refactor CHPA hierarchy SQL

2026-08-20 18:22:16 +08:00
commit 3f3dc443da
5 changed files with 592 additions and 0 deletions
@@ -0,0 +1,86 @@
+-- Databricks notebook source
+-- =============================================================================
+-- Purpose    : Build the flattened IMS ATC level 1-4 hierarchy.
+-- Source     : dwd.dwd_ims_td_therapeutic_class
+-- Target     : dwd.dwd_ims_atc_hierarchy
+-- Grain      : One row per hierarchy path rooted at ATC1_CODE; lower levels may be null.
+-- Write mode : Full refresh (INSERT OVERWRITE).
+-- Downstream : dwd.dwd_ims_td_pack_property, dws.dws_ims_td_atc_cn
+-- Notes      : Parent-code matching is preserved from the legacy script.
+-- =============================================================================
+
+INSERT OVERWRITE TABLE dwd.dwd_ims_atc_hierarchy (
+    ATC1_ID,
+    ATC1_CODE,
+    ATC1_DES,
+    ATC2_ID,
+    ATC2_CODE,
+    ATC2_DES,
+    ATC3_ID,
+    ATC3_CODE,
+    ATC3_DES,
+    ATC4_ID,
+    ATC4_CODE,
+    ATC4_DES
+)
+WITH therapeutic_class AS (
+    SELECT
+        therapeutic_id,
+        therapeutic_code,
+        therapeutic_name,
+        therapeutic_level
+    FROM dwd.dwd_ims_td_therapeutic_class
+),
+atc_level_1 AS (
+    SELECT
+        therapeutic_id AS atc1_id,
+        therapeutic_code AS atc1_code,
+        therapeutic_name AS atc1_des
+    FROM therapeutic_class
+    WHERE therapeutic_level = '1'
+),
+atc_level_2 AS (
+    SELECT
+        therapeutic_id AS atc2_id,
+        therapeutic_code AS atc2_code,
+        therapeutic_name AS atc2_des
+    FROM therapeutic_class
+    WHERE therapeutic_level = '2'
+),
+atc_level_3 AS (
+    SELECT
+        therapeutic_id AS atc3_id,
+        therapeutic_code AS atc3_code,
+        therapeutic_name AS atc3_des
+    FROM therapeutic_class
+    WHERE therapeutic_level = '3'
+),
+atc_level_4 AS (
+    SELECT
+        therapeutic_id AS atc4_id,
+        therapeutic_code AS atc4_code,
+        therapeutic_name AS atc4_des
+    FROM therapeutic_class
+    WHERE therapeutic_level = '4'
+)
+SELECT
+    atc_level_1.atc1_id,
+    atc_level_1.atc1_code,
+    atc_level_1.atc1_des,
+    atc_level_2.atc2_id,
+    atc_level_2.atc2_code,
+    atc_level_2.atc2_des,
+    atc_level_3.atc3_id,
+    atc_level_3.atc3_code,
+    atc_level_3.atc3_des,
+    atc_level_4.atc4_id,
+    atc_level_4.atc4_code,
+    atc_level_4.atc4_des
+FROM atc_level_1
+LEFT JOIN atc_level_2
+    ON atc_level_1.atc1_code = LEFT(atc_level_2.atc2_code, 1)
+LEFT JOIN atc_level_3
+    ON atc_level_2.atc2_code = LEFT(atc_level_3.atc3_code, 3)
+LEFT JOIN atc_level_4
+    ON atc_level_3.atc3_code = LEFT(atc_level_4.atc4_code, 4)
+;