Fix logging percentage

Author: davidgamez

functions-python/reverse_geolocation/src/scripts/reverse_geolocation_process_verifier.py

@@ -80,7 +80,7 @@
     },
 ]
 run_with_feed_index = (
-    6  # Set to an integer index to run with a specific feed from the list above
+    1  # Set to an integer index to run with a specific feed from the list above
 )
 
 
@@ -236,7 +236,7 @@ def create_test_data(feed_stable_id: str, feed_dict: Dict, db_session: Session =
     from gcp_storage_emulator.server import create_server
     from flask import Flask, Request
 
-    strategy = ReverseGeocodingStrategy.PER_POLYGON
+    strategy = ReverseGeocodingStrategy.PER_POINT
 
     feed_dict = feeds[run_with_feed_index]
     feed_stable_id = feed_dict["stable_id"]

functions-python/reverse_geolocation/src/strategy_extraction_per_point.py

@@ -32,8 +32,8 @@ def extract_location_aggregates_per_point(
         logger.warning("No stops to process")
         return
     batch_size = max(
-        int(total_stop_count / 20), total_stop_count
-    )  # Process 5% of the total stops in each batch
+        1, int(total_stop_count * 0.05)
+    )  # Process ~5% of the total stops in each batch
     for _, stop in stops_df.iterrows():
         if i % batch_size == 0:
             remaining_stops_count = total_stop_count - i

functions-python/reverse_geolocation/src/strategy_extraction_per_polygon.py

@@ -74,7 +74,7 @@ def extract_location_aggregates_per_polygon(
     total_stop_count = len(remaining_stops_df)
     last_seen_count = total_stop_count
     batch_size = max(
-        int(total_stop_count / 20), 0
+        1, int(total_stop_count * 0.05)
     )  # Process ~5% of the total stops in each batch
     stop_clustered_total = 0
     while not remaining_stops_df.empty: