From 1719e7090aaeb1ae5f277b27fd44b2d75d5b8346 Mon Sep 17 00:00:00 2001
From: Luke Hubbard <104831245+lhubbardONS@users.noreply.github.com>
Date: Tue, 1 Oct 2024 14:10:40 +0100
Subject: [PATCH] Fixing errors with standardising factor calculation without
 domain (#91)

---
 mbs_results/unsorted/selective_editing.py     | 12 ++++++------
 tests/create_standardising_factor_data.csv    |  4 ++--
 tests/test_unsorted/test_selective_editing.py |  3 ++-
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/mbs_results/unsorted/selective_editing.py b/mbs_results/unsorted/selective_editing.py
index 2c9d678a..214ec19c 100644
--- a/mbs_results/unsorted/selective_editing.py
+++ b/mbs_results/unsorted/selective_editing.py
@@ -94,18 +94,18 @@ def create_standardising_factor(
     previous_df = dataframe[(dataframe[period] == previous_period)]
     previous_df = previous_df[previous_df[question_code].isin([40, 49])]
 
-    previous_df["standardising_factor"] = (
+    # The standardising factor is created for each record before summing for each
+    # domain-question grouping.
+    previous_df["unit_standardising_factor"] = (
         previous_df[predicted_value]
         * previous_df[a_weight]
         * previous_df[o_weight]
         * previous_df[g_weight]
     )
 
-    previous_df = previous_df.assign(
-        standardising_factor=lambda x: x.groupby([domain, question_code]).transform(
-            "sum"
-        )["standardising_factor"]
-    ).astype({"standardising_factor": "float"})
+    previous_df["standardising_factor"] = previous_df.groupby([domain, question_code])[
+        "unit_standardising_factor"
+    ].transform("sum")
 
     output_df = previous_df[
         [
diff --git a/tests/create_standardising_factor_data.csv b/tests/create_standardising_factor_data.csv
index 28b853e0..712deeba 100755
--- a/tests/create_standardising_factor_data.csv
+++ b/tests/create_standardising_factor_data.csv
@@ -10,6 +10,6 @@ reference,period,domain,question_code,predicted_value,imputation_marker,a_weight
 10005,202401,17,40,1001,FIR,2.0,2.0,3.0,95,12012.0
 10005,202402,19,40,532,FIR,7.0,3.0,3.0,29,
 10006,202401,19,40,336,C,2.0,1.0,4.0,14,2688.0
-10006,202401,19,49,461,C,3.0,1.0,4.0,58,9084.0
-10007,202401,19,49,222,BIR,4.0,2.0,2.0,67,9084.0
+10006,202401,19,49,461,C,3.0,1.0,4.0,58,5532.0
+10007,202401,,49,222,BIR,4.0,2.0,2.0,67,
 10008,202401,17,40,,,4.0,1.0,5.0,48,12012.0
diff --git a/tests/test_unsorted/test_selective_editing.py b/tests/test_unsorted/test_selective_editing.py
index 8a8438d0..68211744 100755
--- a/tests/test_unsorted/test_selective_editing.py
+++ b/tests/test_unsorted/test_selective_editing.py
@@ -33,7 +33,8 @@ def test_create_standardising_factor(
         create_standardising_factor_data,
     ):
         expected_output = create_standardising_factor_data[
-            create_standardising_factor_data["standardising_factor"].notna()
+            (create_standardising_factor_data["period"] == 202401)
+            & (create_standardising_factor_data["question_code"].isin([40, 49]))
         ]
         expected_output = expected_output[
             [