merge: unified location_profiles serving model + both scores on map tooltips

# Conflicts:
#	CHANGELOG.md
#	transform/sqlmesh_padelnomics/models/serving/location_opportunity_profile.sql

transform/sqlmesh_padelnomics/CLAUDE.md

@@ -56,27 +56,27 @@ Grain must match reality — use `QUALIFY ROW_NUMBER()` to enforce it.
 |-----------|-------|---------|
 | `foundation.dim_countries` | `country_code` | `dim_cities`, `dim_locations`, `pseo_city_costs_de`, `planner_defaults` — single source for country names, income, PLI/cost overrides |
 | `foundation.dim_venues` | `venue_id` | `dim_cities`, `dim_venue_capacity`, `fct_daily_availability` (via capacity join) |
-| `foundation.dim_cities` | `(country_code, city_slug)` | `serving.city_market_profile` → all pSEO serving models |
-| `foundation.dim_locations` | `(country_code, geoname_id)` | `serving.location_opportunity_profile` — all GeoNames locations (pop ≥1K), incl. zero-court locations |
+| `foundation.dim_cities` | `(country_code, city_slug)` | `serving.location_profiles` (city_slug + city_padel_venue_count) → all pSEO serving models |
+| `foundation.dim_locations` | `(country_code, geoname_id)` | `serving.location_profiles` — all GeoNames locations (pop ≥1K), incl. zero-court locations |
 | `foundation.dim_venue_capacity` | `tenant_id` | `foundation.fct_daily_availability` |
 
 ## Source integration map
 
 ```
 stg_playtomic_venues  ─┐
-stg_playtomic_resources─┤→ dim_venues ─┬→ dim_cities ──────────────→ city_market_profile
-stg_padel_courts      ─┘               └→ dim_venue_capacity              (Marktreife-Score)
-                                                            ↓
+stg_playtomic_resources─┤→ dim_venues ─┬→ dim_cities ──┐
+stg_padel_courts      ─┘               └→ dim_venue_capacity
+                                                        │
 stg_playtomic_availability ──→ fct_availability_slot ──→ fct_daily_availability
                                                             ↓
                                                venue_pricing_benchmarks
                                                             ↓
 stg_population ──→ dim_cities ─────────────────────────────┘
-stg_income     ──→ dim_cities
-
-stg_population_geonames ─┐
-stg_padel_courts         ─┤→ dim_locations ──→ location_opportunity_profile
-stg_tennis_courts        ─┤                         (Marktpotenzial-Score)
+stg_income     ──→ dim_cities                               │
+                                                            ↓
+stg_population_geonames ─┐                          location_profiles
+stg_padel_courts         ─┤→ dim_locations ────────→  (both scores:
+stg_tennis_courts        ─┤                           Marktreife + Marktpotenzial)
 stg_income               ─┘
 ```
 

transform/sqlmesh_padelnomics/models/foundation/dim_cities.sql

@@ -2,7 +2,7 @@
 -- Built from venue locations (dim_venues) as the primary source — padelnomics
 -- tracks cities where padel venues actually exist, not an administrative city list.
 --
--- Conformed dimension: used by city_market_profile and all pSEO serving models.
+-- Conformed dimension: used by location_profiles and all pSEO serving models.
 -- Integrates four sources:
 --   dim_venues           → city list, venue count, coordinates (Playtomic + OSM)
 --   foundation.dim_countries → country_name_en, country_slug, median_income_pps
@@ -128,7 +128,7 @@ SELECT
   vc.padel_venue_count,
   c.median_income_pps,
   c.income_year,
-  -- GeoNames ID: FK to dim_locations / location_opportunity_profile.
+  -- GeoNames ID: FK to dim_locations / location_profiles.
   -- String match preferred; spatial fallback used when name doesn't match (Milano→Milan, etc.)
   COALESCE(gn.geoname_id, gs.spatial_geoname_id)            AS geoname_id
 FROM venue_cities vc

transform/sqlmesh_padelnomics/models/serving/README.md

@@ -3,4 +3,4 @@
 Analytics-ready views consumed by the web app and programmatic SEO.
 Query these from `analytics.py` via DuckDB read-only connection.
 
