giga-spatial 0.6.5__py3-none-any.whl → 0.6.6__py3-none-any.whl

{giga_spatial-0.6.5.dist-info → giga_spatial-0.6.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: giga-spatial
-Version: 0.6.5
+Version: 0.6.6
 Summary: A package for spatial data download & processing
 Home-page: https://github.com/unicef/giga-spatial
 Author: Utku Can Ozturk
@@ -32,6 +32,7 @@ Requires-Dist: pydantic-settings>=2.7.1
 Requires-Dist: hdx-python-api>=6.3.8
 Requires-Dist: bs4==0.0.2
 Requires-Dist: sqlalchemy-trino==0.5.0
+Requires-Dist: dask>=2024.12.1
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

{giga_spatial-0.6.5.dist-info → giga_spatial-0.6.6.dist-info}/RECORD

@@ -1,30 +1,30 @@
-giga_spatial-0.6.5.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-gigaspatial/__init__.py,sha256=KDgkBrBsBSUzbLgrOZ89YsNN06fU4j5bmcuEwo6q5pg,22
+giga_spatial-0.6.6.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+gigaspatial/__init__.py,sha256=I3h5MyD10PkOUQEBnR6L9ja7s4WeTEg8rRjRKTCWYWQ,22
 gigaspatial/config.py,sha256=pLbxGc08OHT2IfTBzZVuIJTPR2vvg3KTFfvciOtRswk,9304
 gigaspatial/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gigaspatial/core/io/__init__.py,sha256=stlpgEeHf5KIb2ZW8yEbdJK5iq6n_wX4DPmKyR9PK-w,317
 gigaspatial/core/io/adls_data_store.py,sha256=Zv-D_8d_2h57HnCUTJb0JWWjXqR_0XH4F8Nu_UFZK9E,11975
-gigaspatial/core/io/data_api.py,sha256=3HMstau3zH3JPRUW0t83DZt74N39bt-jsfAyrUUFMoc,3944
+gigaspatial/core/io/data_api.py,sha256=0TtXEfqIz9m1uC8ktcUhZZtx6ZIPY_SIXNnlIodcry8,3970
 gigaspatial/core/io/data_store.py,sha256=mi8fy78Dtwj4dpKkyDM6kTlna1lfCQ5ro2hUAOFr83A,3223
-gigaspatial/core/io/database.py,sha256=zoOQ1j6bNarngQL8vS8adrWYi9P1NRUytZEzHd08F30,11303
+gigaspatial/core/io/database.py,sha256=kR9ZHuIpZEjXmyj_PnMn6ManQ504kl_f1kJRjHuNWwk,11378
 gigaspatial/core/io/local_data_store.py,sha256=hcu7DNYa3AL6sEPMqguzxWal_bnP7CIpbwpoiyf5TCw,2933
 gigaspatial/core/io/readers.py,sha256=gqFKGRCsAP_EBXipqGtT8MEV-x0u6SrCqaSiOC5YPTA,9284
 gigaspatial/core/io/writers.py,sha256=asb56ZHQEWO2rdilIq7QywDRk8yfebecWv1KwzUpaXI,4367
