core-lens 0.1.dev150__tar.gz → 0.1.dev152__tar.gz

{core_lens-0.1.dev150 → core_lens-0.1.dev152}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev150
+Version: 0.1.dev152
 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.dev150 → core_lens-0.1.dev152}/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.dev150'
-__version_tuple__ = version_tuple = (0, 1, 'dev150')
+__version__ = version = '0.1.dev152'
+__version_tuple__ = version_tuple = (0, 1, 'dev152')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev150 → core_lens-0.1.dev152}/src/core_lens/base/entity.py

@@ -474,7 +474,22 @@ class BaseEntity(ABC):
         if attr_kwargs:
             filter_expr = pl.lit(True)
             for col, val in attr_kwargs.items():
-                filter_expr = filter_expr & (pl.col(col) == val)
+                dtype = schema[col]
+                is_list_col = isinstance(dtype, pl.List) or dtype == pl.List
+                is_val_list = isinstance(val, (list, tuple, set))
+
+                if is_list_col:
+                    if is_val_list:
+                        filter_expr = filter_expr & (
+                            pl.col(col).list.set_intersection(list(val)).list.len() > 0
+                        )
+                    else:
+                        filter_expr = filter_expr & pl.col(col).list.contains(val)
+                else:
+                    if is_val_list:
+                        filter_expr = filter_expr & pl.col(col).is_in(list(val))
+                    else:
+                        filter_expr = filter_expr & (pl.col(col) == val)
             lf = lf.filter(filter_expr)
 
         if not entity_kwargs:

{core_lens-0.1.dev150 → core_lens-0.1.dev152}/src/core_lens/base/result.py

@@ -89,6 +89,14 @@ class Result:
         """
         return collect_lf(self.data)
 
+    def materialise(self) -> "Result":
+        """Evaluate the lazy computation graph and cache it in memory.
+
+        Returns:
+            Result: A new Result with the data cached as an in-memory LazyFrame.
+        """
+        return self._replace(data=self.df().lazy())
+
     def gdf(self) -> "gpd.GeoDataFrame":
         """Return the data as a ``GeoDataFrame``.
 
@@ -156,13 +164,24 @@ class Result:
 
         key_cols = self.key_cols
 
-        # We use a direct left join here instead of a semi-join intermediate step.
-        # A semi-join creates a "diamond" query graph where `self.data` must be evaluated
-        # twice by Polars. Because `self.data` can be an expensive aggregation pipeline,
-        # this caused execution times to double.
-        joined = self.data.join(self.entity.geometry_lazy, on=key_cols, how="left")
+        # 1. Evaluate the heavy aggregation graph ONCE to prevent Polars from
+        # evaluating it twice during the geometry extraction and join.
+        res = self.materialise()
+        keys_df = res.df().select(key_cols)
+
+        # 2. Push down the geometry filter into the Parquet reader using is_in
+        # so we don't scan the entire static geometry file (which takes ~0.4s).
+        geo_lf = self.entity.geometry_lazy
+        if len(key_cols) == 1 and keys_df.height < 50000:
+            key = key_cols[0]
+            geo_lf = geo_lf.filter(pl.col(key).is_in(keys_df[key]))
+        else:
+            geo_lf = geo_lf.join(keys_df.lazy(), on=key_cols, how="semi")
+
+        joined = res.data.join(geo_lf, on=key_cols, how="left")
 
-        return self._replace(data=joined, has_geometry=True)
+        # 3. Cache the joined geometry so multiple plots are instant.
+        return res._replace(data=joined, has_geometry=True).materialise()
 
     def derive(self, name: str, expr: pl.Expr) -> "Result":
         """Return a new ``Result`` with a computed column appended.