feat(sql): thread opportunity_score from location_opportunity_profile into pSEO serving chain
- dim_cities: add geoname_id to geonames_pop CTE and final SELECT
Creates FK between dim_cities (city-with-padel-venues) and dim_locations (all GeoNames),
enabling joins to location_opportunity_profile for the first time.
- city_market_profile: pass geoname_id through base CTE and final SELECT
- pseo_city_costs_de: LEFT JOIN location_opportunity_profile on (country_code, geoname_id),
add opportunity_score to output columns
- pseo_country_overview: add avg_opportunity_score, top_opportunity_score, top_opportunity_slugs,
top_opportunity_names aggregates
Cities with no GeoNames name match get opportunity_score = NULL; templates guard with
{% if opportunity_score %}.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -75,7 +75,7 @@ uk_pop AS (
|
|||||||
),
|
),
|
||||||
-- GeoNames global fallback (all cities ≥50K)
|
-- GeoNames global fallback (all cities ≥50K)
|
||||||
geonames_pop AS (
|
geonames_pop AS (
|
||||||
SELECT city_name, country_code, population, ref_year
|
SELECT geoname_id, city_name, country_code, population, ref_year
|
||||||
FROM staging.stg_population_geonames
|
FROM staging.stg_population_geonames
|
||||||
QUALIFY ROW_NUMBER() OVER (PARTITION BY geoname_id ORDER BY ref_year DESC) = 1
|
QUALIFY ROW_NUMBER() OVER (PARTITION BY geoname_id ORDER BY ref_year DESC) = 1
|
||||||
)
|
)
|
||||||
@@ -153,7 +153,10 @@ SELECT
|
|||||||
)::INTEGER AS population_year,
|
)::INTEGER AS population_year,
|
||||||
vc.padel_venue_count,
|
vc.padel_venue_count,
|
||||||
ci.median_income_pps,
|
ci.median_income_pps,
|
||||||
ci.income_year
|
ci.income_year,
|
||||||
|
-- GeoNames ID: FK to dim_locations / location_opportunity_profile.
|
||||||
|
-- NULL when city name doesn't match any GeoNames entry.
|
||||||
|
gn.geoname_id
|
||||||
FROM venue_cities vc
|
FROM venue_cities vc
|
||||||
LEFT JOIN country_income ci ON vc.country_code = ci.country_code
|
LEFT JOIN country_income ci ON vc.country_code = ci.country_code
|
||||||
-- Eurostat EU population (via city code→name lookup)
|
-- Eurostat EU population (via city code→name lookup)
|
||||||
|
|||||||
@@ -33,6 +33,7 @@ WITH base AS (
|
|||||||
c.padel_venue_count,
|
c.padel_venue_count,
|
||||||
c.median_income_pps,
|
c.median_income_pps,
|
||||||
c.income_year,
|
c.income_year,
|
||||||
|
c.geoname_id,
|
||||||
-- Venue density: padel venues per 100K residents
|
-- Venue density: padel venues per 100K residents
|
||||||
CASE WHEN c.population > 0
|
CASE WHEN c.population > 0
|
||||||
THEN ROUND(c.padel_venue_count::DOUBLE / c.population * 100000, 2)
|
THEN ROUND(c.padel_venue_count::DOUBLE / c.population * 100000, 2)
|
||||||
@@ -107,6 +108,7 @@ SELECT
|
|||||||
s.median_occupancy_rate,
|
s.median_occupancy_rate,
|
||||||
s.median_daily_revenue_per_venue,
|
s.median_daily_revenue_per_venue,
|
||||||
s.price_currency,
|
s.price_currency,
|
||||||
|
s.geoname_id,
|
||||||
CURRENT_DATE AS refreshed_date
|
CURRENT_DATE AS refreshed_date
|
||||||
FROM scored s
|
FROM scored s
|
||||||
ORDER BY s.market_score DESC
|
ORDER BY s.market_score DESC
|
||||||
|
|||||||
@@ -27,6 +27,7 @@ SELECT
|
|||||||
c.padel_venue_count,
|
c.padel_venue_count,
|
||||||
c.venues_per_100k,
|
c.venues_per_100k,
|
||||||
c.market_score,
|
c.market_score,
|
||||||
|
lop.opportunity_score,
|
||||||
c.data_confidence,
|
c.data_confidence,
|
||||||
-- Pricing (from Playtomic, NULL when no coverage)
|
-- Pricing (from Playtomic, NULL when no coverage)
|
||||||
c.median_hourly_rate,
|
c.median_hourly_rate,
|
||||||
@@ -48,6 +49,9 @@ FROM serving.city_market_profile c
|
|||||||
LEFT JOIN serving.planner_defaults p
|
LEFT JOIN serving.planner_defaults p
|
||||||
ON c.country_code = p.country_code
|
ON c.country_code = p.country_code
|
||||||
AND c.city_slug = p.city_slug
|
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
|
||||||
-- Only cities with actual padel presence and at least some rate data
|
-- Only cities with actual padel presence and at least some rate data
|
||||||
WHERE c.padel_venue_count > 0
|
WHERE c.padel_venue_count > 0
|
||||||
AND (p.rate_peak IS NOT NULL OR c.median_peak_rate IS NOT NULL)
|
AND (p.rate_peak IS NOT NULL OR c.median_peak_rate IS NOT NULL)
|
||||||
|
|||||||
@@ -23,6 +23,12 @@ SELECT
|
|||||||
-- Top 5 cities by market score for internal linking (DuckDB list slice syntax)
|
-- Top 5 cities by market score for internal linking (DuckDB list slice syntax)
|
||||||
LIST(city_slug ORDER BY market_score DESC NULLS LAST)[1:5] AS top_city_slugs,
|
LIST(city_slug ORDER BY market_score DESC NULLS LAST)[1:5] AS top_city_slugs,
|
||||||
LIST(city_name ORDER BY market_score DESC NULLS LAST)[1:5] AS top_city_names,
|
LIST(city_name ORDER BY market_score DESC NULLS LAST)[1:5] AS top_city_names,
|
||||||
|
-- Opportunity score aggregates (NULL-safe: cities without geoname_id match excluded from AVG)
|
||||||
|
ROUND(AVG(opportunity_score), 1) AS avg_opportunity_score,
|
||||||
|
MAX(opportunity_score) AS top_opportunity_score,
|
||||||
|
-- Top 5 cities by opportunity score (may differ from top market score cities)
|
||||||
|
LIST(city_slug ORDER BY opportunity_score DESC NULLS LAST)[1:5] AS top_opportunity_slugs,
|
||||||
|
LIST(city_name ORDER BY opportunity_score DESC NULLS LAST)[1:5] AS top_opportunity_names,
|
||||||
-- Pricing medians across cities (NULL when no Playtomic coverage in country)
|
-- Pricing medians across cities (NULL when no Playtomic coverage in country)
|
||||||
ROUND(MEDIAN(median_hourly_rate), 0) AS median_hourly_rate,
|
ROUND(MEDIAN(median_hourly_rate), 0) AS median_hourly_rate,
|
||||||
ROUND(MEDIAN(median_peak_rate), 0) AS median_peak_rate,
|
ROUND(MEDIAN(median_peak_rate), 0) AS median_peak_rate,
|
||||||
|
|||||||
Reference in New Issue
Block a user