-Naming convention: `serving.<purpose>` (e.g. `serving.city_market_profile`)
+Naming convention: `serving.<purpose>` (e.g. `serving.location_profiles`)

transform/sqlmesh_padelnomics/models/serving/city_market_profile.sql

@@ -1,117 +0,0 @@
--- One Big Table: per-city padel market intelligence.
--- Consumed by: SEO article generation, planner city-select pre-fill, API endpoints.
---
--- Padelnomics Marktreife-Score v3 (0–100):
--- Answers "How mature/established is this padel market?"
--- Only computed for cities with ≥1 padel venue (padel_venue_count > 0).
--- For white-space opportunity scoring, see serving.location_opportunity_profile.
---
---   40 pts  supply development — log-scaled density (LN ceiling 20/100k) × count gate
---                                (min(1, count/5) kills small-town inflation)
---   25 pts  demand evidence   — occupancy when available; 40% density proxy otherwise
---   15 pts  addressable market — log-scaled population, ceiling 1M (context only)
---   10 pts  economic context  — income PPS normalised to 200 ceiling
---   10 pts  data quality      — completeness discount
---   No saturation discount: high density = maturity, not a penalty
-
-MODEL (
-  name serving.city_market_profile,
-  kind FULL,
-  cron '@daily',
-  grain (country_code, city_slug)
-);
-
-WITH base AS (
-  SELECT
-    c.country_code,
-    c.country_name_en,
-    c.country_slug,
-    c.city_name,
-    c.city_slug,
-    c.lat,
-    c.lon,
-    c.population,
-    c.population_year,
-    c.padel_venue_count,
-    c.median_income_pps,
-    c.income_year,
-    c.geoname_id,
-    -- Venue density: padel venues per 100K residents
-    CASE WHEN c.population > 0
-      THEN ROUND(c.padel_venue_count::DOUBLE / c.population * 100000, 2)
-      ELSE NULL
-    END                          AS venues_per_100k,
-    -- Data confidence: 1.0 if both population and venues are present
-    CASE
-      WHEN c.population > 0 AND c.padel_venue_count > 0 THEN 1.0
-      WHEN c.population > 0 OR  c.padel_venue_count > 0 THEN 0.5
-      ELSE 0.0
-    END                          AS data_confidence,
-    -- Pricing / occupancy from Playtomic (NULL when no availability data)
-    vpb.median_hourly_rate,
-    vpb.median_peak_rate,
-    vpb.median_offpeak_rate,
-    vpb.median_occupancy_rate,
-    vpb.median_daily_revenue_per_venue,
-    vpb.price_currency
-  FROM foundation.dim_cities c
-  LEFT JOIN serving.venue_pricing_benchmarks vpb
-    ON c.country_code = vpb.country_code
-    AND c.city_slug = vpb.city_slug
-  WHERE c.padel_venue_count > 0
-),
-scored AS (
-  SELECT *,
-    ROUND(
-      -- Supply development (40 pts): THE maturity signal.
-      -- Log-scaled density: LN(density+1)/LN(21) → 20/100k ≈ full marks.
-      -- Count gate: min(1, count/5) — 1 venue=20%, 5+ venues=100%.
-      -- Kills small-town inflation (1 court / 5k pop = 20/100k) without hard cutoffs.
-      40.0 * LEAST(1.0, LN(COALESCE(venues_per_100k, 0) + 1) / LN(21))
-           * LEAST(1.0, padel_venue_count / 5.0)
-      -- Demand evidence (25 pts): occupancy when Playtomic data available.
-      -- Fallback: 40% of density score (avoids double-counting with supply component).
-      + 25.0 * CASE
-          WHEN median_occupancy_rate IS NOT NULL
-            THEN LEAST(1.0, median_occupancy_rate / 0.65)
-          ELSE 0.4 * LEAST(1.0, LN(COALESCE(venues_per_100k, 0) + 1) / LN(21))
-                   * LEAST(1.0, padel_venue_count / 5.0)
-        END
-      -- Addressable market (15 pts): population as context, not maturity signal.
-      -- LN(1) = 0 so zero-pop cities score 0 here.
-      + 15.0 * LEAST(1.0, LN(GREATEST(population, 1)) / LN(1000000))
-      -- Economic context (10 pts): country-level income PPS.
-      -- Flat per country — kept as context modifier, not primary signal.
-      + 10.0 * LEAST(1.0, COALESCE(median_income_pps, 100) / 200.0)
-      -- Data quality (10 pts): completeness discount.
-      + 10.0 * data_confidence
-    , 1)
-                                 AS market_score
-  FROM base
-)
-SELECT
-  s.country_code,
-  s.country_name_en,
-  s.country_slug,
-  s.city_name,
-  s.city_slug,
-  s.lat,
-  s.lon,
-  s.population,
-  s.population_year,
-  s.padel_venue_count,
-  s.venues_per_100k,
-  s.data_confidence,
-  s.market_score,
-  s.median_income_pps,
-  s.income_year,
-  s.median_hourly_rate,
-  s.median_peak_rate,
-  s.median_offpeak_rate,
-  s.median_occupancy_rate,
-  s.median_daily_revenue_per_venue,
-  s.price_currency,
-  s.geoname_id,
-  CURRENT_DATE                   AS refreshed_date
-FROM scored s
-ORDER BY s.market_score DESC

