Merge pull request #209 from CartoDB/use-rasters

Use rasters
This commit is contained in:
john krauss
2016-11-09 16:58:25 -05:00
committed by GitHub
7 changed files with 853 additions and 257 deletions
+2 -2
View File
@@ -61,7 +61,7 @@ def get_tablename_query(column_id, boundary_id, timespan):
METADATA_TABLES = ['obs_table', 'obs_column_table', 'obs_column', 'obs_column_tag',
'obs_tag', 'obs_column_to_column', 'obs_dump_version', 'obs_meta',
'obs_meta_numer', 'obs_meta_denom', 'obs_meta_geom',
'obs_meta_timespan', ]
'obs_meta_timespan', 'obs_column_table_tile', ]
FIXTURES = [
('us.census.acs.B01003001_quantile', 'us.census.tiger.census_tract', '2010 - 2014'),
@@ -290,7 +290,7 @@ def main():
"column_id IN ('{}', '{}')".format(numer_id, geom_id)
for numer_id, geom_id, timespan in FIXTURES
])
elif tablename == 'obs_column_table':
elif tablename in ('obs_column_table', 'obs_column_table_tile', ):
where = 'WHERE column_id IN ({numer_ids}) ' \
'OR column_id IN ({geom_ids}) ' \
'OR table_id IN ({table_ids}) '.format(
+32 -17
View File
@@ -360,6 +360,7 @@ DECLARE
geom_colname TEXT;
geom_geomref_colname TEXT;
geom_tablename TEXT;
geom_id TEXT;
result NUMERIC;
sql TEXT;
numer_name TEXT;
@@ -370,23 +371,6 @@ BEGIN
geom := ST_SnapToGrid(geom, 0.000001);
EXECUTE
$query$
SELECT numer_aggregate, numer_colname, numer_geomref_colname, numer_tablename,
denom_colname, denom_geomref_colname, denom_tablename,
geom_colname, geom_geomref_colname, geom_tablename, numer_name
FROM observatory.obs_meta
WHERE (geom_id = $1 OR ($1 = ''))
AND numer_id = $2
AND (numer_timespan = $3 OR ($3 = ''))
ORDER BY geom_weight DESC, numer_timespan DESC
LIMIT 1
$query$
INTO numer_aggregate, numer_colname, numer_geomref_colname, numer_tablename,
denom_colname, denom_geomref_colname, denom_tablename,
geom_colname, geom_geomref_colname, geom_tablename, numer_name
USING COALESCE(boundary_id, ''), measure_id, COALESCE(time_span, '');
IF ST_GeometryType(geom) = 'ST_Point' THEN
geom_type := 'point';
ELSIF ST_GeometryType(geom) IN ('ST_Polygon', 'ST_MultiPolygon') THEN
@@ -397,6 +381,37 @@ BEGIN
ST_GeometryType(geom);
END IF;
EXECUTE
$query$
WITH meta AS (SELECT numer_aggregate, numer_colname, numer_geomref_colname, numer_tablename,
denom_colname, denom_geomref_colname, denom_tablename,
geom_colname, geom_geomref_colname, geom_tablename,
numer_name, geom_id
FROM observatory.obs_meta
WHERE (geom_id = $1 OR ($1 = ''))
AND numer_id = $2
AND (numer_timespan = $3 OR ($3 = ''))),
scores AS (SELECT *
FROM cdb_observatory._OBS_GetGeometryScores($4,
(SELECT Array_Agg(geom_id) FROM meta), 500))
SELECT meta.*
FROM meta, scores
WHERE meta.geom_id = scores.geom_id
ORDER BY score DESC
LIMIT 1
$query$
INTO numer_aggregate, numer_colname, numer_geomref_colname, numer_tablename,
denom_colname, denom_geomref_colname, denom_tablename,
geom_colname, geom_geomref_colname, geom_tablename, numer_name, geom_id
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 geom
END;
raise notice 'Using boundary %', geom_id;
IF normalize ILIKE 'area' AND numer_aggregate ILIKE 'sum' THEN
map_type := 'areaNormalized';
ELSIF normalize ILIKE 'denominator' THEN
+102 -13
View File
@@ -254,7 +254,14 @@ CREATE OR REPLACE FUNCTION cdb_observatory.OBS_GetAvailableGeometries(
geom_source TEXT,
valid_numer BOOLEAN,
