cartodb4/crankshaft
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'develop' into add-spatial-markov

Browse Source
This commit is contained in:
Andy Eschbacher
2016-06-28 10:19:36 -04:00
parent 4834ee2f42 faa899cf87
commit dd0ca9a24f
69 changed files with 3641 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pg/Makefile
+1 -6
View File
@@ -7,7 +7,6 @@ include ../../Makefile.global
# requires sudo. In additionof the current development version
# named 'dev', an alias 'current' is generating for ease of
# update (upgrade to 'current', then to 'dev').
# the python module is installed in a virtualenv in envs/dev/
# * test runs the tests for the currently generated Development
# extension.
@@ -18,11 +17,8 @@ DATA = $(EXTENSION)--dev.sql \
SOURCES_DATA_DIR = sql
SOURCES_DATA = $(wildcard $(SOURCES_DATA_DIR)/*.sql)
VIRTUALENV_PATH = $(realpath ../../envs)
ESC_VIRVIRTUALENV_PATH = $(subst /,\/,$(VIRTUALENV_PATH))
REPLACEMENTS = -e 's/@@VERSION@@/$(EXTVERSION)/g' \
-e 's/@@VIRTUALENV_PATH@@/$(ESC_VIRVIRTUALENV_PATH)/g'
REPLACEMENTS = -e 's/@@VERSION@@/$(EXTVERSION)/g'
$(DATA): $(SOURCES_DATA)
$(SED) $(REPLACEMENTS) $(SOURCES_DATA_DIR)/*.sql > $@
@@ -54,7 +50,6 @@ release: ../../release/$(EXTENSION).control $(SOURCES_DATA)
$(SED) $(REPLACEMENTS) $(SOURCES_DATA_DIR)/*.sql > ../../release/$(EXTENSION)--$(EXTVERSION).sql
# Install the current relese into the PostgreSQL extensions directory
# and the Python package in a virtual environment envs/X.Y.Z
deploy:
$(INSTALL_DATA) ../../release/$(EXTENSION).control '$(DESTDIR)$(datadir)/extension/'
$(INSTALL_DATA) ../../release/*.sql '$(DESTDIR)$(datadir)/extension/'
src/pg/crankshaft.control
+2 -2
View File
@@ -1,5 +1,5 @@
comment = 'CartoDB Spatial Analysis extension'
default_version = '0.0.2'
requires = 'plpythonu, postgis, cartodb'
default_version = '0.0.4'
requires = 'plpythonu, postgis'
superuser = true
schema = cdb_crankshaft
src/pg/sql/02_py.sql
-23
View File
@@ -1,23 +0,0 @@
CREATE OR REPLACE FUNCTION _cdb_crankshaft_virtualenvs_path()
RETURNS text
AS $$
BEGIN
-- RETURN '/opt/virtualenvs/crankshaft';
RETURN '@@VIRTUALENV_PATH@@';
END;
$$ language plpgsql IMMUTABLE STRICT;
-- Use the crankshaft python module
CREATE OR REPLACE FUNCTION _cdb_crankshaft_activate_py()
RETURNS VOID
AS $$
import os
# plpy.notice('%',str(os.environ))
# activate virtualenv
crankshaft_version = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_internal_version()')[0]['_cdb_crankshaft_internal_version']
base_path = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_virtualenvs_path()')[0]['_cdb_crankshaft_virtualenvs_path']
default_venv_path = os.path.join(base_path, crankshaft_version)
venv_path = os.environ.get('CRANKSHAFT_VENV', default_venv_path)
activate_path = venv_path + '/bin/activate_this.py'
exec(open(activate_path).read(), dict(__file__=activate_path))
$$ LANGUAGE plpythonu;
src/pg/sql/03_random_seeds.sql
-1
View File
@@ -4,7 +4,6 @@
CREATE OR REPLACE FUNCTION
_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft import random_seeds
random_seeds.set_random_seeds(seed_value)
$$ LANGUAGE plpythonu;
src/pg/sql/08_interpolation.sql
+130
View File
@@ -0,0 +1,130 @@
-- 0: nearest neighbor
-- 1: barymetric
-- 2: IDW
CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
IN query text,
IN point geometry,
IN method integer DEFAULT 1,
IN p1 numeric DEFAULT 0,
IN p2 numeric DEFAULT 0
)
RETURNS numeric AS
$$
DECLARE
gs geometry[];
vs numeric[];
output numeric;
BEGIN
EXECUTE 'WITH a AS('||query||') SELECT array_agg(the_geom), array_agg(attrib) FROM a' INTO gs, vs;
SELECT CDB_SpatialInterpolation(gs, vs, point, method, p1,p2) INTO output FROM a;
RETURN output;
END;
$$
language plpgsql IMMUTABLE;
CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
IN geomin geometry[],
IN colin numeric[],
IN point geometry,
IN method integer DEFAULT 1,
IN p1 numeric DEFAULT 0,
IN p2 numeric DEFAULT 0
)
RETURNS numeric AS
$$
DECLARE
gs geometry[];
vs numeric[];
gs2 geometry[];
vs2 numeric[];
g geometry;
vertex geometry[];
sg numeric;
sa numeric;
sb numeric;
sc numeric;