transform/sqlmesh_padelnomics/models/serving/location_opportunity_profile.sql

@@ -1,134 +0,0 @@
--- Per-location padel investment opportunity intelligence.
--- Consumed by: Gemeinde-level pSEO pages, opportunity map, "top markets" lists.
---
--- Padelnomics Marktpotenzial-Score v3 (0–100):
--- Answers "Where should I build a padel court?"
--- Covers ALL GeoNames locations (pop ≥ 1K) — NOT filtered to existing padel markets.
--- Zero-court locations score highest on supply gap component (white space = opportunity).
---
--- H3 catchment methodology (v3):
---   Addressable market and supply gap now use a regional catchment lens rather than
---   the location's own population/court count. Each location is assigned an H3 cell
---   at resolution 4 (~10km center-to-center). Catchment = cell + 6 neighbours (k_ring=1),
---   covering ~462km² — roughly a 15-18km radius, matching realistic driving distance.
---   Population and court counts are first aggregated per H3 cell (hex_stats CTE), then
---   summed across the 7-cell ring (catchment CTE) to avoid scanning all 140K locations
---   per location.
---
---   25 pts  addressable market — log-scaled catchment population, ceiling 500K
---           (opportunity peaks in mid-size catchments; megacities already served)
---   20 pts  economic power     — country income PPS, normalised to 35,000
---                               EU PPS values range 18k-37k; /35k gives real spread.
---                               DE ≈ 13.2pts, ES ≈ 10.7pts, SE ≈ 14.3pts.
---                               Previously /200 caused all countries to saturate at 20/20.
---   30 pts  supply gap         — INVERTED catchment venue density; 0 courts/100K = full marks.
---                               Ceiling 8/100K for a gentler gradient and to account for
---                               ~87% data undercount vs FIP totals.
---                               Linear: GREATEST(0, 1 - catchment_density/8)
---   15 pts  catchment gap      — distance to nearest padel court.
---                               DuckDB LEAST ignores NULLs: LEAST(1.0, NULL/30) = 1.0,
---                               so NULL nearest_km = full marks (no court in bounding box
---                               = high opportunity). COALESCE fallback is dead code.
---   10 pts  sports culture     — tennis courts within 25km (≥10 = full marks).
---                               NOTE: dim_locations tennis data is empty (all 0 rows).
---                               Component contributes 0 pts everywhere until data lands.
-
-MODEL (
-  name serving.location_opportunity_profile,
-  kind FULL,
-  cron '@daily',
-  grain (country_code, geoname_id)
-);
-
-WITH
--- Aggregate population and court counts per H3 cell (res 4, ~10km edge).
--- Grouping by cell first (~30-50K distinct cells vs 140K locations) keeps the
--- subsequent lateral join small.
-hex_stats AS (
-  SELECT
-    h3_cell_res4,
-    SUM(population)        AS hex_population,
-    SUM(padel_venue_count) AS hex_padel_courts
-  FROM foundation.dim_locations
-  GROUP BY h3_cell_res4
-),
--- For each location, sum hex_stats across the cell + 6 neighbours (k_ring=1).
--- Effective catchment: ~462km², ~15-18km radius — realistic driving distance.
-catchment AS (
-  SELECT
-    l.geoname_id,
-    SUM(hs.hex_population)   AS catchment_population,
-    SUM(hs.hex_padel_courts) AS catchment_padel_courts
-  FROM foundation.dim_locations l,
-  LATERAL (SELECT UNNEST(h3_grid_disk(l.h3_cell_res4, 1)) AS cell) ring
-  JOIN hex_stats hs ON hs.h3_cell_res4 = ring.cell
