, path: Path, refresh_window: int) -> bool:
+        """
+        Determine whether a cached Parquet file is fresh enough to use.
+
+        Parameters
+        ----------
+        path : Path
+            Path to the Parquet file.
+        refresh_window : int
+            Number of days the file is considered valid.
+            If 0, the file is always considered fresh (if it exists).
+
+        Returns
+        -------
+        bool
+            True if the file exists and is within the refresh window.
+        """
+        if not path.exists():
+            return False
+
+        # 0 means: never refresh (always use cache if it exists)
+        if refresh_window == 0:
+            return True
+
+        last_modified = datetime.fromtimestamp(path.stat().st_mtime)
+        age = datetime.now() - last_modified
+        return age < timedelta(days=refresh_window)
+
+    def _read_sql(self, sql_file: str):
+        return self._sql_path(sql_file).read_text()
+
+    def _return_sql(self, query: str, conn, **kwargs: Unpack[SQLParquetKwargs]) -> pd.DataFrame:
+        return pd.read_sql(query, conn, **kwargs)
+
+    @timing_sql
+    def get(
+        self,
+        sql: str,
+        parquet_name: str | None = None,
+        conn: Engine | None = None,
+        refresh_days: int | None = None,
+        force: bool = False,
+        **kwargs: Unpack[SQLParquetKwargs],
+    ) -> tuple[pd.DataFrame, str]:
+        """
+        Retrieve a DataFrame from cache or execute the SQL query.
+
+        Parameters
+        ----------
+        sql : str
+            Either a raw SQL query string or the filename of a ``.sql`` file.
+        parquet_name : str, optional
+            Name of the Parquet file (without extension) when passing a raw
+            SQL string. Ignored if a ``.sql`` filename is provided.
+        conn : sqlalchemy.engine.Engine, optional
+            Alternative SQLAlchemy engine to use instead of the default.
+        refresh_days : int, optional
+            Override the instance-level refresh window (in days).
+        force : bool, default False
+            If True, bypass the cache and force re-execution of the query.
+        **kwargs : dict
+            Additional keyword arguments passed to ``pandas.read_sql``.
+            These override any global keyword arguments defined at
+            initialization.
+
+        Returns
+        -------
+        DataFrame
+            The resulting query output.
+        str
+            The data source used: either ``"SQL"`` or ``"Parquet"``.
+
+        Raises
+        ------
+        ValueError
+            If ``sql`` is a raw SQL string and ``parquet_name`` is not provided.
+            If ``sql`` is neither a SQL string nor a ``.sql`` file path.
+
+        Notes
+        -----
+        If the Parquet file exists and is within the refresh window,
+        it is loaded directly using ``pandas.read_parquet``. Otherwise,
+        the SQL query is executed and the result is written to Parquet.
+        """
+        if isinstance(sql, str) and Path(sql).suffix == ".sql":
+            parquet_name = parquet_name or Path(sql).stem
+            query = self._read_sql(sql)
+        elif isinstance(sql, str):
+            if parquet_name is None:
+                raise ValueError("parquet_name must be provided if query is passed directly")
+            query = sql
+        else:
+            raise ValueError("sql must be a SQL string or a path to a .sql file")
+
+        connection = self.conn if conn is None else conn
+        refresh_window = self.refresh_days if refresh_days is None else refresh_days
+        parquet_path = self._parquet_path(parquet_name)
+        self.parquet_dir.mkdir(parents=True, exist_ok=True)
+        sql_kwargs = self.global_kwargs | kwargs
+
+        if not force and self._is_fresh(parquet_path, refresh_window):
+            source = "Parquet"
+            return pd.read_parquet(parquet_path), source
+
+        source = "SQL"
+        df = self._return_sql(query, connection, **sql_kwargs)
+        df.to_parquet(parquet_path, index=False)
+
+        return df, source

