From a948688df6c4e220be03688700834fbb78701ccd Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Wed, 27 Dec 2023 10:28:06 +0000
Subject: [PATCH] set up get_epc_data function

---
 etl/eligibility/ha_15_32/ha16_app.py | 98 ++++++++++++++++++++++++++++
 1 file changed, 98 insertions(+)

diff --git a/etl/eligibility/ha_15_32/ha16_app.py b/etl/eligibility/ha_15_32/ha16_app.py
index 402527df..f930452e 100644
--- a/etl/eligibility/ha_15_32/ha16_app.py
+++ b/etl/eligibility/ha_15_32/ha16_app.py
@@ -248,3 +248,101 @@ def load_data():
     data["warmfront_identified"] = data["warmfront_identified"].fillna(False)
 
     return data
+
+
+def get_epc_data(data, cleaned, cleaning_data, created_at):
+    scoring_data = []
+    results = []
+    nodata = []
+
+    for _, property_meta in tqdm(data.iterrows(), total=len(data)):
+        searcher = SearchEpc(
+            address1=property_meta["HouseNo"],
+            postcode=property_meta["Postcode"],
+            size=1000
+        )
+        searcher.search()
+
+        if searcher.data is None:
+            nodata.append(property_meta)
+            continue
+
+        newest_epc, older_epcs, full_sap_epc = searcher.retrieve(address=property_meta["Address"])
+        # We also want to get the penultimate epc
+        penultimate_epc, _ = searcher.filter_newest_epc(older_epcs)
+        if not penultimate_epc:
+            penultimate_epc = newest_epc
+
+        eligibility = Eligibility(epc=newest_epc, cleaned=cleaned)
+        eligibility.check_gbis_warmfront()
+        eligibility.check_eco4_warmfront()
+
+        if (not eligibility.eco4_warmfront["eligible"]) and (not eligibility.gbis_warmfront) and (
+            property_meta["warmfront_identified"]
+        ):
+            eligibility = Eligibility(epc=penultimate_epc, cleaned=cleaned)
+            eligibility.check_gbis_warmfront()
+            eligibility.check_eco4_warmfront()
+            # If this is the case, we need to update the older epcs
+            older_epcs = [
+                x for x in older_epcs if x["lmk-key"] not in [newest_epc["lmk-key"], penultimate_epc["lmk-key"]]
+            ]
+
+        # Full checks
+        eligibility.check_gbis()
+        eligibility.check_eco4()
+
+        if eligibility.eco4_warmfront["eligible"]:
+            scoring_dictionary = prepare_model_data_row(
+                property_id=eligibility.epc["uprn"],
+                modelling_epc=eligibility.epc,
+                cleaned=cleaned,
+                cleaning_data=cleaning_data,
+                created_at=created_at,
+                old_data=older_epcs,
+                full_sap_epc=full_sap_epc
+            )
+            scoring_data.extend(scoring_dictionary)
+
+        results.append(
+            {
+                "row_id": property_meta["row_id"],
+                "uprn": eligibility.epc["uprn"],
+                "Address": property_meta["Address"],
+                "Postcode": property_meta["Postcode"],
+                "property_type": eligibility.epc["property-type"],
+                "gbis_eligible": eligibility.gbis_warmfront,
+                "eco4_eligible": eligibility.eco4_warmfront["eligible"],
+                "eco4_message": eligibility.eco4_warmfront["message"],
+                "sap": float(eligibility.epc["current-energy-efficiency"]),
+                "gbis_eligible_future": eligibility.gbis["eligible"],
+                "gbis_eligible_future_message": eligibility.gbis["message"],
+                "eco4_eligible_future": eligibility.eco4["eligible"],
+                "eco4_eligible_future_message": eligibility.eco4["message"],
+                # Property components
+                "roof": eligibility.roof["clean_description"],
+                "walls": eligibility.walls["clean_description"],
+                "cavity_type": eligibility.cavity["type"],
+                "heating": eligibility.epc["mainheat-description"],
+                "tenure": eligibility.tenure,
+                "date_epc": eligibility.epc["lodgement-date"],
+            }
+        )
+
+
+def app():
+    data = load_data()
+
+    data["row_id"] = ["ha16" + str(i) for i in range(0, len(data))]
+
+    cleaned = read_from_s3(
+        s3_file_name="cleaned_epc_data/cleaned.bson",
+        bucket_name="retrofit-data-dev"
+    )
+    cleaned = msgpack.unpackb(cleaned, raw=False)
+
+    cleaning_data = read_parquet_from_s3(
+        bucket_name="retrofit-data-dev", file_key="sap_change_model/cleaning_dataset.parquet",
+    )
+
+    created_at = datetime.now().isoformat()