update to ruff

.cspell.json

@@ -4,6 +4,7 @@
   "words": [
     "autoload",
     "geodataframe",
+    "iloc",
     "notna",
     "quadkey",
     "quadkeys",

ruff.toml

@@ -61,8 +61,11 @@ ignore = [
     "Q000",    # bad-quotes-inline-string
     "RUF012",  # mutable-class-default
     "S106",    # hardcoded-password-func-arg
+    "S113",    # Probable use of requests call without timeout
+    "SIM115",  # Use context handler for opening files
     "S311",    # suspicious-non-cryptographic-random-usage
     "S320",    # suspicious-xmle-tree-usage
+    "S324",    # Probable use of insecure hash functions in `hashlib`: `md5`
     "S603",    # subprocess-without-shell-equals-true
     "S607",    # start-process-with-partial-path
     "S701",    # jinja2-autoescape-false

utils/chunk.py

@@ -6,6 +6,4 @@
 
 
 def chunk(full_list: list, chunk_size: int = 100):
-    return [
-        full_list[i * chunk_size : (i + 1) * chunk_size] for i in range((len(full_list) + chunk_size - 1) // chunk_size)
-    ]
+    return [full_list[i * chunk_size : (i + 1) * chunk_size] for i in range((len(full_list) + chunk_size - 1) // chunk_size)]

utils/geocode_addresses.py

@@ -44,9 +44,7 @@ def _process_result(result):
         for i in range(1, 7):
             if result.get("locations")[0].get(f"adminArea{i}Type") is None:
                 continue
-            admin_areas[result.get("locations")[0].get(f"adminArea{i}Type").lower()] = result.get("locations")[0].get(
-                f"adminArea{i}"
-            )
+            admin_areas[result.get("locations")[0].get(f"adminArea{i}Type").lower()] = result.get("locations")[0].get(f"adminArea{i}")
 
         return {
             "quality": quality,
@@ -81,15 +79,13 @@ def geocode_addresses(locations: list[Location], mapquest_api_key: str):
             # Catch invalid API key error before parsing the response
             if response.status_code == 401:
                 raise MapQuestAPIKeyError(
-                    "Failed geocoding property states due to MapQuest error. "
-                    "API Key is invalid with message: {response.content}."
+                    "Failed geocoding property states due to MapQuest error. " "API Key is invalid with message: {response.content}."
                 )
             results += response.json().get("results")
         except Exception as e:
             if response.status_code == 403:
                 raise MapQuestAPIKeyError(
-                    "Failed geocoding property states due to MapQuest error. "
-                    "Your MapQuest API Key is either invalid or at its limit."
+                    "Failed geocoding property states due to MapQuest error. " "Your MapQuest API Key is either invalid or at its limit."
                 )
             else:
                 raise e

utils/normalize_address.py

@@ -142,9 +142,7 @@ def normalize_address(address_val: str):
             normalized_address = _normalize_address_number(addr["AddressNumber"])
 
         if "StreetNamePreDirectional" in addr and addr["StreetNamePreDirectional"] is not None:
-            normalized_address = (
-                normalized_address + " " + _normalize_address_direction(addr["StreetNamePreDirectional"])
-            )
+            normalized_address = normalized_address + " " + _normalize_address_direction(addr["StreetNamePreDirectional"])
 
         if "StreetName" in addr and addr["StreetName"] is not None:
             normalized_address = normalized_address + " " + addr["StreetName"]
@@ -154,9 +152,7 @@ def normalize_address(address_val: str):
             normalized_address = normalized_address + " " + _normalize_address_post_type(addr["StreetNamePostType"])
 
         if "StreetNamePostDirectional" in addr and addr["StreetNamePostDirectional"] is not None:
-            normalized_address = (
-                normalized_address + " " + _normalize_address_direction(addr["StreetNamePostDirectional"])
-            )
+            normalized_address = normalized_address + " " + _normalize_address_direction(addr["StreetNamePostDirectional"])
 
         if "SubaddressType" in addr and addr["SubaddressType"] is not None:
             normalized_address = normalized_address + " " + _normalize_subaddress_type(addr["SubaddressType"])

utils/open_street_map.py

@@ -132,13 +132,7 @@ def get_node_coordinates(node_ids: list[int]):
 
         # Extract the latitude and longitude coordinates of the node from the response
         for element in data["elements"]:
-            if (
-                "type" in element
-                and element["type"] == "node"
-                and "id" in element
-                and "lat" in element
-                and "lon" in element
-            ):
+            if "type" in element and element["type"] == "node" and "id" in element and "lat" in element and "lon" in element:
                 lat = float(element["lat"])
                 lon = float(element["lon"])
                 # Check if coordinates are within valid range
@@ -260,9 +254,7 @@ def process_dataframe_for_osm_buildings(
 
     # check that the method is valid
     if method not in ["geometry_centroid", "osm_id", "lat_long"]:
-        raise ValueError(
-            f"Invalid processing method: {method}, must be one of ['geometry_centroid', 'osm_id', 'lat_long']"
-        )
+        raise ValueError(f"Invalid processing method: {method}, must be one of ['geometry_centroid', 'osm_id', 'lat_long']")
 
     results = []
     error_processing = []

utils/ubid.py

@@ -13,9 +13,7 @@
 def encode_ubid(geometry: Polygon) -> str:
     min_longitude, min_latitude, max_longitude, max_latitude = geometry.bounds
     centroid = geometry.centroid
-    ubid = encode(
-        min_latitude, min_longitude, max_latitude, max_longitude, centroid.y, centroid.x, codeLength=PAIR_CODE_LENGTH_
-    )
+    ubid = encode(min_latitude, min_longitude, max_latitude, max_longitude, centroid.y, centroid.x, codeLength=PAIR_CODE_LENGTH_)
     return ubid
 
 

utils/update_quadkeys.py

@@ -16,12 +16,12 @@ def update_quadkeys(quadkeys: list[int], save_directory: Path = Path("data/quadk
     Skip the download if it has already been downloaded, and it is up-to-date
     """
     save_directory.mkdir(parents=True, exist_ok=True)
-    df = pd.read_csv(save_directory / "dataset-links.csv")
+    df_update = pd.read_csv(save_directory / "dataset-links.csv")
 
     for quadkey in tqdm(quadkeys):
         download = True
         quadkey_file = save_directory / f"{quadkey}.geojsonl.gz"
-        rows = df[df["QuadKey"] == quadkey]
+        rows = df_update[df_update["QuadKey"] == quadkey]
         if rows.shape[0] == 1:
             url = rows.iloc[0]["Url"]
         elif rows.shape[0] > 1: