BUG: assign Crimea to Ukraine in naturalearth_lowres (#2670)

CHANGELOG.md

@@ -2,11 +2,11 @@
 
 ## Development version
 
-
 Bug fixes:
 
 - Correctly handle geometries with Z dimension in ``to_crs()`` when using PyGEOS or
   Shapely >= 2.0 (previously the z coordinates were lost) (#1345).
+- Assign Crimea to Ukraine in naturalearth_lowres (#2670)
 
 ## Version 0.12.1 (October 29, 2022)
 
@@ -19,7 +19,7 @@ test Shapely 2.0 (currently 2.0b1) alongside GeoPandas.
 
 Note that if you also have PyGEOS installed, you need to set an environment variable
 (`USE_PYGEOS=0`) before importing geopandas to actually test Shapely 2.0 features instead of PyGEOS. See
-https://geopandas.org/en/latest/getting_started/install.html#using-the-optional-pygeos-dependency
+<https://geopandas.org/en/latest/getting_started/install.html#using-the-optional-pygeos-dependency>
 for more details.
 
 New features and improvements:
@@ -55,8 +55,8 @@ Small bug-fix release:
   MultiIndex (#2486).
 - Fix regression in ``GeoDataFrame.explode()`` with non-default
   geometry column name.
-- Fix regression in ``apply()`` causing row-wise all nan float columns to be 
-  casted to GeometryDtype (#2482). 
+- Fix regression in ``apply()`` causing row-wise all nan float columns to be
+  casted to GeometryDtype (#2482).
 - Fix a crash in datetime column reading where the file contains mixed timezone
   offsets (#2479). These will be read as UTC localized values.
 - Fix a crash in datetime column reading where the file contains datetimes
@@ -68,7 +68,6 @@ Small bug-fix release:
   feather or parquet writer. ``version`` will only be used to set
   ``schema_version`` if ``version`` is one of 0.1.0 or 0.4.0 (#2496).
 
-
 Version 0.11 (June 20, 2022)
 ----------------------------
 

geopandas/datasets/naturalearth_creation.py

@@ -11,6 +11,7 @@ import requests
 from pathlib import Path
 from zipfile import ZipFile
 import tempfile
+from shapely.geometry import box
 
 version = "latest"
 urlbase = "https://www.naturalearthdata.com/"
@@ -89,6 +90,29 @@ for dl in config:
             gdf = dl["override"](gdf)
         gdf = gdf.loc[:, dl["cols"]]
         gdf = gdf.rename(columns={c: c.lower() for c in gdf.columns})
+
+        # override Crimea #2382
+        if dl["file"] == "ne_110m_admin_0_countries.zip":
+            crimean_bbox = box(32.274, 44.139, 36.65, 46.704)
+            crimea_only = (
+                gdf.loc[gdf.name == "Russia", "geometry"]
+                .iloc[0]
+                .intersection(crimean_bbox)
+            )
+            complete_ukraine = (
+                gdf.loc[gdf.name == "Ukraine", "geometry"].iloc[0].union(crimea_only)
+            )
+            correct_russia = (
+                gdf.loc[gdf.name == "Russia", "geometry"]
+                .iloc[0]
+                .difference(crimean_bbox)
+            )
+            r_ix = gdf.loc[gdf.name == "Russia"].index[0]
+            gdf.at[r_ix, "geometry"] = correct_russia
+
+            u_ix = gdf.loc[gdf.name == "Ukraine"].index[0]
+            gdf.at[u_ix, "geometry"] = complete_ukraine
+
         # get changes between current version and new version
         if not df_same(gdf, gpd.read_file(dl["current"]), dl["file"], log):
             downloads[dl["file"]] = gdf

geopandas/tests/test_sindex.py

@@ -861,7 +861,7 @@ class TestPygeosInterface:
     @pytest.mark.parametrize(
         "predicate, expected_shape",
         [
-            (None, (2, 470)),
+            (None, (2, 471)),
             ("intersects", (2, 213)),
             ("within", (2, 213)),
             ("contains", (2, 0)),