ssb-sgis 1.0.14__tar.gz → 1.1.0__tar.gz

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ssb-sgis
-Version: 1.0.14
+Version: 1.1.0
 Summary: GIS functions used at Statistics Norway.
 Home-page: https://github.com/statisticsnorway/ssb-sgis
 License: MIT

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-sgis"
-version = "1.0.14"
+version = "1.1.0"
 description = "GIS functions used at Statistics Norway."
 authors = ["Morten Letnes <morten.letnes@ssb.no>"]
 license = "MIT"

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/__init__.py

@@ -96,10 +96,10 @@ from .maps.maps import explore
 from .maps.maps import explore_locals
 from .maps.maps import qtm
 from .maps.maps import samplemap
-from .maps.norge_i_bilder_wms import NorgeIBilderWms
 from .maps.thematicmap import ThematicMap
 from .maps.tilesources import kartverket as kartverket_tiles
 from .maps.tilesources import xyz as xyztiles
+from .maps.wms import NorgeIBilderWms
 from .networkanalysis.closing_network_holes import close_network_holes
 from .networkanalysis.closing_network_holes import close_network_holes_to_deadends
 from .networkanalysis.closing_network_holes import get_k_nearest_points_for_deadends

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/geopandas_tools/bounds.py

@@ -669,6 +669,7 @@ def bounds_to_points(
     0  MULTIPOINT (1.00000 0.00000, 1.00000 1.00000, ...
     1                       MULTIPOINT (0.00000 0.00000)
     """
+    gdf = gdf.copy() if copy else gdf
     as_bounds = bounds_to_polygon(gdf, copy=copy)
     if isinstance(gdf, GeoSeries):
         return GeoSeries(extract_unique_points(as_bounds), index=gdf.index)

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/geopandas_tools/buffer_dissolve_explode.py

@@ -5,7 +5,7 @@ for the following:
 
 - Geometries are made valid after buffer and dissolve.
 
-- The buffer resolution defaults to 50 (geopandas' default is 16).
+- The buffer resolution defaults to 30 (geopandas' default is 16).
 
 - If 'by' is not specified, the index will be labeled 0, 1, …, n - 1 after exploded, instead of 0, 0, …, 0 as it will with the geopandas defaults.
 
@@ -49,7 +49,7 @@ def buffdissexp(
     gdf: GeoDataFrame,
     distance: int | float,
     *,
-    resolution: int = 50,
+    resolution: int = 30,
     index_parts: bool = False,
     copy: bool = True,
     grid_size: float | int | None = None,
@@ -68,7 +68,7 @@ def buffdissexp(
         distance: the distance (meters, degrees, depending on the crs) to buffer
             the geometry by
         resolution: The number of segments used to approximate a quarter circle.
-            Here defaults to 50, as opposed to the default 16 in geopandas.
+            Here defaults to 30, as opposed to the default 16 in geopandas.
         index_parts: If False (default), the index after dissolve is respected. If
             True, an integer index level is added during explode.
         copy: Whether to copy the GeoDataFrame before buffering. Defaults to True.
@@ -101,7 +101,7 @@ def buffdissexp(
 def buffdiss(
     gdf: GeoDataFrame,
     distance: int | float,
-    resolution: int = 50,
+    resolution: int = 30,
     copy: bool = True,
     n_jobs: int = 1,
     join_style: int | str = "round",
@@ -119,7 +119,7 @@ def buffdiss(
         distance: the distance (meters, degrees, depending on the crs) to buffer
             the geometry by
         resolution: The number of segments used to approximate a quarter circle.
-            Here defaults to 50, as opposed to the default 16 in geopandas.
+            Here defaults to 30, as opposed to the default 16 in geopandas.
         join_style: Buffer join style.
         copy: Whether to copy the GeoDataFrame before buffering. Defaults to True.
         n_jobs: Number of threads to use. Defaults to 1.
@@ -511,7 +511,7 @@ def buffdissexp_by_cluster(
     gdf: GeoDataFrame,
     distance: int | float,
     *,
-    resolution: int = 50,
+    resolution: int = 30,
     copy: bool = True,
     n_jobs: int = 1,
     join_style: int | str = "round",
@@ -532,7 +532,7 @@ def buffdissexp_by_cluster(
         distance: the distance (meters, degrees, depending on the crs) to buffer
             the geometry by
         resolution: The number of segments used to approximate a quarter circle.
-            Here defaults to 50, as opposed to the default 16 in geopandas.
+            Here defaults to 30, as opposed to the default 16 in geopandas.
         join_style: Buffer join style.
         copy: Whether to copy the GeoDataFrame before buffering. Defaults to True.
         n_jobs: int = 1,
@@ -554,7 +554,7 @@ def buffdissexp_by_cluster(
 def buff(
     gdf: GeoDataFrame | GeoSeries,
     distance: int | float,
-    resolution: int = 50,
+    resolution: int = 30,
     copy: bool = True,
     join_style: int | str = "round",
     **buffer_kwargs,
@@ -566,7 +566,7 @@ def buff(
         distance: the distance (meters, degrees, depending on the crs) to buffer
             the geometry by
         resolution: The number of segments used to approximate a quarter circle.
-            Here defaults to 50, as opposed to the default 16 in geopandas.
+            Here defaults to 30, as opposed to the default 16 in geopandas.
         join_style: Buffer join style.
         copy: Whether to copy the GeoDataFrame before buffering. Defaults to True.
         **buffer_kwargs: additional keyword arguments passed to geopandas' buffer.

