487 coredata modelspoint supportpy test what happens when block id is nan geometry is nan or other columns are nan

CHANGELOG.rst

@@ -1,6 +1,15 @@
 Changes - from version >= 1.x
 =============================
 
+2025-12-21
+----------
+
+**version 1.2.1**
+
+* [enhancement] `Blocks` can handle missing geometries (geometry as `None` or `NaN`)
+* [debug] `Blocks` default value column is `block_values`, and `PointSupport` default value column is `values` (to avoiding naming collisions during the join operation)
+* [debug] `Blocks` object default index is created when it is not provided by the user
+
 2025-11-23
 ----------
 

src/pyinterpolate/core/data_models/blocks.py

@@ -17,8 +17,7 @@
 import geopandas as gpd
 import numpy as np
 import pandas as pd
-
-from shapely.geometry import Polygon
+from shapely import MultiPolygon
 
 from pyinterpolate.distance.angular import calc_angles
 from pyinterpolate.distance.point import point_distance
@@ -219,10 +218,17 @@ def __init__(self,
             self.ds = ds.copy(deep=True)
         else:
             if value_column_name is None:
-                value_column_name = 'values'
-            self.ds = join_any_geometry_and_values(geometry=geometries,
-                                                   values=values,
-                                                   values_column_name=value_column_name)
+                value_column_name = 'block_value'
+            self.ds = join_any_geometry_and_values(
+                geometry=geometries,
+                values=values,
+                values_column_name=value_column_name
+            )
+            if index_column_name is None:
+                index_column_name = 'block_index'
+
+            self.ds.index.name = index_column_name
+            self.ds.reset_index(inplace=True)
 
         self.value_column_name = value_column_name
         self.index_column_name = index_column_name
@@ -716,6 +722,6 @@ def _sample_larges_geometries(geometries: gpd.GeoSeries) -> gpd.GeoSeries:
             present.
         """
         ds = geometries.apply(
-            lambda x: x if isinstance(x, Polygon) else largest_geometry(x)
+            lambda x: largest_geometry(x) if isinstance(x, MultiPolygon) else x
         )
         return ds

src/pyinterpolate/transform/geo.py

@@ -211,8 +211,8 @@ def points_to_lon_lat(points: gpd.GeoSeries) -> Tuple:
         Longitude, latitude (x, y)
     """
 
-    lon = points.apply(lambda pt: pt.x)
-    lat = points.apply(lambda pt: pt.y)
+    lon = points.apply(lambda pt: pt.x if isinstance(pt, Point) else None)
+    lat = points.apply(lambda pt: pt.y if isinstance(pt, Point) else None)
     return lon, lat
 
 

tests/test_core/test_point_support_model.py

@@ -3,6 +3,8 @@
 
 import geopandas as gpd
 
+from shapely.geometry import Point, Polygon
+
 from pyinterpolate.core.data_models.blocks import Blocks
 from pyinterpolate.core.data_models.point_support import PointSupport
 from .sample_data.dataprep import CANCER_DATA_WITH_CENTROIDS, POINT_SUPPORT_DATA
@@ -115,3 +117,255 @@ def test_unique_blocks():
     )
 