-  GROUP BY l.geoname_id
-)
-SELECT
-  l.geoname_id,
-  l.country_code,
-  l.country_name_en,
-  l.country_slug,
-  l.location_name,
-  l.location_slug,
-  l.lat,
-  l.lon,
-  l.admin1_code,
-  l.admin2_code,
-  l.population,
-  l.population_year,
-  l.median_income_pps,
-  l.income_year,
-  l.padel_venue_count,
-  l.padel_venues_per_100k,
-  l.nearest_padel_court_km,
-  l.tennis_courts_within_25km,
-  -- Catchment metrics (H3 res-4 cell + 6 neighbours, ~15-18km radius)
-  COALESCE(c.catchment_population, l.population)::BIGINT               AS catchment_population,
-  COALESCE(c.catchment_padel_courts, l.padel_venue_count)::INTEGER     AS catchment_padel_courts,
-  CASE WHEN COALESCE(c.catchment_population, l.population) > 0
-    THEN ROUND(
-      COALESCE(c.catchment_padel_courts, l.padel_venue_count)::DOUBLE
-      / COALESCE(c.catchment_population, l.population) * 100000, 2)
-    ELSE NULL
-  END                                                                    AS catchment_venues_per_100k,
-  ROUND(
-    -- Addressable market (25 pts): log-scaled catchment population, ceiling 500K.
-    -- v3: uses H3 catchment population (cell + 6 neighbours, ~15-18km radius) instead
-    -- of local city population, so mid-size cities surrounded by dense Gemeinden score
-    -- correctly (e.g. Oldenburg pulls in Ammerland, Wesermarsch, etc.).
-    25.0 * LEAST(1.0, LN(GREATEST(COALESCE(c.catchment_population, l.population), 1)) / LN(500000))
-
-    -- Economic power (20 pts): country-level income PPS normalised to 35,000.
-    -- Drives willingness-to-pay for court fees (€20-35/hr target range).
-    -- EU PPS values range 18k-37k; ceiling 35k gives meaningful spread.
-    -- v1 used /200 which caused LEAST(1.0, 115) = 1.0 for ALL countries (flat, no differentiation).
-    -- v2: /35000 → DE 0.66×20=13.2pts, ES 0.53×20=10.7pts, SE 0.71×20=14.3pts.
-    -- Default 15000 for missing data = reasonable developing-market assumption (~0.43).
-    + 20.0 * LEAST(1.0, COALESCE(l.median_income_pps, 15000) / 35000.0)
-
-    -- Supply gap (30 pts): INVERTED catchment venue density.
-    -- v3: uses catchment courts / catchment population instead of local 5km count / city pop.
-    -- 0 courts/100K across the ~15-18km ring = full 30 pts (genuine white space).
-    -- ≥8/100K = 0 pts (well-served regional market).
-    + 30.0 * GREATEST(0.0, 1.0 - COALESCE(
-        CASE WHEN COALESCE(c.catchment_population, l.population) > 0
-          THEN COALESCE(c.catchment_padel_courts, l.padel_venue_count)::DOUBLE
-               / COALESCE(c.catchment_population, l.population) * 100000
-          ELSE 0.0
-        END, 0.0) / 8.0)
-
-    -- Catchment gap (15 pts): distance to nearest existing padel court.
-    -- >30km = full 15 pts (underserved catchment area).
-    -- NULL = no courts found anywhere (rare edge case) → neutral 0.5.
-    + 15.0 * COALESCE(LEAST(1.0, l.nearest_padel_court_km / 30.0), 0.5)
-
-    -- Sports culture proxy (10 pts): tennis courts within 25km.
-    -- ≥10 courts = full 10 pts (proven racket sport market = faster padel adoption).
-    -- 0 courts = 0 pts. Many new padel courts open inside existing tennis clubs.
-    + 10.0 * LEAST(1.0, l.tennis_courts_within_25km / 10.0)
-  , 1)                                                                   AS opportunity_score,
-  CURRENT_DATE                                                           AS refreshed_date
-FROM foundation.dim_locations l
-LEFT JOIN catchment c ON c.geoname_id = l.geoname_id
-ORDER BY opportunity_score DESC

