From 6e0f75d567ee0c905d87b8ec91575aec2bc5dd35 Mon Sep 17 00:00:00 2001 From: Tom Jemmett Date: Wed, 30 Sep 2026 22:25:48 +0100 Subject: [PATCH 1/3] fixes invest/treat order column in aae hes data --- src/nhp/data/hes/aae/investigations.py | 2 +- src/nhp/data/hes/aae/treatments.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/nhp/data/hes/aae/investigations.py b/src/nhp/data/hes/aae/investigations.py index beaecbe..1f93e69 100644 --- a/src/nhp/data/hes/aae/investigations.py +++ b/src/nhp/data/hes/aae/investigations.py @@ -13,7 +13,7 @@ def get_hes_aae_investigations(spark: SparkSession) -> DataFrame: ) to_melt = [f"invest_{i:02}" for i in range(1, 12)] - melt_str = ",".join([f"'{c}', `{c}`" for c in to_melt]) + melt_str = ",".join([f"'{i + 1}', `{c}`" for i, c in enumerate(to_melt)]) stack_expr = F.expr( f"stack({len(to_melt)}, {melt_str}) as (investigation_order, investigation)" diff --git a/src/nhp/data/hes/aae/treatments.py b/src/nhp/data/hes/aae/treatments.py index be4c10e..4a7f936 100644 --- a/src/nhp/data/hes/aae/treatments.py +++ b/src/nhp/data/hes/aae/treatments.py @@ -13,7 +13,7 @@ def get_hes_aae_treatments(spark: SparkSession) -> DataFrame: ) to_melt = [f"treat_{i:02}" for i in range(1, 12)] - melt_str = ",".join([f"'{c}', `{c}`" for c in to_melt]) + melt_str = ",".join([f"'{i + 1}', `{c}`" for i, c in enumerate(to_melt)]) stack_expr = F.expr( f"stack({len(to_melt)}, {melt_str}) as (treatment_order, treatment)" From 8e0a71946401808c5e463c8099d2b5fd22f69b3b Mon Sep 17 00:00:00 2001 From: Tom Jemmett Date: Thu, 1 Oct 2026 10:58:52 +0100 Subject: [PATCH 2/3] Fix string formatting in melt_str creation Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- src/nhp/data/hes/aae/investigations.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/nhp/data/hes/aae/investigations.py b/src/nhp/data/hes/aae/investigations.py index 1f93e69..62f3947 100644 --- a/src/nhp/data/hes/aae/investigations.py +++ b/src/nhp/data/hes/aae/investigations.py @@ -13,7 +13,7 @@ def get_hes_aae_investigations(spark: SparkSession) -> DataFrame: ) to_melt = [f"invest_{i:02}" for i in range(1, 12)] - melt_str = ",".join([f"'{i + 1}', `{c}`" for i, c in enumerate(to_melt)]) + melt_str = ",".join([f"{i + 1}, `{c}`" for i, c in enumerate(to_melt)]) stack_expr = F.expr( f"stack({len(to_melt)}, {melt_str}) as (investigation_order, investigation)" From c35e44d26d9bea31fe58386c7f04290677bc8955 Mon Sep 17 00:00:00 2001 From: Tom Jemmett Date: Thu, 1 Oct 2026 10:59:03 +0100 Subject: [PATCH 3/3] Fix formatting in melt_str generation Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- src/nhp/data/hes/aae/treatments.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/nhp/data/hes/aae/treatments.py b/src/nhp/data/hes/aae/treatments.py index 4a7f936..77954fb 100644 --- a/src/nhp/data/hes/aae/treatments.py +++ b/src/nhp/data/hes/aae/treatments.py @@ -13,7 +13,7 @@ def get_hes_aae_treatments(spark: SparkSession) -> DataFrame: ) to_melt = [f"treat_{i:02}" for i in range(1, 12)] - melt_str = ",".join([f"'{i + 1}', `{c}`" for i, c in enumerate(to_melt)]) + melt_str = ",".join([f"{i + 1}, `{c}`" for i, c in enumerate(to_melt)]) stack_expr = F.expr( f"stack({len(to_melt)}, {melt_str}) as (treatment_order, treatment)"