 gigaspatial/core/schemas/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gigaspatial/core/schemas/entity.py,sha256=QAhEW0-JgdWh9pjKGbB5ArvqtVK85ayYZJPgjdb-IKw,8590
 gigaspatial/generators/__init__.py,sha256=cKbMTW7Eh-oDPtM9OfGP14_ekVwc2_7Je7n_pr_anig,223
-gigaspatial/generators/poi.py,sha256=cPMH1-0V_P7orGpIcsarZ6rWZiGOfcSxQNxvQJgAuM8,33628
+gigaspatial/generators/poi.py,sha256=FMYH2yPFuCeYiwj-pHYe83bAxXPkQP28VDQx5L2eEnQ,35869
 gigaspatial/generators/zonal/__init__.py,sha256=egnpvGVeIOS2Zg516AT84tJnIqS4owxmMLLmBQJmK7Y,301
 gigaspatial/generators/zonal/admin.py,sha256=rgOyQX3f_g9qnXqrf-NkR2GEdwOqjNuPNe1H7AUVsfg,3698
-gigaspatial/generators/zonal/base.py,sha256=DzIXcOMnUhlCZQ8AxCyGvVuTY8oTCw66xhyWn7tSO-U,22862
-gigaspatial/generators/zonal/geometry.py,sha256=P1vKJNvYpBQj_g-B-OzeJy4KCt8f_SI7h3H4WKTWXiU,19605
+gigaspatial/generators/zonal/base.py,sha256=aoq9AmawPnxu04YI7hPmJzvBTyuUqBQuMZAEUdiVStg,22818
+gigaspatial/generators/zonal/geometry.py,sha256=JbaQ4WS6g45g3uBaATfJd7DS3wW-GPW0GW9FtsvGH-c,21284
 gigaspatial/generators/zonal/mercator.py,sha256=fA02j30PWB5BVjrbNGCMjiOw-ds182yK7R27z8mWFug,5291
 gigaspatial/grid/__init__.py,sha256=ypSSyZ4fYtMNc4IG7chSD7NkUfS2bv9KWRsKR1D9pDI,80
 gigaspatial/grid/mercator_tiles.py,sha256=mAYZDBJ1U0l3z9i4rh5OqiPhOGWcBYzUOI1cvQG_Ff4,11240
-gigaspatial/handlers/__init__.py,sha256=R2rugXR5kF4lLkSO1fjpVDYK_jWdD8U2NbXbW71Ezv8,1523
-gigaspatial/handlers/base.py,sha256=rL94c3wDjsqzLp4na8FfYXW6tNjVGX6v4M-Ce4LrAro,26413
-gigaspatial/handlers/boundaries.py,sha256=TfqjtLE4VdJlUt7APLX16hzGuR1EH2MuRBn8u6R0k9A,18705
-gigaspatial/handlers/ghsl.py,sha256=NFjUSQrv-YrlfnX2erzd7r88PZhhyezLg3HzIikZwaM,30170
+gigaspatial/handlers/__init__.py,sha256=T0_6OxXQ59yTu9g2P6P9vnepudOWp_85R4WQKxRF94c,1618
+gigaspatial/handlers/base.py,sha256=ZcahOEMmS_uECBqOhEEdCoDcPCbVItA5mRS5zEUqR-s,27194
+gigaspatial/handlers/boundaries.py,sha256=jtWyQt3iAzS77mbAOi7mjh3cv_YCV3uB_r1h56gCfeY,20729
+gigaspatial/handlers/ghsl.py,sha256=aSEVQVANzJf8O8TiQYmfwyeM43ZaO65VJHmiuLSQfLs,30524
