ssb-sgis 1.2.3__py3-none-any.whl → 1.2.4__py3-none-any.whl

sgis/__init__.py

@@ -78,6 +78,7 @@ from .geopandas_tools.polygon_operations import get_polygon_clusters
 from .geopandas_tools.polygon_operations import split_polygons_by_lines
 from .geopandas_tools.polygons_as_rings import PolygonsAsRings
 from .geopandas_tools.runners import GridSizeOverlayRunner
+from .geopandas_tools.runners import GridSizeUnionRunner
 from .geopandas_tools.runners import OverlayRunner
 from .geopandas_tools.runners import RTreeQueryRunner
 from .geopandas_tools.runners import UnionRunner

sgis/geopandas_tools/cleaning.py

@@ -603,7 +603,6 @@ def split_by_neighbors(df, split_by, tolerance, grid_size=None) -> GeoDataFrame:
             buff(df, tolerance),
             how="identity",
             grid_size=grid_size,
-            geom_type="polygon",
         )
         .pipe(get_line_segments)
         .reset_index(drop=True)

sgis/geopandas_tools/runners.py

@@ -120,6 +120,53 @@ class UnionRunner(AbstractRunner):
         return agged
 
 
+@dataclass
+class GridSizeUnionRunner(UnionRunner):
+    """Run shapely.union_all with pandas.groupby for different grid sizes until no GEOSException is raised.
+
+    Subclasses must implement a 'run' method that takes the arguments
+    'df' (GeoDataFrame or GeoSeries), 'by' (optional column to group by), 'grid_size'
+    (passed to shapely.union_all) and **kwargs passed to pandas.DataFrame.groupby.
+    Defaults to None, meaning the default runner with number of workers set
+    to 'n_jobs'.
+
+
+    Args:
+        n_jobs: Number of workers.
+        backend: Backend for the workers.
+    """
+
+    n_jobs: int
+    backend: str | None = None
+    grid_sizes: list[float | int] | None = None
+
+    def __post_init__(self) -> None:
+        """Check that grid_sizes is passed."""
+        if self.grid_sizes is None:
+            raise ValueError(
+                f"must set 'grid_sizes' in the {self.__class__.__name__} initialiser."
+            )
+
+    def run(
+        self,
+        df: GeoDataFrame | GeoSeries | pd.DataFrame | pd.Series,
+        by: str | list[str] | None = None,
+        grid_size: int | float | None = None,
+        **kwargs,
+    ) -> GeoSeries | GeoDataFrame:
+        """Run groupby on geometries in parallel (if n_jobs > 1) with grid_sizes."""
+        try:
+            return super().run(df, by=by, grid_size=grid_size, **kwargs)
+        except GEOSException:
+            pass
+        for i, grid_size in enumerate(self.grid_sizes):
+            try:
+                return super().run(df, by=by, grid_size=grid_size, **kwargs)
+            except GEOSException as e:
+                if i == len(self.grid_sizes) - 1:
+                    raise e
+
+
 def _strtree_query(
     arr1: np.ndarray,
     arr2: np.ndarray,

sgis/io/dapla_functions.py

@@ -40,7 +40,10 @@ from ..helpers import _get_file_system
 try:
     from gcsfs import GCSFileSystem
 except ImportError:
-    pass
+
+    class GCSFileSystem:
+        """Placeholder."""
+
 
 PANDAS_FALLBACK_INFO = " Set pandas_fallback=True to ignore this error."
 NULL_VALUE = "__HIVE_DEFAULT_PARTITION__"
@@ -96,6 +99,7 @@ def read_geopandas(
             file_system=file_system,
             use_threads=use_threads,
             pandas_fallback=pandas_fallback,
+            filters=filters,
             **kwargs,
         )
 
@@ -108,7 +112,9 @@ def read_geopandas(
     # because glob is slow without GCSFileSystem from the root partition
     if single_eq_filter:
         try:
-            expression = "".join(next(iter(filters))).replace("==", "=")
+            expression: list[str] = "".join(
+                [str(x) for x in next(iter(filters))]
+            ).replace("==", "=")
             glob_func = _get_glob_func(file_system)
             suffix: str = Path(gcs_path).suffix
             paths = glob_func(str(Path(gcs_path) / expression / f"*{suffix}"))
@@ -119,6 +125,7 @@ def read_geopandas(
                     file_system=file_system,
                     use_threads=use_threads,
                     pandas_fallback=pandas_fallback,
+                    filters=filters,
                     **kwargs,
                 )
         except FileNotFoundError:
@@ -182,7 +189,11 @@ def _read_geopandas_from_iterable(
         paths = list(bounds_series.index)
 
     results: list[pyarrow.Table] = _read_pyarrow_with_treads(
-        paths, file_system=file_system, mask=mask, use_threads=use_threads, **kwargs
+        paths,
+        file_system=file_system,
+        mask=mask,
+        use_threads=use_threads,
+        **kwargs,
     )
     if results:
         try:
@@ -198,10 +209,15 @@ def _read_geopandas_from_iterable(
 
 
 def _read_pyarrow_with_treads(
-    paths: list[str | Path | os.PathLike], file_system, use_threads, mask, **kwargs
+    paths: list[str | Path | os.PathLike],
+    file_system,
+    use_threads,
+    mask,
+    filters,
+    **kwargs,
 ) -> list[pyarrow.Table]:
     read_partial = functools.partial(
-        _read_pyarrow, mask=mask, file_system=file_system, **kwargs
+        _read_pyarrow, filters=filters, mask=mask, file_system=file_system, **kwargs
     )
     if not use_threads:
         return [x for x in map(read_partial, paths) if x is not None]
@@ -645,7 +661,7 @@ def expression_match_path(expression: ds.Expression, path: str) -> bool:
     """Check if a file path match a pyarrow Expression.
 
