v4.5.14.4 fixed bug in aggregate_by_huc.py (#1404)

NOAA-OWP · Jan 31, 2025 · 662bdb5 · 662bdb5
1 parent 5be6514
commit 662bdb5
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 1 deletion.
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
@@ -1,6 +1,17 @@
 All notable changes to this project will be documented in this file.
 We follow the [Semantic Versioning 2.0.0](http://semver.org/) format.
 
+## v4.5.14.4 - 2025-01-31 - [PR#1404]https://github.com/NOAA-OWP/inundation-mapping/pull/1404
+
+This PR resolves warnings when running aggregate_by_huc.py with the bridge_flag option. The warnings happened because the GeoPandas read_file method does not support a dtype argument when reading GeoPackages. This PR also, modifies aggregate_by_huc.py to set the CRS for osm_bridge_points.gpkg. It will only set the CRS if the file does not already have a CRS defined.
+
+### Changes
+
+- `src/aggregate_by_huc.py`: Apply specific data types after reading the file and set a CRS for osm_bridge_points.gpkg.
+
+<br/><br/>
+
+
 ## v4.5.14.3 - 2025-01-31 - [PR#1413](https://github.com/NOAA-OWP/inundation-mapping/pull/1413)
 
 Implements a denylist for flow-based CatFIM (that uses the same conventions as the existing denylist functionality used in stage-based CatFIM. Adds CMUG1 to the denylist for flow-based CatFIM. 

diff --git a/src/aggregate_by_huc.py b/src/aggregate_by_huc.py
@@ -11,11 +11,17 @@
 
 import geopandas as gpd
 import pandas as pd
+from dotenv import load_dotenv
 
 from heal_bridges_osm import flows_from_hydrotable
 from utils.shared_functions import progress_bar_handler
 
 
+load_dotenv('/foss_fim/src/bash_variables.env')
+DEFAULT_FIM_PROJECTION_CRS = os.getenv('DEFAULT_FIM_PROJECTION_CRS')
+ALASKA_CRS = os.getenv('ALASKA_CRS')
+
+
 class HucDirectory(object):
     def __init__(self, fim_directory, huc_id, limit_branches=[]):
         self.fim_directory = fim_directory
@@ -205,7 +211,9 @@ def aggregate_bridge_pnts(self, branch_path, branch_id):
         if not os.path.isfile(bridge_filename):
             return
 
-        bridge_pnts = gpd.read_file(bridge_filename, dtype=self.bridge_dtypes)
+        bridge_pnts = gpd.read_file(bridge_filename)
+        for col, dtype in self.bridge_dtypes.items():
+            bridge_pnts[col] = bridge_pnts[col].astype(dtype)
         if bridge_pnts.empty:
             return
         hydrotable_filename = join(branch_path, f'hydroTable_{branch_id}.csv')
@@ -289,6 +297,15 @@ def agg_function(
                     ] = 1
                     # Write file
                     bridge_pnts = bridge_pnts.astype(self.bridge_dtypes, errors='ignore')
+
+                    # Set the CRS if it is not already set
+                    huc2Identifier = huc_id[:2]
+                    if bridge_pnts.crs is None:
+                        # Alaska
+                        if huc2Identifier == '19':
+                            bridge_pnts.set_crs(ALASKA_CRS, inplace=True)
+                        else:
+                            bridge_pnts.set_crs(DEFAULT_FIM_PROJECTION_CRS, inplace=True)
                     bridge_pnts.to_file(bridge_pnts_file, index=False, engine='fiona')
 
             # print(f"agg_by_huc for huc id {huc_id} is done")