ssb-sgis 0.1.4__tar.gz → 0.1.6__tar.gz

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: ssb-sgis
-Version: 0.1.4
-Summary: GIS utility functions used at Statistics Norway.
+Version: 0.1.6
+Summary: GIS functions used at Statistics Norway.
 Home-page: https://github.com/statisticsnorway/ssb-sgis
 License: MIT
 Author: Statistics Norway
 Author-email: ort@ssb.no
-Requires-Python: >=3.10,<4.0
+Requires-Python: >=3.10,<3.12
 Classifier: Development Status :: 3 - Alpha
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
@@ -68,7 +68,7 @@ Preparing for network analysis:
 
 ```python
 import sgis as sg
-
+import pandas as pd
 
 roads = sg.read_parquet_url(
     "https://media.githubusercontent.com/media/statisticsnorway/ssb-sgis/main/tests/testdata/roads_oslo_2022.parquet"
@@ -97,14 +97,23 @@ nwa
         log=True, detailed_log=True,
     )
 
-Get number of times each line segment was visited.
+Get number of times each line segment was visited, with optional weighting.
 
 ```python
-frequencies = nwa.get_route_frequencies(points.sample(75), points.sample(75))
+origins = points.iloc[:75]
+destinations = points.iloc[75:150]
+
+# creating uniform weights of 10
+od_pairs = pd.MultiIndex.from_product([origins.index, destinations.index])
+weights = pd.DataFrame(index=od_pairs)
+weights["weight"] = 10
 
+frequencies = nwa.get_route_frequencies(origins, destinations, weight_df=weights)
+
+# plot the results
 m = sg.ThematicMap(sg.buff(frequencies, 15), column="frequency", black=True)
 m.cmap = "plasma"
-m.title = "Number of times each road was used."
+m.title = "Number of times each road was used,\nweighted * 10"
 m.plot()
 ```
 
@@ -141,6 +150,7 @@ service_areas = nwa.service_area(
     breaks=np.arange(1, 11),
 )
 
+# plot the results
 m = sg.ThematicMap(service_areas, column="minutes", black=True, size=10)
 m.k = 10
 m.title = "Roads that can be reached within 1 to 10 minutes"
@@ -164,8 +174,6 @@ m.plot()
 
 ![png](docs/examples/network_analysis_examples_files/network_analysis_examples_11_0.png)
 
-More network analysis examples can be found here: https://github.com/statisticsnorway/ssb-sgis/blob/main/docs/network_analysis_demo_template.md
-
 Road data for Norway can be downloaded here: https://kartkatalog.geonorge.no/metadata/nvdb-ruteplan-nettverksdatasett/8d0f9066-34f9-4423-be12-8e8523089313
 
 ## Developer information

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/README.md

@@ -34,7 +34,7 @@ Preparing for network analysis:
 
 ```python
 import sgis as sg
-
+import pandas as pd
 
 roads = sg.read_parquet_url(
     "https://media.githubusercontent.com/media/statisticsnorway/ssb-sgis/main/tests/testdata/roads_oslo_2022.parquet"
@@ -63,14 +63,23 @@ nwa
         log=True, detailed_log=True,
     )
 
-Get number of times each line segment was visited.
+Get number of times each line segment was visited, with optional weighting.
 
 ```python
-frequencies = nwa.get_route_frequencies(points.sample(75), points.sample(75))
+origins = points.iloc[:75]
+destinations = points.iloc[75:150]
+
+# creating uniform weights of 10
+od_pairs = pd.MultiIndex.from_product([origins.index, destinations.index])
+weights = pd.DataFrame(index=od_pairs)
+weights["weight"] = 10
 
+frequencies = nwa.get_route_frequencies(origins, destinations, weight_df=weights)
+
+# plot the results
 m = sg.ThematicMap(sg.buff(frequencies, 15), column="frequency", black=True)
 m.cmap = "plasma"
-m.title = "Number of times each road was used."
+m.title = "Number of times each road was used,\nweighted * 10"
 m.plot()
 ```
 
