minor tweak to asset list to make uprn int

etl/customers/gla_croydon_demo/asset_list.py

@@ -36,7 +36,7 @@ def app():
     epc_data["CURRENT_ENERGY_RATING"].value_counts(normalize=True)
 
     # For the purpose of the sample, take the properties have surveys done in the last 2 years
-    # This gives us 1023 remaining properties
+    # This gives us 1167 remaining properties
     two_years_ago = pd.Timestamp.now() - pd.DateOffset(days=int(2.5 * 365))
     epc_data = epc_data[epc_data["LODGEMENT_DATE"] >= two_years_ago]
 
@@ -45,7 +45,7 @@ def app():
     # 2) Unfilled cavity
     # 3) A roof that could be insulated (flat or pitched with no more than 50mm insulation)
     # 4) EPC E
-    # Different buckets of properties
+    # 12 properties
     archetype_1_sample = epc_data[
         epc_data["PROPERTY_TYPE"].isin(["House"]) &
         (epc_data["CURRENT_ENERGY_RATING"] == "E") &
@@ -69,6 +69,7 @@ def app():
     # 2) Unfilled cavity
     # 3) Another property above
     # 4) EPC E
+    # 14 properties here
     archetype_2_sample = epc_data[
         epc_data["PROPERTY_TYPE"].isin(["Flat"]) &
         (epc_data["CURRENT_ENERGY_RATING"] == "E") &
@@ -108,6 +109,7 @@ def app():
     archetype_4_sample_asset_list = archetype_4_sample[["UPRN", "ADDRESS1", "POSTCODE"]].copy()
     archetype_4_sample_asset_list["ARCHETYPE"] = "Archetype 4"
 
+    # 41 total properties
     asset_list = pd.concat(
         [
             archetype_1_sample_asset_list,
@@ -126,6 +128,8 @@ def app():
         }
     )
 
+    asset_list["uprn"] = asset_list["uprn"].astype(int)
+
     filename = f"{USER_ID}/{PORTFOLIO_ID}/inputs.csv"
     save_csv_to_s3(
         dataframe=asset_list,