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/io/dapla_functions.py

@@ -15,6 +15,7 @@ import pandas as pd
 import pyarrow
 import pyarrow.parquet as pq
 import shapely
+from gcsfs import GCSFileSystem
 from geopandas import GeoDataFrame
 from geopandas import GeoSeries
 from geopandas.io.arrow import _geopandas_to_arrow
@@ -30,7 +31,7 @@ PANDAS_FALLBACK_INFO = " Set pandas_fallback=True to ignore this error."
 def read_geopandas(
     gcs_path: str | Path | list[str | Path] | tuple[str | Path] | GeoSeries,
     pandas_fallback: bool = False,
-    file_system: dp.gcs.GCSFileSystem | None = None,
+    file_system: GCSFileSystem | None = None,
     mask: GeoSeries | GeoDataFrame | shapely.Geometry | tuple | None = None,
     threads: int | None = None,
     **kwargs,
@@ -138,8 +139,7 @@ def read_geopandas(
                     raise e.__class__(
                         f"{e.__class__.__name__}: {e} for {gcs_path}."
                     ) from e
-                df = dp.read_pandas(gcs_path, **kwargs)
-
+                df = pd.read_parquet(file, **kwargs)
                 if pandas_fallback or not len(df):
                     return df
                 else:
@@ -157,7 +157,7 @@ def read_geopandas(
             except ValueError as e:
                 if "Missing geo metadata" not in str(e) and "geometry" not in str(e):
                     raise e
-                df = dp.read_pandas(gcs_path, **kwargs)
+                df = pd.read_parquet(file, **kwargs)
 
                 if pandas_fallback or not len(df):
                     return df
@@ -168,7 +168,7 @@ def read_geopandas(
                     ) from e
             except Exception as e:
                 raise e.__class__(
-                    f"{e.__class__.__name__}: {e} for {df}." + more_txt
+                    f"{e.__class__.__name__}: {e} for {gcs_path}." + more_txt
                 ) from e
 
     if mask is not None:
@@ -177,7 +177,7 @@ def read_geopandas(
 
 
 def _get_bounds_parquet(
-    path: str | Path, file_system: dp.gcs.GCSFileSystem, pandas_fallback: bool = False
+    path: str | Path, file_system: GCSFileSystem, pandas_fallback: bool = False
 ) -> tuple[list[float], dict] | tuple[None, None]:
     with file_system.open(path) as f:
         try:
@@ -202,7 +202,7 @@ def _get_bounds_parquet(
     return meta["bbox"], meta["crs"]
 
 
-def _get_columns(path: str | Path, file_system: dp.gcs.GCSFileSystem) -> pd.Index:
+def _get_columns(path: str | Path, file_system: GCSFileSystem) -> pd.Index:
     with file_system.open(path) as f:
         schema = pq.read_schema(f)
         index_cols = _get_index_cols(schema)
@@ -216,7 +216,7 @@ def _get_index_cols(schema: pyarrow.Schema) -> list[str]:
 
 def get_bounds_series(
     paths: list[str | Path] | tuple[str | Path],
-    file_system: dp.gcs.GCSFileSystem | None = None,
+    file_system: GCSFileSystem | None = None,
     threads: int | None = None,
     pandas_fallback: bool = False,
 ) -> GeoSeries:
@@ -227,7 +227,7 @@ def get_bounds_series(
 