     assert len(ps.unique_blocks) == len(blocks.ds.index)
+
+
+def test_missing_block_values():
+    block_values = [10, np.nan, 11]
+
+    block_geoms = [
+        Polygon(
+            [(0, 0), (10, 0), (10, 10), (0, 10), (0, 0)]
+        ),
+        Polygon(
+            [(10, 0), (20, 0), (20, 10), (10, 10), (10, 0)]
+        ),
+        Polygon(
+            [(10, 10), (20, 10), (20, 20), (10, 20), (10, 10)]
+        )
+    ]
+
+    blocks = Blocks(
+        values=block_values,
+        geometries=block_geoms
+    )
+
+    points_values = [1, 2, 1, 3, 1, 5, 1, 6, 7, 7]
+    points_geoms = [
+        Point(2, 2),
+        Point(3, 3),
+        Point(4, 4),
+        Point(15, 15),
+        Point(16, 16),
+        Point(17, 17),
+        Point(18, 8),
+        Point(19, 9),
+        Point(10, 10),
+        Point(12, 12)
+    ]
+
+    point_support = PointSupport(
+        blocks=blocks,
+        values=points_values,
+        geometries=points_geoms
+    )
+
+    assert isinstance(point_support, PointSupport)
+    assert isinstance(point_support.point_support, gpd.GeoDataFrame)
+
+    points = point_support.get_points_array()
+    assert isinstance(points, np.ndarray)
+
+    indexes = point_support.get_point_to_block_indexes()
+    assert isinstance(indexes, pd.Series)
+    assert (len(indexes) == len(points))
+
+
+def test_missing_block_geometries_none():
+    block_values = [10, 10, 11]
+
+    block_geoms = [
+        Polygon(
+            [(0, 0), (10, 0), (10, 10), (0, 10), (0, 0)]
+        ),
+        None,
+        Polygon(
+            [(10, 10), (20, 10), (20, 20), (10, 20), (10, 10)]
+        )
+    ]
+
+    blocks = Blocks(
+        values=block_values,
+        geometries=block_geoms
+    )
+
+    points_values = [1, 2, 1, 3, 1, 5, 1, 6, 7, 7]
+    points_geoms = [
+        Point(2, 2),
+        Point(3, 3),
+        Point(4, 4),
+        Point(15, 15),
+        Point(16, 16),
+        Point(17, 17),
+        Point(18, 8),
+        Point(19, 9),
+        Point(10, 10),
+        Point(12, 12)
+    ]
+
+    point_support = PointSupport(
+        blocks=blocks,
+        values=points_values,
+        geometries=points_geoms
+    )
+
+    assert isinstance(point_support, PointSupport)
+    assert isinstance(point_support.point_support, gpd.GeoDataFrame)
+
+    points = point_support.get_points_array()
+    assert isinstance(points, np.ndarray)
+
+    indexes = point_support.get_point_to_block_indexes()
+    assert isinstance(indexes, pd.Series)
+    assert (len(indexes) == len(points))
+
+
+def test_missing_block_geometries_nan():
+    block_values = [10, 10, 11]
+
+    block_geoms = [
+        Polygon(
+            [(0, 0), (10, 0), (10, 10), (0, 10), (0, 0)]
+        ),
+        np.nan,
+        Polygon(
+            [(10, 10), (20, 10), (20, 20), (10, 20), (10, 10)]
+        )
+    ]
+
+    blocks = Blocks(
+        values=block_values,
+        geometries=block_geoms
+    )
+
+    points_values = [1, 2, 1, 3, 1, 5, 1, 6, 7, 7]
+    points_geoms = [
+        Point(2, 2),
+        Point(3, 3),
+        Point(4, 4),
+        Point(15, 15),
+        Point(16, 16),
+        Point(17, 17),
+        Point(18, 8),
+        Point(19, 9),
+        Point(10, 10),
+        Point(12, 12)
+    ]
+
+    point_support = PointSupport(
+        blocks=blocks,
+        values=points_values,
+        geometries=points_geoms
+    )
+
+    assert isinstance(point_support, PointSupport)
+    assert isinstance(point_support.point_support, gpd.GeoDataFrame)
+
+    points = point_support.get_points_array()
+    assert isinstance(points, np.ndarray)
+
+    indexes = point_support.get_point_to_block_indexes()
+    assert isinstance(indexes, pd.Series)
+    assert (len(indexes) == len(points))
+
+
+def test_missing_point_support_values():
+    block_values = [10, 9, 11]
+
+    block_geoms = [
+        Polygon(
+            [(0, 0), (10, 0), (10, 10), (0, 10), (0, 0)]
+        ),
+        Polygon(
+            [(10, 0), (20, 0), (20, 10), (10, 10), (10, 0)]
+        ),
+        Polygon(
+            [(10, 10), (20, 10), (20, 20), (10, 20), (10, 10)]
+        )
+    ]
+
+    blocks = Blocks(
+        values=block_values,
+        geometries=block_geoms
+    )
+
+    points_values = [1, 2, 1, np.nan, 1, 5, None, 6, 7, 7]
+    points_geoms = [
+        Point(2, 2),
+        Point(3, 3),
+        Point(4, 4),
+        Point(15, 15),
+        Point(16, 16),
+        Point(17, 17),
+        Point(18, 8),
+        Point(19, 9),
+        Point(10, 10),
+        Point(12, 12)
+    ]
+
+    point_support = PointSupport(
+        blocks=blocks,
+        values=points_values,
+        geometries=points_geoms
+    )
+
+    assert isinstance(point_support, PointSupport)
+    assert isinstance(point_support.point_support, gpd.GeoDataFrame)
+
+    points = point_support.get_points_array()
+    assert isinstance(points, np.ndarray)
+
+    indexes = point_support.get_point_to_block_indexes()
+    assert isinstance(indexes, pd.Series)
+    assert (len(indexes) == len(points))
+
+
+def test_missing_point_support_geometries():
+    block_values = [10, 9, 11]
+
+    block_geoms = [
+        Polygon(
+            [(0, 0), (10, 0), (10, 10), (0, 10), (0, 0)]
+        ),
+        Polygon(
+            [(10, 0), (20, 0), (20, 10), (10, 10), (10, 0)]
+        ),
+        Polygon(
+            [(10, 10), (20, 10), (20, 20), (10, 20), (10, 10)]
+        )
+    ]
+
+    blocks = Blocks(
+        values=block_values,
+        geometries=block_geoms
+    )
+
+    points_values = [1, 2, 1, 3, 1, 5, 1, 6, 7, 7]
+    points_geoms = [
+        Point(2, 2),
+        Point(3, 3),
+        Point(4, 4),
+        None,
+        Point(16, 16),
+        Point(17, 17),
+        np.nan,
+        Point(19, 9),
+        Point(10, 10),
+        Point(12, 12)
+    ]
+
+    point_support = PointSupport(
+        blocks=blocks,
+        values=points_values,
+        geometries=points_geoms
+    )
+
+    assert isinstance(point_support, PointSupport)
+    assert isinstance(point_support.point_support, gpd.GeoDataFrame)
+
+    points = point_support.get_points_array()
+    assert isinstance(points, np.ndarray)
+
+    indexes = point_support.get_point_to_block_indexes()
+    assert isinstance(indexes, pd.Series)
+    assert (len(indexes) == len(points))
+