transform/sqlmesh_padelnomics/models/serving/location_profiles.sql

@@ -0,0 +1,243 @@
+-- Unified location profile: both scores at (country_code, geoname_id) grain.
+-- Base: dim_locations (ALL GeoNames locations, pop ≥ 1K, ~140K rows).
+-- Enriched with dim_cities (city_slug, city_name, exact venue count) and
+-- venue_pricing_benchmarks (Playtomic pricing/occupancy).
+--
+-- Two scores per location:
+--
+-- Padelnomics Market Score (Marktreife-Score v3, 0–100):
+--   "How mature/established is this padel market?"
+--   Only meaningful for locations matched to a dim_cities row (city_slug IS NOT NULL)
+--   with padel venues. 0 for all other locations.
+--
+--   40 pts  supply development — log-scaled density (LN ceiling 20/100k) × count gate
+--   25 pts  demand evidence   — occupancy when available; 40% density proxy otherwise
+--   15 pts  addressable market — log-scaled population, ceiling 1M
+--   10 pts  economic context  — income PPS normalised to 200 ceiling
+--   10 pts  data quality      — completeness discount
+--
+-- Padelnomics Opportunity Score (Marktpotenzial-Score v3, 0–100):
+--   "Where should I build a padel court?"
+--   Computed for ALL locations — zero-court locations score highest on supply gap.
+--   H3 catchment methodology: addressable market and supply gap use a regional
+--   H3 catchment (res-4 cell + 6 neighbours, ~462km², ~15-18km radius).
+--
+--   25 pts  addressable market — log-scaled catchment population, ceiling 500K
+--   20 pts  economic power     — income PPS, normalised to 35,000
+--   30 pts  supply gap         — inverted catchment venue density; 0 courts = full marks
+--   15 pts  catchment gap      — distance to nearest padel court
+--   10 pts  sports culture     — tennis courts within 25km
+--
+-- Consumers query directly with WHERE filters:
+--   cities API:       WHERE country_slug = ? AND city_slug IS NOT NULL
+--   opportunity API:  WHERE country_slug = ? AND opportunity_score > 0
+--   planner_defaults: WHERE city_slug IS NOT NULL
+--   pseo_*:           WHERE city_slug IS NOT NULL AND city_padel_venue_count > 0
+
+MODEL (
+  name serving.location_profiles,
+  kind FULL,
+  cron '@daily',
+  grain (country_code, geoname_id)
+);
+
+WITH
+-- All locations from dim_locations (superset)
+base AS (
+  SELECT
+    l.geoname_id,
+    l.country_code,
+    l.country_name_en,
+    l.country_slug,
+    l.location_name,
+    l.location_slug,
+    l.lat,
+    l.lon,
+    l.admin1_code,
+    l.admin2_code,
+    l.population,
+    l.population_year,
+    l.median_income_pps,
+    l.income_year,
+    l.padel_venue_count,
+    l.padel_venues_per_100k,
+    l.nearest_padel_court_km,
+    l.tennis_courts_within_25km,
+    l.h3_cell_res4
+  FROM foundation.dim_locations l
+),
+-- Aggregate population and court counts per H3 cell (res 4, ~10km edge).
+-- Grouping by cell first (~30-50K distinct cells vs 140K locations) keeps the
+-- subsequent lateral join small.
+hex_stats AS (
+  SELECT
+    h3_cell_res4,
+    SUM(population)        AS hex_population,
+    SUM(padel_venue_count) AS hex_padel_courts
+  FROM foundation.dim_locations
