core-lens 0.1.dev120__tar.gz → 0.1.dev123__tar.gz

{core_lens-0.1.dev120 → core_lens-0.1.dev123}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev120
+Version: 0.1.dev123
 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.dev120 → core_lens-0.1.dev123}/examples/demo_mws.py

@@ -7,7 +7,7 @@ geometry, derive, stats, plot, temporal queries, and export.
 
 Prerequisites
 -------------
-    pip install core-lens geopandas shapely polars scipy plotly lonboard
+    pip install core-lens geopandas shapely polars scipy bokeh lonboard
 
 Data layout expected
 --------------------
@@ -30,10 +30,17 @@ from __future__ import annotations
 
 import polars as pl
 import shapely.geometry as sgeom
+from bokeh.io import save
 
 from core_lens import AoI, SeasonConfig
 from core_lens.entities import MWSEntity
 from core_lens.export import geoparquet
+from core_lens.base.namespaces.stats import (
+    CorrelateMethod,
+    SimilarityMethod,
+    TestMethod,
+)
+from core_lens.base.view import Season
 
 DATA_ROOT = "/home/akashyap/Finals"
 
@@ -127,7 +134,7 @@ print("Resolution            :", result_annual.resolution)
 print("Has geometry          :", result_annual.has_geometry)  # False by default
 
 # Fortnightly data for a specific season and year
-result_fn = view_barmer.between(season="kharif", year=2021).fortnightly
+result_fn = view_barmer.between(season=Season.KHARIF, year=2021).fortnightly
 print("\nFortnightly columns (first 10):", result_fn.columns[:10])
 
 
@@ -170,7 +177,7 @@ print(desc_annual_by_entity.df().head(5))
 # Pairwise correlations on fortnightly data
 corr = result_fn.stats.correlate(
     columns=["df_precipitation", "df_et"],
-    method="pearson",
+    method=CorrelateMethod.PEARSON,
     across="entity",
 )
 print("\nCorrelation (Precipitation vs ET):")
@@ -183,7 +190,7 @@ print(corr.df())
 test_result = result_static_derived.stats.test(
     column="di_avg_dryspe",
     groups="district",
-    method="mann-whitney",
+    method=TestMethod.MANN_WHITNEY,
 )
 print("\nHypothesis test — dryspell by district:")
 print(test_result.df())
@@ -212,7 +219,7 @@ sim = result_static_derived.stats.similarity(
         "area_in_ha": None,
         "di_avg_dryspe": None,
     },
-    method="euclidean",
+    method=SimilarityMethod.EUCLIDEAN,
     top_n=5,
 )
 print(f"\nMost similar MWS to {target_id}:")
@@ -253,7 +260,7 @@ except Exception:
 
 try:
     line_fig = result_annual.plot.timeseries(x="year", y="dw_et")
-    line_fig.write_html("mws_et_trend.html")
+    save(line_fig, filename="mws_et_trend.html")
     print("Saved line plot to mws_et_trend.html")
 except Exception:
     pass
@@ -262,7 +269,7 @@ except Exception:
 # ── 21. Plot — scatter ───────────────────────────────────────────────────────
 try:
     scatter_fig = result_static_derived.plot.scatter(x="area_km2", y="dryspell_score")
-    scatter_fig.write_html("mws_scatter.html")
+    save(scatter_fig, filename="mws_scatter.html")
 except Exception:
     pass
 
@@ -289,7 +296,7 @@ print("GeoParquet written: output_mws.geoparquet")
 
 final = (
     aoi.mws.where(ba_name="Barmer")
-    .between(season="kharif", year=2021)
+    .between(season=Season.KHARIF, year=2021)
     .fortnightly.derive(
         "et_ratio", (pl.col("df_et") / pl.col("df_precipitation")).round(3)
     )

{core_lens-0.1.dev120 → core_lens-0.1.dev123}/examples/demo_tehsil.py

@@ -7,7 +7,7 @@ geometry, derive, stats, plot, and export.
 