{penwings-0.1.3.dev1 → penwings-0.2.0}/src/penwings/paths.py

@@ -4,9 +4,11 @@ home_dir = pathlib.Path.cwd()
 proj_dir = pathlib.Path.cwd().parent
 
 input_dir = home_dir / "input"
-model_dir = home_dir / "model"
 output_dir = home_dir / "output"
 
+sql_dir = input_dir / "sql"
+parquet_dir = input_dir / "parquet"
+
 if __name__ == "__main__":
     i = 1
     for name, value in dict(locals()).items():

{penwings-0.1.3.dev1 → penwings-0.2.0/src/penwings.egg-info}/PKG-INFO

@@ -1,27 +1,43 @@
 Metadata-Version: 2.4
 Name: penwings
-Version: 0.1.3.dev1
+Version: 0.2.0
 Summary: Lightweight library to handle data and reproduce workflows
-Author-email: Raf Blanckaert <R.Blanckaert@outlook.com>
-License: LICENSE
+Author-email: Raf Blanckaert <r.blanckaert@outlook.com>
+License-Expression: MIT
 Project-URL: Homepage, https://github.com/Frissie/penwings
 Project-URL: Repository, https://github.com/Frissie/penwings
 Project-URL: Issues, https://github.com/Frissie/penwings/issues
+Keywords: data,workflow,reproducibility,sql,analytics
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: sqlalchemy<3.0.0,>=2.0.46
-Requires-Dist: pyodbc<6.0.0,>=5.3.0
-Requires-Dist: pandas<4.0.0,>=3.0.0
-Requires-Dist: numpy<3.0.0,>=2.4.1
+Requires-Dist: sqlalchemy<3.0,>=2.0
+Requires-Dist: pyodbc<6.0,>=5.0
+Requires-Dist: pandas<4.0,>=2.2
+Requires-Dist: numpy<3.0,>=1.26
+Provides-Extra: excel
+Requires-Dist: openpyxl<4.0,>=3.1; extra == "excel"
+Provides-Extra: ml
+Requires-Dist: scikit-learn<2.0,>=1.4; extra == "ml"
 Provides-Extra: scipy
-Requires-Dist: scipy<2.0.0,>=1.17.0; extra == "scipy"
-Provides-Extra: sklearn
-Requires-Dist: scikit-learn<2.0.0,>=1.8.0; extra == "sklearn"
+Requires-Dist: scipy<2.0,>=1.11; extra == "scipy"
 Provides-Extra: optuna
-Requires-Dist: optuna<5.0.0,>=4.7.0; extra == "optuna"
+Requires-Dist: optuna<5.0,>=3.5; extra == "optuna"
 Provides-Extra: all
-Requires-Dist: openpyxl<4.0.0,>=3.1.5; extra == "all"
+Requires-Dist: openpyxl<4.0,>=3.1; extra == "all"
+Requires-Dist: scikit-learn<2.0,>=1.4; extra == "all"
+Requires-Dist: scipy<2.0,>=1.11; extra == "all"
+Requires-Dist: optuna<5.0,>=3.5; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: ruff>=0.3; extra == "dev"
+Requires-Dist: mypy>=1.8; extra == "dev"
 Dynamic: license-file
 
 # Penwings

{penwings-0.1.3.dev1 → penwings-0.2.0}/src/penwings.egg-info/SOURCES.txt

@@ -4,9 +4,8 @@ README.md
 pyproject.toml
 uv.lock
 src/penwings/__init__.py
+src/penwings/_version.py
 src/penwings/paths.py
-src/penwings/tuner.py
-src/penwings/views.py
 src/penwings.egg-info/PKG-INFO
 src/penwings.egg-info/SOURCES.txt
 src/penwings.egg-info/dependency_links.txt

