perf(transform): optimize dim_locations spatial joins via IEJoin + country filters

Replace ABS() bbox predicates with BETWEEN in all three spatial CTEs
(nearest_padel, padel_local, tennis_nearby). BETWEEN enables DuckDB's
IEJoin (interval join) which is O((N+M) log M) vs the previous O(N×M)
nested-loop cross-join.

Add country pre-filters to restrict the left side from ~140K global
locations to ~20K rows for padel/tennis CTEs (~8 countries each).

Expected: ~50-200x speedup on the spatial CTE portion of the model.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.env.prod.sops

@@ -32,10 +32,6 @@ LITESTREAM_R2_BUCKET=ENC[AES256_GCM,data:pAqSkoJzsw==,iv:5J1Js7JPH/j1oTmEBdNXjwd
 LITESTREAM_R2_ACCESS_KEY_ID=ENC[AES256_GCM,data:e89yGzousImmdO7WVqmRWLJNejDFH5eTaw7G74CyZSw=,iv:bR1jgqSzJlxPA8LMMg2Mc1Lnp01iZgaqa9dgAoV0RpY=,tag:m92xzCP0qaP2onK7ChwA1Q==,type:str]
 LITESTREAM_R2_SECRET_ACCESS_KEY=ENC[AES256_GCM,data:yzXeb8c/Y0d+EluY7g6buo4BnFvBDEVblOi7doNgOp3siLvfMmPkjdRLqZzA14ET6CW5vef9i51yijPYwuhnbw==,iv:IYQRZ8SsquUQpsHH3X/iovz2wFskR4iHyvr0arY7Ag4=,tag:9G5lpHloacjQbEhSk9T2pw==,type:str]
 LITESTREAM_R2_ENDPOINT=ENC[AES256_GCM,data:qqDLfsPeiWOfwtgpZeItypnYNmIOD07fV0IPlZfphhUFeY0Z/BRpkVXA7nfqQ2M6PmcYKVIlBiBY,iv:hsEBxxv1+fvUY4v3nhBP8puKlu216eAGZDUNBAjibas=,tag:MvnsJ8W3oSrv4ZrWW/p+dg==,type:str]
-#ENC[AES256_GCM,data:YGV2exKdGOUkblNZZos=,iv:NuabFM/gNHIzYmDMRZ2tglFYdMPVFuHFGd+AAWvvu6Q=,tag:gZRoNNEmjL9v3nC8j9YkHw==,type:comment]
-DUCKDB_PATH=ENC[AES256_GCM,data:GgOEQ5B1KeQrVavhoMU/JGXcVu3H,iv:XY8JiaosxaUDv5PwizrZFWuNKMSOeuE3cfVyp51r++8=,tag:RnoDE5+7WQolFLejfRZ//w==,type:str]
-SERVING_DUCKDB_PATH=ENC[AES256_GCM,data:U2X9KmlgnWXM9uCfhHCJ03HMGCLm,iv:KHHdBTq+ct4AG7Jt4zLog/5jbDC7LvHA6KzWNTDS/Yw=,tag:m5uIG/bS4vaBooSYoYa6SA==,type:str]
-LANDING_DIR=ENC[AES256_GCM,data:NkEmV8LOwEiN9Sal,iv:mQHBVT6lNoEEEVbl7a5bNN5qoF/LvTyWXQvvkv/z/B0=,tag:IgA5A1nfF91fOBdYxEN71g==,type:str]
 #ENC[AES256_GCM,data:jvZYm7ceM4jtNRg=,iv:nuv65SDTZiaVukVZ40seBZevpqP8uiKCgJyQcIrY524=,tag:cq6gB3vmJzJWIXCLHaIc9g==,type:comment]
 REPO_DIR=ENC[AES256_GCM,data:ae8i6PpGFaiYFA/gGIhczg==,iv:nmsIRMPJYocIO6Z2Gz4OIzAOvSpdgDYmUaIr2hInFo0=,tag:EmAYG5NujnHg8lPaO/uAnQ==,type:str]
 WORKFLOWS_PATH=ENC[AES256_GCM,data:sGU4l68Pbb1thsPyG104mWXWD+zJGTIcR/TqVbPmew==,iv:+xhGkX+ep4kFEAU65ELdDrfjrl/WyuaOi35JI3OB/zM=,tag:brauZhFq8twPXmvhZKjhDQ==,type:str]
@@ -62,7 +58,7 @@ sops_age__list_1__map_enc=-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb2
 sops_age__list_1__map_recipient=age1wjepykv3glvsrtegu25tevg7vyn3ngpl607u3yjc9ucay04s045s796msw
 sops_age__list_2__map_enc=-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBFeHhaOURNZnRVMEwxNThu\nUjF4Q0kwUXhTUE1QSzZJbmpubnh3RnpQTmdvCjRmWWxpNkxFUmVGb3NRbnlydW5O\nWEg3ZXJQTU4vcndzS2pUQXY3Q0ttYjAKLS0tIE9IRFJ1c2ZxbGVHa2xTL0swbGN1\nTzgwMThPUDRFTWhuZHJjZUYxOTZrU00KY62qrNBCUQYxwcLMXFEnLkwncxq3BPJB\nKm4NzeHBU87XmPWVrgrKuf+PH1mxJlBsl7Hev8xBTy7l6feiZjLIvQ==\n-----END AGE ENCRYPTED FILE-----\n
 sops_age__list_2__map_recipient=age1c783ym2q5x9tv7py5d28uc4k44aguudjn03g97l9nzs00dd9tsrqum8h4d
-sops_lastmodified=2026-02-28T17:03:44Z
+sops_lastmodified=2026-03-01T00:26:54Z
-sops_mac=ENC[AES256_GCM,data:IQ9jpRxVUssaMK+qFcM3nPdzXHkiqp6E+DhEey1TfqUu5GCBNsWeVy9m9A6p9RWhu2NtJV7aKdUeqneuMtD1q5Tnm6L96zuyot2ESnx2N2ssD9ilrDauQxoBJcrJVnGV61CgaCz9458w8BuVUZydn3MoHeRaU7bOBBzQlTI6vZk=,iv:qHqdt3av/KZRQHr/OS/9KdAJUgKlKEDgan7qI3Zzkck=,tag:fOvdO9iRTTF1Siobu2mLqg==,type:str]
+sops_mac=ENC[AES256_GCM,data:DdcABGVm9KbAcFrF0iuZlAaugsouNs7Hon2mZISaHs15/2H/Pd9FniXW3KeQ0+/NdZFQkz/h3i3bVFampcpFS1AxuOE5+1/IgWn8sKtaqPc7E9y8g6lxMnwTkUX2z+n/Q2nR8KAcO9IyE0GNjIluMWkxPWQuLzlRYDOjRN4/1e0=,iv:rm+6lXhYu6VUmrdCIrU0BRN2/ooa21Fw1ESWxr7vATg=,tag:GZmLLZf/LQaNeNNAAEg5bA==,type:str]
 sops_unencrypted_suffix=_unencrypted
 sops_version=3.12.1

