sibi-dst 2025.9.10__py3-none-any.whl → 2025.9.12__py3-none-any.whl

sibi_dst/utils/business_days.py

@@ -1,19 +1,22 @@
+from __future__ import annotations
+
 import datetime as dt
 from typing import Any, Dict, Iterable, Optional
-from sibi_dst.utils import Logger
+
+import dask.dataframe as dd
 import numpy as np
 import pandas as pd
-import dask.dataframe as dd
+
+from sibi_dst.utils import Logger
 
 
 # ---------------- Vectorized helpers (used by Dask map_partitions) ----------------
 
 def _to_np_days(series: pd.Series) -> np.ndarray:
     """Coerce to numpy datetime64[D] with NaT-safe conversion."""
-    # Use pandas for robust parsing, then cast to date-days
     s = pd.to_datetime(series, errors="coerce")
-    # Convert to numpy datetime64[D] (day precision)
-    return s.values.astype("datetime64[D]")
+    # Return day precision array directly
+    return s.dt.floor("D").to_numpy(dtype="datetime64[D]")
 
 
 def _vectorized_busday_count(
@@ -24,8 +27,8 @@ def _vectorized_busday_count(
         weekmask: Optional[str],
         inclusive: bool,
 ) -> pd.Series:
-    start = _to_np_days(part[begin_col])  # numpy datetime64[D]
-    end = _to_np_days(part[end_col])  # numpy datetime64[D]
+    start = _to_np_days(part[begin_col])
+    end = _to_np_days(part[end_col])
 
     kwargs: Dict[str, Any] = {}
     if holidays:
@@ -38,7 +41,7 @@ def _vectorized_busday_count(
         with np.errstate(invalid="ignore"):
             end_adj = end + np.timedelta64(1, "D")
 
-    valid = (~pd.isna(start)) & (~pd.isna(end))  # numpy bool mask
+    valid = (~pd.isna(start)) & (~pd.isna(end))
     result = np.full(part.shape[0], np.nan, dtype="float64")
     if valid.any():
         counts = np.busday_count(
@@ -59,8 +62,8 @@ def _vectorized_busday_offset(
         weekmask: Optional[str],
         roll: str,
 ) -> pd.Series:
-    start = _to_np_days(part[start_col])  # numpy datetime64[D]
-    n_days = pd.to_numeric(part[n_days_col], errors="coerce").to_numpy()  # numpy float -> cast later
+    start = _to_np_days(part[start_col])
+    n_days = pd.to_numeric(part[n_days_col], errors="coerce").to_numpy()
 
     kwargs: Dict[str, Any] = {"roll": roll}
     if holidays:
@@ -68,7 +71,7 @@ def _vectorized_busday_offset(
     if weekmask:
         kwargs["weekmask"] = weekmask
 
-    valid = (~pd.isna(start)) & (~pd.isna(n_days))  # numpy bool mask
+    valid = (~pd.isna(start)) & (~pd.isna(n_days))
     out = np.full(part.shape[0], np.datetime64("NaT", "ns"), dtype="datetime64[ns]")
     if valid.any():
         offs = np.busday_offset(
@@ -86,26 +89,6 @@ def _vectorized_busday_offset(
 class BusinessDays:
     """
     Business day calculations with custom holidays and optional weekmask.
-
-    Features
-    - Scalar helpers:
-        - get_business_days_count(begin, end, inclusive=False) -> int
-        - add_business_days(start_date, n_days, roll='forward') -> np.datetime64
-    - Dask DataFrame helpers (vectorized via map_partitions):
-        - calc_business_days_from_df(df, begin_col, end_col, result_col='business_days', inclusive=False)
-        - calc_sla_end_date(df, start_date_col, n_days_col, result_col='sla_end_date', roll='forward')
-
-    Parameters
-    ----------
-    holiday_list : dict[str, list[str]] | Iterable[str]
-        Either a mapping of year -> [YYYY-MM-DD, ...] or a flat iterable of YYYY-MM-DD strings.
-    logger : Any
-        Logger with .debug/.info/.warning/.error.
-    weekmask : str | None
-        A numpy business day weekmask like '1111100' (Mon–Fri). None means default Mon–Fri.
-        Examples:
-            '1111100' -> Mon-Fri
-            '1111110' -> Mon-Sat
     """
 
     def __init__(
@@ -119,12 +102,11 @@ class BusinessDays:
         self.logger = logger or Logger.default_logger(logger_name=self.__class__.__name__)
         self.weekmask = weekmask
 