     Args:
         paths: Iterable of file paths in gcs.
-        file_system: Optional instance of dp.gcs.GCSFileSystem.
+        file_system: Optional instance of GCSFileSystem.
             If None, an instance is created within the function.
             Note that this is slower in long loops.
         threads: Number of threads to use if reading multiple files. Defaults to
@@ -307,7 +307,7 @@ def write_geopandas(
     gcs_path: str | Path,
     overwrite: bool = True,
     pandas_fallback: bool = False,
-    file_system: dp.gcs.GCSFileSystem | None = None,
+    file_system: GCSFileSystem | None = None,
     write_covering_bbox: bool = False,
     **kwargs,
 ) -> None:

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/maps/explore.py

@@ -44,7 +44,7 @@ from ..geopandas_tools.general import clean_geoms
 from ..geopandas_tools.general import make_all_singlepart
 from ..geopandas_tools.geometry_types import get_geom_type
 from ..geopandas_tools.geometry_types import to_single_geom_type
-from .norge_i_bilder_wms import NorgeIBilderWms
+from .wms import WmsLoader
 
 try:
     from ..raster.image_collection import Band
@@ -280,7 +280,7 @@ class Explore(Map):
         max_images: int = 10,
         max_nodata_percentage: int = 100,
         display: bool = True,
-        norge_i_bilder: bool = False,
+        wms: WmsLoader | None = None,
         **kwargs,
     ) -> None:
         """Initialiser.
@@ -310,9 +310,7 @@ class Explore(Map):
             max_nodata_percentage: Maximum percentage nodata values (e.g. clouds) ro allow in
                 image arrays.
             display: Whether to display the map interactively.
-            norge_i_bilder: If True, all Norge i bilder images in bounds will be loaded
-                into the map. Can optionally be set to an instance of NorgeIBilderWms to filter
-                years and names.
+            wms: A WmsLoader instance for loading image tiles as layers. E.g. NorgeIBilderWms.
             **kwargs: Additional keyword arguments. Can also be geometry-like objects
                 where the key is the label.
         """
@@ -329,7 +327,7 @@ class Explore(Map):
         self.max_images = max_images
         self.max_nodata_percentage = max_nodata_percentage
         self.display = display
-        self.norge_i_bilder = norge_i_bilder
+        self.wms = [wms] if isinstance(wms, WmsLoader) else wms
         self.legend = None
 
         self.browser = browser
@@ -768,13 +766,11 @@ class Explore(Map):
         for tile in tiles:
             to_tile(tile, max_zoom=self.max_zoom).add_to(mapobj)
 
-    def _add_norge_i_bilder(self, map_: folium.Map, bbox: Any) -> None:
-        if not isinstance(self.norge_i_bilder, NorgeIBilderWms):
-            self.norge_i_bilder = NorgeIBilderWms()
-
-        tiles = self.norge_i_bilder.get_tiles(bbox, max_zoom=self.max_zoom)
-        for tile in tiles.values():
-            map_.add_child(tile)
+    def _add_wms(self, map_: folium.Map, bbox: Any) -> None:
+        for wms in self.wms:
+            tiles = wms.get_tiles(bbox, max_zoom=self.max_zoom)
+            for tile in tiles.values():
+                map_.add_child(tile)
 
     def _create_continous_map(self):
         self._prepare_continous_map()
@@ -982,8 +978,8 @@ class Explore(Map):
             m.get_root().add_child(style)
             # folium.LayerControl(collapsed=False).add_to(m)
 
-        if self.norge_i_bilder:
-            self._add_norge_i_bilder(m, bounds)
+        if self.wms:
+            self._add_wms(m, bounds)
 
         return m
 

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/maps/maps.py

@@ -31,8 +31,8 @@ from ..geopandas_tools.geocoding import address_to_gdf
 from ..geopandas_tools.geometry_types import get_geom_type
 from .explore import Explore
 from .map import Map
-from .norge_i_bilder_wms import NorgeIBilderWms
 from .thematicmap import ThematicMap
+from .wms import WmsLoader
 
 try:
     from torchgeo.datasets.geo import RasterDataset
@@ -91,7 +91,7 @@ def explore(
     size: int | None = None,
     max_images: int = 10,
     max_nodata_percentage: int = 100,
-    norge_i_bilder: bool | NorgeIBilderWms = False,
+    wms: WmsLoader | None = None,
     **kwargs,
 ) -> Explore:
     """Interactive map of GeoDataFrames with layers that can be toggled on/off.
@@ -123,9 +123,7 @@ def explore(
             map. Defaults to 10.
         max_nodata_percentage: Maximum percentage nodata values (e.g. clouds) ro allow in
             image arrays.
-        norge_i_bilder: If True, all Norge i bilder images in bounds will be loaded
-            into the map. Can optionally be set to an instance of NorgeIBilderWms to filter
-            years and names.
+        wms: A WmsLoader instance for loading image tiles as layers. E.g. NorgeIBilderWms.
         **kwargs: Keyword arguments to pass to geopandas.GeoDataFrame.explore, for
             instance 'cmap' to change the colors, 'scheme' to change how the data
             is grouped. This defaults to 'fisherjenkssampled' for numeric data.
@@ -175,7 +173,7 @@ def explore(
             max_zoom=max_zoom,
             max_images=max_images,
             max_nodata_percentage=max_nodata_percentage,
-            norge_i_bilder=norge_i_bilder,
+            wms=wms,
             **kwargs,
         )
 
