Fix using Ruff

Author: f-PLT

geospatial_tools/geotools_types.py

@@ -1,7 +1,5 @@
 """This module contains constants and functions pertaining to data types."""
 
-from typing import Union
-
 from shapely.geometry import (
     GeometryCollection,
     LineString,
@@ -13,4 +11,4 @@
 )
 
 BBoxLike = tuple[float, float, float, float]
-IntersectsLike = Union[Point, Polygon, LineString, MultiPolygon, MultiPoint, MultiLineString, GeometryCollection]
+IntersectsLike = Point | Polygon | LineString | MultiPolygon | MultiPoint | MultiLineString | GeometryCollection

geospatial_tools/utils.py

@@ -182,6 +182,7 @@ def create_crs(dataset_crs: str | int, logger=LOGGER):
             return CRS.from_epsg(recovered_code)
 
     logger.error(f"Encountered problem while trying to format EPSG code from input : [{dataset_crs}]")
+    return None
 
 
 def download_url(url: str, filename: str | pathlib.Path, overwrite: bool = False, logger=LOGGER) -> pathlib.Path | None:

geospatial_tools/vector.py

@@ -458,11 +458,13 @@ def add_and_fill_contained_column(
     logger.info(f"Selecting all vector features that are within {feature_name}")
     selected_features = select_all_within_feature(polygon_feature=polygon_feature, vector_features=vector_features)
     logger.info(f"Writing [{feature_name}] to selected vector features")
-    [  # pylint: disable=W0106
-        vector_features.at[idx, vector_column_name].add(feature_name) for idx in selected_features.index
-    ]
+
+    vector_features.loc[selected_features.index, vector_column_name] = vector_features.loc[
+        selected_features.index, vector_column_name
+    ].apply(lambda s: s | {feature_name})
 
 
+# Potential outdated function
 def find_and_write_all_contained_features(
     polygon_features: gpd.GeoDataFrame,
     polygon_column: str,

pyproject.toml

@@ -203,12 +203,16 @@ ignore = [
   "E266",  # too many leading '#' for comments
   "E501",  # line too long (we enforce via line-length instead)
   "RET504",
-  "RUF013"
+  "RUF013",
+  "PTH123"
 ]
 
 [tool.ruff.lint.pydocstyle]
 convention = "numpy" # Corresponds to flake8's docstring-convention and docformatter style.
 
+[tool.ruff.lint.pylint]
+max-args = 16
+
 [tool.ruff.lint.mccabe]
 # cyclomatic complexity
 max-complexity = 18

tests/test_notebooks/test_planetary_computer_sentinel2.ipynb

@@ -1810,8 +1810,9 @@
     "\n",
     "intersect_polygons_subset_filename = TEST_TMP_DIR / \"intersecting_polygon_grid_10km_subset.gpkg\"\n",
     "print(\"Starting intersect selection\")\n",
-    "intersect_polygons_subset = select_polygons_by_location(intersecting_polygons, s2_grid_subset, predicate=\"within\",\n",
-    "                                                        num_of_workers=4)\n",
+    "intersect_polygons_subset = select_polygons_by_location(\n",
+    "    intersecting_polygons, s2_grid_subset, predicate=\"within\", num_of_workers=4\n",
+    ")\n",
     "# intersect_polygons_subset = gpd.read_file(intersect_polygons_subset_filename)\n",
     "\n",
     "# Optionally save to a new file\n",
@@ -1842,11 +1843,13 @@
     "vector_column_name = \"s2_tiles\"\n",
     "\n",
     "# Initiating our client\n",
-    "best_products_client = BestProductsForFeatures(sentinel2_tiling_grid=s2_grid_subset,\n",
-    "                                               sentinel2_tiling_grid_column=s2_feature_name_columns,\n",
-    "                                               vector_features=intersect_polygons_subset,\n",
-    "                                               vector_features_column=vector_column_name,\n",
-    "                                               max_cloud_cover=15)"
+    "best_products_client = BestProductsForFeatures(\n",
+    "    sentinel2_tiling_grid=s2_grid_subset,\n",
+    "    sentinel2_tiling_grid_column=s2_feature_name_columns,\n",
+    "    vector_features=intersect_polygons_subset,\n",
+    "    vector_features_column=vector_column_name,\n",
+    "    max_cloud_cover=15,\n",
+    ")"
    ]
   },
   {
@@ -1970,7 +1973,7 @@
     "\n",
     "best_results_path = TEST_TMP_DIR / \"vector_tiles_with_s2tiles_subset.gpkg\"\n",
     "best_results = best_products_client.select_best_products_per_feature()\n",
-    "to_geopackage(best_results, best_results_path)\n"
+    "to_geopackage(best_results, best_results_path)"
    ]
   },
   {
@@ -2201,10 +2204,9 @@
     "download_directory = TEST_TMP_DIR / \"example_s2_download_and_processing\"\n",
     "\n",
     "for p in product_list:\n",
-    "    processed_product = download_and_process_sentinel2_asset(product_id=p,\n",
-    "                                                             product_bands=bands,\n",
-    "                                                             base_directory=download_directory,\n",
-    "                                                             target_projection=5070)\n",
+    "    processed_product = download_and_process_sentinel2_asset(\n",
+    "        product_id=p, product_bands=bands, base_directory=download_directory, target_projection=5070\n",
+    "    )\n",
     "\n",
     "    product_asset_list.append(processed_product)"
    ]
@@ -2238,7 +2240,7 @@
    "source": [
     "for p in product_asset_list:\n",
     "    print(f\"Asset ID : [{p.asset_id}]\")\n",
-    "    print(f\"Reprojected ID path : \\n[{p.reprojected_asset_path}]\\n\")\n"
+    "    print(f\"Reprojected ID path : \\n[{p.reprojected_asset_path}]\\n\")"
    ]
   },
   {
@@ -2255,8 +2257,10 @@
    "source": [
     "# Here, we are creating a new Asset object simply for convenience, from the printed outputs above\n",
     "\n",
-    "product = Asset(asset_id=\"S2A_MSIL2A_20240705T185921_R013_T10SDJ_20240706T050346\",\n",
-    "                reprojected_asset=download_directory / \"S2A_MSIL2A_20240705T185921_R013_T10SDJ_20240706T050346_reprojected.tif\", )"
+    "product = Asset(\n",
+    "    asset_id=\"S2A_MSIL2A_20240705T185921_R013_T10SDJ_20240706T050346\",\n",
+    "    reprojected_asset=download_directory / \"S2A_MSIL2A_20240705T185921_R013_T10SDJ_20240706T050346_reprojected.tif\",\n",
+    ")"
    ]
   },
   {
@@ -2298,7 +2302,6 @@
     }
    ],
    "source": [
-    "\n",
     "s2_product_id = product.asset_id\n",
     "product_path = product.reprojected_asset_path\n",
     "product_id_series = group_by_product[group_by_product[\"best_s2_product_id\"] == s2_product_id]\n",
@@ -2340,10 +2343,12 @@
     }
    ],
    "source": [
-    "clip_list = clip_raster_with_polygon(raster_image=product_path,\n",
-    "                                     polygon_layer=vector_features_path,\n",
-    "                                     base_output_filename=s2_product_id,\n",
-    "                                     output_dir=download_directory / \"test_sentinel2_clip\")"
+    "clip_list = clip_raster_with_polygon(\n",
+    "    raster_image=product_path,\n",
+    "    polygon_layer=vector_features_path,\n",
+    "    base_output_filename=s2_product_id,\n",
+    "    output_dir=download_directory / \"test_sentinel2_clip\",\n",
+    ")"
    ]
   },
   {