-        # Normalize holidays to a flat, sorted tuple of 'YYYY-MM-DD'
         if isinstance(holiday_list, dict):
             flat = [d for _, days in sorted(holiday_list.items()) for d in days]
         else:
             flat = list(holiday_list)
-        # Deduplicate while preserving order
+
         seen = set()
         flat_unique = []
         for d in flat:
@@ -142,7 +124,6 @@ class BusinessDays:
             *,
             inclusive: bool = False,
     ) -> int:
-        """Business days between two dates. If inclusive=True, include the end date."""
         b = pd.to_datetime(begin_date).date()
         e = pd.to_datetime(end_date).date()
 
@@ -153,11 +134,11 @@ class BusinessDays:
             kwargs["weekmask"] = self.weekmask
 
         if inclusive:
-            e_np = np.datetime64(e) + np.timedelta64(1, "D")
+            e_np = np.datetime64(e, "D") + np.timedelta64(1, "D")
         else:
-            e_np = np.datetime64(e)
+            e_np = np.datetime64(e, "D")
 
-        val = int(np.busday_count(np.datetime64(b), e_np, **kwargs))
+        val = int(np.busday_count(np.datetime64(b, "D"), e_np, **kwargs))
         return val
 
     def add_business_days(
@@ -167,11 +148,6 @@ class BusinessDays:
             *,
             roll: str = "forward",
     ) -> np.datetime64:
-        """
-        Add (or subtract) business days to a date. Returns numpy datetime64[D].
-        roll: {'forward','backward','following','preceding','modifiedfollowing',
-               'modifiedpreceding','nat'}
-        """
         s = pd.to_datetime(start_date).date()
         kwargs: Dict[str, Any] = {"roll": roll}
         if self.holidays:
@@ -179,7 +155,7 @@ class BusinessDays:
         if self.weekmask:
             kwargs["weekmask"] = self.weekmask
 
-        return np.busday_offset(np.datetime64(s), int(n_days), **kwargs)
+        return np.busday_offset(np.datetime64(s, "D"), int(n_days), **kwargs)
 
     # -------- Dask API --------
 
@@ -192,10 +168,6 @@ class BusinessDays:
             *,
             inclusive: bool = False,
     ) -> dd.DataFrame:
-        """
-        Vectorized business-day difference between two date columns.
-        Produces float64 (NaN where either side is missing).
-        """
         missing = {begin_date_col, end_date_col} - set(df.columns)
         if missing:
             self.logger.error(f"Missing columns: {missing}")
@@ -224,10 +196,6 @@ class BusinessDays:
             *,
             roll: str = "forward",
     ) -> dd.DataFrame:
-        """
-        Vectorized business-day offset for SLA end date.
-        Produces datetime64[ns] with NaT where invalid.
-        """
         missing = {start_date_col, n_days_col} - set(df.columns)
         if missing:
             self.logger.error(f"Missing columns: {missing}")

sibi_dst/utils/dask_utils.py

@@ -1,7 +1,10 @@
+from __future__ import annotations
+
 import asyncio
 from typing import List, Any, Dict
 
 import dask
+#dask.config.set({"distributed.worker.daemon": False})
 import dask.dataframe as dd
 
 def _to_int_safe(x) -> int:
@@ -58,4 +61,124 @@ class UniqueValuesExtractor:
             return col, await self.compute_to_list(ser)
 