 gigaspatial/handlers/giga.py,sha256=F5ZfcE37a24X-c6Xhyt72C9eZZbyN_gV7w_InxKFMQQ,28348
 gigaspatial/handlers/google_open_buildings.py,sha256=Liqk7qJhDtB4Ia4uhBe44LFcf-XVKBjRfj-pWlE5erY,16594
 gigaspatial/handlers/hdx.py,sha256=LTEs_xZF1yPhD8dAdZ_YN8Vcan7iB5_tZ8NjF_ip6u0,18001
@@ -37,14 +37,14 @@ gigaspatial/handlers/osm.py,sha256=sLNMkOVh1v50jrWw7Z0-HILY5QTQjgKCHCeAfXj5jA8,1
 gigaspatial/handlers/overture.py,sha256=lKeNw00v5Qia7LdWORuYihnlKEqxE9m38tdeRrvag9k,4218
 gigaspatial/handlers/rwi.py,sha256=eAaplDysVeBhghJusYUKZYbKL5hW-klWvi8pWhILQkY,4962
 gigaspatial/handlers/unicef_georepo.py,sha256=ODYNvkU_UKgOHXT--0MqmJ4Uk6U1_mp9xgehbTzKpX8,31924
-gigaspatial/handlers/worldpop.py,sha256=oJ39NGajXi0rn829ZoFiaeG4_wavyPvljdActpxs12I,9850
+gigaspatial/handlers/worldpop.py,sha256=pkTmqb0k0vpa58t6tM3jfcpMHt1YuayLPFEFEULlrLs,30156
 gigaspatial/processing/__init__.py,sha256=QDVL-QbLCrIb19lrajP7LrHNdGdnsLeGcvAs_jQpdRM,183
 gigaspatial/processing/algorithms.py,sha256=6fBCwbZrI_ISWJ7UpkH6moq1vw-7dBy14yXSLHZprqY,6591
-gigaspatial/processing/geo.py,sha256=tAykXH5UwrXtfnyZ9CClvejo9Ae7Yw6ij7EbF-7WLhQ,40091
+gigaspatial/processing/geo.py,sha256=8kD7-LQdGzKVfuZDWr3zK5uQhPzgxbZ3JBPosLRBJ5M,41390
 gigaspatial/processing/sat_images.py,sha256=YUbH5MFNzl6NX49Obk14WaFcr1s3SyGJIOk-kRpbBNg,1429
 gigaspatial/processing/tif_processor.py,sha256=QLln9D-_zBhdYQL9NAL_bmo0bmmxE3sxDUQEglYQK94,27490
 gigaspatial/processing/utils.py,sha256=HC85vGKQakxlkoQAkZmeAXWHsenAwTIRn7jPKUA7x20,1500
-giga_spatial-0.6.5.dist-info/METADATA,sha256=eZHvzPKaNla-npj8PwfruUNp0chqxxst_mugbde6OL8,7506
-giga_spatial-0.6.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-giga_spatial-0.6.5.dist-info/top_level.txt,sha256=LZsccgw6H4zXT7m6Y4XChm-Y5LjHAwZ2hkGN_B3ExmI,12
-giga_spatial-0.6.5.dist-info/RECORD,,
+giga_spatial-0.6.6.dist-info/METADATA,sha256=ZKoXmthabbL_5xJYHdQfk3ev4Dz02tWU6RAtpv0vWSU,7537
+giga_spatial-0.6.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+giga_spatial-0.6.6.dist-info/top_level.txt,sha256=LZsccgw6H4zXT7m6Y4XChm-Y5LjHAwZ2hkGN_B3ExmI,12
+giga_spatial-0.6.6.dist-info/RECORD,,

