ObjectNat 0.2.1__tar.gz → 0.2.3__tar.gz

{objectnat-0.2.1 → objectnat-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ObjectNat
-Version: 0.2.1
+Version: 0.2.3
 Summary: ObjectNat is an open-source library created for geospatial analysis created by IDU team
 License: BSD-3-Clause
 Author: DDonnyy
@@ -14,6 +14,7 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: geopandas (>=0.14.3,<0.15.0)
 Requires-Dist: iduedu (>=0.1.4,<0.2.0)
 Requires-Dist: joblib (>=1.4.2,<2.0.0)
+Requires-Dist: jupyter (>=1.1.1,<2.0.0)
 Requires-Dist: networkit (>=11.0,<12.0)
 Requires-Dist: networkx (>=3.2.1,<4.0.0)
 Requires-Dist: numpy (>=1.23.5,<2.0.0)
@@ -44,7 +45,7 @@ Description-Content-Type: text/markdown
 
 ## Features and how to use
 
-1. **[City graph from OSM (IduEdu)](https://github.com/DDonnyy/IduEdu/blob/main/examples/get_any_graph.ipynb)** - Functions to assemble a road, pedestrian,
+1. **[City graph from OSM (IduEdu)](./examples/get_any_graph.ipynb)** - Functions to assemble a road, pedestrian,
    and public transport graph from OpenStreetMap (OSM) and creating Intermodal graph. 
 
    <img src="https://github.com/user-attachments/assets/8dc98da9-8462-415e-8cc8-bdfca788e206" alt="IntermodalGraph" height="250">

{objectnat-0.2.1 → objectnat-0.2.3}/README.md

@@ -17,7 +17,7 @@
 
 ## Features and how to use
 
-1. **[City graph from OSM (IduEdu)](https://github.com/DDonnyy/IduEdu/blob/main/examples/get_any_graph.ipynb)** - Functions to assemble a road, pedestrian,
+1. **[City graph from OSM (IduEdu)](./examples/get_any_graph.ipynb)** - Functions to assemble a road, pedestrian,
    and public transport graph from OpenStreetMap (OSM) and creating Intermodal graph. 
 
    <img src="https://github.com/user-attachments/assets/8dc98da9-8462-415e-8cc8-bdfca788e206" alt="IntermodalGraph" height="250">

{objectnat-0.2.1 → objectnat-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ObjectNat"
-version = "0.2.1"
+version = "0.2.3"
 description = "ObjectNat is an open-source library created for geospatial analysis created by IDU team"
 license = "BSD-3-Clause"
 authors = ["DDonnyy <63115678+DDonnyy@users.noreply.github.com>"]
@@ -22,6 +22,7 @@ population-restorator = "^0.2.3"
 iduedu = "^0.1.4"
 joblib = "^1.4.2"
 scikit-learn = "^1.4.0"
+jupyter = "^1.1.1"
 
 
 [tool.poetry.group.dev.dependencies]

{objectnat-0.2.1 → objectnat-0.2.3}/src/objectnat/_config.py

@@ -44,6 +44,7 @@ class Config:
         self.enable_tqdm_bar = enable_tqdm_bar
         self.logger = logger
         self.iduedu_config = iduedu_config
+        self.pandarallel_use_file_system = False
 
     def change_logger_lvl(self, lvl: Literal["TRACE", "DEBUG", "INFO", "WARN", "ERROR"]):
         self.logger.remove()
@@ -62,6 +63,9 @@ class Config:
         self.enable_tqdm_bar = enable
         self.iduedu_config.set_enable_tqdm(enable)
 
+    def set_pandarallel_use_file_system(self, enable: bool):
+        self.pandarallel_use_file_system = enable
+
 
 config = Config()
 config.change_logger_lvl("INFO")

objectnat-0.2.3/src/objectnat/_version.py

@@ -0,0 +1 @@
+VERSION = "0.2.3"

