Update preprocessing/pipeline_components.py

preprocessing/pipeline_components.py

@@ -7,10 +7,17 @@ from sklearn.base import BaseEstimator, TransformerMixin
 from scipy.stats import gaussian_kde
 from sklearn.preprocessing import StandardScaler
 from sklearn.neighbors import NearestNeighbors
-import pgeocode
 from datetime import datetime
 import pgeocode
-
+# IMMEDIATELY after importing pgeocode, force its STORAGE_DIR
+# This must be done before any pgeocode.Nominatim() calls
+try:
+    pgeocode.STORAGE_DIR = "/tmp/pgeocode"
+    # Ensure the directory exists as pgeocode might not create it if overridden this way
+    os.makedirs(pgeocode.STORAGE_DIR, exist_ok=True)
+    print(f"DEBUG: Successfully forced pgeocode.STORAGE_DIR to '{pgeocode.STORAGE_DIR}' and ensured directory exists.")
+except Exception as e:
+    print(f"ERROR: Failed to force pgeocode.STORAGE_DIR or create directory: {e}")
 
 class DataCleaner(BaseEstimator, TransformerMixin):
     def __init__(self):