From 7d209d5d8e07b4112bffcdcfc748d04cc299abe6 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Sun, 17 Nov 2024 16:28:43 +0000
Subject: [PATCH] creating loss and gain columns

---
 .../stonewater/Wave 3 Preparation.py          | 48 +++++++++++++++----
 1 file changed, 40 insertions(+), 8 deletions(-)

diff --git a/etl/customers/stonewater/Wave 3 Preparation.py b/etl/customers/stonewater/Wave 3 Preparation.py
index d2110de8..b36ae756 100644
--- a/etl/customers/stonewater/Wave 3 Preparation.py	
+++ b/etl/customers/stonewater/Wave 3 Preparation.py	
@@ -1703,7 +1703,7 @@ def propsed_wave_3_sample():
 
         region_assets["Confidence Tier"] = np.where(
             region_assets["Current EPC Band"].isin(["C", "B", "A"]),
-            "6 - property was surveyed", region_assets["Confidence Tier"]
+            "5 - property was surveyed", region_assets["Confidence Tier"]
         )
 
         archetypes = region_assets[
@@ -1721,6 +1721,7 @@ def propsed_wave_3_sample():
                 (survey_results["Postal Region"] == region)
                 ].groupby("Archetype ID")[["Current SAP Rating"]].mean().reset_index()
             region_surveyed["Current EPC Band"] = region_surveyed["Current SAP Rating"].apply(sap_to_epc)
+            region_surveyed = region_surveyed.drop(columns=["Current SAP Rating"])
 
         region_assets = region_assets.merge(
             region_surveyed,
@@ -1743,7 +1744,7 @@ def propsed_wave_3_sample():
         # Handle EPC C
         region_assets["Confidence Tier"] = np.where(
             region_assets["Current EPC Band"].isin(["C", "B", "A"]) & pd.isnull(region_assets["Confidence Tier"]),
-            "6 - EPC C or above", region_assets["Confidence Tier"]
+            "5 - EPC C or above", region_assets["Confidence Tier"]
         )
 
         region_assets = region_assets.drop(columns=["Current EPC Band_method1"])
@@ -1773,7 +1774,8 @@ def propsed_wave_3_sample():
         )
 
         region_assets["Confidence Tier"] = np.where(
-            region_assets["Current EPC Band_method2"].isin(["D", "E", "F", "G"]),
+            region_assets["Current EPC Band_method2"].isin(["D", "E", "F", "G"]) & pd.isnull(
+                region_assets["Confidence Tier"]),
             "2 - same archetype", region_assets["Confidence Tier"]
         )
 
@@ -1786,8 +1788,8 @@ def propsed_wave_3_sample():
 
         # We label EPC C properties
         region_assets["Confidence Tier"] = np.where(
-            region_assets["Current EPC Band"].isin(["C", "B", "A"]),
-            "6 - EPC C or above", region_assets["Confidence Tier"]
+            region_assets["Current EPC Band"].isin(["C", "B", "A"]) & pd.isnull(region_assets["Confidence Tier"]),
+            "5 - EPC C or above", region_assets["Confidence Tier"]
         )
 
         missed_addressids = region_assets[pd.isnull(region_assets["Confidence Tier"])]["Address ID"].unique().tolist()
@@ -1823,7 +1825,7 @@ def propsed_wave_3_sample():
                 final_missed_matches.append(
                     {
                         "Address ID": a_id,
-                        "Confidence Tier": "5 - no similar property, needs survey to confirm",
+                        "Confidence Tier": "4 - no similar property, needs survey to confirm",
                         "Current EPC Band": "Unknown"
                     }
                 )
@@ -1832,7 +1834,7 @@ def propsed_wave_3_sample():
             expected_sap = surveyed_similar["Current SAP Rating"].mean()
             expected_epc = sap_to_epc(expected_sap)
             if expected_epc in ["C", "B", "A"]:
-                tier = "6 - EPC C or above"
+                tier = "5 - EPC C or above"
             else:
                 tier = "3 - similar property"
 
@@ -1861,12 +1863,42 @@ def propsed_wave_3_sample():
             region_assets["Current EPC Band_method3"], region_assets["Current EPC Band"]
         )
 
-        region_assets = region_assets.drop(columns=["Confidence Tier_method3"])
+        region_assets = region_assets.drop(columns=["Confidence Tier_method3", "Current EPC Band_method3"])
 
         if pd.isnull(region_assets["Current EPC Band"]).sum():
             raise Exception("Something went wrong")
 
         results.append(region_assets)
 
+    results = pd.concat(results)
+
+    # Create a pivot table for counts of Confidence Tier by Postal Region
+    geographic_summary = results.pivot_table(
+        index='Postal Region',
+        columns='Confidence Tier',
+        aggfunc='size',
+        fill_value=0
+    ).reset_index()
+
+    # We create the gain and loss columns
+    # Gain is the sum of these columns:
+    # '1 - Archetype surveyed', '1 - property was surveyed',
+    #        '2 - same archetype', '3 - similar property',
+    # Loss is the sum of these columns:
+    # '4 - no similar property, needs survey to confirm',
+    # '5 - EPC C or above', '5 - property was surveyed'
+    geographic_summary["Gain"] = geographic_summary[
+        ['1 - Archetype surveyed', '1 - property was surveyed', '2 - same archetype', '3 - similar property']
+    ].sum(axis=1)
+
+    geographic_summary["Loss"] = geographic_summary[
+        ['4 - no similar property, needs survey to confirm', '5 - EPC C or above', '5 - property was surveyed']
+    ].sum(axis=1)
+
+    geographic_summary.sum()
+
+    geographic_summary = geographic_summary.sort_values("Loss", ascending=True)
+    geographic_summary["Loss Cumulative Sum"] = geographic_summary["Loss"].cumsum()
+
 # if __name__ == "__main__":
 #     main()