 Prerequisites
 -------------
-    pip install core-lens geopandas shapely polars scipy plotly lonboard
+    pip install core-lens geopandas shapely polars scipy bokeh lonboard
 
 Data layout expected
 --------------------
@@ -33,6 +33,7 @@ from core_lens.base.namespaces.stats import (
     TestMethod,
 )
 import shapely.geometry as sgeom
+from bokeh.io import show
 
 
 DATA_ROOT = "data/"
@@ -288,19 +289,19 @@ result_plot = (
 
 # ── 19. Plot — scatter ────────────────────────────────────────────────────────
 scatter_fig = result_plot.plot.scatter(x="area_km2", y="Shape_Leng")
-scatter_fig.show()
+show(scatter_fig)
 
 
 # ── 20. Plot — distribution ───────────────────────────────────────────────────
 dist_fig = result_plot.plot.distribution(x="area_km2")
-dist_fig.show()
+show(dist_fig)
 
 
 # ── 21. Plot — correlation matrix ────────────────────────────────────────────
 corr_fig = result_plot.plot.correlation(
     columns=["area_km2", "Shape_Leng", "compactness"]
 )
-corr_fig.show()
+show(corr_fig)
 
 
 # ── 22. Plot — heatmap ────────────────────────────────────────────────────────
@@ -312,7 +313,7 @@ heatmap_fig = result_plot.plot.heatmap(
     y="STATE",
     value="area_km2",
 )
-heatmap_fig.show()
+show(heatmap_fig)
 
 
 # ── 23. AoI map ───────────────────────────────────────────────────────────────

{core_lens-0.1.dev120 → core_lens-0.1.dev123}/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.dev120'
-__version_tuple__ = version_tuple = (0, 1, 'dev120')
+__version__ = version = '0.1.dev123'
+__version_tuple__ = version_tuple = (0, 1, 'dev123')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev120 → core_lens-0.1.dev123}/src/core_lens/base/namespaces/plot.py

@@ -144,12 +144,33 @@ def _wkb_to_arrow_table(
     idx = arrow_table.schema.get_field_index(geom_col)
     schema = arrow_table.schema.remove(idx)
 
+    import json
+
+    arr_geo = ac.Array(geo_col)
+    ac_geo = ac.ChunkedArray([arr_geo])
+    geom_field = arr_geo.field.with_name(geom_col)
+
+    ext_meta = dict(geom_field.metadata or {})
+    geo_meta = {}
+    if b"ARROW:extension:metadata" in ext_meta:
+        try:
+            geo_meta = json.loads(ext_meta[b"ARROW:extension:metadata"].decode("utf-8"))
+        except Exception:
+            pass
+    geo_meta["crs"] = "EPSG:4326"
+    ext_meta[b"ARROW:extension:metadata"] = json.dumps(geo_meta).encode("utf-8")
+    new_geom_field = geom_field.with_metadata(ext_meta)
+
+    new_fields = [
+        ac.Field.from_arrow(schema.field(i)) for i in range(len(schema.names))
+    ]
+    new_fields.insert(idx, new_geom_field)
+    new_schema = ac.Schema(new_fields)
+
     tbl_cols = [ac.ChunkedArray(arrow_table.column(c)) for c in schema.names]
-    tbl_cols.insert(idx, ac.ChunkedArray([ac.Array(geo_col)]))
-    names = list(schema.names)
-    names.insert(idx, geom_col)
+    tbl_cols.insert(idx, ac_geo)
 
-    tbl = ac.Table.from_arrays(tbl_cols, names=names)
+    tbl = ac.Table.from_arrays(tbl_cols, schema=new_schema)
     return tbl
 
 
@@ -277,15 +298,20 @@ class PlotNamespace:
         # --- Direct Polars → GeoArrow → Lonboard path (zero Shapely, zero GeoPandas) ---
         arrow_table = _wkb_to_arrow_table(df, geom_col, extra_cols=extra)
 
+        import warnings
+
         # Extract colormap values from the already-filtered arrow_table.
         # arrow_table has the same row order as df post-filter, so indices align.
-        values = np.asarray(arrow_table.column(column).to_pylist())
-        v_min, v_max = np.nanmin(values), np.nanmax(values)
-        norm_values = (
-            (values - v_min) / (v_max - v_min)
-            if v_max > v_min
-            else np.zeros_like(values)
-        )
+        values = np.asarray(arrow_table.column(column).to_pylist(), dtype=float)
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", category=RuntimeWarning)
+            v_min, v_max = np.nanmin(values), np.nanmax(values)
+
+        if np.isnan(v_min) or np.isnan(v_max) or v_min >= v_max:
+            norm_values = np.where(np.isnan(values), np.nan, 0.0)
+        else:
+            norm_values = (values - v_min) / (v_max - v_min)
 
         cmap = mpl.colormaps["plasma"]