@@ -233,7 +231,7 @@ def explore(
             max_zoom=max_zoom,
             max_images=max_images,
             max_nodata_percentage=max_nodata_percentage,
-            norge_i_bilder=norge_i_bilder,
+            wms=wms,
             **kwargs,
         )
 
@@ -245,7 +243,7 @@ def explore(
         smooth_factor=smooth_factor,
         max_images=max_images,
         max_nodata_percentage=max_nodata_percentage,
-        norge_i_bilder=norge_i_bilder,
+        wms=wms,
         **kwargs,
     )
 
@@ -271,7 +269,7 @@ def samplemap(
     browser: bool = False,
     max_images: int = 10,
     max_nodata_percentage: int = 100,
-    norge_i_bilder: bool | NorgeIBilderWms = False,
+    wms: WmsLoader | None = None,
     **kwargs,
 ) -> Explore:
     """Shows an interactive map of a random area of GeoDataFrames.
@@ -307,9 +305,7 @@ def samplemap(
             map. Defaults to 10.
         max_nodata_percentage: Maximum percentage nodata values (e.g. clouds) ro allow in
             image arrays.
-        norge_i_bilder: If True, all Norge i bilder images in bounds will be loaded
-            into the map. Can optionally be set to an instance of NorgeIBilderWms to filter
-            years and names.
+        wms: A WmsLoader instance for loading image tiles as layers. E.g. NorgeIBilderWms.
         **kwargs: Keyword arguments to pass to geopandas.GeoDataFrame.explore, for
             instance 'cmap' to change the colors, 'scheme' to change how the data
             is grouped. This defaults to 'fisherjenkssampled' for numeric data.
@@ -393,7 +389,7 @@ def samplemap(
         smooth_factor=smooth_factor,
         max_images=max_images,
         max_nodata_percentage=max_nodata_percentage,
-        norge_i_bilder=norge_i_bilder,
+        wms=wms,
         **kwargs,
     )
 
@@ -408,7 +404,7 @@ def clipmap(
     browser: bool = False,
     max_images: int = 10,
     max_nodata_percentage: int = 100,
-    norge_i_bilder: bool | NorgeIBilderWms = False,
+    wms: WmsLoader | None = None,
     **kwargs,
 ) -> Explore | Map:
     """Shows an interactive map of a of GeoDataFrames clipped to the mask extent.
@@ -439,9 +435,7 @@ def clipmap(
             map. Defaults to 10.
         max_nodata_percentage: Maximum percentage nodata values (e.g. clouds) ro allow in
             image arrays.
-        norge_i_bilder: If True, all Norge i bilder images in bounds will be loaded
-            into the map. Can optionally be set to an instance of NorgeIBilderWms to filter
-            years and names.
+        wms: A WmsLoader instance for loading image tiles as layers. E.g. NorgeIBilderWms.
         **kwargs: Keyword arguments to pass to geopandas.GeoDataFrame.explore, for
             instance 'cmap' to change the colors, 'scheme' to change how the data
             is grouped. This defaults to 'fisherjenkssampled' for numeric data.
@@ -477,7 +471,7 @@ def clipmap(
             smooth_factor=smooth_factor,
             max_images=max_images,
             max_nodata_percentage=max_nodata_percentage,
-            norge_i_bilder=norge_i_bilder,
+            wms=wms,
             **kwargs,
         )
         m.mask = mask

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/maps/thematicmap.py

@@ -280,7 +280,10 @@ class ThematicMap(Map):
         return self
 
     def add_background(
-        self, gdf: GeoDataFrame, color: str | None = None
+        self,
+        gdf: GeoDataFrame,
+        color: str | None = None,
+        **kwargs,
     ) -> "ThematicMap":
         """Add a GeoDataFrame as a background layer.
 