valid_denom BOOLEAN,
valid_timespan BOOLEAN
valid_timespan BOOLEAN,
score NUMERIC,
numtiles BIGINT,
notnull_percent NUMERIC,
numgeoms NUMERIC,
percentfill NUMERIC,
estnumgeoms NUMERIC,
meanmediansize NUMERIC
) AS $$
DECLARE
geom_clause TEXT;
@@ -271,18 +278,27 @@ BEGIN
RETURN QUERY
EXECUTE
format($string$
SELECT geom_id::TEXT,
geom_name::TEXT,
geom_description::TEXT,
geom_weight::NUMERIC,
NULL::TEXT geom_aggregate,
NULL::TEXT license,
NULL::TEXT source,
$1 = ANY(numers) valid_numer,
$2 = ANY(denoms) valid_denom,
$3 = ANY(timespans) valid_timespan
FROM observatory.obs_meta_geom
WHERE %s (geom_tags ?& $4 OR CARDINALITY($4) = 0)
WITH available_geoms AS (
SELECT geom_id::TEXT,
geom_name::TEXT,
geom_description::TEXT,
geom_weight::NUMERIC,
NULL::TEXT geom_aggregate,
NULL::TEXT license,
NULL::TEXT source,
$1 = ANY(numers) valid_numer,
$2 = ANY(denoms) valid_denom,
$3 = ANY(timespans) valid_timespan
FROM observatory.obs_meta_geom
WHERE %s (geom_tags ?& $4 OR CARDINALITY($4) = 0)
), scores AS (
SELECT * FROM cdb_observatory._OBS_GetGeometryScores($5,
(SELECT ARRAY_AGG(geom_id) FROM available_geoms)
)
) SELECT available_geoms.*, score, numtiles, notnull_percent, numgeoms,
percentfill, estnumgeoms, meanmediansize
FROM available_geoms, scores
WHERE available_geoms.geom_id = scores.geom_id
$string$, geom_clause)
USING numer_id, denom_id, timespan, filter_tags, bounds;
RETURN;
@@ -397,3 +413,76 @@ BEGIN
RETURN;
END
$$ LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION cdb_observatory._OBS_GetGeometryScores(
bounds Geometry(Geometry, 4326) DEFAULT NULL,
filter_geom_ids TEXT[] DEFAULT NULL,
desired_num_geoms INTEGER DEFAULT 3000
) RETURNS TABLE (
score NUMERIC,
numtiles BIGINT,
geom_id TEXT,
notnull_percent NUMERIC,
numgeoms NUMERIC,
percentfill NUMERIC,
estnumgeoms NUMERIC,
meanmediansize NUMERIC
) AS $$
BEGIN
filter_geom_ids := COALESCE(filter_geom_ids, (ARRAY[])::TEXT[]);
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
AS score, *
FROM (
WITH clipped_geom AS (
SELECT column_id, table_id
, CASE WHEN $1 IS NOT NULL THEN ST_Clip(tile, $1, True)
ELSE tile END clipped_tile
, tile
FROM observatory.obs_column_table_tile
WHERE ($1 IS NULL OR ST_Intersects($1, tile))
AND (column_id = ANY($2) OR cardinality($2) = 0)
), clipped_geom_countagg AS (
SELECT column_id, table_id
, ST_CountAgg(clipped_tile, 2, True)::Numeric notnull_pixels
, ST_CountAgg(clipped_tile, 2, False)::Numeric pixels
FROM clipped_geom
GROUP BY column_id, table_id
) SELECT
count(*)::BIGINT, a.column_id
, (CASE WHEN cdb_observatory.FIRST(notnull_pixels) > 0
THEN cdb_observatory.FIRST(notnull_pixels) / cdb_observatory.FIRST(pixels)
ELSE 1
END)::Numeric AS notnull_percent
, (CASE WHEN cdb_observatory.FIRST(notnull_pixels) > 0
THEN (ST_SummaryStatsAgg(clipped_tile, 2, True)).sum
ELSE COALESCE(ST_Value(cdb_observatory.FIRST(tile), 2, ST_PointOnSurface($1)), 0) * (ST_Area($1) / ST_Area(ST_PixelAsPolygon(cdb_observatory.FIRST(tile), 0, 0)) * cdb_observatory.FIRST(pixels))
END)::Numeric AS numgeoms
, (CASE WHEN cdb_observatory.FIRST(notnull_pixels) > 0
THEN (ST_SummaryStatsAgg(clipped_tile, 3, True)).mean
ELSE COALESCE(ST_Value(cdb_observatory.FIRST(tile), 3, ST_PointOnSurface($1)), 0)
END)::Numeric AS percentfill
, ((ST_Area(ST_Transform($1, 3857)) / 1000000) / NullIf(