{objectnat-0.2.1 → objectnat-0.2.3}/src/objectnat/methods/cluster_points_in_polygons.py

@@ -21,10 +21,10 @@ def _get_cluster(services_select, min_dist, min_point, method):
     return services_select
 
 
-def _get_service_ratio(loc):
+def _get_service_ratio(loc, service_code_column):
     all_services = loc.shape[0]
-    loc["service_code"] = loc["service_code"].astype(str)
-    services_count = loc.groupby("service_code").size()
+    loc[service_code_column] = loc[service_code_column].astype(str)
+    services_count = loc.groupby(service_code_column).size()
     return (services_count / all_services).round(2)
 
 
@@ -33,6 +33,7 @@ def get_clusters_polygon(
     min_dist: float | int = 100,
     min_point: int = 5,
     method: Literal["DBSCAN", "HDBSCAN"] = "HDBSCAN",
+    service_code_column: str = "service_code",
 ) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]:
     """
     Generate cluster polygons for given points based on a specified minimum distance and minimum points per cluster.
@@ -49,7 +50,8 @@ def get_clusters_polygon(
         Minimum number of points required to form a cluster. Defaults to 5.
     method : Literal["DBSCAN", "HDBSCAN"], optional
         The clustering method to use. Must be either "DBSCAN" or "HDBSCAN". Defaults to "HDBSCAN".
-
+    service_code_column : str, optional
+        Column, containing service type for relative ratio in clasterized polygons. Defaults to "service_code".
     Returns
     -------
     tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]
@@ -72,17 +74,19 @@ def get_clusters_polygon(
 
     services_select = _get_cluster(points, min_dist, min_point, method)
 
-    if "service_code" not in points.columns:
+    if service_code_column not in points.columns:
         logger.warning(
-            "No 'service_code' column in provided GeoDataFrame, cluster polygons will be without relative ratio."
+            f"No {service_code_column} column in provided GeoDataFrame, cluster polygons will be without relative ratio"
         )
-        points["service_code"] = 1
+        points[service_code_column] = service_code_column
 
     services_normal = services_select[services_select["cluster"] != -1]
     services_outlier = services_select[services_select["cluster"] == -1]
 
     if len(services_normal) > 0:
-        cluster_service = services_normal.groupby("cluster", group_keys=True).apply(_get_service_ratio)
+        cluster_service = services_normal.groupby("cluster", group_keys=True).apply(
+            _get_service_ratio, service_code_column=service_code_column
+        )
         if isinstance(cluster_service, pd.Series):
             cluster_service = cluster_service.unstack(level=1, fill_value=0)
 
@@ -98,7 +102,9 @@ def get_clusters_polygon(
         new_clusters = list(range(clusters_outlier, clusters_outlier + len(services_outlier)))
         services_outlier.loc[:, "cluster"] = new_clusters
 
-        cluster_service = services_outlier.groupby("cluster", group_keys=True).apply(_get_service_ratio)
+        cluster_service = services_outlier.groupby("cluster", group_keys=True).apply(
+            _get_service_ratio, service_code_column=service_code_column
+        )
         if isinstance(cluster_service, pd.Series):
             cluster_service = cluster_service.unstack(level=1, fill_value=0)
 

{objectnat-0.2.1 → objectnat-0.2.3}/src/objectnat/methods/isochrones.py

@@ -45,16 +45,19 @@ def get_accessibility_isochrones(
     -------
     tuple[gpd.GeoDataFrame, gpd.GeoDataFrame | None, gpd.GeoDataFrame | None]
         A tuple containing:
-        - isochrones : GeoDataFrame with the calculated isochrone geometries.
-        - public transport stops (if applicable) : GeoDataFrame with public transport stops within the isochrone, or None if not applicable.
-        - public transport routes (if applicable) : GeoDataFrame with public transport routes within the isochrone, or None if not applicable.
+        - isochrones :
+            GeoDataFrame with the calculated isochrone geometries.
+        - public transport stops (if applicable) :
+            GeoDataFrame with public transport stops within the isochrone, or None if not applicable.
+        - public transport routes (if applicable) :
+            GeoDataFrame with public transport routes within the isochrone, or None if not applicable.
 