penwings-0.2.0/src/penwings.egg-info/requires.txt

@@ -0,0 +1,27 @@
+sqlalchemy<3.0,>=2.0
+pyodbc<6.0,>=5.0
+pandas<4.0,>=2.2
+numpy<3.0,>=1.26
+
+[all]
+openpyxl<4.0,>=3.1
+scikit-learn<2.0,>=1.4
+scipy<2.0,>=1.11
+optuna<5.0,>=3.5
+
+[dev]
+pytest>=8.0
+ruff>=0.3
+mypy>=1.8
+
+[excel]
+openpyxl<4.0,>=3.1
+
+[ml]
+scikit-learn<2.0,>=1.4
+
+[optuna]
+optuna<5.0,>=3.5
+
+[scipy]
+scipy<2.0,>=1.11

penwings-0.1.3.dev1/pyproject.toml

@@ -1,59 +0,0 @@
-[project]
-name = "penwings"
-dynamic = ["version"]
-description = "Lightweight library to handle data and reproduce workflows"
-readme = "README.md"
-license = {text = "LICENSE"}
-authors = [
-    {name = "Raf Blanckaert",email = "R.Blanckaert@outlook.com"}
-]
-requires-python = ">=3.11"
-dependencies = [
-    "sqlalchemy (>=2.0.46,<3.0.0)",
-    "pyodbc (>=5.3.0,<6.0.0)",
-    "pandas (>=3.0.0,<4.0.0)",
-    "numpy (>=2.4.1,<3.0.0)"
-]
-
-[project.urls]
-Homepage = "https://github.com/Frissie/penwings"
-Repository = "https://github.com/Frissie/penwings"
-Issues = "https://github.com/Frissie/penwings/issues"
-
-
-[tool.setuptools_scm]
-version_scheme = "guess-next-dev"
-local_scheme = "no-local-version"
-tag_regex = "^v(?P<version>.*)$"
-
-[tool.setuptools]
-package-dir = {"" = "src"}
-
-[tool.setuptools.packages.find]
-where = ["src"]
-include = ["penwings*"]
-exclude = ["penwings._*"]
-
-[build-system]
-requires = ["setuptools>=68", "wheel", "setuptools-scm"]
-build-backend = "setuptools.build_meta"
-
-[dependency-groups]
-dev = [
-    "openpyxl>=3.1.5",
-    "optuna>=4.7.0",
-    "scikit-learn>=1.8.0",
-    "scipy>=1.17.0",
-]
-
-[project.optional-dependencies]
-scipy = ["scipy (>=1.17.0,<2.0.0)"]
-sklearn = ["scikit-learn (>=1.8.0,<2.0.0)"]
-optuna= ["optuna (>=4.7.0,<5.0.0)"]
-all = ["openpyxl (>=3.1.5,<4.0.0)"]
-
-[[tool.uv.index]]
-name = "testpypi"
-url = "https://test.pypi.org/simple/"
-publish-url = "https://test.pypi.org/legacy/"
-explicit = true