CASE WHEN cdb_observatory.FIRST(notnull_pixels) > 0
THEN (ST_SummaryStatsAgg(clipped_tile, 1, True)).mean
ELSE Coalesce(ST_Value(cdb_observatory.FIRST(tile), 1, ST_PointOnSurface($1)), 0)
END, 0))::Numeric AS estnumgeoms
, (CASE WHEN cdb_observatory.FIRST(notnull_pixels) > 0
THEN (ST_SummaryStatsAgg(clipped_tile, 1, True)).mean
ELSE COALESCE(ST_Value(cdb_observatory.FIRST(tile), 1, ST_PointOnSurface($1)), 0)
END)::Numeric AS meanmediansize
FROM clipped_geom_countagg a, clipped_geom b
WHERE a.table_id = b.table_id
AND a.column_id = b.column_id
GROUP BY a.column_id, a.table_id
ORDER BY a.column_id, a.table_id
) foo
$string$) USING bounds, filter_geom_ids, desired_num_geoms;
RETURN;
END
$$ LANGUAGE plpgsql;
@@ -144,6 +144,48 @@ t
_obs_getavailablegeometries_foobarbaz_denom_not_in_2010_2014
t
(1 row)
_obs_geometryscores_500m_buffer
t
(1 row)
_obs_geometryscores_5km_buffer
t
(1 row)
_obs_geometryscores_50km_buffer
t
(1 row)
_obs_geometryscores_500km_buffer
t
(1 row)
_obs_geometryscores_2500km_buffer
t
(1 row)
_obs_geometryscores_numgeoms_500m_buffer
t
(1 row)
_obs_geometryscores_numgeoms_5km_buffer
t
(1 row)
_obs_geometryscores_numgeoms_50km_buffer
t
(1 row)
_obs_geometryscores_numgeoms_500km_buffer
t
(1 row)
_obs_geometryscores_numgeoms_2500km_buffer
t
(1 row)
_obs_geometryscores_500km_buffer_50_geoms
t
(1 row)
_obs_geometryscores_500km_buffer_500_geoms
t
(1 row)
_obs_geometryscores_500km_buffer_2500_geoms
t
(1 row)
_obs_geometryscores_500km_buffer_25000_geoms
t
(1 row)
_total_pop_in_legacy_builder_metadata
t
(1 row)
+1
View File
@@ -12,6 +12,7 @@ DROP TABLE IF EXISTS observatory.obs_meta_numer;
DROP TABLE IF EXISTS observatory.obs_meta_denom;
DROP TABLE IF EXISTS observatory.obs_meta_geom;
DROP TABLE IF EXISTS observatory.obs_meta_timespan;
DROP TABLE IF EXISTS observatory.obs_column_table_tile;
DROP TABLE IF EXISTS observatory.obs_fcd4e4f5610f6764973ef8c0c215b2e80bec8963;
DROP TABLE IF EXISTS observatory.obs_c6fb99c47d61289fbb8e561ff7773799d3fcc308;
DROP TABLE IF EXISTS observatory.obs_6c1309a64d8f3e6986061f4d1ca7b57743e75e74;
+547 -224
View File
File diff suppressed because one or more lines are too long
@@ -346,7 +346,134 @@ FROM cdb_observatory.OBS_GetAvailableTimespans(
) WHERE valid_denom = True)
AS _obs_getavailablegeometries_foobarbaz_denom_not_in_2010_2014;
--
-- _OBS_GetGeometryScores tests
--
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']
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']);
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']
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']);
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']
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),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'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']
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),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'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']
AS _obs_geometryscores_2500km_buffer
FROM cdb_observatory._OBS_GetGeometryScores(
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 2500000)::Geometry(Geometry, 4326),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'us.census.tiger.zcta5', 'us.census.tiger.county']);
SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text