     Examples
     --------
     >>> from iduedu import get_intermodal_graph
     >>> graph = get_intermodal_graph(polygon=my_territory_polygon)
     >>> points = gpd.GeoDataFrame(geometry=[Point(30.33, 59.95)], crs=4326).to_crs(graph.graph['crs'])
-    >>> isochrones, pt_stops, pt_routes = get_accessibility_isochrones(points, weight_value=15, weight_type="time_min", graph_nx=my_graph)
+    >>> isochrones, pt_stops, pt_routes = get_accessibility_isochrones(points,weight_value=15, weight_type="time_min", graph_nx=my_graph)
 
     """
 

{objectnat-0.2.1 → objectnat-0.2.3}/src/objectnat/methods/living_buildings_osm.py

@@ -31,7 +31,7 @@ def eval_is_living(row: gpd.GeoSeries):
     >>> buildings = download_buildings(osm_territory_id=421007)
     >>> buildings['is_living'] = buildings.apply(eval_is_living, axis=1)
     """
-    if row["building"] in (
+    return row["building"] in (
         "apartments",
         "house",
         "residential",
@@ -41,10 +41,7 @@ def eval_is_living(row: gpd.GeoSeries):
         "bungalow",
         "cabin",
         "farm",
-    ):
-        return True
-    else:
-        return False
+    )
 
 
 def eval_population(source: gpd.GeoDataFrame, population_column: str, area_per_person: float = 33):
@@ -111,7 +108,8 @@ def download_buildings(
     area_per_person: float = 33,
 ) -> gpd.GeoDataFrame | None:
     """
-    Download building geometries and evaluate 'is_living' and 'population' attributes for a specified territory from OpenStreetMap.
+    Download building geometries and evaluate 'is_living' and 'population'
+     attributes for a specified territory from OpenStreetMap.
 
     Parameters
     ----------
@@ -146,27 +144,27 @@ def download_buildings(
             (buildings["geometry"].geom_type == "Polygon") | (buildings["geometry"].geom_type == "MultiPolygon")
         ]
     if buildings.empty:
-        logger.warning(f"There are no buildings in the specified territory. Output GeoDataFrame is empty.")
+        logger.warning("There are no buildings in the specified territory. Output GeoDataFrame is empty.")
         return buildings
-    else:
-        buildings[is_living_column] = buildings.apply(eval_is_living, axis=1)
-        buildings = eval_population(buildings, population_column, area_per_person)
-        buildings.reset_index(drop=True, inplace=True)
-        logger.debug("Done!")
-        return buildings[
-            [
-                "building",
-                "addr:street",
-                "addr:housenumber",
-                "amenity",
-                "area",
-                "name",
-                "building:levels",
-                "leisure",
-                "design:year",
-                is_living_column,
-                "building:levels_is_real",
-                population_column,
-                "geometry",
-            ]
+
+    buildings[is_living_column] = buildings.apply(eval_is_living, axis=1)
+    buildings = eval_population(buildings, population_column, area_per_person)
+    buildings.reset_index(drop=True, inplace=True)
+    logger.debug("Done!")
+    return buildings[
+        [
+            "building",
+            "addr:street",
+            "addr:housenumber",
+            "amenity",
+            "area",
+            "name",
+            "building:levels",
+            "leisure",
+            "design:year",
+            is_living_column,
+            "building:levels_is_real",
+            population_column,
+            "geometry",
         ]
+    ]