gigaspatial/__init__.py

@@ -1 +1 @@
-__version__ = "0.6.5"
+__version__ = "0.6.6"

gigaspatial/core/io/data_api.py

@@ -35,7 +35,9 @@ class GigaDataAPI:
         :param sort: Whether to sort the country list alphabetically (default is True).
         """
         country_list = [
-            t.name for t in self.client.list_all_tables() if t.share == self.share_name
+            t.name
+            for t in self.client.list_all_tables()
+            if t.schema == self.schema_name
         ]
         if sort:
             country_list.sort()

gigaspatial/core/io/database.py

@@ -272,6 +272,7 @@ class DBConnection:
     def read_sql_to_dask_dataframe(
         self,
         table_name: str,
+        index_col: str,
         columns: Optional[List[str]] = None,
         limit: Optional[int] = None,
         **kwargs,
@@ -310,7 +311,9 @@ class DBConnection:
             if limit:
                 query = query.limit(limit)
 
-            return dd.read_sql_query(sql=query, con=connection_string, **kwargs)
+            return dd.read_sql_query(
+                sql=query, con=connection_string, index_col=index_col, **kwargs
+            )
         except Exception as e:
             print(f"Error reading SQL to Dask DataFrame: {e}")
             raise ValueError(f"Failed to read SQL to Dask DataFrame: {e}") from e

gigaspatial/generators/poi.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import List, Optional, Union, Tuple
+from typing import List, Optional, Union, Tuple, Literal
 from pydantic.dataclasses import dataclass, Field
 
 import geopandas as gpd
@@ -13,6 +13,7 @@ from gigaspatial.config import config as global_config
 from gigaspatial.handlers.google_open_buildings import GoogleOpenBuildingsHandler
 from gigaspatial.handlers.microsoft_global_buildings import MSBuildingsHandler
 from gigaspatial.handlers.ghsl import GHSLDataHandler
+from gigaspatial.handlers.worldpop import WPPopulationHandler
 from gigaspatial.processing.geo import (
     convert_to_geodataframe,
     buffer_geodataframe,
@@ -468,7 +469,7 @@ class PoiViewGenerator:
         map_radius_meters: Optional[float] = None,
         output_column: str = "zonal_stat",
         value_column: Optional[str] = None,
-        area_weighted: bool = False,
+        predicate: Literal["intersects", "within", "fractional"] = "intersects",
         **kwargs,
     ) -> pd.DataFrame:
         """
@@ -496,9 +497,8 @@ class PoiViewGenerator:
             value_column (str, optional):
                 For polygon data: Name of the column to aggregate. Required for polygon data.
                 Not used for raster data.
-            area_weighted (bool, optional):
-                For polygon data: Whether to weight values by fractional area of
-                intersection. Defaults to False.
+            predicate (Literal["intersects", "within", "fractional"], optional):
+                The spatial relationship to use for aggregation. Defaults to "intersects".
             **kwargs:
                 Additional keyword arguments passed to the sampling/aggregation functions.
 
@@ -575,7 +575,7 @@ class PoiViewGenerator:
                 )
 
             self.logger.info(
-                f"Aggregating {value_column} within {map_radius_meters}m buffers around POIs"
+                f"Aggregating {value_column} within {map_radius_meters}m buffers around POIs using predicate '{predicate}'"
             )
 
             # Create buffers around POIs
@@ -591,12 +591,17 @@ class PoiViewGenerator:
                 zones=buffer_gdf,
                 value_columns=value_column,
                 aggregation=stat,
-                area_weighted=area_weighted,
+                predicate=predicate,
                 zone_id_column="poi_id",
+                output_suffix="",
+                drop_geometry=True,
                 **kwargs,
             )
 
-            results_df = aggregation_result_gdf[["poi_id", value_column]].copy()
+            results_df = aggregation_result_gdf[["poi_id", value_column]]
+
+            if output_column != "zonal_stat":
+                results_df = results_df.rename(columns={value_column: output_column})
 
         else:
             raise ValueError(
@@ -662,7 +667,6 @@ class PoiViewGenerator:
 
     def map_smod(
         self,
-        stat="median",
         dataset_year=2020,
         dataset_resolution=1000,
         output_column="smod_class",
@@ -703,11 +707,67 @@ class PoiViewGenerator:
 
         return self.map_zonal_stats(
             data=tif_processors,
-            stat=stat,  # Use median for categorical data
             output_column=output_column,
             **kwargs,
         )
 
