improvements to scoring, fixing oversimplification and removing some premature optimization
This commit is contained in:
@@ -341,7 +341,7 @@ CREATE OR REPLACE FUNCTION cdb_observatory.OBS_GetMeasure(
|
||||
normalize TEXT DEFAULT NULL,
|
||||
boundary_id TEXT DEFAULT NULL,
|
||||
time_span TEXT DEFAULT NULL,
|
||||
simplification NUMERIC DEFAULT 0.0001
|
||||
simplification NUMERIC DEFAULT 0.00001
|
||||
)
|
||||
RETURNS NUMERIC
|
||||
AS $$
|
||||
@@ -408,7 +408,7 @@ BEGIN
|
||||
USING COALESCE(boundary_id, ''), measure_id, COALESCE(time_span, ''),
|
||||
CASE WHEN ST_GeometryType(geom) = 'ST_Point' THEN
|
||||
st_buffer(geom::geography, 10)::geometry(geometry, 4326)
|
||||
ELSE ST_Envelope(geom)
|
||||
ELSE geom
|
||||
END;
|
||||
|
||||
IF geom_id IS NULL THEN
|
||||
@@ -485,7 +485,7 @@ BEGIN
|
||||
sql = format('WITH _subdivided AS (
|
||||
SELECT ST_Subdivide($1) AS geom
|
||||
), _geom AS (SELECT SUM(ST_Area(ST_Intersection(s.geom, geom.%I)))
|
||||
/ ST_Area(FIRST(geom.%I)) overlap, geom.%I geom_ref
|
||||
/ ST_Area(cdb_observatory.FIRST(geom.%I)) overlap, geom.%I geom_ref
|
||||
FROM observatory.%I geom, _subdivided s
|
||||
WHERE ST_Intersects(s.geom, geom.%I)
|
||||
GROUP BY geom.%I),
|
||||
|
||||
@@ -431,10 +431,7 @@ BEGIN
|
||||
RETURN QUERY
|
||||
EXECUTE format($string$
|
||||
SELECT
|
||||
(1 / (abs(numgeoms - $3)
|
||||
--* (1 / Coalesce(NullIf(notnull_percent, 0), 1))
|
||||
--* (1 / Coalesce(NullIf(percentfill, 0), 0.0001))
|
||||
))::Numeric * percentfill
|
||||
((100.0 / (1+abs(log(1 + $3) - log(1 + numgeoms)))) * percentfill)::Numeric
|
||||
AS score, *
|
||||
FROM (
|
||||
WITH clipped_geom AS (
|
||||
|
||||
@@ -352,25 +352,25 @@ AS _obs_getavailablegeometries_foobarbaz_denom_not_in_2010_2014;
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']
|
||||
'us.census.tiger.county', 'us.census.tiger.zcta5']
|
||||
AS _obs_geometryscores_500m_buffer
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 500)::Geometry(Geometry, 4326),
|
||||
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']);
|
||||
'us.census.tiger.county', 'us.census.tiger.zcta5']);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']
|
||||
'us.census.tiger.county', 'us.census.tiger.zcta5']
|
||||
AS _obs_geometryscores_5km_buffer
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 5000)::Geometry(Geometry, 4326),
|
||||
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']);
|
||||
'us.census.tiger.county', 'us.census.tiger.zcta5']);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY['us.census.tiger.census_tract', 'us.census.tiger.zcta5',
|
||||
'us.census.tiger.county', 'us.census.tiger.block_group']
|
||||
ARRAY['us.census.tiger.census_tract', 'us.census.tiger.block_group',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']
|
||||
AS _obs_geometryscores_50km_buffer
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
|
||||
@@ -378,8 +378,8 @@ SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY[ 'us.census.tiger.county', 'us.census.tiger.zcta5',
|
||||
'us.census.tiger.census_tract', 'us.census.tiger.block_group']
|
||||
ARRAY[ 'us.census.tiger.zcta5', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.county', 'us.census.tiger.block_group']
|
||||
AS _obs_geometryscores_500km_buffer
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 500000)::Geometry(Geometry, 4326),
|
||||
@@ -436,8 +436,8 @@ SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text =
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY['us.census.tiger.county', 'us.census.tiger.zcta5',
|
||||
'us.census.tiger.census_tract', 'us.census.tiger.block_group']
|
||||
ARRAY['us.census.tiger.county', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.block_group']
|
||||
AS _obs_geometryscores_500km_buffer_50_geoms
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
|
||||
@@ -445,8 +445,8 @@ SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county'], 50);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC)
|
||||
= ARRAY['us.census.tiger.zcta5', 'us.census.tiger.county',
|
||||
'us.census.tiger.census_tract', 'us.census.tiger.block_group']
|
||||
= ARRAY['us.census.tiger.zcta5', 'us.census.tiger.census_tract',
|
||||
'us.census.tiger.block_group', 'us.census.tiger.county']
|
||||
AS _obs_geometryscores_500km_buffer_500_geoms
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
|
||||
@@ -454,8 +454,8 @@ SELECT ARRAY_AGG(geom_id ORDER BY score DESC)
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county'], 500);
|
||||
|
||||
SELECT ARRAY_AGG(geom_id ORDER BY score DESC) =
|
||||
ARRAY['us.census.tiger.census_tract', 'us.census.tiger.zcta5',
|
||||
'us.census.tiger.county', 'us.census.tiger.block_group']
|
||||
ARRAY['us.census.tiger.census_tract', 'us.census.tiger.block_group',
|
||||
'us.census.tiger.zcta5', 'us.census.tiger.county']
|
||||
AS _obs_geometryscores_500km_buffer_2500_geoms
|
||||
FROM cdb_observatory._OBS_GetGeometryScores(
|
||||
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
|
||||
|
||||
Reference in New Issue
Block a user