core-lens 0.1.dev111__tar.gz → 0.1.dev113__tar.gz

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev111
+Version: 0.1.dev113
 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.dev111 → core_lens-0.1.dev113}/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.dev111'
-__version_tuple__ = version_tuple = (0, 1, 'dev111')
+__version__ = version = '0.1.dev113'
+__version_tuple__ = version_tuple = (0, 1, 'dev113')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/src/core_lens/aoi.py

@@ -360,7 +360,7 @@ class AoI:
                 or col in candidate.schema_profile.extra_static_cols
             ):
                 if isinstance(val, list):
-                    lf = lf.join(pl.LazyFrame({col: val}), on=col, how="inner")
+                    lf = lf.filter(pl.col(col) == val)
                 else:
                     filter_expr = filter_expr & (pl.col(col) == val)
 

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/src/core_lens/base/namespaces/plot.py

@@ -78,15 +78,16 @@ def _wkb_to_arrow_table(
     keep = [geom_col] + (extra_cols or [])
     df = df.select([c for c in keep if c in df.columns])
 
-    def _wkb_geom_type(b: bytes) -> int:
-        """Return the WKB geometry type integer (1-7), or 0 on invalid input."""
-        if not b or len(b) < 5:
-            return 0
-        endian = b[0]  # 1 = little-endian, 0 = big-endian
-        raw = int.from_bytes(b[1:5], "little" if endian == 1 else "big")
-        return raw & 0xFFFF  # strip ISO Z/M/SRID flags
-
-    geom_type_series = df[geom_col].map_elements(_wkb_geom_type, return_dtype=pl.Int32)
+    # WKB type detection: slice byte 1 (skip endian flag) — single byte covers
+    # all standard types 1-7.  bin.slice returns BinaryView in this Polars build
+    # which cannot be cast to UInt8 directly, so we extract the int value via
+    # map_elements on the already-sliced 1-byte series (no endian logic, no
+    # int.from_bytes on 4 bytes — still much cheaper than the original path).
+    geom_type_series = (
+        df[geom_col]
+        .bin.slice(1, 1)
+        .map_elements(lambda b: b[0] if b else 0, return_dtype=pl.UInt8)
+    )
 
     # --- Fast path: pure Polygon / MultiPolygon rows (no Shapely) ---
     poly_mask = geom_type_series.is_in([3, 6])
@@ -134,6 +135,9 @@ def _wkb_to_arrow_table(
         return ac.Table.from_arrow(arrow_table)
 
     arrow_table = df_poly.to_arrow()
+    del (
+        df_poly
+    )  # free Polars WKB buffer before PyArrow combine_chunks() allocates its copy
     wkb_col = arrow_table.column(geom_col).combine_chunks()
     geo_col = ga.from_wkb(wkb_col)
 

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/src/core_lens/base/result.py

@@ -148,7 +148,7 @@ class Result:
         geo_df = collect_lf(
             pl.scan_parquet(static_path)
             .select(key_cols + [geom_col])
-            .join(self.data.select(key_cols).unique().lazy(), on=key_cols, how="inner")
+            .join(self.data.select(key_cols).lazy(), on=key_cols, how="semi")
         )
 
         joined = self.data.join(geo_df, on=key_cols, how="left")

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/src/core_lens/utils/polars_utils.py

@@ -100,14 +100,14 @@ def scan_with_key_filter(
     Returns:
         A ``pl.LazyFrame`` ready to be ``.collect()``-ed.
     """
-    lf = pl.scan_parquet(path)
+    lf = pl.scan_parquet(path, hive_partitioning=True)
 
     # Use an inner join to filter the parquet file down to the exact requested keys.
     # This avoids building a massive literal expression tree (which consumes gigabytes
     # of RAM) that occurs when passing large lists to pl.col().is_in().
-    lf = lf.join(key_values.lazy(), on=key_cols, how="inner")
-
     if time_expr is not None:
         lf = lf.filter(time_expr)
 
+    lf = lf.join(key_values.lazy(), on=key_cols, how="semi")
+
     return lf

{core_lens-0.1.dev111 → core_lens-0.1.dev113}/src/core_lens/utils/spatial.py

@@ -197,7 +197,7 @@ def exact_spatial_filter(
     full_df = (
         pl.scan_parquet(static_path)
         .select(key_cols + [geometry_col])
-        .join(candidates.select(key_cols).lazy(), on=key_cols, how="inner")
+        .join(candidates.select(key_cols).lazy(), on=key_cols, how="semi")
         .collect()
     )
 
@@ -230,6 +230,8 @@ def exact_spatial_filter(
             if inter_area / entity_area >= threshold:
                 hit_indices.append(i)
 
+    del geoms  # free all decoded Shapely geometries before assembling result
+
     matched: pl.DataFrame = full_df[hit_indices].select(key_cols)
     return matched