@@ -288,6 +291,7 @@ class ThematicMap(Map):
             gdf: a GeoDataFrame.
             color: Single color. Defaults to gray (shade depends on whether the map
                 facecolor is black or white).
+            **kwargs: Keyword arguments sent to GeoDataFrame.plot.
         """
         if color:
             self.bg_gdf_color = color
@@ -299,6 +303,7 @@ class ThematicMap(Map):
             )
         if self.bounds is None:
             self.bounds = to_bbox(self._gdf.total_bounds)
+        self.bg_gdf_kwargs = kwargs
         return self
 
     def plot(self, **kwargs) -> None:
@@ -515,7 +520,9 @@ class ThematicMap(Map):
     def _actually_add_background(self) -> None:
         self.ax.set_xlim([self.minx - self.diffx * 0.03, self.maxx + self.diffx * 0.03])
         self.ax.set_ylim([self.miny - self.diffy * 0.03, self.maxy + self.diffy * 0.03])
-        self._background_gdfs.plot(ax=self.ax, color=self.bg_gdf_color)
+        self._background_gdfs.plot(
+            ax=self.ax, color=self.bg_gdf_color, **self.bg_gdf_kwargs
+        )
 
     @staticmethod
     def _get_matplotlib_figure_and_axix(

ssb_sgis-1.0.14/src/sgis/maps/norge_i_bilder_wms.py → ssb_sgis-1.1.0/src/sgis/maps/wms.py

@@ -1,3 +1,4 @@
+import abc
 import datetime
 import json
 import re
@@ -24,7 +25,28 @@ DEFAULT_YEARS: tuple[str] = tuple(
 
 
 @dataclass
-class NorgeIBilderWms:
+class WmsLoader(abc.ABC):
+    """Abstract base class for wms loaders.
+
+    Child classes must implement the method 'get_tiles',
+    which should return a list of folium.WmsTileLayer.
+    """
+
+    @abc.abstractmethod
+    def get_tiles(self, bbox: Any, max_zoom: int = 40) -> list[folium.WmsTileLayer]:
+        """Get all tiles intersecting with a bbox."""
+
+    @abc.abstractmethod
+    def load_tiles(self) -> None:
+        """Load all tiles into self.tiles.
+
+        Not needed in sgis.explore.
+        """
+        pass
+
+
+@dataclass
+class NorgeIBilderWms(WmsLoader):
     """Loads Norge i bilder tiles as folium.WmsTiles."""
 
     years: Iterable[int | str] = DEFAULT_YEARS

{ssb_sgis-1.0.14 → ssb_sgis-1.1.0}/src/sgis/parallel/parallel.py

@@ -590,7 +590,7 @@ class Parallel:
         with_neighbors: bool = False,
         funcdict: dict[str, Callable] | None = None,
         file_type: str = "parquet",
-        muni_number_col: str = "KOMMUNENR",
+        muni_number_col: str = "komm_nr",
         strict: bool = False,
         write_empty: bool = False,
         id_assign_func: Callable | functools.partial = clean_overlay,
@@ -622,7 +622,7 @@ class Parallel:
                 the data is read.
             file_type: Defaults to parquet.
             muni_number_col: String column name with municipality
-                number/identifier. Defaults to KOMMUNENR. If the column is not present
+                number/identifier. Defaults to komm_nr. If the column is not present
                 in the data to be split, the data will be intersected with the
                 municipalities.
             strict: If False (default), the dictionaries 'out_data' and 'funcdict' does
@@ -761,7 +761,7 @@ def write_municipality_data(
     out_folder: str,
     municipalities: GeoDataFrame | list[str] | None = None,
     with_neighbors: bool = False,
-    muni_number_col: str = "KOMMUNENR",
+    muni_number_col: str = "komm_nr",
     file_type: str = "parquet",
     func: Callable | None = None,
     write_empty: bool = False,
@@ -840,7 +840,7 @@ def _write_municipality_data(
     data: str | GeoDataFrame | DataFrame,
     out_folder: str,
     municipalities: GeoDataFrame | list[str] | None = None,
-    muni_number_col: str = "KOMMUNENR",
+    muni_number_col: str = "komm_nr",
     file_type: str = "parquet",
     func: Callable | None = None,
     write_empty: bool = False,
@@ -896,7 +896,7 @@ def _write_neighbor_municipality_data(
     data: str | GeoDataFrame | DataFrame,
     out_folder: str,
     municipalities: GeoDataFrame,
-    muni_number_col: str = "KOMMUNENR",
+    muni_number_col: str = "komm_nr",
     file_type: str = "parquet",
     func: Callable | None = None,
     write_empty: bool = False,