+    def map_wp_pop(
+        self,
+        country: Union[str, List[str]],
+        map_radius_meters: float,
+        resolution=1000,
+        predicate: Literal[
+            "centroid_within", "intersects", "fractional", "within"
+        ] = "fractional",
+        output_column: str = "population",
+        **kwargs,
+    ):
+        if isinstance(country, str):
+            country = [country]
+
+        handler = WPPopulationHandler(
+            project="pop", resolution=resolution, data_store=self.data_store, **kwargs
+        )
+
+        self.logger.info(
+            f"Mapping WorldPop Population data (year: {handler.config.year}, resolution: {handler.config.resolution}m)"
+        )
+
+        if predicate == "fractional" and resolution == 100:
+            self.logger.warning(
+                "Fractional aggregations only supported for datasets with 1000m resolution. Using `intersects` as predicate"
+            )
+            predicate = "intersects"
+        
+        if predicate == "centroid_within":
+            data = []
+            for c in country:
+                data.extend(
+                    handler.load_data(c, ensure_available=self.config.ensure_available)
+                )
+        else:
+            data = pd.concat(
+                [
+                    handler.load_into_geodataframe(
+                        c, ensure_available=self.config.ensure_available
+                    )
+                    for c in country
+                ],
+                ignore_index=True,
+            )
+
+        self.logger.info(f"Mapping WorldPop Population data into {map_radius_meters}m zones around POIs using 'sum' statistic")
+
+        return self.map_zonal_stats(
+            data,
+            stat="sum",
+            map_radius_meters=map_radius_meters,
+            value_column="pixel_value",
+            predicate=predicate,
+            output_column=output_column,
+            **kwargs
+        )
+
     def save_view(
         self,
         name: str,
@@ -778,8 +838,11 @@ class PoiViewGenerator:
         Returns:
             gpd.GeoDataFrame: The current view merged with point geometries.
         """
-        return self.view.merge(
-            self.points_gdf[["poi_id", "geometry"]], on="poi_id", how="left"
+        return gpd.GeoDataFrame(
+            self.view.merge(
+                self.points_gdf[["poi_id", "geometry"]], on="poi_id", how="left"
+            ),
+            crs="EPSG:4326",
         )
 
     def chain_operations(self, operations: List[dict]) -> "PoiViewGenerator":

gigaspatial/generators/zonal/base.py

@@ -13,7 +13,6 @@ from gigaspatial.core.io.local_data_store import LocalDataStore
 from gigaspatial.core.io.writers import write_dataset
 from gigaspatial.config import config as global_config
 from gigaspatial.processing.geo import (
-    convert_to_geodataframe,
     aggregate_polygons_to_zones,
     aggregate_points_to_zones,
 )
@@ -242,36 +241,37 @@ class ZonalViewGenerator(ABC, Generic[T]):
         if mapping_function is not None:
             return mapping_function(self, points, **mapping_kwargs)
 
-        else:
+        self.logger.warning(
+            "Using default points mapping implementation. Consider creating a specialized mapping function."
+        )
+        result = aggregate_points_to_zones(
+            points=points,
+            zones=self.zone_gdf,
+            value_columns=value_columns,
+            aggregation=aggregation,
+            point_zone_predicate=predicate,
+            zone_id_column="zone_id",
+            output_suffix=output_suffix,
+        )
+
+        if isinstance(value_columns, str):
+            return result.set_index("zone_id")[value_columns].to_dict()
+        elif isinstance(value_columns, list):
+            # If multiple value columns, return a dictionary of dictionaries
+            # Or, if preferred, a dictionary where values are lists/tuples of results
+            # For now, let's return a dict of series, which is common.
+            # The previous version implied a single dictionary result from map_points/polygons
+            # but with multiple columns, it's usually {zone_id: {col1: val1, col2: val2}}
+            # or {col_name: {zone_id: val}}
+            # In this version, it'll return a dictionary for each column.
+            return {
+                col: result.set_index("zone_id")[col].to_dict() for col in value_columns
+            }
+        else:  # If value_columns is None, it should return point_count
             self.logger.warning(
-                "Using default points mapping implementation. Consider creating a specialized mapping function."
-            )
-            result = aggregate_points_to_zones(
-                points=points,
-                zones=self.zone_gdf,
-                value_columns=value_columns,
-                aggregation=aggregation,
-                point_zone_predicate=predicate,
-                zone_id_column="zone_id",
-                output_suffix=output_suffix,
+                "No `value_columns` provided. Mapping point counts. Consider passing `value_columns` and `aggregation` or `mapping_function`."
             )
-
-            if isinstance(value_columns, str):
-                return result.set_index("zone_id")[value_columns].to_dict()
-            elif isinstance(value_columns, list):
-                # If multiple value columns, return a dictionary of dictionaries
-                # Or, if preferred, a dictionary where values are lists/tuples of results
-                # For now, let's return a dict of series, which is common.
-                # The previous version implied a single dictionary result from map_points/polygons
-                # but with multiple columns, it's usually {zone_id: {col1: val1, col2: val2}}
-                # or {col_name: {zone_id: val}}
-                # In this version, it'll return a dictionary for each column.
-                return {
-                    col: result.set_index("zone_id")[col].to_dict()
-                    for col in value_columns
-                }
-            else:  # If value_columns is None, it should return point_count
-                return result.set_index("zone_id")["point_count"].to_dict()
+            return result.set_index("zone_id")["point_count"].to_dict()
 