         pairs = await asyncio.gather(*(one(c) for c in columns))
-        return dict(pairs)
+        return dict(pairs)
+
+from contextlib import suppress
+from dask.distributed import Client, LocalCluster, get_client
+import os
+
+class DaskClientMixin:
+    """
+    Provides shared Dask client lifecycle management.
+    Ensures reuse of an existing client if available,
+    or creates a local in-process Dask cluster for fallback.
+    """
+
+    def _init_dask_client(
+        self,
+        dask_client=None,
+        logger=None,
+        *,
+        n_workers: int = 1,
+        threads_per_worker: int = 1,
+        processes: bool = False,
+        asynchronous: bool = False,
+        memory_limit: str = "auto",
+        #dashboard_address: str | None = None,
+        local_directory: str | None = None,
+        silence_logs: str = "info",
+        resources: dict | None = None,
+        timeout: int = 30,
+    ):
+        self.dask_client = dask_client
+        self.own_dask_client = False
+        self.logger = logger
+
+        if self.dask_client is None:
+            with suppress(ValueError, RuntimeError):
+                # Try to attach to an existing client (common in shared Dask setups)
+                self.dask_client = get_client()
+
+        if self.dask_client is None:
+            # Default to half of logical cores if not specified
+            n_workers = n_workers or max(2, os.cpu_count() // 2)
+
+            cluster = LocalCluster(
+                n_workers=n_workers,
+                threads_per_worker=threads_per_worker,
+                processes=processes,
+                asynchronous=asynchronous,
+                memory_limit=memory_limit,
+                local_directory=local_directory,
+                silence_logs=silence_logs,
+                resources=resources,
+                timeout=timeout,
+            )
+
+            self.dask_client = Client(cluster)
+            self.own_dask_client = True
+
+            if self.logger:
+                self.logger.info(
+                    f"Started local Dask cluster with {n_workers} workers × {threads_per_worker} threads "
+                    f"({memory_limit} memory per worker). Dashboard: {self.dask_client.dashboard_link}"
+                )
+        else:
+            if self.logger:
+                self.logger.debug(
+                    f"Using existing Dask client: {self.dask_client.dashboard_link}"
+                )
+
+    def _close_dask_client(self):
+        """Close the Dask client if this instance created it."""
+        if getattr(self, "own_dask_client", False) and self.dask_client is not None:
+            try:
+                cluster = getattr(self.dask_client, "cluster", None)
+                self.dask_client.close()
+                if cluster is not None:
+                    cluster.close()
+                if self.logger:
+                    self.logger.info("Closed local Dask client and cluster.")
+            except Exception as e:
+                if self.logger:
+                    self.logger.warning(f"Error while closing Dask client: {e}")
+
+# from contextlib import suppress
+# from dask.distributed import Client, get_client
+#
+# class DaskClientMixin:
+#     """
+#     Provides shared Dask client lifecycle management.
+#     Ensures reuse of existing client when available, otherwise creates a lightweight local one.
+#     """
+#
+#     def _init_dask_client(self, dask_client=None, logger=None):
+#         self.dask_client = dask_client
+#         self.own_dask_client = False
+#         self.logger = logger
+#
+#         if self.dask_client is None:
+#             with suppress(ValueError, RuntimeError):
+#                 # Try to attach to an existing active client if running inside a Dask context
+#                 self.dask_client = get_client()
+#
+#         if self.dask_client is None:
+#             # Start a local in-process scheduler for fallback
+#             self.dask_client = Client(processes=False)
+#             self.own_dask_client = True
+#             if self.logger:
+#                 self.logger.info(f"Started local Dask client: {self.dask_client.dashboard_link}")
+#         else:
+#             if self.logger:
+#                 self.logger.debug(f"Using existing Dask client: {self.dask_client.dashboard_link}")
+#
+#     def _close_dask_client(self):
+#         """Close client only if this instance created it."""
+#         if getattr(self, "own_dask_client", False) and self.dask_client is not None:
+#             try:
+#                 self.dask_client.close()
+#                 if self.logger:
+#                     self.logger.info("Closed local Dask client.")
+#             except Exception as e:
+#                 if self.logger:
+#                     self.logger.warning(f"Error while closing Dask client: {e}")

sibi_dst/utils/data_wrapper.py

@@ -87,17 +87,6 @@ class DataWrapper(ManagedResource):
             "dataclass": self.dataclass.__name__
         })
 
-    # --------------------- Context Management ---------------------
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        """Ensure manifest is saved and resources are cleaned up on context exit."""
-        if self.mmanifest:
-            try:
-                self.mmanifest.save()
-            except Exception as e:
-                self.logger.error(f"Failed to save manifest in __exit__: {e}", extra=self.logger_extra)
-        # Call parent's __exit__ which triggers _cleanup
-        return super().__exit__(exc_type, exc_val, exc_tb)
-
     # --------------------- Cleanup ---------------------
     def _cleanup(self) -> None:
         """Signal shutdown during class-specific cleanup."""

sibi_dst/utils/filepath_generator.py

@@ -160,160 +160,7 @@ class FilePathGenerator:
         # For local file, return absolute-like path without scheme or keep 'file://'? Keep scheme for consistency.
         return f"{self._protocol}://{path}"
 