+  GROUP BY h3_cell_res4
+),
+-- For each location, sum hex_stats across the cell + 6 neighbours (k_ring=1).
+-- Effective catchment: ~462km², ~15-18km radius — realistic driving distance.
+catchment AS (
+  SELECT
+    l.geoname_id,
+    SUM(hs.hex_population)   AS catchment_population,
+    SUM(hs.hex_padel_courts) AS catchment_padel_courts
+  FROM base l,
+  LATERAL (SELECT UNNEST(h3_grid_disk(l.h3_cell_res4, 1)) AS cell) ring
+  JOIN hex_stats hs ON hs.h3_cell_res4 = ring.cell
+  GROUP BY l.geoname_id
+),
+-- Match dim_cities via (country_code, geoname_id) to get city_slug + exact venue count.
+-- QUALIFY handles rare multi-city-per-geoname collisions (keep highest venue count).
+city_match AS (
+  SELECT
+    c.country_code,
+    c.geoname_id,
+    c.city_slug,
+    c.city_name,
+    c.padel_venue_count AS city_padel_venue_count
+  FROM foundation.dim_cities c
+  WHERE c.geoname_id IS NOT NULL
+  QUALIFY ROW_NUMBER() OVER (
+    PARTITION BY c.country_code, c.geoname_id
+    ORDER BY c.padel_venue_count DESC
+  ) = 1
+),
+-- Pricing / occupancy from Playtomic (via city_slug) + H3 catchment
+with_pricing AS (
+  SELECT
+    b.*,
+    cm.city_slug,
+    cm.city_name,
+    cm.city_padel_venue_count,
+    vpb.median_hourly_rate,
+    vpb.median_peak_rate,
+    vpb.median_offpeak_rate,
+    vpb.median_occupancy_rate,
+    vpb.median_daily_revenue_per_venue,
+    vpb.price_currency,
+    COALESCE(ct.catchment_population, b.population)::BIGINT           AS catchment_population,
+    COALESCE(ct.catchment_padel_courts, b.padel_venue_count)::INTEGER AS catchment_padel_courts
+  FROM base b
+  LEFT JOIN city_match cm
+    ON b.country_code = cm.country_code
+    AND b.geoname_id = cm.geoname_id
+  LEFT JOIN serving.venue_pricing_benchmarks vpb
+    ON cm.country_code = vpb.country_code
+    AND cm.city_slug = vpb.city_slug
+  LEFT JOIN catchment ct
+    ON b.geoname_id = ct.geoname_id
+),
+-- Both scores computed from the enriched base
+scored AS (
+  SELECT *,
+    -- City-level venue density (from dim_cities exact count, not dim_locations spatial 5km)
+    CASE WHEN population > 0
+      THEN ROUND(COALESCE(city_padel_venue_count, 0)::DOUBLE / population * 100000, 2)
+      ELSE NULL
+    END AS city_venues_per_100k,
+    -- Data confidence (for market_score)
+    CASE
+      WHEN population > 0 AND COALESCE(city_padel_venue_count, 0) > 0 THEN 1.0
+      WHEN population > 0 OR  COALESCE(city_padel_venue_count, 0) > 0 THEN 0.5
+      ELSE 0.0
+    END AS data_confidence,
+    -- ── Market Score (Marktreife-Score v3) ──────────────────────────────────
+    -- 0 when no city match or no venues (city_padel_venue_count NULL or 0)
+    CASE WHEN COALESCE(city_padel_venue_count, 0) > 0 THEN
+      ROUND(
+        -- Supply development (40 pts)
+        40.0 * LEAST(1.0, LN(
+            COALESCE(
+              CASE WHEN population > 0
+                THEN COALESCE(city_padel_venue_count, 0)::DOUBLE / population * 100000
+                ELSE 0 END
+            , 0) + 1) / LN(21))
+             * LEAST(1.0, COALESCE(city_padel_venue_count, 0) / 5.0)
