Script runs without error

DOI-USGS · Aug 8, 2024 · cfb29a8 · cfb29a8
1 parent d8bd6cb
commit cfb29a8
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 6 deletions.
diff --git a/demos/nawqa_data_pull/README.md b/demos/nawqa_data_pull/README.md
@@ -1,6 +1,9 @@
 # Retrieva data from the National Water Quality Assessment Program (NAWQA)
 
-This examples walks through using lithops to retrieve data from every NAWQA monitoring site, then write the results to a parquet filel on s3.
+This examples walks through using lithops to retrieve data from every NAWQA
+monitoring site, then write the results to a parquet filel on s3. Also
+searches the NLDI for neighboring sites with NAWQA data and merges those
+data assuming the monitoring site was relocated.
 
 1. Set up a Python environment
 ```bash

diff --git a/demos/nawqa_data_pull/lithops.yaml b/demos/nawqa_data_pull/lithops.yaml
@@ -7,7 +7,7 @@ aws:
 
 aws_lambda:
     execution_role: arn:aws:iam::807615458658:role/lambdaLithopsExecutionRole
-    runtime: discontinuum-runtime
+    runtime: dataretrieval-runtime
     runtime_memory: 2000
 
 aws_s3:

diff --git a/demos/nawqa_data_pull/retrieve_nawqa_with_lithops.py b/demos/nawqa_data_pull/retrieve_nawqa_with_lithops.py
@@ -43,21 +43,24 @@ def find_neighboring_sites(site, search_factor=0.05):
     """
     site_df, _ = nwis.get_info(sites=site)
     drain_area_sq_mi = site_df["drain_area_va"].values[0]
-    distance = _estimate_watershed_length_km(drain_area_sq_mi)
+    length = _estimate_watershed_length_km(drain_area_sq_mi)
+    search_distance = length * search_factor
+    # clip between 1 and 9999km
+    search_distance = max(1.0, min(9999.0, search_distance))
 
     upstream_gdf = nldi.get_features(
         feature_source="WQP",
         feature_id=f"USGS-{site}",
         navigation_mode="UM",
-        distance=distance * search_factor,
+        distance=search_distance,
         data_source="nwissite",
         )
 
     downstream_gdf = nldi.get_features(
         feature_source="WQP",
         feature_id=f"USGS-{site}",
         navigation_mode="DM",
-        distance=distance * search_factor,
+        distance=search_distance,
         data_source="nwissite",
         )
 
@@ -101,7 +104,7 @@ def _estimate_watershed_length_km(drain_area_sq_mi):
         )
 
     site_list = site_df['SITE_QW_ID'].to_list()
-    site_list = site_list[:4]  # prune for testing
+    # site_list = site_list[:4]  # prune for testing
 
     fexec = lithops.FunctionExecutor(config_file="lithops.yaml")
     futures = fexec.map(map_retrieval, site_list)