@@ -107,6 +116,7 @@ service_areas = nwa.service_area(
     breaks=np.arange(1, 11),
 )
 
+# plot the results
 m = sg.ThematicMap(service_areas, column="minutes", black=True, size=10)
 m.k = 10
 m.title = "Roads that can be reached within 1 to 10 minutes"
@@ -130,8 +140,6 @@ m.plot()
 
 ![png](docs/examples/network_analysis_examples_files/network_analysis_examples_11_0.png)
 
-More network analysis examples can be found here: https://github.com/statisticsnorway/ssb-sgis/blob/main/docs/network_analysis_demo_template.md
-
 Road data for Norway can be downloaded here: https://kartkatalog.geonorge.no/metadata/nvdb-ruteplan-nettverksdatasett/8d0f9066-34f9-4423-be12-8e8523089313
 
 ## Developer information

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "ssb-sgis"
-version = "0.1.4"
-description = "GIS utility functions used at Statistics Norway."
+version = "0.1.6"
+description = "GIS functions used at Statistics Norway."
 authors = ["Statistics Norway <ort@ssb.no>"]
 license = "MIT"
 readme = "README.md"
@@ -17,7 +17,7 @@ classifiers = [
 Changelog = "https://github.com/statisticsnorway/ssb-sgis/releases"
 
 [tool.poetry.dependencies]
-python = ">=3.10,<4.0"
+python = ">=3.10,<3.12"
 branca = "^0.6.0"
 folium = "^0.14.0"
 geopandas = "^0.12.2"

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/src/sgis/geopandas_tools/general.py

@@ -234,7 +234,7 @@ def random_points_in_polygons(
 
     Examples
     --------
-    Buffer 100 random points.
+    First create and buffer 100 random points.
 
     >>> import sgis as sg
     >>> gdf = sg.random_points(100)
@@ -311,9 +311,22 @@ def random_points_in_polygons(
             bounds = gdf__.bounds
             temp_idx____ = gdf__["temp_idx____"].values
 
+    all_points = all_points.sort_index().drop(["temp_idx____", "index_right"], axis=1)
+
+    if gdf.index.is_unique:
+        gdf = gdf.drop("temp_idx____", axis=1)
+        return all_points
+
+    original_index = {
+        temp_idx: idx for temp_idx, idx in zip(gdf.temp_idx____, gdf.index)
+    }
+
+    all_points.index = all_points.index.map(original_index)
+    all_points.index.name = None
+
     gdf = gdf.drop("temp_idx____", axis=1)
 
-    return all_points.sort_index().drop(["temp_idx____", "index_right"], axis=1)
+    return all_points
 
 
 def points_in_bounds(gdf: GeoDataFrame, n2: int):
@@ -355,8 +368,8 @@ def to_lines(*gdfs: GeoDataFrame, copy: bool = True) -> GeoDataFrame:
     >>> poly1["poly1"] = 1
     >>> line = sg.to_lines(poly1)
     >>> line
-        poly1                                           geometry
-    0      1  LINESTRING (0.00000 0.00000, 0.00000 1.00000, ...
+                                                geometry  poly1
+    0  LINESTRING (0.00000 0.00000, 0.00000 1.00000, ...      1
 
     Convert two overlapping polygons to linestrings.
 
@@ -372,13 +385,11 @@ def to_lines(*gdfs: GeoDataFrame, copy: bool = True) -> GeoDataFrame:
     4    NaN    1.0  LINESTRING (0.50000 1.00000, 0.50000 1.50000, ...
     5    NaN    1.0      LINESTRING (1.00000 0.50000, 0.50000 0.50000)
 
-    Plot before and after (plots not showing in terminal).
+    Plot before and after.
 
     >>> sg.qtm(poly1, poly2)
-    <Axes: >
     >>> lines["l"] = lines.length
     >>> sg.qtm(lines, "l")
-    <Axes: >
     """
 
     if any(any(gdf.geom_type.isin(["Point", "MultiPoint"])) for gdf in gdfs):

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/src/sgis/geopandas_tools/geometry_types.py

@@ -60,7 +60,7 @@ def to_single_geom_type(
     0  GEOMETRYCOLLECTION (POINT (0.00000 0.00000), L...
 