-# import datetime
-# import re
-#
-# import fsspec
-#
-# from .log_utils import Logger
-#
-#
-# class FilePathGenerator:
-#     """
-#     Dynamically generates file paths by scanning directories starting from the base path
-#     and determining the innermost directory structure.
-#
-#     Now supports generating appropriate paths for both pandas and Dask.
-#     """
-#
-#     def __init__(self, base_path='', fs=None, logger=None, **kwargs):
-#         """
-#         Initialize the FilePathGenerator.
-#
-#         Parameters:
-#             base_path (str): Base directory path where data files are stored.
-#             fs (fsspec.AbstractFileSystem, optional): Filesystem object to use for file operations.
-#             logger (Logger, optional): Logger instance for logging information.
-#             **kwargs: Additional keyword arguments.
-#                 - debug (bool): If True, enables debug logging.
-#                 - storage_options (dict): Options for the filesystem (e.g., credentials, tokens).
-#                 - exclude_patterns (list): List of regex patterns to exclude from file paths.
-#                 - file_extension (str): File extension to look for (default: 'parquet').
-#         """
-#         self.base_path = base_path.rstrip('/')
-#         self.fs = fs  # Filesystem object
-#         self.logger = logger or Logger.default_logger(logger_name=self.__class__.__name__)
-#         self.debug = kwargs.get('debug', False)
-#         self.storage_options = kwargs.get('storage_options', {})
-#         self.exclude_patterns = kwargs.get('exclude_patterns', [])
-#         self.file_extension = kwargs.get('file_extension', 'parquet').lstrip('.')
-#
-#         # If fs is not provided, initialize it based on base_path and storage_options
-#         if self.fs is None:
-#             self.fs, _ = fsspec.core.url_to_fs(self.base_path, **self.storage_options)
-#
-#     def generate_file_paths(self, start_date, end_date, engine='dask'):
-#         """
-#         Generate paths dynamically for files within the date range by scanning directories.
-#         Returns a list of file paths compatible with the specified engine.
-#
-#         Parameters:
-#             start_date (str or datetime): Start date in 'YYYY-MM-DD' format or datetime object.
-#             end_date (str or datetime): End date in 'YYYY-MM-DD' format or datetime object.
-#             engine (str): 'pandas' or 'dask' to specify which library the paths are intended for.
-#
-#         Returns:
-#             list: List of file paths.
-#         """
-#         start_date = self._convert_to_datetime(start_date)
-#         end_date = self._convert_to_datetime(end_date)
-#
-#         paths = []
-#         curr_date = start_date
-#
-#         while curr_date <= end_date:
-#             year, month, day = curr_date.year, curr_date.month, curr_date.day
-#             day_paths = self._collect_paths(year, month, day, engine)
-#             if day_paths:
-#                 paths.extend(day_paths)
-#             curr_date += datetime.timedelta(days=1)
-#
-#         return paths
-#
-#     def _collect_paths(self, year, month, day, engine):
-#         """
-#         Collect appropriate paths for a given date, depending on the engine.
-#
-#         Parameters:
-#             year (int): Year component of the date.
-#             month (int): Month component of the date.
-#             day (int): Day component of the date.
-#             engine (str): 'pandas' or 'dask'.
-#
-#         Returns:
-#             list: List of file or directory paths.
-#         """
-#         base_dir = f"{self.base_path}/{year}/{str(month).zfill(2)}/{str(day).zfill(2)}"
-#
-#         if not self.fs.exists(base_dir):
-#             if self.debug:
-#                 self.logger.debug(f"Directory does not exist: {base_dir}")
-#             return []
-#
-#         if engine == 'dask':
-#             # Collect individual file paths
-#             file_pattern = f"{base_dir}/**/*.{self.file_extension}"
-#             all_paths = self.fs.glob(file_pattern)
-#
-#             if not all_paths and self.debug:
-#                 self.logger.debug(f"No files found with pattern: {file_pattern}")
-#
-#             # Exclude unwanted files and directories
-#             filtered_paths = self._exclude_unwanted_paths(all_paths)
-#
-#             # Filter out directories
-#             file_paths = [path for path in filtered_paths if not self.fs.isdir(path)]
-#
-#         elif engine == 'pandas':
-#             # Collect dataset directories
-#             # Assume that the base_dir is a Parquet dataset
-#             if self.fs.isdir(base_dir):
-#                 file_paths = [base_dir]
-#             else:
-#                 file_paths = []
-#
-#         else:
-#             raise ValueError("Engine must be 'pandas' or 'dask'.")
-#
-#         protocol = self.fs.protocol if isinstance(self.fs.protocol, str) else self.fs.protocol[0]
-#
-#         # Ensure the protocol is included in the paths
-#         file_paths = [
-#             f"{protocol}://{path}" if not path.startswith(f"{protocol}://") else path
-#             for path in file_paths
-#         ]
-#
-#         if self.debug:
-#             self.logger.debug(f"Collected {len(file_paths)} paths from {base_dir} for engine '{engine}'")
-#
-#         return file_paths
-#
-#     def _exclude_unwanted_paths(self, paths):
-#         """
-#         Exclude paths that match any of the exclusion patterns.
-#         """
-#         # Combine default patterns with user-provided patterns
-#         exclude_patterns = self.exclude_patterns
-#
-#         # Compile regex patterns for efficiency
-#         compiled_patterns = [re.compile(pattern) for pattern in exclude_patterns]
-#
-#         # Filter out paths matching any of the exclude patterns
-#         filtered_paths = [
-#             path for path in paths
-#             if not any(pattern.match(path) for pattern in compiled_patterns)
-#         ]
-#
-#         return filtered_paths
-#
-#     @staticmethod
-#     def _convert_to_datetime(date):
-#         """Convert a date string or datetime object into a datetime object."""
-#         if isinstance(date, str):
-#             return datetime.datetime.strptime(date, '%Y-%m-%d')
-#         return date
-#
-#
+
 # """
 # Usage:
 # # Initialize the generator