+        -- Demand evidence (25 pts)
+        + 25.0 * CASE
+            WHEN median_occupancy_rate IS NOT NULL
+              THEN LEAST(1.0, median_occupancy_rate / 0.65)
+            ELSE 0.4 * LEAST(1.0, LN(
+                COALESCE(
+                  CASE WHEN population > 0
+                    THEN COALESCE(city_padel_venue_count, 0)::DOUBLE / population * 100000
+                    ELSE 0 END
+                , 0) + 1) / LN(21))
+                     * LEAST(1.0, COALESCE(city_padel_venue_count, 0) / 5.0)
+          END
+        -- Addressable market (15 pts)
+        + 15.0 * LEAST(1.0, LN(GREATEST(population, 1)) / LN(1000000))
+        -- Economic context (10 pts)
+        + 10.0 * LEAST(1.0, COALESCE(median_income_pps, 100) / 200.0)
+        -- Data quality (10 pts)
+        + 10.0 * CASE
+            WHEN population > 0 AND COALESCE(city_padel_venue_count, 0) > 0 THEN 1.0
+            WHEN population > 0 OR  COALESCE(city_padel_venue_count, 0) > 0 THEN 0.5
+            ELSE 0.0
+          END
+      , 1)
+    ELSE 0
+    END AS market_score,
+    -- ── Opportunity Score (Marktpotenzial-Score v3, H3 catchment) ──────────
+    ROUND(
+      -- Addressable market (25 pts): log-scaled catchment population, ceiling 500K
+      25.0 * LEAST(1.0, LN(GREATEST(catchment_population, 1)) / LN(500000))
+      -- Economic power (20 pts): income PPS normalised to 35,000
+      + 20.0 * LEAST(1.0, COALESCE(median_income_pps, 15000) / 35000.0)
+      -- Supply gap (30 pts): inverted catchment venue density
+      + 30.0 * GREATEST(0.0, 1.0 - COALESCE(
+          CASE WHEN catchment_population > 0
+            THEN catchment_padel_courts::DOUBLE / catchment_population * 100000
+            ELSE 0.0
+          END, 0.0) / 8.0)
+      -- Catchment gap (15 pts): distance to nearest court
+      + 15.0 * COALESCE(LEAST(1.0, nearest_padel_court_km / 30.0), 0.5)
+      -- Sports culture (10 pts): tennis courts within 25km
+      + 10.0 * LEAST(1.0, tennis_courts_within_25km / 10.0)
+    , 1) AS opportunity_score
+  FROM with_pricing
+)
+SELECT
+  s.geoname_id,
+  s.country_code,
+  s.country_name_en,
+  s.country_slug,
+  s.location_name,
+  s.location_slug,
+  s.city_slug,
+  s.city_name,
+  s.lat,
+  s.lon,
+  s.admin1_code,
+  s.admin2_code,
+  s.population,
+  s.population_year,
+  s.median_income_pps,
+  s.income_year,
+  s.padel_venue_count,
+  s.padel_venues_per_100k,
+  s.nearest_padel_court_km,
+  s.tennis_courts_within_25km,
+  s.city_padel_venue_count,
+  s.city_venues_per_100k,
+  s.data_confidence,
+  s.catchment_population,
+  s.catchment_padel_courts,
+  CASE WHEN s.catchment_population > 0
+    THEN ROUND(s.catchment_padel_courts::DOUBLE / s.catchment_population * 100000, 2)
+    ELSE NULL
+  END AS catchment_venues_per_100k,
+  s.market_score,
+  s.opportunity_score,
+  s.median_hourly_rate,
+  s.median_peak_rate,
+  s.median_offpeak_rate,
+  s.median_occupancy_rate,
+  s.median_daily_revenue_per_venue,
+  s.price_currency,
+  CURRENT_DATE AS refreshed_date
+FROM scored s
+ORDER BY s.market_score DESC, s.opportunity_score DESC