     Examples:
-    --------
+    ---------
     >>> import pyarrow.compute as pc
     >>> path = 'data/file.parquet/x=1/y=10/name0.parquet'
     >>> expression = (pc.Field("x") == 1) & (pc.Field("y") == 10)
@@ -758,6 +774,7 @@ def _read_partitioned_parquet(
         ),
         file_system=file_system,
         mask=mask,
+        filters=filters,
         use_threads=use_threads,
         **kwargs,
     )

sgis/maps/thematicmap.py

@@ -296,13 +296,11 @@ class ThematicMap(Map):
         if self._gdf[self._column].isna().any():
             isnas = []
             for label, gdf in self._gdfs.items():
-
                 isnas.append(gdf[gdf[self._column].isna()])
                 self._gdfs[label] = gdf[gdf[self._column].notna()]
-            color = self.facecolor if nan_hatch else self.nan_color
             self._more_data[nan_label] = {
                 "gdf": pd.concat(isnas, ignore_index=True),
-                "color": color,
+                "color": self.nan_color,
                 "hatch": nan_hatch,
             } | new_kwargs
             self._gdf = pd.concat(self.gdfs.values(), ignore_index=True)

{ssb_sgis-1.2.3.dist-info → ssb_sgis-1.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ssb-sgis
-Version: 1.2.3
+Version: 1.2.4
 Summary: GIS functions used at Statistics Norway.
 Home-page: https://github.com/statisticsnorway/ssb-sgis
 License: MIT