= '{ "us.census.tiger.block_group" : 9, "us.census.tiger.census_tract" : 3, "us.census.tiger.zcta5" : 0, "us.census.tiger.county" : 0 }'
AS _obs_geometryscores_numgeoms_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']);
SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text =
'{ "us.census.tiger.block_group" : 899, "us.census.tiger.census_tract" : 328, "us.census.tiger.zcta5" : 45, "us.census.tiger.county" : 1 }'
AS _obs_geometryscores_numgeoms_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']);
SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text =
'{ "us.census.tiger.block_group" : 12112, "us.census.tiger.census_tract" : 3792, "us.census.tiger.zcta5" : 550, "us.census.tiger.county" : 13 }'
AS _obs_geometryscores_numgeoms_50km_buffer
FROM cdb_observatory._OBS_GetGeometryScores(
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'us.census.tiger.zcta5', 'us.census.tiger.county']);
SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text =
'{ "us.census.tiger.block_group" : 48415, "us.census.tiger.census_tract" : 15776, "us.census.tiger.zcta5" : 6534, "us.census.tiger.county" : 295 }'
AS _obs_geometryscores_numgeoms_500km_buffer
FROM cdb_observatory._OBS_GetGeometryScores(
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 500000)::Geometry(Geometry, 4326),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'us.census.tiger.zcta5', 'us.census.tiger.county']);
SELECT JSON_Object_Agg(geom_id, numgeoms::int ORDER BY numgeoms DESC)::Text =
'{ "us.census.tiger.block_group" : 165489, "us.census.tiger.census_tract" : 55152, "us.census.tiger.zcta5" : 26500, "us.census.tiger.county" : 2551 }'
AS _obs_geometryscores_numgeoms_2500km_buffer
FROM cdb_observatory._OBS_GetGeometryScores(
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 2500000)::Geometry(Geometry, 4326),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'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']
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),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'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']
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),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'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']
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),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'us.census.tiger.zcta5', 'us.census.tiger.county'], 2500);
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']
AS _obs_geometryscores_500km_buffer_25000_geoms
FROM cdb_observatory._OBS_GetGeometryScores(
ST_Buffer(ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)::Geography, 50000)::Geometry(Geometry, 4326),
ARRAY['us.census.tiger.block_group', 'us.census.tiger.census_tract',
'us.census.tiger.zcta5', 'us.census.tiger.county'], 25000);
--
-- OBS_LegacyBuilderMetadata tests
--
SELECT 'us.census.acs.B01003001' IN (SELECT
(jsonb_array_elements(((jsonb_array_elements(subsection))->'f1')->'columns')->'f1')->>'id' AS id
@@ -367,4 +494,3 @@ SELECT 'us.census.acs.B19013001' NOT IN (SELECT
(jsonb_array_elements(((jsonb_array_elements(subsection))->'f1')->'columns')->'f1')->>'id' AS id
FROM cdb_observatory.OBS_LegacyBuilderMetadata('sum')
) AS _median_income_not_in_legacy_builder_metadata_sums;