penwings-0.1.3.dev1/src/penwings/io/cache.py

@@ -1,93 +0,0 @@
-import pandas as pd
-
-from sqlalchemy import Engine
-from pathlib import Path
-from datetime import datetime, timedelta
-from typing import Unpack, Union, Optional
-from .._utils._typing import SQLParquetKwargs
-from .._utils._decorators import timing_sql
-
-
-class SQLParquetCache:
-    def __init__(
-        self,
-        parquet_dir: Union[Path, str],
-        conn: Engine,
-        sql_dir: Optional[Union[Path, str]] = None,
-        refresh_days: int = 0,  # zero disables refresh when force == false
-        verbose: bool = True,
-        **kwargs: Unpack[SQLParquetKwargs],
-    ):
-
-        if sql_dir is not None:
-            self.sql_dir: Path = Path(sql_dir)
-        self.parquet_dir: Path = Path(parquet_dir)
-        self.refresh_days = refresh_days
-        self.conn = conn
-        self.global_kwargs = kwargs
-
-        self.verbose = verbose
-        self.source = "SQL"
-
-    def set_params(self, **params):
-        for key, value in params.items():
-            if not hasattr(self, key):
-                raise ValueError(f"Invalid parameter: {key}")
-            setattr(self, key, value)
-        return self
-
-    def _sql_path(self, sql_file: str) -> Path:
-        return self.sql_dir / sql_file
-
-    def _parquet_path(self, sql_file: str, parquet_name: str | None = None) -> Path:
-        name = parquet_name or Path(sql_file).stem
-        return self.parquet_dir / f"{name}.parquet"
-
-    def _is_new(self, path: Path, refresh_window: int) -> bool:
-        if not path.exists():
-            return False
-        if self.refresh_days == 0:
-            return True
-        last_modified = datetime.fromtimestamp(path.stat().st_mtime)
-        return datetime.now() - last_modified < timedelta(days=refresh_window)
-
-    def _read_sql(self, sql_file: str):
-        return self._sql_path(sql_file).read_text()
-
-    def _return_sql(self, query: str, conn, **kwargs: Unpack[SQLParquetKwargs]) -> pd.DataFrame:
-        return pd.read_sql(query, conn, **kwargs)
-
-    @timing_sql
-    def get(
-        self,
-        sql: str,
-        parquet_name: Union[str, None] = None,
-        conn: Engine | None = None,
-        refresh_days: int | None = None,
-        force: bool = False,
-        **kwargs: Unpack[SQLParquetKwargs],
-    ) -> tuple[pd.DataFrame, str]:
-        if isinstance(sql, str) and Path(sql).suffix == ".sql":
-            query = self._read_sql(sql)
-        elif isinstance(sql, str):
-            if parquet_name is None:
-                raise ValueError("parquet_name must be provided if query is passed directly")
-            query = sql
-        else:
-            raise ValueError("sql must be a SQL string or a path to a .sql file")
-
-        connection = conn or self.conn
-        refresh_window = refresh_days or self.refresh_days
-        parquet_path = self._parquet_path(query)
-        sql_kwargs = self.global_kwargs | kwargs
-
-        if not force and self._is_new(parquet_path, refresh_window):
-            source = "Parquet"
-            return pd.read_parquet(parquet_path), source
-
-        source = "SQL"
-        df = self._return_sql(query, connection, **sql_kwargs)
-        self.parquet_dir.mkdir(parents=True, exist_ok=True)
-        df.to_parquet(parquet_path, index=False)
-
-        return df, source

penwings-0.1.3.dev1/src/penwings/tuner.py

@@ -1,42 +0,0 @@
-from optuna.trial import Trial
-
-
-def tune_lgbm_params(trial: Trial, model="classifier"):
-    if model == "classifier":
-        metrics = {
-            "objective": "binary",
-            "metric": "auc",
-        }
-
-    params = {
-        # Core
-        "verbosity": -1,
-        "boosting_type": "gbdt",
-        # GPU
-        "device": "gpu",
-        "gpu_platform_id": 0,
-        "gpu_device_id": 0,
-        # Learning
-        "learning_rate": trial.suggest_float("learning_rate", 0.005, 0.05, log=True),
-        "n_estimators": trial.suggest_int("n_estimators", 1500, 5000),
-        # Tree structure (GPU-safe)
-        "num_leaves": trial.suggest_int("num_leaves", 31, 128),
-        "max_depth": trial.suggest_int("max_depth", 4, 10),
-        # Regularization / stability
-        "min_child_samples": trial.suggest_int("min_child_samples", 10, 80),
-        "min_child_weight": trial.suggest_float("min_child_weight", 1e-3, 10.0, log=True),
-        "min_split_gain": trial.suggest_float("min_split_gain", 0.0, 1.0),
-        # Sampling
-        "subsample": trial.suggest_float("subsample", 0.6, 1.0),
-        "subsample_freq": trial.suggest_int("subsample_freq", 1, 10),
-        "feature_fraction": trial.suggest_float("feature_fraction", 0.6, 1.0),
-        # Regularization
-        "reg_alpha": trial.suggest_float("reg_alpha", 1e-8, 1.0, log=True),
-        "reg_lambda": trial.suggest_float("reg_lambda", 1e-8, 5.0, log=True),
-        # Histogram
-        "max_bin": trial.suggest_int("max_bin", 64, 255),
-        # Class imbalance (keep only if needed)
-        "scale_pos_weight": trial.suggest_float("scale_pos_weight", 0.8, 3.0),
-    }
-
-    return metrics | params