     >>> to_single_geom_type(gdf, "line")
-                    geometry
+                                            geometry
     2  LINESTRING (1.00000 1.00000, 2.00000 2.00000)
     """
     if not isinstance(gdf, (GeoDataFrame, GeoSeries)):

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/src/sgis/geopandas_tools/line_operations.py

@@ -698,7 +698,7 @@ def close_network_holes_to_deadends(
 
     Fill gaps shorter than 1.1 meters.
 
-    >>> filled = sg.close_network_holes_to_deadends(roads, max_distance=1.1, max_angle=30)
+    >>> filled = sg.close_network_holes_to_deadends(roads, max_distance=1.1)
     >>> roads = sg.get_largest_component(roads)
     >>> roads.connected.value_counts()
     1.0    100315

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/src/sgis/geopandas_tools/overlay.py

@@ -77,6 +77,9 @@ def overlay(
             f"'how' was {how!r} but is expected to be in {', '.join(allowed_hows)}"
         )
 
+    if df1.crs != df2.crs:
+        raise ValueError(f"crs mismatch. Got {df1.crs} and {df2.crs}")
+
     df1 = clean_geoms(df1)
     df2 = clean_geoms(df2)
 
@@ -295,6 +298,8 @@ def _union(pairs, df1, df2, left, right):
         merged.append(intersections)
     symmdiff = _symmetric_difference(pairs, df1, df2, left, right)
     merged.append(symmdiff)
+    crs = merged[0].crs
+    merged = [gdf.to_crs(crs) for gdf in merged]
     return pd.concat(merged, ignore_index=True).pipe(_push_geom_col)
 
 
@@ -305,6 +310,8 @@ def _identity(pairs, df1, left):
         merged.append(intersections)
     diff = _difference(pairs, df1, left)
     merged.append(diff)
+    crs = merged[0].crs
+    merged = [gdf.to_crs(crs) for gdf in merged]
     return pd.concat(merged, ignore_index=True).pipe(_push_geom_col)
 
 
@@ -317,6 +324,8 @@ def _symmetric_difference(pairs, df1, df2, left, right):
         merged.append(clip_right)
     diff_right = _add_from_right(df1, df2, right)
     merged.append(diff_right)
+    crs = merged[0].crs
+    merged = [gdf.to_crs(crs) for gdf in merged]
     return pd.concat(merged, ignore_index=True).pipe(_push_geom_col)
 
 
@@ -327,6 +336,8 @@ def _difference(pairs, df1, left):
         merged.append(clip_left)
     diff_left = _add_from_left(df1, left)
     merged.append(diff_left)
+    crs = merged[0].crs
+    merged = [gdf.to_crs(crs) for gdf in merged]
     return pd.concat(merged, ignore_index=True).pipe(_push_geom_col)
 
 

{ssb_sgis-0.1.4 → ssb_sgis-0.1.6}/src/sgis/maps/explore.py

@@ -9,6 +9,7 @@ from statistics import mean
 import branca as bc
 import folium
 import matplotlib
+import numpy as np
 import pandas as pd
 from geopandas import GeoDataFrame
 from shapely.geometry import LineString
@@ -30,7 +31,7 @@ NAN_COLOR = "#969696"
 
 
 # cols to not show when hovering over geometries (tooltip)
-COLS_TO_DROP = ["color", "geometry"]
+COLS_TO_DROP = ["color", "col_as_int", "geometry"]
 
 
 # from geopandas
@@ -71,49 +72,19 @@ class Explore(Map):
         self.max_zoom = max_zoom
         self.show_in_browser = show_in_browser
 