{sibi_dst-2025.9.10.dist-info → sibi_dst-2025.9.12.dist-info}/METADATA

@@ -1,34 +1,31 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: sibi-dst
-Version: 2025.9.10
-Summary: Data Science Toolkit
-Author: Luis Valverde
-Author-email: lvalverdeb@gmail.com
-Requires-Python: >=3.11,<4.0
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: clickhouse-connect (>=0.8.18,<0.9.0)
-Requires-Dist: clickhouse-driver (>=0.2.9,<0.3.0)
-Requires-Dist: dask[complete] (>=2025.9.0,<2026.0.0)
-Requires-Dist: distributed (>=2025.9.1,<2026.0.0)
-Requires-Dist: mysqlclient (>=2.2.7,<3.0.0)
-Requires-Dist: opentelemetry-exporter-otlp (>=1.35.0,<2.0.0)
-Requires-Dist: opentelemetry-sdk (>=1.35.0,<2.0.0)
-Requires-Dist: pandas (>=2.3.1,<3.0.0)
-Requires-Dist: psycopg2 (>=2.9.10,<3.0.0)
-Requires-Dist: pyarrow (>=20.0.0,<21.0.0)
-Requires-Dist: pydantic (>=2.11.7,<3.0.0)
-Requires-Dist: pyiceberg[hive,s3fs] (>=0.9.1,<0.10.0)
-Requires-Dist: pymysql (>=1.1.1,<2.0.0)
-Requires-Dist: pyrosm (>=0.6.2,<0.7.0)
-Requires-Dist: s3fs (>=2025.5.1,<2026.0.0)
-Requires-Dist: sqlalchemy (>=2.0.41,<3.0.0)
-Requires-Dist: sse-starlette (>=3.0.2,<4.0.0)
-Requires-Dist: tqdm (>=4.67.1,<5.0.0)
-Requires-Dist: webdav4 (>=0.10.0,<0.11.0)
+Version: 2025.9.12
+Summary: A data science toolkit for scalable data processing and analysis.
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
+Requires-Dist: clickhouse-connect>=0.9.2
+Requires-Dist: clickhouse-driver>=0.2.9
+Requires-Dist: dask>=2025.9.1
+Requires-Dist: distributed>=2025.9.1
+Requires-Dist: fastapi>=0.118.0
+Requires-Dist: folium>=0.20.0
+Requires-Dist: mysqlclient>=2.2.7
+Requires-Dist: opentelemetry-api>=1.37.0
+Requires-Dist: opentelemetry-exporter-otlp>=1.37.0
+Requires-Dist: opentelemetry-sdk>=1.37.0
+Requires-Dist: pandas>=2.3.3
+Requires-Dist: psycopg2>=2.9.10
+Requires-Dist: pyarrow>=21.0.0
+Requires-Dist: pydantic>=2.11.10
+Requires-Dist: pymysql>=1.1.2
+Requires-Dist: redis>=6.4.0
+Requires-Dist: s3fs>=2025.9.0
+Requires-Dist: sqlalchemy>=2.0.43
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: uvicorn>=0.37.0
+Requires-Dist: webdav4>=0.10.0
+Requires-Dist: wheel>=0.45.1
 
 ### SIBI-DST
 
@@ -60,4 +57,3 @@ pip install sibi-dst[dev,test,geospatial]  # Install all optional dependencies
 
