Port and modernize building density code

Author: collijk

poetry.lock

@@ -34,7 +34,7 @@ python = ">=3.10, <3.13"
 click = "^8.1.8"
 requests = "^2.32.3"
 tqdm = "^4.67.1"
-rra-tools = "^1.0.17"
+rra-tools = "^1.0.20"
 geopandas = "^1.0.1"
 shapely = "^2.0.6"
 contextily = "^1.6.2"
@@ -60,6 +60,9 @@ pytest-github-actions-annotate-failures = "*"
 pytest-cov = "*"
 python-kacl = "*"
 ruff = ">=0.2.0"
+types-pyyaml = "^6.0.12.20241230"
+types-requests = "^2.32.0.20241016"
+types-tqdm = "^4.67.0.20241221"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]
@@ -87,6 +90,9 @@ ignore = [
     "RET505",   # Else after return, makes a lot of false positives
     "E501",     # Line too long, this is autoformatted
     "PLR0913",  # Too many args, bad check for CLIs
+    "T201",     # We're using print for now until I have time to think about logging
+    "RET504",   # Unneccesary assignment before return.  I like this pattern for debugging
+    "PD901",    # df is fine
 ]
 
 [tool.ruff.lint.per-file-ignores]
@@ -131,17 +137,18 @@ exclude_lines = [
 # This is the global mypy configuration.
 # Avoid changing this!
 strict = true  # See all the enabled flags `mypy --help | grep -A 10 'Strict mode'`
-disallow_any_unimported = true
+disallow_any_unimported = false
 
 # If you need to ignore something for some specific module,
 # add overrides for them. Avoid changing the global config!
 # For example:
-# [[tool.mypy.overrides]]
-# module = [
-#  "my_unpyted_dependency1.*",
-#  "my_unpyted_dependency2.*"
-# ]
-# ignore_missing_imports = true
+[[tool.mypy.overrides]]
+module = [
+    "affine.*",
+    "geopandas.*",
+    "shapely.*",
+]
+ignore_missing_imports = true
 
 # [[tool.mypy.overrides]]
 # module = [

pyproject.toml

@@ -2,8 +2,8 @@
 
 from rra_building_density import (
     extract,
-    format,
     postprocess,
+    process,
 )
 
 
@@ -17,7 +17,7 @@ def bdtask() -> None:
     """Run an individual modeling task in the building density pipeline."""
 
 
-for module in [extract, format, postprocess]:
+for module in [extract, process, postprocess]:
     runners = getattr(module, "RUNNERS", {})
     task_runners = getattr(module, "TASK_RUNNERS", {})
 

src/rra_building_density/cli.py

@@ -80,6 +80,7 @@ def with_time_point(
         convert=choices is not None and allow_all,
     )
 
+
 def with_version(
     choices: Collection[str],
     *,
@@ -93,24 +94,27 @@ def with_version(
         convert=allow_all,
     )
 
+
 def with_tile_size() -> ClickOption[_P, _T]:
-    return ClickOption(
+    return click.option(
         "--tile-size",
         type=int,
         default=512,
         help="The number of pixels in each tile dimension.",
         show_default=True,
     )
 
+
 def with_block_size() -> ClickOption[_P, _T]:
-    return ClickOption(
+    return click.option(
         "--block-size",
         type=int,
         default=16,
         help="The number of tiles in each block dimension",
         show_default=True,
     )
 
+
 def with_block_key() -> ClickOption[_P, _T]:
     return click.option(
         "--block-key",
@@ -120,8 +124,9 @@ def with_block_key() -> ClickOption[_P, _T]:
         help="Block key of block to run.",
     )
 
+
 def with_resolution(
-    choices: Collection[int],
+    choices: Collection[str],
     *,
     allow_all: bool = False,
 ) -> ClickOption[_P, _T]:

src/rra_building_density/cli_options.py

@@ -1,10 +1,9 @@
 import itertools
 from pathlib import Path
-import pyproj
 
+import pyproj
 from pydantic import BaseModel, model_validator
 
-
 RRA_ROOT = Path("/mnt/team/rapidresponse/")
 RRA_CREDENTIALS_ROOT = RRA_ROOT / "priv" / "shared" / "credentials"
 RRA_BINARIES_ROOT = RRA_ROOT / "priv" / "shared" / "bin"
@@ -26,30 +25,34 @@
 GHSL_TIME_POINTS = [f"{y}q1" for y in GHSL_YEARS]
 