-        if not self._is_categorical:
+        if any(get_geom_type(gdf) == "mixed" for gdf in self.gdfs):
+            self._make_all_polygon()
+
+        if self._is_categorical:
+            if len(self.gdfs) == 1:
+                self._split_categories()
+        else:
             if not self._cmap:
                 self._cmap = "viridis"
             self.cmap_start = kwargs.pop("cmap_start", 0)
             self.cmap_stop = kwargs.pop("cmap_stop", 256)
 
     def explore(self, column: str | None = None, **kwargs) -> None:
-        """Interactive map of the GeoDataFrames with layers that can be toggles on/off.
-
-        It displays all the GeoDataFrames and displays them together in an interactive
-        map with a common legend. The layers can be toggled on and off.
-
-        Args:
-            column: The column to color the geometries by. Defaults to the column
-                that was specified last.
-            **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 'fisherjenks' for numeric data.
-
-        See also:
-            samplemap: same functionality, but shows only a random area of a given size.
-            clipmap: same functionality, but shows only the areas clipped by a given
-            mask.
-
-        Examples
-        --------
-        >>> from sgis import read_parquet_url
-        >>> roads = read_parquet_url("https://media.githubusercontent.com/media/statisticsnorway/ssb-sgis/main/tests/testdata/roads_oslo_2022.parquet")
-        >>> points = read_parquet_url("https://media.githubusercontent.com/media/statisticsnorway/ssb-sgis/main/tests/testdata/points_oslo.parquet")
-
-        Simple explore of two GeoDataFrames.
-
-        >>> from sgis import Explore
-        >>> ex = Explore(roads, points)
-        >>> ex.explore()
-
-        With column.
-
-        >>> roads["meters"] = roads.length
-        >>> points["meters"] = points.length
-        >>> ex = Explore(roads, points, column="meters")
-        >>> ex.samplemap()
-        """
         if column:
             self._column = column
             self._update_column()
@@ -128,34 +99,6 @@ class Explore(Map):
         sample_from_first: bool = True,
         **kwargs,
     ) -> None:
-        """Shows an interactive map of a random area of the GeoDataFrames.
-
-        It takes a random sample point of the GeoDataFrames, and shows all geometries
-        within a given radius of this point. Displays an interactive map with a common
-        legend. The layers can be toggled on and off.
-
-        The radius to plot can be changed with the 'size' parameter.
-
-        For more info about the labeling and coloring of the map, see the explore
-        method.
-
-        Args:
-            size: the radius to buffer the sample point by before clipping with the
-                data.
-            column: The column to color the geometries by. Defaults to the column
-                that was specified last.
-            sample_from_first: If True (default), the sample point is taken from
-                the first specified GeoDataFrame. If False, all GeoDataFrames are
-                considered.
-            **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 'fisherjenks' for numeric data.
-
-        See also:
-            explore: same functionality, but shows the entire area of the geometries.
-            clipmap: same functionality, but shows only the areas clipped by a given
-            mask.
-        """
         if column:
             self._column = column
             self._update_column()
@@ -193,27 +136,6 @@ class Explore(Map):
         column: str | None = None,
         **kwargs,
     ) -> None:
-        """Shows an interactive map of a of the GeoDataFrames clipped by the mask.
-
-        It clips all the GeoDataFrames in the Explore instance to the mask extent,
-        and displays the resulting geometries in an interactive map with a common
-        legends. The layers can be toggled on and off.
-
-        For more info about the labeling and coloring of the map, see the explore
-        method.
-
-        Args:
-            mask: the geometry to clip the data by.
-            column: The column to color the geometries by. Defaults to the column
-                that was specified last.
-            **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 'fisherjenks' for numeric data.
-
-        See also:
-            explore: same functionality, but shows the entire area of the geometries.
-            samplemap: same functionality, but shows only a random area of a given size.
-        """
         if column:
             self._column = column
             self._update_column()
@@ -222,16 +144,15 @@ class Explore(Map):
         gdfs: tuple[GeoDataFrame] = ()
         for gdf in self._gdfs:
             gdf = gdf.clip(mask)
+            collections = gdf.loc[gdf.geom_type == "GeometryCollection"]
+            if len(collections):
+                collections = collections.explode(index_parts=False)
+                gdf = pd.concat([gdf, collections], ignore_index=False)
             gdfs = gdfs + (gdf,)
         self._gdfs = gdfs
         self._gdf = pd.concat(gdfs, ignore_index=True)
         self._explore(**kwargs)
 
