remove force data type and update classifier

city_metrix/layers/smart_surface_lulc.py

@@ -34,12 +34,12 @@ def get_data(self, bbox):
 
         # Open space
         open_space_osm = OpenStreetMap(osm_class=OpenStreetMapClass.OPEN_SPACE_HEAT).get_data(bbox).to_crs(crs).reset_index()
-        open_space_osm['Value'] = np.uint16(10)
+        open_space_osm['Value'] = 10
 
 
         # Water
         water_osm = OpenStreetMap(osm_class=OpenStreetMapClass.WATER).get_data(bbox).to_crs(crs).reset_index()
-        water_osm['Value'] = np.uint16(20)
+        water_osm['Value'] = 20
 
 
         # Roads
@@ -60,7 +60,7 @@ def get_data(self, bbox):
             roads_osm['lanes'] = roads_osm['lanes'].fillna(roads_osm['avg_lanes'])
 
             # Add value field (30)
-            roads_osm['Value'] = np.uint16(30)
+            roads_osm['Value'] = 30
 
             # Buffer roads by lanes * 10 ft (3.048 m)
             # https://nacto.org/publication/urban-street-design-guide/street-design-elements/lane-width/#:~:text=wider%20lane%20widths.-,Lane%20widths%20of%2010%20feet%20are%20appropriate%20in%20urban%20areas,be%20used%20in%20each%20direction
@@ -74,7 +74,7 @@ def get_data(self, bbox):
             )
         else:
             # Add value field (30)
-            roads_osm['Value'] = np.uint16(30)
+            roads_osm['Value'] = 30
 
 
         # Building
@@ -113,7 +113,7 @@ def get_data(self, bbox):
 
         # Parking
         parking_osm = OpenStreetMap(osm_class=OpenStreetMapClass.PARKING).get_data(bbox).to_crs(crs).reset_index()
-        parking_osm['Value'] = np.uint16(50)
+        parking_osm['Value'] = 50
 
 
         # combine features: open space, water, road, building, parking

city_metrix/models/building_classifier/building_classifier.py

@@ -50,8 +50,8 @@ def get_data_esa_reclass(self, bbox, crs):
         # Perform the reclassification
         reclassified_esa = reclassify(esa_world_cover, bins=list(reclass_map.keys()), new_values=list(reclass_map.values()))
 
-        # Convert to int8 and chunk the data for Dask processing
-        reclassified_esa = reclassified_esa.astype(np.uint16).chunk({'x': 512, 'y': 512})
+        # Chunk the data for Dask processing
+        reclassified_esa = reclassified_esa.chunk({'x': 512, 'y': 512})
 
         reclassified_esa = reclassified_esa.rio.write_crs(esa_world_cover.rio.crs, inplace=True)
 
@@ -79,8 +79,8 @@ def get_data_ulu(self, bbox, crs, snap_to):
         for from_val, to_val in mapping.items():
             ulu_lulc = ulu_lulc.where(ulu_lulc != from_val, to_val)
 
-        # Convert to int8 and chunk the data for Dask processing
-        ulu_lulc = ulu_lulc.astype(np.uint16).chunk({'x': 512, 'y': 512})
+        # Chunk the data for Dask processing
+        ulu_lulc = ulu_lulc.chunk({'x': 512, 'y': 512})
 
         ####### 1-Non-residential as default
         # 0-Unclassified as nodata 
@@ -112,7 +112,7 @@ def get_data_anbh(self, bbox, snap_to):
 
     def rasterize_polygon(self, gdf, snap_to):
         if gdf.empty:
-            raster = np.full(snap_to.shape, 0, dtype=np.uint16)
+            raster = np.full(snap_to.shape, 0)
             raster = xr.DataArray(raster, dims=snap_to.dims, coords=snap_to.coords)
 
             return raster.rio.write_crs(snap_to.rio.crs, inplace=True)
@@ -121,7 +121,7 @@ def rasterize_polygon(self, gdf, snap_to):
             vector_data=gdf,
             measurements=["Value"],
             like=snap_to,
-            fill=np.uint16(0)
+            fill=0
         ).Value
 
         return raster.rio.reproject_match(snap_to)
@@ -149,7 +149,7 @@ def building_classifier_tree(self):
         # set classifier parameters
         clf = DecisionTreeClassifier(max_depth=5)
         # encode labels
-        buildings_sample['Slope_encoded'] = buildings_sample['Slope'].map({'low': np.uint16(42), 'high': np.uint16(40)})
+        buildings_sample['Slope_encoded'] = buildings_sample['Slope'].map({'low': 42, 'high': 40})
 
         # Select these rows for the training set
         build_train = buildings_sample[buildings_sample['Model']=='training']

environment.yml

@@ -21,7 +21,7 @@ dependencies:
   - geemap=0.32.0
   - pip=23.3.1
   - boto3=1.34.124
-  - scikit-learn=1.5.0
+  - scikit-learn=1.5.1
   - pip:
       - git+https://github.com/isciences/exactextract
       - overturemaps==0.6.0

setup.py

@@ -30,6 +30,6 @@
         "boto3",
         "exactextract",
         "overturemaps",
-        "scikit-learn>=1.5.0",
+        "scikit-learn>=1.5.1",
     ],
 )