From d557653129a3aac4b8b45d1c5d6a14d01ac6ac8b Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Wed, 24 Jan 2024 14:16:33 +0000
Subject: [PATCH] patched issue with cleaned lookup

---
 .../ha_15_32/ha_analysis_batch_3.py           | 86 +++++++++++++++++++
 1 file changed, 86 insertions(+)

diff --git a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
index 9143df5f..85486e17 100644
--- a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
+++ b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
@@ -609,6 +609,75 @@ def get_epc_data(
                 }
             )
 
+        scoring_df = pd.DataFrame(scoring_data)
+        scoring_df = scoring_df.drop(
+            columns=[
+                "rdsap_change", "heat_demand_change", "carbon_change", "sap_ending", "heat_demand_ending",
+                "carbon_ending"
+            ]
+        )
+
+        model_api = ModelApi(portfolio_id="-".join([ha_name, "eligibility"]), timestamp=created_at)
+
+        all_predictions = model_api.predict_all(
+            df=scoring_df,
+            bucket="retrofit-data-dev",
+            prediction_buckets={
+                "sap_change_predictions": "retrofit-sap-predictions-dev",
+                "heat_demand_predictions": "retrofit-heat-predictions-dev",
+                "carbon_change_predictions": "retrofit-carbon-predictions-dev"
+            }
+        )
+
+        results_df = pd.DataFrame(results)
+
+        predictions = all_predictions["sap_change_predictions"].copy()
+
+        predictions = predictions.rename(columns={"property_id": "row_id"}).merge(
+            results_df[["row_id", "sap"]], how="left", on="row_id"
+        )
+        predictions["sap_uplift"] = predictions["predictions"] - predictions["sap"]
+        predictions = predictions.groupby("row_id")["sap_uplift"].sum().reset_index()
+
+        results_df = results_df.merge(
+            predictions[["sap_uplift", "row_id"]],
+            how="left",
+            on="row_id"
+        )
+        results_df["post_install_sap"] = results_df["sap"] + results_df["sap_uplift"]
+
+        eligibility_assessment = []
+        for _, row in results_df[results_df["eco4_eligible"] == True].iterrows():
+            # The upgrade requirements are dependent on the current SAP
+
+            # If the property is an F or G, it only needs to upgrade to an %
+            if row["sap"] <= 38:
+                if row["post_install_sap"] >= 57:
+                    eligibility_classification = "highest confidence"
+                elif row["post_install_sap"] >= 55:
+                    eligibility_classification = "high confidence"
+                elif row["post_install_sap"] >= 53:
+                    eligibility_classification = "medium confidence"
+                else:
+                    eligibility_classification = "unlikely"
+            else:
+
+                if row["post_install_sap"] >= 71:
+                    eligibility_classification = "highest confidence"
+                elif row["post_install_sap"] >= 69:
+                    eligibility_classification = "high confidence"
+                elif row["post_install_sap"] >= 67:
+                    eligibility_classification = "medium confidence"
+                else:
+                    eligibility_classification = "unlikely"
+
+            eligibility_assessment.append(
+                {
+                    "row_id": row["row_id"],
+                    "eligibility_classification": eligibility_classification
+                }
+            )
+
 
 def analyse_ha_data():
     """
@@ -706,6 +775,23 @@ def app():
         ]
     )
 
+    # We treat unknown loft insulation as no insulation
+    cleaned["roof-description"].extend(
+        [
+            {'original_description': 'Pitched, Unknown loft insulation', 'clean_description': 'Pitched, no insulation',
+             'thermal_transmittance': None, 'thermal_transmittance_unit': None, 'is_pitched': True,
+             'is_roof_room': False,
+             'is_loft': False, 'is_flat': False, 'is_thatched': False, 'is_at_rafters': False, 'is_assumed': True,
+             'has_dwelling_above': False, 'is_valid': True, 'insulation_thickness': 'none'}
+        ]
+    )
+
+    # We patch this record because there is another property below
+    for x in cleaned["floor-description"]:
+        if x["original_description"] == '(Same dwelling below) insulated (assumed)':
+            x["another_property_below"] = True
+            x["thermal_transmittance"] = 0
+
     cleaning_data = read_dataframe_from_s3_parquet(
         bucket_name="retrofit-data-dev", file_key="sap_change_model/cleaning_dataset.parquet",
     )