     def map_polygons(
         self,
@@ -415,10 +415,6 @@ class ZonalViewGenerator(ABC, Generic[T]):
         if mapping_function is not None:
             return mapping_function(self, tif_processors, **mapping_kwargs)
 
-        self.logger.warning(
-            "Using default raster mapping implementation. Consider creating a specialized mapping function."
-        )
-
         raster_crs = tif_processors[0].crs
 
         if raster_crs != self.zone_gdf.crs:
@@ -522,6 +518,9 @@ class ZonalViewGenerator(ABC, Generic[T]):
         Returns:
             gpd.GeoDataFrame: The current view merged with zone geometries.
         """
-        return self.view.merge(
-            self.zone_gdf[["zone_id", "geometry"]], on="zone_id", how="left"
+        return gpd.GeoDataFrame(
+            (self.view).merge(
+                self.zone_gdf[["zone_id", "geometry"]], on="zone_id", how="left"
+            ),
+            crs=self.zone_gdf.crs,
         )

gigaspatial/generators/zonal/geometry.py

@@ -6,7 +6,6 @@ import pandas as pd
 import logging
 
 from gigaspatial.core.io.data_store import DataStore
-from gigaspatial.config import config as global_config
 from gigaspatial.processing.geo import (
     add_area_in_meters,
     get_centroids,
@@ -14,6 +13,7 @@ from gigaspatial.processing.geo import (
 from gigaspatial.handlers.ghsl import GHSLDataHandler
 from gigaspatial.handlers.google_open_buildings import GoogleOpenBuildingsHandler
 from gigaspatial.handlers.microsoft_global_buildings import MSBuildingsHandler
+from gigaspatial.handlers.worldpop import WPPopulationHandler
 from gigaspatial.generators.zonal.base import (
     ZonalViewGenerator,
     ZonalViewGeneratorConfig,
@@ -156,7 +156,7 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         year=2020,
         resolution=100,
         stat: str = "sum",
-        name_prefix: str = "built_surface_m2_",
+        output_column: str = "built_surface_m2",
         **kwargs,
     ) -> pd.DataFrame:
         """Map GHSL Built-up Surface data to zones.
@@ -165,15 +165,14 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         data using appropriate default parameters for built surface analysis.
 
         Args:
-            ghsl_data_config (GHSLDataConfig): Configuration for GHSL Built-up Surface data.
-                Defaults to GHS_BUILT_S product for 2020 at 100m resolution.
+            year: The year of the data (default: 2020)
+            resolution: The resolution in meters (default: 100)
             stat (str): Statistic to calculate for built surface values within each zone.
                 Defaults to "sum" which gives total built surface area.
-            name_prefix (str): Prefix for the output column name. Defaults to "built_surface_m2_".
-
+            output_column (str): The output column name. Defaults to "built_surface_m2".
         Returns:
-            pd.DataFrame: Updated GeoDataFrame with zones and built surface metrics.
-                Adds a column named "{name_prefix}{stat}" containing the aggregated values.
+            pd.DataFrame: Updated view DataFrame and settlement classification.
+                Adds a column with `output_column` containing the aggregated values.
         """
         handler = GHSLDataHandler(
             product="GHS_BUILT_S",
@@ -184,7 +183,7 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         )
 
