From b26e44b465e5c832a65b5bd09767f1015c2dfc1a Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Tue, 27 Feb 2024 15:45:33 +0000
Subject: [PATCH] Extending to HA 7

---
 .../ha_15_32/ha_analysis_batch_3.py           | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

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 da484daa..2fb26e73 100644
--- a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
+++ b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
@@ -48,6 +48,10 @@ PROPERTY_TYPE_LOOKUP = {
             'EXTRACARE SCHEME': "Flat",
         }
     },
+    "HA7": {
+        "property_type": {},
+        "built_form": {}
+    },
     "HA14": {
         "property_type": {
             "House": "House",
@@ -143,6 +147,13 @@ class DataLoader:
             asset_list["matching_postcode"] = asset_list[
                 self.COLUMN_CONFIG[ha_name]["postcode"]
             ].str.lower().str.strip()
+        elif ha_name == "HA7":
+            # Create matching_address by concatenating Address 1, Address 2, Address 3, Address 4, Postcode
+            asset_list["matching_address"] = asset_list["Address"].str.lower().str.strip() + ", " + \
+                                             asset_list["Address2"].str.lower().str.strip() + ", " + \
+                                             asset_list["Address3"].str.lower().str.strip() + ", " + \
+                                             asset_list["Postcode"].str.lower().str.strip()
+            asset_list["matching_postcode"] = asset_list["Postcode"].str.lower().str.strip()
         elif ha_name == "HA14":
             # Create matching_address by concatenating Address 1, Address 2, Address 3, Address 4, Postcode
             asset_list["matching_address"] = asset_list["Address 1"].str.lower().str.strip() + ", " + \
@@ -241,6 +252,8 @@ class DataLoader:
     def get_asset_sheetname(workbook):
         if "Asset List" in workbook.sheetnames:
             return "Asset List"
+        elif "Asset" in workbook.sheetnames and "Assets" not in workbook.sheetnames:
+            return "Asset"
         else:
             return "Assets"
 
@@ -311,6 +324,8 @@ class DataLoader:
         survey_list = pd.DataFrame(survey_rows, columns=[cell.value for cell in survey_sheet[1]])
         # Remove columns that are None
         survey_list = survey_list.loc[:, survey_list.columns.notnull()]
+        # Remove rows that are completely empty
+        survey_list = survey_list.loc[survey_list.loc[:, survey_list.columns].notnull().any(axis=1)]
         survey_list["survey_list_row_id"] = [ha_name + "_survey_" + str(i) for i in range(0, len(survey_list))]
 
         # Perform survey list merge
@@ -328,6 +343,8 @@ class DataLoader:
         ciga_list = pd.DataFrame(ciga_rows, columns=[cell.value for cell in ciga_sheet[1]])
         # Remove columns that are None
         ciga_list = ciga_list.loc[:, ciga_list.columns.notnull()]
+        # Remove rows that are completely None
+        ciga_list = ciga_list.loc[ciga_list.loc[:, ciga_list.columns].notnull().any(axis=1)]
         # Perform ciga list merge
         if not ciga_list.empty:
             # Remove rows with missing postcode which happens in a small number of cases
@@ -1880,7 +1897,7 @@ def app():
     # Grab the December HA figures filepath
     december_figures_filepath = "local_data/ha_data/HA_December_figures.csv"
 
-    priority_has = ["HA1", "HA6", "HA14", "HA39", "HA107"]
+    priority_has = ["HA1", "HA6", "HA7", "HA14", "HA39", "HA107"]
     # Filter down the directories to only the priority HAs
     directories = [d for d in directories if d.split("/")[2] in priority_has]