{ssb_sgis-1.2.3.dist-info → ssb_sgis-1.2.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sgis/__init__.py,sha256=40JJSoA8sXzp7VNoUCeFuEbZPGuEbnMjpypmNxPsMA0,7690
+sgis/__init__.py,sha256=FcE8XYmVlyO-6s15AC8dLqIjp2KZpar2ND3siIxX830,7747
 sgis/conf.py,sha256=pLqmvIKoKmXoW8chja3iQpbDUp9Z39vzl97MGH8ZHW0,2614
 sgis/debug_config.py,sha256=Tfr19kU46hSkkspsIJcrUWvlhaL4U3-f8xEPkujSCAQ,593
 sgis/exceptions.py,sha256=WNaEBPNNx0rmz-YDzlFX4vIE7ocJQruUTqS2RNAu2zU,660
@@ -6,7 +6,7 @@ sgis/geopandas_tools/__init__.py,sha256=bo8lFMcltOz7TtWAi52_ekR2gd3mjfBfKeMDV5zu
 sgis/geopandas_tools/bounds.py,sha256=YJyF0gp78hFAjLLZmDquRKCBAtbt7QouG3snTcJeNQs,23822
 sgis/geopandas_tools/buffer_dissolve_explode.py,sha256=ReIgoeh6CUVcLmsUZ_pyoWYg6iBZzYiGmFq6CMOKRvE,19535
 sgis/geopandas_tools/centerlines.py,sha256=Q65Sx01SeAlulBEd9oaZkB2maBBNdLcJwAbTILg4SPU,11848
-sgis/geopandas_tools/cleaning.py,sha256=PkAVVZ84ahek8_uVlTRtCO8nCWO6DdGltWLTmPOsvxM,24426
+sgis/geopandas_tools/cleaning.py,sha256=fST0xFztmyn-QUOAfvjZmu7aO_zPiolWK7gd7TR6ffI,24393
 sgis/geopandas_tools/conversion.py,sha256=w3W0Utaw7SESRR659percNLwOY9_yfg6DL5hcuM1CUA,25017
 sgis/geopandas_tools/duplicates.py,sha256=TDDM4u1n7SIkyJrOfl1Lno92AmUPqtXBHsj1IUKC0hI,14992
 sgis/geopandas_tools/general.py,sha256=YRpNEdwTHyFdQOdAfbCmYXS7PxoDjXxoagwpteXkYdI,43937
@@ -17,13 +17,13 @@ sgis/geopandas_tools/overlay.py,sha256=5i9u8GgFuU0fCqzELsbIaoUPhw-E7eZHl_yKB0wEc
 sgis/geopandas_tools/point_operations.py,sha256=JM4hvfIVxZaZdGNlGzcCurrKzkgC_b9hzbFYN42f9WY,6972
 sgis/geopandas_tools/polygon_operations.py,sha256=v-B9IgbFfm4dVHKPyzvmnNiqVCdtl9ddpCsQpZZ-9sU,49284
 sgis/geopandas_tools/polygons_as_rings.py,sha256=BX_GZS6F9I4NbEpiOlNBd7zywJjdfdJVi_MkeONBuiM,14941
-sgis/geopandas_tools/runners.py,sha256=IMClw80YAUGyPyowBXNidZu-z_rErpzj0w-GUQRI-Y0,11320
+sgis/geopandas_tools/runners.py,sha256=J4lH0RXYDYTLVeQFgNv8gEY0E97QGIQ4zPW5vfoxgDU,12979
 sgis/geopandas_tools/sfilter.py,sha256=BPz6-_9B7QdyYmVatZXavdHj7FIW_ztIyJHQOkKJt7A,10284
 sgis/geopandas_tools/utils.py,sha256=X0pRvB1tWgV_0BCrRS1HU9LtLGnZCpvVPxyqM9JGb0Y,1415
 sgis/helpers.py,sha256=4N6vFWQ3TYVzRHNcWY_fNa_GkFuaZB3vtCkkFND-qs0,9628
 sgis/io/__init__.py,sha256=uyBr20YDqB2bQttrd5q1JuGOvX32A-MSvS7Wmw5f5qg,177
 sgis/io/_is_dapla.py,sha256=wmfkSe98IrLhUg3dtXZusV6OVC8VlY1kbc5EQDf3P-Q,358
-sgis/io/dapla_functions.py,sha256=cwCmwgOoWOaYMJ35hgAJtCJ7m8bQBM4RsL7y3afjnLc,30539
+sgis/io/dapla_functions.py,sha256=AbP400wE8wd3KhfoX_BoEC6ba9fR0gCg8qWSqdkJ5dU,30815
 sgis/io/opener.py,sha256=HWO3G1NB6bpXKM94JadCD513vjat1o1TFjWGWzyVasg,898
 sgis/io/read_parquet.py,sha256=FvZYv1rLkUlrSaUY6QW6E1yntmntTeQuZ9ZRgCDO4IM,3776
 sgis/maps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -34,7 +34,7 @@ sgis/maps/legend.py,sha256=qq2RkebuaNAdFztlXrDOWbN0voeK5w5VycmRKyx0NdM,26512
 sgis/maps/map.py,sha256=q0gqOg_DD1ea7B_8__nuFN1dYA7o3uIxS6KuJwmVNhQ,30269
 sgis/maps/maps.py,sha256=Ti4nfm6bz_8ZWVHoEHF61moI3LQH9Ee6Jd8NHzInWkw,23135
 sgis/maps/norge_i_bilder.json,sha256=VKmb7rg4jvgc8_Ve1fFnHyZ_Dkv4T5GTA0UCpqpFAi4,492751
-sgis/maps/thematicmap.py,sha256=xTX_Y6ZXLcjNCgfUOr87pAMD4cjKxhFudZZXn_ewpII,25171
+sgis/maps/thematicmap.py,sha256=Z3o_Bca0oty5Cn35pZfX5Qy52sXDVIMVSFD6IlZrovo,25111
 sgis/maps/tilesources.py,sha256=F4mFHxPwkiPJdVKzNkScTX6xbJAMIUtlTq4mQ83oguw,1746
 sgis/maps/wms.py,sha256=UjsKAvrZkcYRgjVGGeg6XA4Lkx6WU9w6WTyeSkwN78w,6931
 sgis/networkanalysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -61,7 +61,7 @@ sgis/raster/indices.py,sha256=efJmgfPg_VuSzXFosXV661IendF8CwPFWtMhyP4TMUg,222
 sgis/raster/regex.py,sha256=kYhVpRYzoXutx1dSYmqMoselWXww7MMEsTPmLZwHjbM,3759
 sgis/raster/sentinel_config.py,sha256=nySDqn2R8M6W8jguoBeSAK_zzbAsqmaI59i32446FwY,1268
 sgis/raster/zonal.py,sha256=D4Gyptw-yOLTCO41peIuYbY-DANsJCG19xXDlf1QAz4,2299
-ssb_sgis-1.2.3.dist-info/LICENSE,sha256=np3IfD5m0ZUofn_kVzDZqliozuiO6wrktw3LRPjyEiI,1073
-ssb_sgis-1.2.3.dist-info/METADATA,sha256=14UzO4efbS_k7OMKyV7rCQjZknag0TTuwQ6sgaQvaww,11740
-ssb_sgis-1.2.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-ssb_sgis-1.2.3.dist-info/RECORD,,
+ssb_sgis-1.2.4.dist-info/LICENSE,sha256=np3IfD5m0ZUofn_kVzDZqliozuiO6wrktw3LRPjyEiI,1073
+ssb_sgis-1.2.4.dist-info/METADATA,sha256=0vA7hJ78jGcP1uHtgeeNYN-Ne_9xZQ_fX3SRamcESxw,11740
+ssb_sgis-1.2.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+ssb_sgis-1.2.4.dist-info/RECORD,,