         return self.map_ghsl(
-            handler=handler, stat=stat, name_prefix=name_prefix, **kwargs
+            handler=handler, stat=stat, output_column=output_column, **kwargs
         )
 
     def map_smod(
@@ -192,7 +191,7 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         year=2020,
         resolution=1000,
         stat: str = "median",
-        name_prefix: str = "smod_class_",
+        output_column: str = "smod_class",
         **kwargs,
     ) -> pd.DataFrame:
         """Map GHSL Settlement Model data to zones.
@@ -201,15 +200,14 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         data using appropriate default parameters for settlement classification analysis.
 
         Args:
-            ghsl_data_config (GHSLDataConfig): Configuration for GHSL Settlement Model data.
-                Defaults to GHS_SMOD product for 2020 at 1000m resolution in Mollweide projection.
+            year: The year of the data (default: 2020)
+            resolution: The resolution in meters (default: 1000)
             stat (str): Statistic to calculate for settlement class values within each zone.
                 Defaults to "median" which gives the predominant settlement class.
-            name_prefix (str): Prefix for the output column name. Defaults to "smod_class_".
-
+            output_column (str): The output column name. Defaults to "smod_class".
         Returns:
-            pd.DataFrame: Updated DataFrame with zones and settlement classification.
-                Adds a column named "{name_prefix}{stat}" containing the aggregated values.
+            pd.DataFrame: Updated view DataFrame and settlement classification.
+                Adds a column with `output_column` containing the aggregated values.
         """
         handler = GHSLDataHandler(
             product="GHS_SMOD",
@@ -221,14 +219,14 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         )
 
         return self.map_ghsl(
-            handler=handler, stat=stat, name_prefix=name_prefix, **kwargs
+            handler=handler, stat=stat, output_column=output_column, **kwargs
         )
 
     def map_ghsl(
         self,
         handler: GHSLDataHandler,
         stat: str,
-        name_prefix: Optional[str] = None,
+        output_column: Optional[str] = None,
         **kwargs,
     ) -> pd.DataFrame:
         """Map Global Human Settlement Layer data to zones.
@@ -237,16 +235,15 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         the raster values within each zone using the specified statistic.
 
         Args:
-            ghsl_data_config (GHSLDataConfig): Configuration specifying which GHSL
-                product, year, resolution, and coordinate system to use.
+            hander (GHSLDataHandler): Handler for the GHSL data.
             stat (str): Statistic to calculate for raster values within each zone.
                 Common options: "mean", "sum", "median", "min", "max".
-            name_prefix (str, optional): Prefix for the output column name.
+            output_column (str): The output column name.
                 If None, uses the GHSL product name in lowercase followed by underscore.
 
         Returns:
             pd.DataFrame: Updated DataFrame with GHSL metrics.
-                Adds a column named "{name_prefix}{stat}" containing the sampled values.
+                Adds a column named as `output_column` containing the sampled values.
 
         Note:
             The method automatically determines which GHSL tiles intersect with the zones
@@ -265,10 +262,12 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
         )
         sampled_values = self.map_rasters(tif_processors=tif_processors, stat=stat)
 
