core-lens 0.1.dev152__tar.gz → 0.1.dev154__tar.gz

{core_lens-0.1.dev152 → core_lens-0.1.dev154}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev152
+Version: 0.1.dev154
 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.dev152 → core_lens-0.1.dev154}/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.dev152'
-__version_tuple__ = version_tuple = (0, 1, 'dev152')
+__version__ = version = '0.1.dev154'
+__version_tuple__ = version_tuple = (0, 1, 'dev154')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev152 → core_lens-0.1.dev154}/src/core_lens/base/namespaces/stats.py

@@ -859,9 +859,12 @@ class StatsNamespace:
         df = self._r.df()
         key = self._r.key_cols[0]
 
+        min_year: int | None = None
+        max_year: int | None = None
+
         # --- Build feature DataFrame ------------------------------------------
         # Universe of entity keys from result.data.
-        feat = df.select([key])
+        feat = df.select([key]).unique()
 
         for col_name, spec in columns.items():
             if spec is None:
@@ -881,6 +884,23 @@ class StatsNamespace:
             resolution_str, filter_dict = spec
             filter_dict = dict(filter_dict) if filter_dict else {}
 
+            if "year" in filter_dict:
+                yr = filter_dict["year"]
+                y0: int | None = None
+                y1: int | None = None
+
+                if isinstance(yr, (list, tuple)) and len(yr) >= 2:
+                    y0, y1 = int(yr[0]), int(yr[1])
+                elif isinstance(yr, int):
+                    y0, y1 = yr, yr
+
+                if y0 is not None:
+                    if min_year is None or y0 < min_year:
+                        min_year = y0
+                if y1 is not None:
+                    if max_year is None or y1 > max_year:
+                        max_year = y1
+
             entity = self._r.entity
             path: str | None
             if resolution_str == "static":
@@ -1006,13 +1026,26 @@ class StatsNamespace:
         dists[tidx] = float("inf")  # exclude target itself
         top_idx = np.argsort(dists)[:top_n]
 
-        data = pl.DataFrame(
-            {
-                key: [ids[i] for i in top_idx],
-                "similarity_score": [float(1.0 / (1.0 + dists[i])) for i in top_idx],
-                "rank": list(range(1, len(top_idx) + 1)),
-            }
-        )
+        if min_year is None and max_year is None:
+            year_col = self._year_col()
+            if year_col and year_col in df.columns:
+                yr_min = df[year_col].min()
+                yr_max = df[year_col].max()
+                if yr_min is not None and yr_max is not None:
+                    min_year = int(cast(int, yr_min))
+                    max_year = int(cast(int, yr_max))
+
+        output_dict: dict[str, Any] = {
+            key: [ids[i] for i in top_idx],
+            "similarity_score": [float(1.0 / (1.0 + dists[i])) for i in top_idx],
+            "rank": list(range(1, len(top_idx) + 1)),
+        }
+
+        if min_year is not None and max_year is not None:
+            output_dict["year_from"] = [min_year] * len(top_idx)
+            output_dict["year_to"] = [max_year] * len(top_idx)
+
+        data = pl.DataFrame(output_dict)
         metadata: dict[str, Any] = {
             "method": method.value if method is not None else None,
             "target": target,

{core_lens-0.1.dev152 → core_lens-0.1.dev154}/src/core_lens/base/result.py

@@ -174,7 +174,7 @@ class Result:
         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]))
+            geo_lf = geo_lf.filter(pl.col(key).is_in(keys_df[key].to_list()))
         else:
             geo_lf = geo_lf.join(keys_df.lazy(), on=key_cols, how="semi")
 

{core_lens-0.1.dev152 → core_lens-0.1.dev154}/src/core_lens/utils/polars_utils.py

@@ -146,7 +146,7 @@ def scan_with_key_filter(
         # predicate pushdown in the Parquet reader, avoiding a full table scan.
         # The literal tree RAM issue only occurs with hundreds of thousands of keys.
         key = key_cols[0]
-        lf = lf.filter(pl.col(key).is_in(kv_df[key]))
+        lf = lf.filter(pl.col(key).is_in(kv_df[key].to_list()))
     else:
         # Fallback to semi-join for massive key arrays (e.g. state-wide scopes)
         lf = lf.join(kv_df.lazy(), on=key_cols, how="semi")