transform/sqlmesh_padelnomics/models/serving/planner_defaults.sql

@@ -76,11 +76,12 @@ city_profiles AS (
     city_slug,
     country_code,
     city_name,
-    padel_venue_count,
+    city_padel_venue_count AS padel_venue_count,
     population,
     market_score,
-    venues_per_100k
-  FROM serving.city_market_profile
+    city_venues_per_100k AS venues_per_100k
+  FROM serving.location_profiles
+  WHERE city_slug IS NOT NULL
 )
 SELECT
   cp.city_slug,

transform/sqlmesh_padelnomics/models/serving/pseo_city_costs_de.sql

@@ -31,10 +31,10 @@ SELECT
   c.lon,
   -- Market metrics
   c.population,
-  c.padel_venue_count,
-  c.venues_per_100k,
+  c.city_padel_venue_count AS padel_venue_count,
+  c.city_venues_per_100k AS venues_per_100k,
   c.market_score,
-  lop.opportunity_score,
+  c.opportunity_score,
   c.data_confidence,
   -- Pricing (from Playtomic, NULL when no coverage)
   c.median_hourly_rate,
@@ -85,15 +85,13 @@ SELECT
   cc.working_capital                AS "workingCapital",
   cc.permits_compliance             AS "permitsCompliance",
   CURRENT_DATE                      AS refreshed_date
-FROM serving.city_market_profile c
+FROM serving.location_profiles c
 LEFT JOIN serving.planner_defaults p
   ON c.country_code = p.country_code
   AND c.city_slug = p.city_slug
-LEFT JOIN serving.location_opportunity_profile lop
-  ON c.country_code = lop.country_code
-  AND c.geoname_id = lop.geoname_id
 LEFT JOIN foundation.dim_countries cc
   ON c.country_code = cc.country_code
 -- Only cities with actual padel presence and at least some rate data
-WHERE c.padel_venue_count > 0
+WHERE c.city_slug IS NOT NULL
+  AND c.city_padel_venue_count > 0
   AND (p.rate_peak IS NOT NULL OR c.median_peak_rate IS NOT NULL)

transform/sqlmesh_padelnomics/models/serving/pseo_city_pricing.sql

@@ -1,6 +1,6 @@
 -- pSEO article data: per-city padel court pricing.
 -- One row per city — consumed by the city-pricing.md.jinja template.
--- Joins venue_pricing_benchmarks (real Playtomic data) with city_market_profile
+-- Joins venue_pricing_benchmarks (real Playtomic data) with location_profiles
 -- (population, venue count, country metadata).
 --
 -- Stricter filter than pseo_city_costs_de: requires >= 2 venues with real
@@ -16,7 +16,7 @@ MODEL (
 SELECT
   -- Composite natural key: country_slug + city_slug ensures uniqueness across countries
   c.country_slug || '-' || c.city_slug  AS city_key,
-  -- City identity (from city_market_profile, which has the canonical city_slug)
+  -- City identity (from location_profiles, which has the canonical city_slug)
   c.city_slug,
   c.city_name,
   c.country_code,
@@ -24,8 +24,8 @@ SELECT
   c.country_slug,
   -- Market context
   c.population,
-  c.padel_venue_count,
-  c.venues_per_100k,
+  c.city_padel_venue_count AS padel_venue_count,
+  c.city_venues_per_100k AS venues_per_100k,
   c.market_score,
   -- Pricing benchmarks (from Playtomic availability data)
   vpb.median_hourly_rate,
@@ -38,9 +38,10 @@ SELECT
   vpb.price_currency,
   CURRENT_DATE AS refreshed_date
 FROM serving.venue_pricing_benchmarks vpb
--- Join city_market_profile to get the canonical city_slug and country metadata
-INNER JOIN serving.city_market_profile c
+-- Join location_profiles to get canonical city metadata
+INNER JOIN serving.location_profiles c
   ON  vpb.country_code = c.country_code
   AND vpb.city_slug = c.city_slug
+  AND c.city_slug IS NOT NULL
 -- Only cities with enough venues for meaningful pricing statistics
 WHERE vpb.venue_count >= 2