 
 ```
-

{sibi_dst-2025.9.10.dist-info → sibi_dst-2025.9.12.dist-info}/RECORD

@@ -1,6 +1,6 @@
-sibi_dst/__init__.py,sha256=D4TMsAMGRl54J5PNYMDf_z0NcCnS_lZK1YHze2eJvpc,464
-sibi_dst/df_helper/__init__.py,sha256=aOQFmWpLeSq-7O8IYEKaxR1nvuIe9F7SJsOsgwj1ECg,579
-sibi_dst/df_helper/_artifact_updater_async.py,sha256=0VBwGMIQXKagr4MpshvfuhplwePD2VQbN2MOUTgQyJs,9992
+sibi_dst/__init__.py,sha256=QQVT3Xlj8iZN17sSMfRQFSb_DHr8A7giJP8hn02K2Oo,585
+sibi_dst/df_helper/__init__.py,sha256=7rUdMybgCNZhQL_J7IFTTHz_xtFin81xavi5-PUExkA,463
+sibi_dst/df_helper/_artifact_updater_async.py,sha256=AZp0vM3vji0tjiaScr8a9SUMH15NjPIKYPdRQ7SJe3Y,11372
 sibi_dst/df_helper/_artifact_updater_threaded.py,sha256=M5GNZismOqMmBrcyfolP1DPv87VILQf_P18is_epn50,7238
 sibi_dst/df_helper/_df_helper.py,sha256=rgVP4ggiCW6tTHmUz2UqUvLznwOtY5IyoVS3WSlg73U,17005
 sibi_dst/df_helper/_parquet_artifact.py,sha256=UXkhDSAVRNKp9DykVhJd3agnryCZT0Sj2qhdhUZomuM,19421
@@ -9,7 +9,7 @@ sibi_dst/df_helper/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMp
 sibi_dst/df_helper/backends/http/__init__.py,sha256=d1pfgYxbiYg7E0Iw8RbJ7xfqIfJShqqTBQQGU_S6OOo,105
 sibi_dst/df_helper/backends/http/_http_config.py,sha256=eGPFdqZ5M3Tscqx2P93B6XoBEEzlmdt7yNg7PXUQnNQ,4726
 sibi_dst/df_helper/backends/parquet/__init__.py,sha256=0A6BGHZLwiLBmuBBaUvEHfeWTcInvy2NbymlrI_nuXE,104
-sibi_dst/df_helper/backends/parquet/_parquet_options.py,sha256=KlzmTMVHME5kmhEBRzWdWPcih-jYaslkyhHOZdQ1gLA,11802
+sibi_dst/df_helper/backends/parquet/_parquet_options.py,sha256=OeeWWFhrolayg8MGZxbbAVNIC9zZB9cCXxTGGLPX0og,11746
 sibi_dst/df_helper/backends/sqlalchemy/__init__.py,sha256=LjWm9B7CweTvlvFOgB90XjSe0lVLILAIYMWKPkFXFm8,265
 sibi_dst/df_helper/backends/sqlalchemy/_db_connection.py,sha256=6705rABdh0RY0JisxD7sE62m6890hMCAv_cpyHOMSvM,8729
 sibi_dst/df_helper/backends/sqlalchemy/_db_gatekeeper.py,sha256=GQwDy2JwPUx37vpwxPM5hg4ZydilPIP824y5C_clsl0,383
@@ -22,59 +22,58 @@ sibi_dst/df_helper/core/_defaults.py,sha256=9UMEMu2wXznO5UzEhnQ82f_ZazZ20JRyRXIi
 sibi_dst/df_helper/core/_filter_handler.py,sha256=9C30zrT8wSGy1X8ryiTWc0XfnbpeoHndHgoOcHKOPOo,19309
 sibi_dst/df_helper/core/_params_config.py,sha256=DYx2drDz3uF-lSPzizPkchhy-kxRrQKE5FQRxcEWsac,6736
 sibi_dst/df_helper/core/_query_config.py,sha256=1ApqmuSGXTC3CdF-xMsSbCa3V2Z5hOP3Wq5huhzZwqY,439
-sibi_dst/df_helper/data_cleaner.py,sha256=lkxQoXLvGzXCicFUimnA5nen5qkrO1oxgl_p2Be2o8w,5183
 sibi_dst/geopy_helper/__init__.py,sha256=Q1RJiUZIOlV0QNNLjxZ_2IZS5LqIe5jRbeQkfD1Vm60,112
 sibi_dst/geopy_helper/geo_location_service.py,sha256=1ArI980QF_gRw096ZsABHwJt-m55jrfOlB8tPwL1BvY,2959
 sibi_dst/geopy_helper/utils.py,sha256=Sb7qfSqIyWh-AZ4GBdB9-z5FrQPWtrdtQLLcNjph0yw,3351
-sibi_dst/osmnx_helper/__init__.py,sha256=On2_pD13HmzZjP-YrXV9BA9uFK-z26QkQE-MliGdv5w,134
+sibi_dst/osmnx_helper/__init__.py,sha256=hTv1uCnN35MSUEYNWk30OHHSflDb1qidwfLDXhUU8cE,243
