From 21082d8d3779a75cae422becf1a6e589ebcbaba6 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Wed, 6 Mar 2024 19:46:28 +0000
Subject: [PATCH] fixed duplication variance for HA16

---
 .../ha_15_32/ha_analysis_batch_3.py           | 20 ++++++++++++++++++-
 1 file changed, 19 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 8c9f59c2..7859d6d2 100644
--- a/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
+++ b/etl/eligibility/ha_15_32/ha_analysis_batch_3.py
@@ -960,6 +960,21 @@ class DataLoader:
             survey_list["NO."]
         )
 
+        # Delete some duplicated entries
+        survey_list = survey_list[
+            ~((survey_list["Street / Block Name"] == "york road") &
+              (survey_list["NO."].astype(str) == "12") &
+              (survey_list["Post Code"] == "M44 5HU") &
+              (survey_list["SUBMISSION DATE"].astype(str) == "45229"))
+        ]
+
+        survey_list = survey_list[
+            ~((survey_list["Street / Block Name"] == "peatfield avenue") &
+              (survey_list["NO."].astype(str) == "23") &
+              (survey_list["Post Code"] == "M27 9XG") &
+              (survey_list["SUBMISSION DATE"].astype(str) == "45236"))
+        ]
+
         return survey_list
 
     @staticmethod
@@ -3265,7 +3280,7 @@ def forecast_remaining_sales(loader):
             asset_list_remaining = asset_list_remaining[pd.isnull(asset_list_remaining["installation_status"])]
             asset_list_remaining = asset_list_remaining.drop(columns=["installation_status"])
 
-        # # TODO: TEMP
+        # TODO: TEMP
         # n_pre_ciga = asset_list[
         #     asset_list["ECO Eligibility"].isin(
         #         [
@@ -3304,6 +3319,9 @@ def forecast_remaining_sales(loader):
         # pre_ciga_revenue - (pre_ciga_remaining_revenue + sold_revenue)
         # # MISSING 1 SALE from sold
         # cancelled = survey_list[survey_list["installation_status"].str.contains("ECO4")].shape[0]
+        # dupes = survey_list[survey_list["asset_list_row_id"].duplicated()]["asset_list_row_id"].values
+        # z = survey_list[survey_list["asset_list_row_id"].isin(dupes)]
+        # z[['NO.', 'Street / Block Name', 'Post Code', 'INSTALLED OR CANCELLED', 'SUBMISSION DATE']]
         # # TODO: END TEMP
 
         eligiblity_counts = pd.DataFrame(asset_list["ECO Eligibility"].value_counts()).reset_index()