From a40c1670cbf971a5dac633b7c0574df0268f0789 Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Thu, 28 Dec 2023 14:08:40 +0000
Subject: [PATCH] completed ha25 analysis

---
 etl/eligibility/ha_15_32/ha25_app.py | 53 ++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/etl/eligibility/ha_15_32/ha25_app.py b/etl/eligibility/ha_15_32/ha25_app.py
index 07470b51..4d86a546 100644
--- a/etl/eligibility/ha_15_32/ha25_app.py
+++ b/etl/eligibility/ha_15_32/ha25_app.py
@@ -450,6 +450,46 @@ def get_epc_data(data, cleaned, cleaning_data, created_at):
     return results_df, scoring_data, nodata
 
 
+def analyse_results(results_df, data, eco4_prospects_survey_list):
+    analysis_data = data[["row_id", "survey_key", "warmfront_identified"]].merge(
+        results_df, how="left", on="row_id"
+    )
+
+    warmfront_identified = analysis_data[analysis_data["warmfront_identified"]]
+
+    # Of the ECO jobs, what proportion to we get right
+
+    success_rate = (warmfront_identified["eco4_eligible"] | warmfront_identified["gbis_eligible"]).sum() / \
+                   warmfront_identified.shape[
+                       0]
+
+    # No gbis for this
+    # gbis_success_rate = warmfront_identified_gbis["gbis_eligible"].sum() / warmfront_identified_gbis.shape[0]
+
+    # Additional identified
+    additional_identified_eco = analysis_data[
+        (analysis_data["eco4_eligible"] == True) & (analysis_data["warmfront_identified"] == False)
+        ]
+
+    additional_identified_eco["eligibility_classification"].value_counts()
+
+    additional_identified_gbis = analysis_data[
+        (analysis_data["gbis_eligible"] == True) & (analysis_data["eco4_eligible"] == False) & (
+            analysis_data["warmfront_identified"] == False
+        )
+        ].shape[0]
+
+    # Future
+    additional_identified_eco_future = analysis_data[
+        (analysis_data["eco4_eligible_future"] == True) & (analysis_data["warmfront_identified"] == False)
+        ].shape[0]
+    additional_identified_gbis_future = analysis_data[
+        (analysis_data["gbis_eligible_future"] == True) & (analysis_data["eco4_eligible_future"] == False) & (
+            analysis_data["warmfront_identified"] == False
+        )
+        ].shape[0]
+
+
 def app():
     data, eco4_prospects_survey_list = load_data()
 
@@ -466,3 +506,16 @@ def app():
     )
 
     created_at = datetime.now().isoformat()
+
+    results_df, scoring_data, nodata = get_epc_data(data, cleaned, cleaning_data, created_at)
+    # Pickle the outputs
+    # import pickle
+    # with open("ha25.pickle", "wb") as f:
+    #     pickle.dump(
+    #         {
+    #             "results_df": results_df,
+    #             "scoring_data": scoring_data,
+    #             "nodata": nodata
+    #         },
+    #         f
+    #     )