core-lens 0.1.dev194__tar.gz → 0.1.dev196__tar.gz

{core_lens-0.1.dev194 → core_lens-0.1.dev196}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: core-lens
-Version: 0.1.dev194
+Version: 0.1.dev196
 Summary: Query, analyse, and visualise CoreStack's microwatershed and Earth science data through a clean, composable Python API.
 Project-URL: Homepage, https://github.com/ApoorvaKashyap/core-lens
 Project-URL: Issues, https://github.com/ApoorvaKashyap/core-lens/issues

{core_lens-0.1.dev194 → core_lens-0.1.dev196}/src/core_lens/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.1.dev194'
-__version_tuple__ = version_tuple = (0, 1, 'dev194')
+__version__ = version = '0.1.dev196'
+__version_tuple__ = version_tuple = (0, 1, 'dev196')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev194 → core_lens-0.1.dev196}/src/core_lens/base/entity.py

@@ -475,7 +475,11 @@ class BaseEntity(ABC):
                 )
 
         # --- Combine attribute and spatial filters into a single lazy pipeline ---
-        lf = pl.scan_parquet(parquet_scan_path(static))
+        _so = self._storage_options or {}
+        lf = pl.scan_parquet(
+            parquet_scan_path(static),
+            storage_options=_so or None,
+        )
 
         if attr_kwargs:
             filter_expr = pl.lit(True)
@@ -510,11 +514,18 @@ class BaseEntity(ABC):
 
             lookup_geoms = []
             for entity_kwarg_name, entity_kwarg_val in entity_kwargs.items():
-                other_entity = _REGISTRY[entity_kwarg_name](data_root=self._data_root)
+                other_entity = _REGISTRY[entity_kwarg_name](
+                    data_root=self._data_root,
+                    storage_options=self._storage_options,
+                )
                 other_profile = other_entity.schema_profile
                 other_static = other_entity._resolve(other_entity.static_path)
 
-                other_lf = pl.scan_parquet(other_static)
+                other_so = other_entity._storage_options or {}
+                other_lf = pl.scan_parquet(
+                    other_static,
+                    storage_options=other_so or None,
+                )
                 match_expr = pl.lit(False)
                 other_schema = cached_read_schema(
                     other_static, other_entity._storage_options

{core_lens-0.1.dev194 → core_lens-0.1.dev196}/src/core_lens/utils/polars_utils.py

@@ -150,12 +150,7 @@ def scan_with_key_filter(
     2. **Time filter** — an optional Polars expression appended with ``&``,
        pushed down when the Parquet file carries min/max column statistics.
 
-    ``use_statistics=True`` and ``parallel="columns"`` are set explicitly on
-    the underlying ``pl.scan_parquet`` call so that:
-
-    * Row-group skipping via Parquet min/max statistics is always active.
-    * On wide Parquet files, column chunks within each row group are fetched
-      concurrently instead of serially — reduces round trips on S3.
+    ``use_statistics=True`` is set explicitly on the underlying ``pl.scan_parquet`` call so that row-group skipping via Parquet min/max statistics is always active.
 
     Args:
         path (str): Absolute path or cloud URI to a Parquet file.
@@ -176,7 +171,6 @@ def scan_with_key_filter(
         path,
         hive_partitioning=True,
         use_statistics=True,
-        parallel="columns",
         storage_options=_so or None,
     )
 

{core_lens-0.1.dev194 → core_lens-0.1.dev196}/src/core_lens/utils/spatial.py

@@ -668,11 +668,15 @@ def execute_spatial_join(
     ):
         # Pre-filter other_entity using its in-memory bounding box index
         candidates = bbox_intersects_geometry(other_entity._index, primary_total_box)
+        other_so = getattr(other_entity, "_storage_options", None) or {}
         if candidates.is_empty():
             other_df = pl.DataFrame(schema={c: pl.Utf8 for c in other_cols})
         else:
             other_df = (
-                pl.scan_parquet(other_static)
+                pl.scan_parquet(
+                    other_static,
+                    storage_options=other_so or None,
+                )
                 .select(other_cols)
                 .join(
                     candidates.select(other_key_cols).lazy(),
@@ -682,7 +686,12 @@ def execute_spatial_join(
                 .collect()
             )
     else:
-        other_df = pl.read_parquet(other_static, columns=other_cols)
+        other_so = getattr(other_entity, "_storage_options", None) or {}
+        other_df = pl.read_parquet(
+            other_static,
+            columns=other_cols,
+            storage_options=other_so or None,
+        )
 
     if other_df.is_empty():
         other_geoms = np.array([])
@@ -847,8 +856,12 @@ def point_in_entities(
         key_cols: list[str] = entity.key_cols
         static_path: str = entity._resolve(entity.static_path)
 
+        so = getattr(entity, "_storage_options", None) or {}
         geom_df = (
-            pl.scan_parquet(parquet_scan_path(static_path))
+            pl.scan_parquet(
+                parquet_scan_path(static_path),
+                storage_options=so or None,
+            )
             .select(key_cols + [geom_col])
             .join(candidates.select(key_cols).lazy(), on=key_cols, how="semi")
             .collect()