penwings-0.1.3.dev1/src/penwings/views.py

@@ -1,79 +0,0 @@
-from sklearn.pipeline import Pipeline
-from sklearn.compose import ColumnTransformer, make_column_selector
-from sklearn.preprocessing import (
-    TargetEncoder,
-    OneHotEncoder,
-    RobustScaler,
-    KBinsDiscretizer,
-    FunctionTransformer,
-    PolynomialFeatures,
-    OrdinalEncoder,
-    StandardScaler,
-)
-
-LinearView = ColumnTransformer(
-    [
-        ("numerical", RobustScaler(), make_column_selector(dtype_exclude="category")),
-        ("category", TargetEncoder(shuffle=True, smooth=10, random_state=42), make_column_selector(dtype_include="category")),
-    ],
-    remainder="drop",
-    verbose_feature_names_out=False,
-).set_output(transform="pandas")
-
-DenseView = ColumnTransformer(
-    [
-        ("numerical", StandardScaler(), make_column_selector(dtype_exclude="category")),
-        ("category", TargetEncoder(shuffle=True, smooth=10, random_state=42), make_column_selector(dtype_include="category")),
-    ],
-    remainder="drop",
-    verbose_feature_names_out=False,
-).set_output(transform="pandas")
-
-CategoricalView = Pipeline(
-    [
-        (
-            "bins",
-            ColumnTransformer(
-                [
-                    (
-                        "numerical",
-                        KBinsDiscretizer(n_bins=4, strategy="quantile", quantile_method="averaged_inverted_cdf", encode="ordinal"),
-                        make_column_selector(dtype_exclude="category"),
-                    ),
-                    (
-                        "category",
-                        OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1),
-                        make_column_selector(dtype_include="category"),
-                    ),
-                ],
-                remainder="drop",
-                verbose_feature_names_out=False,
-            ).set_output(transform="pandas"),
-        ),
-        ("cats", FunctionTransformer(lambda df: df.astype(int).astype("category"), feature_names_out="one-to-one")),
-    ]
-)
-
-PolynomialView = Pipeline(
-    [
-        ("Linear", LinearView),
-        ("poly", PolynomialFeatures(degree=2).set_output(transform="pandas")),
-    ]
-)
-
-SparseView = ColumnTransformer(
-    [
-        (
-            "num_bins",
-            KBinsDiscretizer(n_bins=10, quantile_method="averaged_inverted_cdf", encode="onehot"),
-            make_column_selector(dtype_exclude="category"),
-        ),
-        (
-            "cat_ohe",
-            OneHotEncoder(handle_unknown="ignore"),
-            make_column_selector(dtype_include="category"),
-        ),
-    ],
-    remainder="drop",
-    verbose_feature_names_out=False,
-)

penwings-0.1.3.dev1/src/penwings.egg-info/requires.txt

@@ -1,16 +0,0 @@
-sqlalchemy<3.0.0,>=2.0.46
-pyodbc<6.0.0,>=5.3.0
-pandas<4.0.0,>=3.0.0
-numpy<3.0.0,>=2.4.1
-
-[all]
-openpyxl<4.0.0,>=3.1.5
-
-[optuna]
-optuna<5.0.0,>=4.7.0
-
-[scipy]
-scipy<2.0.0,>=1.17.0
-
-[sklearn]
-scikit-learn<2.0.0,>=1.8.0