 sibi_dst/osmnx_helper/base_osm_map.py,sha256=L7g3VBiayHX41BcCBTOCS0iJOKzp2ZZYcrp8N-mnU90,19392
+sibi_dst/osmnx_helper/route_path_builder.py,sha256=XJJyu4YXegAkCRjE-knyQncwXaxDVXZhalYacLcb7e0,3557
+sibi_dst/osmnx_helper/utils.py,sha256=7-lFVhGn4rHjGz6FvpXtC2jY8UzGIVyKR3MVyEfB7nw,14407
 sibi_dst/osmnx_helper/basemaps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sibi_dst/osmnx_helper/basemaps/calendar_html.py,sha256=UArt6FDgoCgoRte45Xo3IHqd-RNzW0YgitgZYfOFasY,4031
 sibi_dst/osmnx_helper/basemaps/route_map_plotter.py,sha256=rsJidieojcqIoe0kBanZbrxcelrS6nWoAyWoQXWdPiQ,11849
 sibi_dst/osmnx_helper/basemaps/router_plotter.py,sha256=UAiijn-J-jjX4YnL0_P9SFqTadrxMx-YK4djYhqPqfQ,10941
-sibi_dst/osmnx_helper/route_path_builder.py,sha256=XJJyu4YXegAkCRjE-knyQncwXaxDVXZhalYacLcb7e0,3557
-sibi_dst/osmnx_helper/utils.py,sha256=7-lFVhGn4rHjGz6FvpXtC2jY8UzGIVyKR3MVyEfB7nw,14407
 sibi_dst/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sibi_dst/tests/test_baseclass.py,sha256=5huAwjWo_SOEZR2_0y5w9qUmw5G7pVdm8X1OTG87JK0,11562
 sibi_dst/tests/test_data_wrapper_class.py,sha256=6uFmZR2DxnxQz49L5jT2ehlKvlLnpUHMLFB_PqqUq7k,3336
-sibi_dst/utils/__init__.py,sha256=vShNCOMPw8KKwlb4tq5XGrpjqakJ_OE8YDc_xDAWAxI,1302
+sibi_dst/utils/__init__.py,sha256=eoW7iROrCUVYjNT1owMgGvW6U7lolbNy3FrBb_wInPs,1304
 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=89oepkDCnjegnhzd6Kgga71AH17KSvNMlgD83CAAmg8,582
-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=LQZBACksqHO3tQ8OhWShfqjiGyda7UhrmllRq3eWQfU,5690
-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/business_days.py,sha256=DPZExTXTt7n3IbAaEuVacm-vZgbR_Ug2bJTPBUaoP3g,6694
 sibi_dst/utils/clickhouse_writer.py,sha256=8W_dTEOKQp4pXANznVSxRqFA2H5oD8UJifiBAONpXWY,17001
 sibi_dst/utils/credentials.py,sha256=cHJPPsmVyijqbUQIq7WWPe-lIallA-mI5RAy3YUuRME,1724
-sibi_dst/utils/dask_utils.py,sha256=QhFcmpH4fXAy6b3DugIX5JvH4h-P3M3hXKnBYTLRkq0,1991
+sibi_dst/utils/dask_utils.py,sha256=UA8Bp0Qm7n8WSyjFmxNSrWdJ5TG_v6NCrmgLxPbnXlA,6692
 sibi_dst/utils/data_from_http_source.py,sha256=AcpKNsqTgN2ClNwuhgUpuNCx62r5_DdsAiKY8vcHEBA,1867
 sibi_dst/utils/data_utils.py,sha256=7bLidEjppieNoozDFb6OuRY0W995cxg4tiGAlkGfePI,7768
-sibi_dst/utils/data_wrapper.py,sha256=-a5LkkjBVXUPwDYngn5K98oSNYsQf87zNaih9IJxs-I,18543
+sibi_dst/utils/data_wrapper.py,sha256=9HTuDXgvfhmFAOyNG_GEOaHuojxE3639yyzOoBt7Unc,18000
 sibi_dst/utils/date_utils.py,sha256=hBVWu9_cqiZ-XsLR7QY9Iek09DQKLwrY1ZlYxWlXj7g,31101
 sibi_dst/utils/df_utils.py,sha256=bQGromLOEdRTvbVVcuHq0vQ0fIgqhwOoD_eIp5v7VEY,10899
 sibi_dst/utils/file_age_checker.py,sha256=44B3lwH_PLwzMfiKkgvJKjKx-qSgITIXxKfNbdf_VeA,11552
 sibi_dst/utils/file_utils.py,sha256=cm__02IKCfEOzAKAZwdNIjnRL8H4XtPa6hKcj510pto,1310
-sibi_dst/utils/filepath_generator.py,sha256=Ke_OwBjLJkNMeOP0QjbLIZpSMkzhAIxKyf4hZ5P5re0,12916
+sibi_dst/utils/filepath_generator.py,sha256=Nt6JGEM01_bPCMuWs8_TnTm0CqV5Hv9o1zu9QvN4WFk,6774