-        name_prefix = (
-            name_prefix if name_prefix else handler.config.product.lower() + "_"
+        column_name = (
+            output_column
+            if output_column
+            else f"{handler.config.product.lower()}_{stat}"
         )
-        column_name = f"{name_prefix}{stat}"
+
         self.add_variable_to_view(sampled_values, column_name)
 
         return self.view
@@ -442,16 +441,14 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
 
     def map_ghsl_pop(
         self,
-        year=2020,
         resolution=100,
         stat: str = "sum",
-        name_prefix: str = "ghsl_pop_",
+        output_column: str = "ghsl_pop",
         predicate: Literal["intersects", "fractional"] = "intersects",
         **kwargs,
     ):
         handler = GHSLDataHandler(
             product="GHS_POP",
-            year=year,
             resolution=resolution,
             data_store=self.data_store,
             **kwargs,
@@ -464,7 +461,7 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
                 )
                 predicate = "intersects"
             else:
-                gdf_pop = handler.load_into_geodataframe()
+                gdf_pop = handler.load_into_geodataframe(self.zone_gdf)
 
                 result = self.map_polygons(
                     gdf_pop,
@@ -473,10 +470,68 @@ class GeometryBasedZonalViewGenerator(ZonalViewGenerator[T]):
                     predicate="fractional",
                 )
 
-                column_name = f"{name_prefix}{stat}"
-                self.add_variable_to_view(result, column_name)
+                self.add_variable_to_view(result, output_column)
                 return self.view
 
         return self.map_ghsl(
-            handler=handler, stat=stat, name_prefix=name_prefix, **kwargs
+            handler=handler, stat=stat, output_column=output_column, **kwargs
+        )
+
+    def map_wp_pop(
+        self,
+        country: Union[str, List[str]],
+        resolution=1000,
+        predicate: Literal["intersects", "fractional"] = "intersects",
+        output_column: str = "population",
+        **kwargs,
+    ):
+        if isinstance(country, str):
+            country = [country]
+
+        handler = WPPopulationHandler(
+            project="pop", resolution=resolution, data_store=self.data_store, **kwargs
+        )
+
+        self.logger.info(
+            f"Mapping WorldPop Population data (year: {handler.config.year}, resolution: {handler.config.resolution}m)"
         )
+
+        if predicate == "fractional":
+            if resolution == 100:
+                self.logger.warning(
+                    "Fractional aggregations only supported for datasets with 1000m resolution. Using `intersects` as predicate"
+                )
+                predicate = "intersects"
+            else:
+                gdf_pop = pd.concat(
+                    [
+                        handler.load_into_geodataframe(
+                            c, ensure_available=self.config.ensure_available
+                        )
+                        for c in country
+                    ],
+                    ignore_index=True,
+                )
+
+                result = self.map_polygons(
+                    gdf_pop,
+                    value_columns="pixel_value",
+                    aggregation="sum",
+                    predicate=predicate,
+                )
+
+                self.add_variable_to_view(result, output_column)
+                return self.view
+
+        tif_processors = []
+        for c in country:
+            tif_processors.extend(
+                handler.load_data(c, ensure_available=self.config.ensure_available)
+            )
+
+        self.logger.info(f"Sampling WorldPop Population data using 'sum' statistic")
+        sampled_values = self.map_rasters(tif_processors=tif_processors, stat="sum")
+
+        self.add_variable_to_view(sampled_values, output_column)
+
+        return self.view

gigaspatial/handlers/__init__.py

@@ -21,7 +21,14 @@ from gigaspatial.handlers.osm import OSMLocationFetcher
 from gigaspatial.handlers.overture import OvertureAmenityFetcher
 from gigaspatial.handlers.mapbox_image import MapboxImageDownloader
 from gigaspatial.handlers.maxar_image import MaxarConfig, MaxarImageDownloader
-from gigaspatial.handlers.worldpop import WorldPopConfig, WorldPopDownloader
+
+from gigaspatial.handlers.worldpop import (
+    WPPopulationConfig,
+    WPPopulationReader,
+    WPPopulationDownloader,
+    WPPopulationHandler,
+    WorldPopRestClient,
+)
 from gigaspatial.handlers.ookla_speedtest import (
     OoklaSpeedtestTileConfig,
     OoklaSpeedtestConfig,