core-lens 0.1.dev108__tar.gz → 0.1.dev110__tar.gz

{core_lens-0.1.dev108 → core_lens-0.1.dev110}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev108
+Version: 0.1.dev110
 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.dev108 → core_lens-0.1.dev110}/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.dev108'
-__version_tuple__ = version_tuple = (0, 1, 'dev108')
+__version__ = version = '0.1.dev110'
+__version_tuple__ = version_tuple = (0, 1, 'dev110')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev108 → core_lens-0.1.dev110}/src/core_lens/aoi.py

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

{core_lens-0.1.dev108 → core_lens-0.1.dev110}/src/core_lens/base/namespaces/plot.py

@@ -460,7 +460,9 @@ class PlotNamespace:
         unique_entities = entity_df[key_col].unique()
         if len(unique_entities) > top_n:
             entities = unique_entities.limit(top_n).to_list()
-            entity_df = entity_df.filter(pl.col(key_col).is_in(entities))
+            entity_df = entity_df.join(
+                pl.DataFrame({key_col: entities}), on=key_col, how="inner"
+            )
         entity_pdf = entity_df.to_pandas()
 
         fig_entity = _make_fig(entity_pdf, f"Timeseries — {y_col} (Per Entity)")
@@ -512,7 +514,7 @@ class PlotNamespace:
         unique_entities = df[key_col].unique()
         if len(unique_entities) > top_n:
             entities = unique_entities.limit(top_n).to_list()
-            df = df.filter(pl.col(key_col).is_in(entities))
+            df = df.join(pl.DataFrame({key_col: entities}), on=key_col, how="inner")
 
         df_pd = df.to_pandas()
 
@@ -583,7 +585,7 @@ class PlotNamespace:
         unique_entities = df[key_col].unique()
         if len(unique_entities) > top_n:
             entities = unique_entities.limit(top_n).to_list()
-            df = df.filter(pl.col(key_col).is_in(entities))
+            df = df.join(pl.DataFrame({key_col: entities}), on=key_col, how="inner")
 
         df_pd = df.to_pandas()
 

{core_lens-0.1.dev108 → core_lens-0.1.dev110}/src/core_lens/base/result.py

@@ -148,11 +148,7 @@ class Result:
         geo_df = collect_lf(
             pl.scan_parquet(static_path)
             .select(key_cols + [geom_col])
-            .filter(
-                pl.col(key_cols[0]).is_in(self.data[key_cols[0]].to_list())
-                if len(key_cols) == 1
-                else pl.lit(True)
-            )
+            .join(self.data.select(key_cols).unique().lazy(), on=key_cols, how="inner")
         )
 
         joined = self.data.join(geo_df, on=key_cols, how="left")

{core_lens-0.1.dev108 → core_lens-0.1.dev110}/src/core_lens/utils/spatial.py

@@ -77,26 +77,37 @@ def build_bbox_index(
             + "Cannot compute bounds from separate lat/lon columns without bbox hints."
         )
 
-    df = pl.read_parquet(static_path, columns=cols_to_read)
-    geom_series = df[geometry_col]
+    import pyarrow.parquet as pq  # type: ignore[import-untyped]
 
-    geom_array = geom_series.to_numpy()
+    pf = pq.ParquetFile(static_path)
+    chunks = []
 
-    if geometry_type == "wkb":
-        geoms = shapely.from_wkb(geom_array)
-    else:
-        geoms = shapely.from_wkt(geom_array)
+    for batch in pf.iter_batches(batch_size=25_000, columns=cols_to_read):
+        batch_df = pl.from_arrow(batch)
+        assert isinstance(batch_df, pl.DataFrame)
 
-    if len(geoms) > 0:
-        bnds = shapely.bounds(geoms)
-        return df.select(key_cols).with_columns(
-            pl.Series("minx", bnds[:, 0], dtype=pl.Float64),
-            pl.Series("miny", bnds[:, 1], dtype=pl.Float64),
-            pl.Series("maxx", bnds[:, 2], dtype=pl.Float64),
-            pl.Series("maxy", bnds[:, 3], dtype=pl.Float64),
-        )
+        geom_array = batch_df.get_column(geometry_col).to_numpy()
 
-    return df.select(key_cols).with_columns(
+        if geometry_type == "wkb":
+            geoms = shapely.from_wkb(geom_array)
+        else:
+            geoms = shapely.from_wkt(geom_array)
+
+        if len(geoms) > 0:
+            bnds = shapely.bounds(geoms)
+            chunk = batch_df.select(key_cols).with_columns(
+                pl.Series("minx", bnds[:, 0], dtype=pl.Float64),
+                pl.Series("miny", bnds[:, 1], dtype=pl.Float64),
+                pl.Series("maxx", bnds[:, 2], dtype=pl.Float64),
+                pl.Series("maxy", bnds[:, 3], dtype=pl.Float64),
+            )
+            chunks.append(chunk)
+
+    if chunks:
+        return pl.concat(chunks)
+
+    empty_df = pl.read_parquet(static_path, columns=key_cols)
+    return empty_df.with_columns(
         pl.Series("minx", [], dtype=pl.Float64),
         pl.Series("miny", [], dtype=pl.Float64),
         pl.Series("maxx", [], dtype=pl.Float64),
@@ -182,17 +193,13 @@ def exact_spatial_filter(
     if candidates.is_empty():
         return candidates.select(key_cols)
 
-    # Build a filter expression to read only the candidate rows.
-    full_df = pl.read_parquet(static_path, columns=key_cols + [geometry_col])
-
-    # Filter to candidate keys.
-    if len(key_cols) == 1:
-        key = key_cols[0]
-        candidate_keys = candidates[key].to_list()
-        full_df = full_df.filter(pl.col(key).is_in(candidate_keys))
-    else:
-        # Composite key: join on all key columns.
-        full_df = full_df.join(candidates.select(key_cols), on=key_cols, how="inner")
+    # Build a lazy scan and push down an inner join to load only required geometries.
+    full_df = (
+        pl.scan_parquet(static_path)
+        .select(key_cols + [geometry_col])
+        .join(candidates.select(key_cols).lazy(), on=key_cols, how="inner")
+        .collect()
+    )
 
     geom_array = full_df[geometry_col].to_numpy()
     if geometry_type == "wkb":