 MICROSOFT_TIME_POINTS = {
-    "2": [f"{y}q{q}" for q, y in itertools.product(range(1, 5), range(2018, 2024))][:-1],
+    "2": [f"{y}q{q}" for q, y in itertools.product(range(1, 5), range(2018, 2024))][
+        :-1
+    ],
     "3": ["2023q3"],
     "4": ["2023q4"],
 }
 MICROSOFT_VERSIONS = list(MICROSOFT_TIME_POINTS)
 
-ALL_TIME_POINTS = sorted(set(GHSL_TIME_POINTS) | set().union(*MICROSOFT_TIME_POINTS.values()))
+ALL_TIME_POINTS = sorted(
+    set(GHSL_TIME_POINTS) | set().union(*MICROSOFT_TIME_POINTS.values())
+)
 
 
 class CRS(BaseModel):
     name: str
-    bounds: tuple[float, float, float, float] | None = None
+    bounds: tuple[float, float, float, float]
     code: str = ""
     proj_string: str = ""
 
     @model_validator(mode="after")
-    def validate_code_or_proj_string(self):
+    def validate_code_or_proj_string(self) -> "CRS":
         if not self.code and not self.proj_string:
             msg = "Either code or proj_string must be provided."
             raise ValueError(msg)
         return self
 
     @model_validator(mode="after")
-    def validate_code_and_proj_string(self):
+    def validate_code_and_proj_string(self) -> "CRS":
         if self.code and self.proj_string:
             code_proj = pyproj.CRS.from_user_input(self.code)
             proj_proj = pyproj.CRS.from_user_input(self.proj_string)
@@ -58,7 +61,7 @@ def validate_code_and_proj_string(self):
                 raise ValueError(msg)
         return self
 
-    def to_pyproj(self):
+    def to_pyproj(self) -> pyproj.CRS:
         if self.proj_string:
             return pyproj.CRS.from_proj4(self.proj_string)
         return pyproj.CRS.from_user_input(self.code)
@@ -69,17 +72,18 @@ def to_pyproj(self):
         name="WGS84",
         code="EPSG:4326",
         proj_string="+proj=longlat +datum=WGS84 +no_defs +type=crs",
-        bounds=(-180., -90., 180., 90.),
+        bounds=(-180.0, -90.0, 180.0, 90.0),
     ),
     "wgs84_anti_meridian": CRS(
         name="WGS84 Anti-Meridian",
         proj_string="+proj=longlat +lon_0=180 +datum=WGS84 +no_defs +type=crs",
-        bounds=(-180., -90., 180., 90.),
+        bounds=(-180.0, -90.0, 180.0, 90.0),
     ),
     "itu_anti_meridian": CRS(
         name="PDC Mercator",
         code="EPSG:3832",
         proj_string="+proj=merc +lon_0=150 +k=1 +x_0=0 +y_0=0 +datum=WGS84 +units=m +no_defs +type=crs",
+        bounds=(-5711803.07, -8362698.55, 15807367.69, 10023392.49),
     ),
     "mollweide": CRS(
         name="Mollweide",
@@ -107,6 +111,7 @@ def to_pyproj(self):
         name="Web Mercator",
         code="EPSG:3857",
         proj_string="+proj=merc +a=6378137 +b=6378137 +lat_ts=0 +lon_0=0 +x_0=0 +y_0=0 +k=1 +units=m +nadgrids=@null +wktext +no_defs +type=crs",
+        bounds=(-20037508.34, -20048966.1, 20037508.34, 20048966.1),
     ),
 }
 

src/rra_building_density/constants.py

@@ -1,6 +1,6 @@
 import itertools
-from typing import Any
 from pathlib import Path
+from typing import Any
 
 import geopandas as gpd
 import rasterra as rt
@@ -9,7 +9,6 @@
 from pydantic import BaseModel
 from rra_tools.shell_tools import mkdir, touch
 
-
 from rra_building_density import constants as bdc
 
 
@@ -347,4 +346,4 @@ def save_raster_to_cog(
         "driver": "COG",
         "overview_resampling": resampling,
     }
-    save_raster(raster, output_path, num_cores, **cog_save_params)
+    save_raster(raster, output_path, num_cores, **cog_save_params)