From fa5148228bac3819429d39b10b7edbbe8e75abfe Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Wed, 6 Dec 2023 16:33:22 +0000
Subject: [PATCH] completed merge of ha15 and ha32

---
 backend/SearchEpc.py                      | 32 +++++++++++++
 etl/eligibility/ha_15_32/app.py           | 55 ++++-------------------
 etl/eligibility/ha_15_32/requirements.txt |  4 +-
 3 files changed, 43 insertions(+), 48 deletions(-)
 create mode 100644 backend/SearchEpc.py

diff --git a/backend/SearchEpc.py b/backend/SearchEpc.py
new file mode 100644
index 00000000..41fbbb0f
--- /dev/null
+++ b/backend/SearchEpc.py
@@ -0,0 +1,32 @@
+from epc_api.client import EpcClient
+
+class SearchEpc:
+    """
+    Given address information about a home, this class is responsible for retrieving the EPC data associated
+    to the property.
+
+    For a home, we might have address lines 1, 2, 3 and 4, as well as a postcode.
+
+    Often, simply searching the EPC database with address line 1 and postcode will be enough to find
+    the property, but there are some cases where this is not true and we might need to utilise other
+    combinations about the home to find the property
+    """
+
+    def __init__(self, address1, postcode, address2=None, address3=None, address4=None):
+        """
+        Address lines 1 and postcode are mandatory fields. The other address lines are optional
+        but can be used to find the epc for the home, if address1 and postcode are insufficient
+        :param address1: string, propery's address line 1
+        :param postcode: string, propery's postcode
+        :param address2: string, optional, propery's address line 2
+        :param address3: string, optional, propery's address line 3
+        :param address4: string, optional, propery's address line 4
+        """
+
+        self.address1 = address1
+        self.postcode = postcode
+        self.address2 = address2
+        self.address3 = address3
+        self.address4 = address4
+
+    def search(self):
diff --git a/etl/eligibility/ha_15_32/app.py b/etl/eligibility/ha_15_32/app.py
index cf836439..90229801 100644
--- a/etl/eligibility/ha_15_32/app.py
+++ b/etl/eligibility/ha_15_32/app.py
@@ -155,7 +155,9 @@ def marge_ha_32(asset_list, identified_addresses):
     if missed.shape[0] != 36:
         raise ValueError("We have a problem here, investigate me, missings beyond the Hessle Road addresses")
 
-    # TODO: Finish me
+    # Finally, we return the data we need
+
+    return merged_data, dropped_identified_merge_keys
 
 
 def merge_ha_15(asset_list, identified_addresses):
@@ -303,55 +305,14 @@ def merge_ha_15(asset_list, identified_addresses):
         ~identified_addresses["merge_key"].isin(merged_data["merge_key4"])
         ]
 
-    if ha == "ha32":
-        if missed.shape[0] != 36:
-            raise ValueError("We have a problem here, investigate me, missings beyond the Hessle Road addresses")
+    if missed.shape[0]:
+        raise ValueError("We have a problem here, investigate me, should not have any missings for ha15")
 
-    missed.shape
-
-    missed["Address"].unique()
-
-    len([m for m in missed["Address"].unique() if "Mary Mac" in m])
-
-    a = identified_addresses[
-        identified_addresses["Address"].str.contains("103 Priory Crescent")
-    ]
-    b = asset_list[
-        asset_list["Address Line 1"].str.contains("103 Priory Crescent")
-    ]
-
-    a["merge_key"]
-    b["merge_key"]
-    b["merge_key2"]
-    b["merge_key3"]
-
-    identified_addresses["merge_key"].isin(merged_data["merge_key"])
-
-    identified_addresses["merge_key"].isin(asset_list["merge_key"]).sum()
-    identified_addresses["merge_key2"].isin(asset_list["merge_key2"]).sum()
-
-    # Find merge keys not in the identified addresses
-
-    missed = identified_addresses[
-        ~identified_addresses["merge_key"].isin(merged_data["merge_key"])
-    ]
-
-    identified_addresses[
-        (identified_addresses["Address"].str.contains("Ashbury Court"))
-    ]
-
-    asset_list[
-        (asset_list["Street"].str.contains("Ashbury Court"))
-    ]
-
-    # Drop the UPRN column from the merged data
-    merged_data = merged_data.drop(columns=["UPRN"])
-
-    return merged_data
+    return merged_data, dropped_identified_merge_keys
 
 
 def app():
     ha32_asset_list, ha15_asset_list, ha32_identified_addresses, ha15_identified_addresses = load_data()
 
-    ha32 = marge_ha_32(asset_list=ha32_asset_list, identified_addresses=ha32_identified_addresses)
-    ha15 = merge_ha_15(asset_list=ha15_asset_list, identified_addresses=ha15_identified_addresses)
+    ha32, _ = marge_ha_32(asset_list=ha32_asset_list, identified_addresses=ha32_identified_addresses)
+    ha15, _ = merge_ha_15(asset_list=ha15_asset_list, identified_addresses=ha15_identified_addresses)
diff --git a/etl/eligibility/ha_15_32/requirements.txt b/etl/eligibility/ha_15_32/requirements.txt
index 1411a4a0..390d7de9 100644
--- a/etl/eligibility/ha_15_32/requirements.txt
+++ b/etl/eligibility/ha_15_32/requirements.txt
@@ -1 +1,3 @@
-pandas
\ No newline at end of file
+pandas
+pydantic==1.10.11
+epc-api-python==1.0.2