ssb-sgis 1.1.6__tar.gz → 1.1.8__tar.gz

{ssb_sgis-1.1.6 → ssb_sgis-1.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ssb-sgis
-Version: 1.1.6
+Version: 1.1.8
 Summary: GIS functions used at Statistics Norway.
 Home-page: https://github.com/statisticsnorway/ssb-sgis
 License: MIT

{ssb_sgis-1.1.6 → ssb_sgis-1.1.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-sgis"
-version = "1.1.6"
+version = "1.1.8"
 description = "GIS functions used at Statistics Norway."
 authors = ["Morten Letnes <morten.letnes@ssb.no>"]
 license = "MIT"

{ssb_sgis-1.1.6 → ssb_sgis-1.1.8}/src/sgis/geopandas_tools/duplicates.py

@@ -164,6 +164,8 @@ def update_geometries(
 
     copied.index = copied.index.map(index_mapper)
 
+    copied = make_all_singlepart(copied)
+
     # TODO check why polygons dissappear in rare cases. For now, just add back the missing
     dissapeared = sfilter_inverse(gdf, copied.buffer(-PRECISION))
     copied = pd.concat([copied, dissapeared])

{ssb_sgis-1.1.6 → ssb_sgis-1.1.8}/src/sgis/io/dapla_functions.py

@@ -99,12 +99,14 @@ def read_geopandas(
             **kwargs,
         )
 
-    if (
+    single_eq_filter = (
         isinstance(filters, Iterable)
         and len(filters) == 1
         and ("=" in next(iter(filters)) or "==" in next(iter(filters)))
-    ):
-        # try to read only files in the relevant partition, because glob is slow without GCSFileSystem
+    )
+    # try to read files in subfolder path / "column=value"
+    # because glob is slow without GCSFileSystem from the root partition
+    if single_eq_filter:
         try:
             expression = "".join(next(iter(filters))).replace("==", "=")
             glob_func = _get_glob(file_system)
@@ -126,7 +128,7 @@ def read_geopandas(
         return gpd.GeoDataFrame(
             _read_partitioned_parquet(
                 gcs_path,
-                read_func=_read_geopandas,
+                read_func=pq.read_table,
                 file_system=file_system,
                 mask=mask,
                 filters=filters,
@@ -143,7 +145,7 @@ def read_geopandas(
         read_func = gpd.read_file
 
     with file_system.open(gcs_path, mode="rb") as file:
-        df = _read_geopandas(
+        return _read_geopandas(
             file,
             read_func=read_func,
             file_format=file_format,
@@ -151,8 +153,6 @@ def read_geopandas(
             **kwargs,
         )
 
-    return df
-
 
 def _read_geopandas_from_iterable(
     paths, mask, file_system, use_threads, pandas_fallback, **kwargs
@@ -761,17 +761,16 @@ def _read_partitioned_parquet(
 
     if results:
         if all(isinstance(x, DataFrame) for x in results):
-            results = pd.concat(results)
+            return pd.concat(results)
         else:
             geo_metadata = _get_geo_metadata(next(iter(child_paths)), file_system)
-            results = _arrow_to_geopandas(
+            return _arrow_to_geopandas(
                 pyarrow.concat_tables(
                     results,
                     promote_options="permissive",
                 ),
                 geo_metadata,
             )
-        return results
 
     # add columns to empty DataFrame
     first_path = next(iter(child_paths + [path]))

{ssb_sgis-1.1.6 → ssb_sgis-1.1.8}/src/sgis/maps/map.py

@@ -128,6 +128,8 @@ class Map:
             categorical: Set to True to convert 'column' to string values.
             **kwargs: Arbitrary keyword arguments.
         """
+        self.kwargs = {}
+
         gdfs, column, kwargs = self._separate_args(gdfs, column, kwargs)
 
         self._column = column
@@ -175,7 +177,6 @@ class Map:
         self.labels = new_labels
 
         # pop all geometry-like items from kwargs into self._gdfs
-        self.kwargs = {}
         i = 0
         for key, value in kwargs.items():
             try:
@@ -237,8 +238,8 @@ class Map:
             self._gdf = pd.concat(self._gdfs, ignore_index=True)
 
         self._nan_idx = self._gdf[self._column].isna()
-        self._get_unique_values()
         self._to_categorical()
+        self._get_unique_values()
 
     def _to_categorical(self):
         if not (self._is_categorical and self.column is not None):
@@ -262,9 +263,9 @@ class Map:
                 self._gdfs[i][self.column] = to_string_via_int(gdf[self.column])
         self._gdf[self.column] = to_string_via_int(self._gdf[self.column])
 
-    def __getattr__(self, attr: str) -> Any:
-        """Search for attribute in kwargs."""
-        return self.kwargs.get(attr, super().__getattribute__(attr))
+    # def __getattr__(self, attr: str) -> Any:
+    #     """Search for attribute in kwargs."""
+    #     return self.kwargs.get(attr, super().__getattribute__(attr))
 
     def __bool__(self) -> bool:
         """True of any gdfs with more than 0 rows."""
@@ -554,12 +555,6 @@ class Map:
         )
         n = n + maybe_area + maybe_length
 
-        if n == 0:
-            raise ValueError(
-                f"The column {self._column!r} is not present in any "
-                "of the passed GeoDataFrames."
-            )
-
     def _check_if_categorical(self) -> bool:
         """Quite messy this..."""
         if not self._column or not self._gdfs: