sibi-dst 2025.9.8__py3-none-any.whl → 2025.9.9__py3-none-any.whl

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/utils/boilerplate/base_attacher.py

@@ -1,25 +1,70 @@
 from typing import Any, Awaitable, Callable, Sequence, Type
 
-def make_attacher(
-    cube_cls: Type,
-    fieldnames: Sequence[str],
-    column_names: Sequence[str],
-) -> Callable[..., Awaitable[Any]]:
+
+class AttachmentMaker:
     """
-    Factory for async attachers.
+    Async attacher class.
     Skips work if any param value is falsy ([], None, {}, etc.).
     """
 
-    async def attach(*, logger=None, debug: bool = False, **params: Any):
+    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": tuple(fieldnames),
-            "column_names": list(column_names),
+            "fieldnames": self.fieldnames,
+            "column_names": self.column_names,
             **params,
         }
-        return await cube_cls(logger=logger, debug=debug).aload(**call_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
 
-    return attach
 
-__all__ = ['make_attacher']
+__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/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.dist-info → sibi_dst-2025.9.9.dist-info}/METADATA

@@ -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.dist-info → sibi_dst-2025.9.9.dist-info}/RECORD

@@ -40,12 +40,13 @@ sibi_dst/tests/test_data_wrapper_class.py,sha256=6uFmZR2DxnxQz49L5jT2ehlKvlLnpUH
 sibi_dst/utils/__init__.py,sha256=vShNCOMPw8KKwlb4tq5XGrpjqakJ_OE8YDc_xDAWAxI,1302
 sibi_dst/utils/async_utils.py,sha256=53aywfgq1Q6-0OVr9qR1Sf6g7Qv3I9qunAAR4fjFXBE,351
 sibi_dst/utils/base.py,sha256=sFngliI7Ku8bZMz0YdVhppuaPNZ0dvqRwCsPe9XdF1A,16256
-sibi_dst/utils/boilerplate/__init__.py,sha256=Zi4jHfYm_fGsXwG6TVxUUPjWQMYgZS-HsGcva7QxosU,430
-sibi_dst/utils/boilerplate/base_attacher.py,sha256=JRAyvfljQjKVD5BJDDd09cBY9pGPIe8LQp0aUv_xJs0,736
+sibi_dst/utils/boilerplate/__init__.py,sha256=St0xyt-PMgzYKquKU9QTUyMRrJU2Nf-tpFLHuJj87H8,507
+sibi_dst/utils/boilerplate/base_attacher.py,sha256=iZftWNUx8y370OJP_kGCs5v3t2RgPuARIK_jQeFfbAU,2089
 sibi_dst/utils/boilerplate/base_data_cube.py,sha256=ErKTM2kT8LsSXADcyYvT436O_Mp0J2hm8xs1IUircb4,2760
 sibi_dst/utils/boilerplate/base_parquet_artifact.py,sha256=oqPbjHFfChA9j1WL-eDAh7XLA3zmf-Rq7s_kzITVniA,3753
 sibi_dst/utils/boilerplate/base_parquet_reader.py,sha256=3kN9_bbxyX-WuJLMBWejeApW2V_BDArSljhSUOAOhVU,692
 sibi_dst/utils/boilerplate/base_pipeline.py,sha256=R9_mMEn8gCtfTS7c3DyzWMf_oQjCSL_O7CR8z_t3nmc,6323
+sibi_dst/utils/boilerplate/base_pipeline_template.py,sha256=D5HFA4odsR2wlTY6iLg1tm57Tsh91QkoYjjX8eUgrjU,1574
 sibi_dst/utils/boilerplate/hybrid_data_loader.py,sha256=Tazn7QL3FmWKVMXxzkvxPrG_2ucsPHvSotIW9dBLoNc,6018
 sibi_dst/utils/business_days.py,sha256=dP0Xj4FhTBIvZZrZYLOHZl5zOpDAgWkD4p_1a7BOT7I,8461
 sibi_dst/utils/clickhouse_writer.py,sha256=IQJ_rgd7VuF-g-aPbo9TfqZi0EB_3evCFTzcCNHSmpw,16969
@@ -94,6 +95,6 @@ sibi_dst/v2/df_helper/core/_params_config.py,sha256=DYx2drDz3uF-lSPzizPkchhy-kxR
 sibi_dst/v2/df_helper/core/_query_config.py,sha256=Y8LVSyaKuVkrPluRDkQoOwuXHQxner1pFWG3HPfnDHM,441
 sibi_dst/v2/utils/__init__.py,sha256=6H4cvhqTiFufnFPETBF0f8beVVMpfJfvUs6Ne0TQZNY,58
 sibi_dst/v2/utils/log_utils.py,sha256=rfk5VsLAt-FKpv6aPTC1FToIPiyrnHAFFBAkHme24po,4123
-sibi_dst-2025.9.8.dist-info/METADATA,sha256=rQ9QLcSm_bvFK2KOgi1ZmIgVZMwixMWvXT9SNmBU6fg,2710
-sibi_dst-2025.9.8.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-sibi_dst-2025.9.8.dist-info/RECORD,,
+sibi_dst-2025.9.9.dist-info/METADATA,sha256=aAHhqJxfHiRrDTTAGrOQ3WbRDPMmLV0I4k2OTDRu5s4,2710
+sibi_dst-2025.9.9.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+sibi_dst-2025.9.9.dist-info/RECORD,,