{objectnat-0.2.1 → objectnat-0.2.3}/src/objectnat/methods/provision/provision.py

@@ -4,7 +4,7 @@ import geopandas as gpd
 import numpy as np
 import pandas as pd
 
-from .city_provision import CityProvision
+from .provision_model import Provision
 
 
 def get_service_provision(
@@ -12,6 +12,8 @@ def get_service_provision(
     adjacency_matrix: pd.DataFrame,
     services: gpd.GeoDataFrame,
     threshold: int,
+    buildings_demand_column: str = "demand",
+    services_capacity_column: str = "capacity",
 ) -> Tuple[gpd.GeoDataFrame, gpd.GeoDataFrame, gpd.GeoDataFrame]:
     """Calculate load from buildings with demands on the given services using the distances matrix between them.
 
@@ -20,11 +22,19 @@ def get_service_provision(
         adjacency_matrix (pd.DataFrame): DataFrame representing the adjacency matrix
         buildings (gpd.GeoDataFrame): GeoDataFrame of demanded buildings
         threshold (int): Threshold value
+        buildings_demand_column (str): column name of buildings demands
+        services_capacity_column (str): column name of services capacity
     Returns:
         Tuple[gpd.GeoDataFrame, gpd.GeoDataFrame, gpd.GeoDataFrame]: Tuple of GeoDataFrames representing provision
         buildings, provision services, and provision links
     """
-    provision_buildings, provision_services, provision_links = CityProvision(
+    buildings = buildings.copy()
+    services = services.copy()
+    adjacency_matrix = adjacency_matrix.copy()
+    buildings["demand"] = buildings[buildings_demand_column]
+    services["capacity"] = services[services_capacity_column]
+
+    provision_buildings, provision_services, provision_links = Provision(
         services=services,
         demanded_buildings=buildings,
         adjacency_matrix=adjacency_matrix,
@@ -40,6 +50,9 @@ def clip_provision(
     assert (
         selection_zone.crs == buildings.crs == services.crs == links.crs
     ), f"CRS mismatch: buildings_crs:{buildings.crs}, links_crs:{links.crs} , services_crs:{services.crs}, selection_zone_crs:{selection_zone.crs}"
+    buildings = buildings.copy()
+    links = links.copy()
+    services = services.copy()
 
     s = buildings.intersects(selection_zone.unary_union)
     buildings = buildings.loc[s[s].index]

objectnat-0.2.1/src/objectnat/methods/provision/city_provision.py → objectnat-0.2.3/src/objectnat/methods/provision/provision_model.py

@@ -5,17 +5,15 @@ import geopandas as gpd
 import numpy as np
 import pandas as pd
 from shapely import LineString
-
+from pandarallel import pandarallel
 from objectnat import config
 
 from .provision_exceptions import CapacityKeyError, DemandKeyError
 
 logger = config.logger
 
-from pandarallel import pandarallel
-
 
-class CityProvision:
+class Provision:
     """
     Represents the logic for city provision calculations using a gravity or linear model.
 
@@ -27,7 +25,7 @@ class CityProvision:
         calculation_type (str, optional): Type of calculation ("gravity" or "linear"). Defaults to "gravity".
 
     Returns:
-        CityProvision: The CityProvision object.
+        Provision: The CityProvision object.
 
     Raises: KeyError: If the 'demand' column is missing in the provided 'demanded_buildings' GeoDataFrame,
     or if the 'capacity' column is missing in the provided 'services' GeoDataFrame. ValueError: If the 'capacity'
@@ -45,16 +43,16 @@ class CityProvision:
     ):
         self.services = self.ensure_services(services)
         self.demanded_buildings = self.ensure_buildings(demanded_buildings)
-        self.adjacency_matrix = self.delete_useless_matrix_rows(adjacency_matrix.copy(), demanded_buildings, services)
+        self.adjacency_matrix = self.delete_useless_matrix_rows_columns(adjacency_matrix, demanded_buildings, services)
         self.threshold = threshold
         self.check_crs(self.demanded_buildings, self.services)
-        pandarallel.initialize(progress_bar=False, verbose=0)
+        print(config.pandarallel_use_file_system)
+        pandarallel.initialize(progress_bar=False, verbose=0, use_memory_fs=config.pandarallel_use_file_system)
 
