Handling missing dates in SearchEpc class

backend/SearchEpc.py

@@ -30,7 +30,7 @@ vartypes = {
     'environment-impact-potential': "Int64",
     'glazed-type': 'str',
     'heating-cost-current': 'float',
-    'address3': 'str',
+    # 'address3': 'str',
     'mainheatcont-description': 'str',
     'sheating-energy-eff': 'str',
     'property-type': 'str',
@@ -40,7 +40,7 @@ vartypes = {
     'mechanical-ventilation': 'str',
     'hot-water-cost-current': 'str',
     'county': 'str',
-    'postcode': 'str',
+    # 'postcode': 'str',
     'solar-water-heating-flag': 'str',
     'constituency': 'str',
     'co2-emissions-potential': 'float',
@@ -55,7 +55,7 @@ vartypes = {
     # 'inspection-date': str,
     'mains-gas-flag': 'str',
     'co2-emiss-curr-per-floor-area': 'float',
-    'address1': 'str',
+    # 'address1': 'str',
     'heat-loss-corridor': 'str',
     'flat-storey-count': "Int64",
     'constituency-label': 'str',
@@ -67,7 +67,7 @@ vartypes = {
     'roof-description': 'str',
     'floor-energy-eff': 'str',
     'number-habitable-rooms': 'float',
-    'address2': 'str',
+    # 'address2': 'str',
     'hot-water-env-eff': 'str',
     'posttown': 'str',
     'mainheatc-energy-eff': 'str',
@@ -98,7 +98,7 @@ vartypes = {
     # 'lodgement-date',
     'extension-count': "Int64",
     'mainheatc-env-eff': 'str',
-    'lmk-key': 'str',
+    # 'lmk-key': 'str',
     'wind-turbine-count': "Int64",
     'tenure': 'str',
     'floor-level': 'str',
@@ -575,6 +575,11 @@ class SearchEpc:
             property_type=property_type
         )
 
+        # If we have missing lodgment date, we fill it with inspection-date
+        epc_data["lodgement-datetime"] = epc_data["lodgement-datetime"].fillna(epc_data["inspection-date"])
+        # If we still have missing dates, we set it to the mean of the non NA dates
+        epc_data["lodgement-datetime"] = epc_data["lodgement-datetime"].fillna(epc_data["lodgement-datetime"].mean())
+
         # For each attribute, we need to determine the datatype and use an appropriate method
         # to estimate.
         estimated_epc = {}

etl/eligibility/ha_15_32/ha_analysis_batch_3.py

@@ -1135,6 +1135,7 @@ def get_epc_data(
         scoring_data = []
         nodata = []
         failed_model_rows = []
+        # Failed at index 13691
         for index, property_meta in tqdm(asset_list.iterrows(), total=len(asset_list)):
 
             if property_meta["matching_postcode"] is None: