sibi-dst 2025.9.8__tar.gz → 2025.9.9__tar.gz

{sibi_dst-2025.9.8 → sibi_dst-2025.9.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sibi-dst
-Version: 2025.9.8
+Version: 2025.9.9
 Summary: Data Science Toolkit
 Author: Luis Valverde
 Author-email: lvalverdeb@gmail.com

{sibi_dst-2025.9.8 → sibi_dst-2025.9.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sibi-dst"
-version = "2025.9.8"
+version = "2025.9.9"
 description = "Data Science Toolkit"
 authors = ["Luis Valverde <lvalverdeb@gmail.com>"]
 readme = "README.md"

{sibi_dst-2025.9.8 → sibi_dst-2025.9.9}/sibi_dst/utils/boilerplate/__init__.py

@@ -4,6 +4,7 @@ from .base_attacher import make_attacher
 from .base_parquet_reader import BaseParquetReader
 from .hybrid_data_loader import HybridDataLoader
 from .base_pipeline import BasePipeline
+from .base_pipeline_template import PipelineTemplate
 
 __all__ = [
     "BaseDataCube",
@@ -12,5 +13,6 @@ __all__ = [
     "BaseParquetReader",
     "HybridDataLoader",
     "BasePipeline",
+    "PipelineTemplate",
 ]
 

sibi_dst-2025.9.9/sibi_dst/utils/boilerplate/base_attacher.py

@@ -0,0 +1,70 @@
+from typing import Any, Awaitable, Callable, Sequence, Type
+
+
+class AttachmentMaker:
+    """
+    Async attacher class.
+    Skips work if any param value is falsy ([], None, {}, etc.).
+    """
+
+    def __init__(
+            self,
+            cube_cls: Type,
+            fieldnames: Sequence[str],
+            column_names: Sequence[str],
+    ):
+        self.cube_cls = cube_cls
+        self.fieldnames = tuple(fieldnames)
+        self.column_names = list(column_names)
+
+    async def attach(self, *, logger=None, debug: bool = False, **params: Any):
+        if any(not v for v in params.values()):
+            return None
+        call_params = {
+            "fieldnames": self.fieldnames,
+            "column_names": self.column_names,
+            **params,
+        }
+        return await self.cube_cls(logger=logger, debug=debug).aload(**call_params)
+
+
+# Factory function for backward compatibility
+def make_attacher(
+        cube_cls: Type,
+        fieldnames: Sequence[str],
+        column_names: Sequence[str],
+) -> Callable[..., Awaitable[Any]]:
+    """
+    Factory for async attachers.
+    Skips work if any param value is falsy ([], None, {}, etc.).
+    """
+    attacher = AttachmentMaker(cube_cls, fieldnames, column_names)
+    return attacher.attach
+
+
+__all__ = ['AttachmentMaker', 'make_attacher']
+# from typing import Any, Awaitable, Callable, Sequence, Type
+#
+# def make_attacher(
+#     cube_cls: Type,
+#     fieldnames: Sequence[str],
+#     column_names: Sequence[str],
+# ) -> Callable[..., Awaitable[Any]]:
+#     """
+#     Factory for async attachers.
+#     Skips work if any param value is falsy ([], None, {}, etc.).
+#     """
+#
+#     async def attach(*, logger=None, debug: bool = False, **params: Any):
+#         if any(not v for v in params.values()):
+#             return None
+#         call_params = {
+#             "fieldnames": tuple(fieldnames),
+#             "column_names": list(column_names),
+#             **params,
+#         }
+#         return await cube_cls(logger=logger, debug=debug).aload(**call_params)
+#
+#     return attach
+#
+# __all__ = ['make_attacher']

sibi_dst-2025.9.9/sibi_dst/utils/boilerplate/base_pipeline_template.py

@@ -0,0 +1,54 @@
+from __future__ import annotations
+
+import pandas as pd
+
+from sibi_dst.utils.boilerplate import BasePipeline
+
+
+class PipelineTemplate:
+    """
+    A reusable base class for executing product-related pipelines end-to-end.
+    """
+
+    def __init__(
+        self,
+        start_date: str,
+        end_date: str,
+        fs_instance,
+        storage_path: str,
+        dataset_cls,
+        filename: str,
+        date_field: str = "last_activity_dt",
+        **kwargs
+    ):
+        self.start_date = start_date
+        self.end_date = end_date
+        self.max_workers = kwargs.pop('max_workers', 4)
+        self.fs = fs_instance
+        self.storage_path = storage_path
+
+        self.pipeline = BasePipeline(
+            start_date=self.start_date,
+            end_date=self.end_date,
+            dataset_cls=dataset_cls,
+            parquet_storage_path=self.storage_path,
+            fs=self.fs,
+            filename=filename,
+            date_field=date_field,
+            max_workers=self.max_workers,
+        )
+
+    async def to_parquet(self, **kwargs) -> pd.DataFrame:
+        await self.pipeline.to_parquet(**kwargs)
+        df = await self.pipeline.from_parquet(**kwargs)
+        return df
+
+    async def from_parquet(self, **kwargs) -> pd.DataFrame:
+        df = await self.pipeline.from_parquet(**kwargs)
+        return df
+
+    async def to_clickhouse(self, clickhouse_conf, **kwargs) -> None:
+        cnf = clickhouse_conf.copy()
+        cnf["table"] = self.pipeline.filename
+        cnf["overwrite"] = True
+        await self.pipeline.to_clickhouse(cnf, **kwargs)

sibi_dst-2025.9.8/sibi_dst/utils/boilerplate/base_attacher.py

@@ -1,25 +0,0 @@
-from typing import Any, Awaitable, Callable, Sequence, Type
-
-def make_attacher(
-    cube_cls: Type,
-    fieldnames: Sequence[str],
-    column_names: Sequence[str],
-) -> Callable[..., Awaitable[Any]]:
-    """
-    Factory for async attachers.
-    Skips work if any param value is falsy ([], None, {}, etc.).
-    """
-
-    async def attach(*, logger=None, debug: bool = False, **params: Any):
-        if any(not v for v in params.values()):
-            return None
-        call_params = {
-            "fieldnames": tuple(fieldnames),
-            "column_names": list(column_names),
-            **params,
-        }
-        return await cube_cls(logger=logger, debug=debug).aload(**call_params)
-
-    return attach
-
-__all__ = ['make_attacher']