     @staticmethod
     def ensure_buildings(v: gpd.GeoDataFrame) -> gpd.GeoDataFrame:
         if "demand" not in v.columns:
             raise DemandKeyError
-        v = v.copy()
         v["demand_left"] = v["demand"]
         return v
 
@@ -62,7 +60,6 @@ class CityProvision:
     def ensure_services(v: gpd.GeoDataFrame) -> gpd.GeoDataFrame:
         if "capacity" not in v.columns:
             raise CapacityKeyError
-        v = v.copy()
         v["capacity_left"] = v["capacity"]
         return v
 
@@ -73,7 +70,7 @@ class CityProvision:
         ), f"\nThe CRS in the provided geodataframes are different.\nBuildings CRS:{demanded_buildings.crs}\nServices CRS:{services.crs} \n"
 
     @staticmethod
-    def delete_useless_matrix_rows(adjacency_matrix, demanded_buildings, services):
+    def delete_useless_matrix_rows_columns(adjacency_matrix, demanded_buildings, services):
         adjacency_matrix.index = adjacency_matrix.index.astype(int)
 
         builds_indexes = set(demanded_buildings.index.astype(int).tolist())
@@ -142,12 +139,11 @@ class CityProvision:
         def apply_function_based_on_size(df, func, axis, threshold=500):
             if len(df) > threshold:
                 return df.parallel_apply(func, axis=axis)
-            else:
-                return df.apply(func, axis=axis)
+            return df.apply(func, axis=axis)
 
         def _calculate_flows_y(loc):
-            import numpy as np
-            import pandas as pd
+            import numpy as np  # pylint: disable=redefined-outer-name,reimported,import-outside-toplevel
+            import pandas as pd  # pylint: disable=redefined-outer-name,reimported,import-outside-toplevel
 
             c = services_table.loc[loc.name]["capacity_left"]
             p = 1 / loc / loc
@@ -165,8 +161,8 @@ class CityProvision:
             return choice
 
         def _balance_flows_to_demands(loc):
-            import numpy as np
-            import pandas as pd
+            import numpy as np  # pylint: disable=redefined-outer-name,reimported,import-outside-toplevel
+            import pandas as pd  # pylint: disable=redefined-outer-name,reimported,import-outside-toplevel
 
             d = houses_table.loc[loc.name]["demand_left"]
             loc = loc[loc > 0]
@@ -228,6 +224,11 @@ def _calc_links(
     buildings: gpd.GeoDataFrame,
     distance_matrix: pd.DataFrame,
 ):
+    buildings_ = buildings.copy()
+    services_ = services.copy()
+    buildings_.geometry = buildings_.representative_point()
+    services_.geometry = services_.representative_point()
+
     def subfunc(loc):
         try:
             return [
@@ -244,15 +245,11 @@ def _calc_links(
     def subfunc_geom(loc):
         return LineString(
             (
-                buildings_["geometry"][loc["building_index"]],
-                services_["geometry"][loc["service_index"]],
+                buildings_.geometry[loc["building_index"]],
+                services_.geometry[loc["service_index"]],
             )
         )
 
-    buildings_ = buildings.copy()
-    services_ = services.copy()
-    buildings_.geometry = buildings_.representative_point()
-    services_.geometry = services_.representative_point()
     flat_matrix = destination_matrix.transpose().apply(lambda x: subfunc(x[x > 0]), result_type="reduce")
 
     distribution_links = gpd.GeoDataFrame(data=[item for sublist in list(flat_matrix) for item in sublist])

objectnat-0.2.1/src/objectnat/_version.py

@@ -1 +0,0 @@
-VERSION = "0.2.1"