transform/sqlmesh_padelnomics/models/foundation/dim_locations.sql

@@ -19,8 +19,10 @@
 --   4. Country-level income       (global fallback from stg_income / ilc_di03)
 --
 -- Distance calculations use ST_Distance_Sphere (DuckDB spatial extension).
--- A bounding-box pre-filter (~0.5°, ≈55km) reduces the cross-join before the
+-- Spatial joins use BETWEEN predicates (not ABS()) to enable DuckDB's IEJoin
--- exact sphere distance is computed.
+-- (interval join) optimization: O((N+M) log M) vs O(N×M) nested-loop.
+-- Country pre-filters restrict the left side to ~20K rows for padel/tennis CTEs
+-- (~8 countries each), down from ~140K global locations.
 
 MODEL (
   name foundation.dim_locations,
@@ -147,6 +149,8 @@ padel_courts AS (
   WHERE lat IS NOT NULL AND lon IS NOT NULL
 ),
 -- Nearest padel court distance per location (bbox pre-filter → exact sphere distance)
+-- BETWEEN enables DuckDB IEJoin (O((N+M) log M)) vs ABS() nested-loop (O(N×M)).
+-- Country pre-filter reduces left side from ~140K to ~20K rows (padel is ~8 countries).
 nearest_padel AS (
   SELECT
     l.geoname_id,
@@ -158,9 +162,12 @@ nearest_padel AS (
     ) AS nearest_padel_court_km
   FROM locations l
   JOIN padel_courts p
-    -- ~55km bounding box pre-filter to limit cross-join before sphere calc
+    -- ~55km bounding box pre-filter; BETWEEN triggers IEJoin optimization
-    ON ABS(l.lat - p.lat) < 0.5
+    ON l.lat BETWEEN p.lat - 0.5 AND p.lat + 0.5
-    AND ABS(l.lon - p.lon) < 0.5
+    AND l.lon BETWEEN p.lon - 0.5 AND p.lon + 0.5
+  WHERE l.country_code IN (
+    SELECT DISTINCT country_code FROM padel_courts WHERE country_code IS NOT NULL
+  )
   GROUP BY l.geoname_id
 ),
 -- Padel venues within 5km of each location (counts as "local padel supply")
@@ -170,24 +177,35 @@ padel_local AS (
     COUNT(*) AS padel_venue_count
   FROM locations l
   JOIN padel_courts p
-    ON ABS(l.lat - p.lat) < 0.05    -- ~5km bbox pre-filter
+    -- ~5km bbox pre-filter; BETWEEN triggers IEJoin optimization
-    AND ABS(l.lon - p.lon) < 0.05
+    ON l.lat BETWEEN p.lat - 0.05 AND p.lat + 0.05
-  WHERE ST_Distance_Sphere(
+    AND l.lon BETWEEN p.lon - 0.05 AND p.lon + 0.05
+  WHERE l.country_code IN (
+    SELECT DISTINCT country_code FROM padel_courts WHERE country_code IS NOT NULL
+  )
+    AND ST_Distance_Sphere(
       ST_Point(l.lon, l.lat),
       ST_Point(p.lon, p.lat)
     ) / 1000.0 <= 5.0
   GROUP BY l.geoname_id
 ),
 -- Tennis courts within 25km of each location (sports culture proxy)
+-- Country pre-filter reduces left side from ~140K to ~20K rows (tennis courts are European only).
 tennis_nearby AS (
   SELECT
     l.geoname_id,
     COUNT(*) AS tennis_courts_within_25km
   FROM locations l
   JOIN staging.stg_tennis_courts t
-    ON ABS(l.lat - t.lat) < 0.23   -- ~25km bbox pre-filter
+    -- ~25km bbox pre-filter; BETWEEN triggers IEJoin optimization
-    AND ABS(l.lon - t.lon) < 0.23
+    ON l.lat BETWEEN t.lat - 0.23 AND t.lat + 0.23
-  WHERE ST_Distance_Sphere(
+    AND l.lon BETWEEN t.lon - 0.23 AND t.lon + 0.23
+  WHERE l.country_code IN (
+    SELECT DISTINCT country_code
+    FROM staging.stg_tennis_courts
+    WHERE country_code IS NOT NULL
+  )
+    AND ST_Distance_Sphere(
       ST_Point(l.lon, l.lat),
       ST_Point(t.lon, t.lat)
     ) / 1000.0 <= 25.0