core-lens 0.1.dev111__tar.gz → 0.1.dev112__tar.gz

{core_lens-0.1.dev111 → core_lens-0.1.dev112}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev111
+Version: 0.1.dev112
 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.dev112}/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.dev112'
+__version_tuple__ = version_tuple = (0, 1, 'dev112')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev111 → core_lens-0.1.dev112}/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.dev112}/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.dev112}/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.dev112}/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()
     )