-    def _update_column(self):
-        self._is_categorical = self._check_if_categorical()
-        self._fill_missings()
-        self._gdf = pd.concat(self._gdfs, ignore_index=True)
-
     def _explore(self, **kwargs):
         self.kwargs = self.kwargs | kwargs
 
@@ -245,10 +166,46 @@ class Explore(Map):
         else:
             display(self.map)
 
+    def _split_categories(self):
+        new_gdfs, new_labels = [], []
+        for cat in self._unique_values:
+            gdf = self.gdf.loc[self.gdf[self.column] == cat]
+            new_gdfs.append(gdf)
+            new_labels.append(cat)
+        self._gdfs = new_gdfs
+        self._gdf = pd.concat(new_gdfs, ignore_index=True)
+        self.labels = new_labels
+
+    def _make_all_polygon(self):
+        """Buffer gdf if mixed geometry types
+
+        Because Folium does not handle GeometryCollection well
+        """
+
+        new_gdfs = []
+        for gdf in self.gdfs:
+            if get_geom_type(gdf) == "mixed":
+                gdf[gdf._geometry_column_name] = gdf.buffer(0.1)
+            new_gdfs.append(gdf)
+        self._gdfs = new_gdfs
+        self._gdf = pd.concat(new_gdfs, ignore_index=True)
+        self._nan_idx = self._gdf[self._column].isna()
+
+    def _update_column(self):
+        self._is_categorical = self._check_if_categorical()
+        self._fill_missings()
+        self._gdf = pd.concat(self._gdfs, ignore_index=True)
+
     def _create_categorical_map(self):
         self._get_categorical_colors()
 
-        self.map = self._explore_return(self._gdf, return_="empty_map", **self.kwargs)
+        self.map = self._explore_return(
+            self._gdf,
+            return_="empty_map",
+            max_zoom=self.max_zoom,
+            popup=self.popup,
+            **self.kwargs,
+        )
 
         for gdf, label in zip(self._gdfs, self.labels, strict=True):
             if not len(gdf):
@@ -280,17 +237,22 @@ class Explore(Map):
 
     def _create_continous_map(self):
         self._prepare_continous_map()
-        self.colorlist = self._get_continous_colors()
-        self.colors = self._classify_from_bins(self._gdf)
+        if self.scheme:
+            classified = self._classify_from_bins(self._gdf, bins=self.bins)
+            classified_sequential = self._push_classification(classified)
+            n_colors = len(np.unique(classified_sequential)) - any(self._nan_idx)
+            unique_colors = self._get_continous_colors(n=n_colors)
 
         self.map = self._explore_return(
             self._gdf,
             return_="empty_map",
+            max_zoom=self.max_zoom,
+            popup=self.popup,
             **self.kwargs,
         )
 
         colorbar = bc.colormap.StepColormap(
-            self.colorlist,
+            unique_colors,
             vmin=self._gdf[self._column].min(),
             vmax=self._gdf[self._column].max(),
             caption=self._column,
@@ -303,12 +265,13 @@ class Explore(Map):
                 continue
             f = folium.FeatureGroup(name=label)
 
-            self.colors = self._classify_from_bins(gdf)
+            classified = self._classify_from_bins(gdf, bins=self.bins)
+            colorarray = unique_colors[classified]
 
             gjs = self._explore_return(
                 gdf,
                 tooltip=self._tooltip_cols(gdf),
-                color=self.colors,
+                color=colorarray,
                 return_="geojson",
                 **{key: value for key, value in self.kwargs.items() if key != "title"},
             )
@@ -415,7 +378,7 @@ class Explore(Map):
             if isinstance(tiles, xyzservices.TileProvider):
                 attr = attr if attr else tiles.html_attribution
                 map_kwds["min_zoom"] = tiles.get("min_zoom", 0)
-                map_kwds["max_zoom"] = tiles.get("max_zoom", 18)
+                map_kwds["max_zoom"] = tiles.get("max_zoom", 30)
                 tiles = tiles.build_url(scale_factor="{r}")
 
             m = folium.Map(