tests/test_notebooks/test_stac_api_tools.ipynb

@@ -107,10 +107,9 @@
     "end_year = 2024\n",
     "start_month = 6\n",
     "end_month = 7\n",
-    "date_ranges = create_date_range_for_specific_period(start_year=start_year,\n",
-    "                                                    end_year=end_year,\n",
-    "                                                    start_month_range=start_month,\n",
-    "                                                    end_month_range=end_month)\n",
+    "date_ranges = create_date_range_for_specific_period(\n",
+    "    start_year=start_year, end_year=end_year, start_month_range=start_month, end_month_range=end_month\n",
+    ")\n",
     "\n",
     "# Search arguments\n",
     "collection = \"sentinel-2-l2a\"\n",
@@ -122,10 +121,9 @@
     "\n",
     "# Searching for results\n",
     "search_client = StacSearch(PLANETARY_COMPUTER)\n",
-    "search_client.search_for_date_ranges(date_ranges=date_ranges,\n",
-    "                                     collections=collection,\n",
-    "                                     query=query,\n",
-    "                                     sortby=sortby, limit=100)\n",
+    "search_client.search_for_date_ranges(\n",
+    "    date_ranges=date_ranges, collections=collection, query=query, sortby=sortby, limit=100\n",
+    ")\n",
     "\n",
     "# Selecting optimal result\n",
     "search_client.sort_results_by_cloud_coverage()\n",
@@ -166,13 +164,17 @@
    "source": [
     "print(\"\\nSorted results\")\n",
     "for item in filtered_items:\n",
-    "    print(f\"Item: {item.id}, {item.datetime}, \"\n",
-    "          f\"Cloud cover: {item.properties['eo:cloud_cover']}, \"\n",
-    "          f\"Nodata: {item.properties['s2:nodata_pixel_percentage']}\")\n",
+    "    print(\n",
+    "        f\"Item: {item.id}, {item.datetime}, \"\n",
+    "        f\"Cloud cover: {item.properties['eo:cloud_cover']}, \"\n",
+    "        f\"Nodata: {item.properties['s2:nodata_pixel_percentage']}\"\n",
+    "    )\n",
     "\n",
-    "print(f\"\\nOptimal result: {optimal_result.id}, {optimal_result.datetime}, \"\n",
-    "      f\"Cloud cover: {optimal_result.properties['eo:cloud_cover']}, \"\n",
-    "      f\"Nodata: {optimal_result.properties['s2:nodata_pixel_percentage']}\")"
+    "print(\n",
+    "    f\"\\nOptimal result: {optimal_result.id}, {optimal_result.datetime}, \"\n",
+    "    f\"Cloud cover: {optimal_result.properties['eo:cloud_cover']}, \"\n",
+    "    f\"Nodata: {optimal_result.properties['s2:nodata_pixel_percentage']}\"\n",
+    ")"
    ]
   },
   {
@@ -266,9 +268,9 @@
    ],
    "source": [
     "merged = best_result.merge_asset(base_directory=file_base_path, delete_sub_items=True)\n",
-    "reprojected = best_result.reproject_merged_asset(target_projection=5070,\n",
-    "                                                 base_directory=file_base_path,\n",
-    "                                                 delete_merged_asset=True)"
+    "reprojected = best_result.reproject_merged_asset(\n",
+    "    target_projection=5070, base_directory=file_base_path, delete_merged_asset=True\n",
+    ")"
    ]
   },
   {