 sibi_dst/utils/iceberg_saver.py,sha256=l1UWJWrLqe2OxCdP1mRyXlG9It1-F3MN_ZvHPmxqRJ4,5253
 sibi_dst/utils/log_utils.py,sha256=1xXTDfwMwWIdj37hjyXSpHx3ft2GMiXsAfxq9AArMTY,11588
 sibi_dst/utils/manifest_manager.py,sha256=9y4cV-Ig8O-ekhApp_UObTY-cTsl-bGnvKIThItEzg4,7394
 sibi_dst/utils/parquet_saver.py,sha256=Itctsf8UnBCnD6NrP00FK0y9KzZgKYfjUk1CC-0x-F0,20486
 sibi_dst/utils/periods.py,sha256=8eTGi-bToa6_a8Vwyg4fkBPryyzft9Nzy-3ToxjqC8c,1434
 sibi_dst/utils/phone_formatter.py,sha256=oeM22nLjhObENrpItCNeVpkYS4pXRm5hSxdk0M4nvwU,4580
-sibi_dst/utils/progress/__init__.py,sha256=VELVxzo2cePN_-LL0veel8-F3po6tokY5MOOpu6pz1A,92
-sibi_dst/utils/progress/jobs.py,sha256=nE58ng9GPCPZhnaCDltr1tQgu3AJVqBJ1dWbGcCH4xo,3089
-sibi_dst/utils/progress/sse_runner.py,sha256=NttASZH_ayXo1Zi6I4tSwYnWySLxexOYQGlqzOZiXlI,4965
 sibi_dst/utils/storage_config.py,sha256=DLtP5jKVM0mdFdgRw6LQfRqyavMjJcCVU7GhsUCRH78,4427
 sibi_dst/utils/storage_hive.py,sha256=eZ3nq2YWLUUG-06iJubSC15cwSHEbKKdKIwoVhD_I_E,8568
 sibi_dst/utils/storage_manager.py,sha256=La1NY79bhRAmHWXp7QcXJZtbHoRboJMgoXOSXbIl1SA,6643
 sibi_dst/utils/update_planner.py,sha256=1UOh4MjZSfaA_ZO-nKailOGal5EY-xVR8KSCJzo7p_g,16834
 sibi_dst/utils/webdav_client.py,sha256=D9J5d1f1qQwHGm5FE5AMVpOPwcU5oD7K8JZoKGP8NpM,5811
 sibi_dst/utils/write_gatekeeper.py,sha256=V8sY9YMO-JuN8Ps7prqwVSjP4f1HGH9KiVV-aTPCC_k,569
+sibi_dst/utils/boilerplate/__init__.py,sha256=89oepkDCnjegnhzd6Kgga71AH17KSvNMlgD83CAAmg8,582
+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=cPVvjGxd0tDDvP_c27MNDHNuNnM6k3yx5bivN5ZFgrQ,5587
+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/progress/__init__.py,sha256=VELVxzo2cePN_-LL0veel8-F3po6tokY5MOOpu6pz1A,92
+sibi_dst/utils/progress/jobs.py,sha256=nE58ng9GPCPZhnaCDltr1tQgu3AJVqBJ1dWbGcCH4xo,3089
+sibi_dst/utils/progress/sse_runner.py,sha256=NttASZH_ayXo1Zi6I4tSwYnWySLxexOYQGlqzOZiXlI,4965
 sibi_dst/v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sibi_dst/v2/df_helper/__init__.py,sha256=XuH6jKYAPg2DdRbsxxBSxp9X3x-ARyaT0xe27uILrVo,99
 sibi_dst/v2/df_helper/_df_helper.py,sha256=9pED3bjQ2Z81zqzJrZ9e7SguoO4-hBmNTJK4WOKrr4M,9297
@@ -95,6 +94,7 @@ 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-2025.9.10.dist-info/METADATA,sha256=Sy1u7f-x3I_Ap-n2NklwyhAPWk1cluc0vX5Qn_BgS7c,2761
-sibi_dst-2025.9.10.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-sibi_dst-2025.9.10.dist-info/RECORD,,
+sibi_dst-2025.9.12.dist-info/METADATA,sha256=6WESOFkRannoMbUj_V-dDpti2qQ5XIxUgHSTfaqKAHA,2413
+sibi_dst-2025.9.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sibi_dst-2025.9.12.dist-info/top_level.txt,sha256=g3Cj4R-rciuNyJgcxuxNgw5nhN0n4TCB0ujcTEjZNiU,9
+sibi_dst-2025.9.12.dist-info/RECORD,,

{sibi_dst-2025.9.10.dist-info → sibi_dst-2025.9.12.dist-info}/WHEEL

@@ -1,4 +1,5 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
+