va numeric;
vb numeric;
vc numeric;
output numeric;
BEGIN
output := -999.999;
-- nearest
IF method = 0 THEN
WITH a as (SELECT unnest(geomin) as g, unnest(colin) as v)
SELECT a.v INTO output FROM a ORDER BY point<->a.g LIMIT 1;
RETURN output;
-- barymetric
ELSIF method = 1 THEN
WITH a as (SELECT unnest(geomin) AS e),
b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e),0.001, 0) AS t FROM a),
c as (SELECT (ST_Dump(t)).geom as v FROM b),
d as (SELECT v FROM c WHERE ST_Within(point, v))
SELECT v INTO g FROM d;
IF g is null THEN
-- out of the realm of the input data
RETURN -888.888;
END IF;
-- vertex of the selected cell
WITH a AS (SELECT (ST_DumpPoints(g)).geom AS v)
SELECT array_agg(v) INTO vertex FROM a;
-- retrieve the value of each vertex
WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
SELECT c INTO va FROM a WHERE ST_Equals(geo, vertex[1]);
WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
SELECT c INTO vb FROM a WHERE ST_Equals(geo, vertex[2]);
WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
SELECT c INTO vc FROM a WHERE ST_Equals(geo, vertex[3]);
SELECT ST_area(g), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[2], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[1], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point,vertex[1],vertex[2], point]))) INTO sg, sa, sb, sc;
output := (coalesce(sa,0) * coalesce(va,0) + coalesce(sb,0) * coalesce(vb,0) + coalesce(sc,0) * coalesce(vc,0)) / coalesce(sg);
RETURN output;
-- IDW
-- p1: limit the number of neighbors, 0->no limit
-- p2: order of distance decay, 0-> order 1
ELSIF method = 2 THEN
IF p2 = 0 THEN
p2 := 1;
END IF;
WITH a as (SELECT unnest(geomin) as g, unnest(colin) as v),
b as (SELECT a.g, a.v FROM a ORDER BY point<->a.g)
SELECT array_agg(b.g), array_agg(b.v) INTO gs, vs FROM b;
IF p1::integer>0 THEN
gs2:=gs;
vs2:=vs;
FOR i IN 1..p1
LOOP
gs2 := gs2 || gs[i];
vs2 := vs2 || vs[i];
END LOOP;
ELSE
gs2:=gs;
vs2:=vs;
END IF;
WITH a as (SELECT unnest(gs2) as g, unnest(vs2) as v),
b as (
SELECT
(1/ST_distance(point, a.g)^p2::integer) as k,
(a.v/ST_distance(point, a.g)^p2::integer) as f
FROM a
)
SELECT sum(b.f)/sum(b.k) INTO output FROM b;
RETURN output;
END IF;
RETURN -777.777;
END;
$$
language plpgsql IMMUTABLE;
src/pg/sql/10_moran.sql
-4
View File
@@ -10,7 +10,6 @@ CREATE OR REPLACE FUNCTION
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, significance NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
@@ -28,7 +27,6 @@ CREATE OR REPLACE FUNCTION
id_col TEXT)
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
@@ -122,7 +120,6 @@ CREATE OR REPLACE FUNCTION
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran FLOAT, significance FLOAT)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
@@ -143,7 +140,6 @@ CREATE OR REPLACE FUNCTION
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local_rate
# TODO: use named parameters or a dictionary
return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
src/pg/sql/11_kmeans.sql
+49
View File
@@ -0,0 +1,49 @@
CREATE OR REPLACE FUNCTION CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
RETURNS table (cartodb_id integer, cluster_no integer) as $$
from crankshaft.clustering import kmeans
return kmeans(query,no_clusters,no_init)
$$ language plpythonu;
CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
RETURNS Numeric[] AS
$$
DECLARE
newX NUMERIC;
newY NUMERIC;
newW NUMERIC;
BEGIN
IF weight IS NULL OR the_geom IS NULL THEN
newX = state[1];
newY = state[2];
newW = state[3];
ELSE
newX = state[1] + ST_X(the_geom)*weight;
newY = state[2] + ST_Y(the_geom)*weight;
newW = state[3] + weight;
END IF;
RETURN Array[newX,newY,newW];
END
$$ LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
RETURNS GEOMETRY AS
$$
BEGIN
IF state[3] = 0 THEN
RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
ELSE
RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
END IF;
END
$$ LANGUAGE plpgsql;
CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC)(
SFUNC = CDB_WeightedMeanS,
FINALFUNC = CDB_WeightedMeanF,
STYPE = Numeric[],
INITCOND = "{0.0,0.0,0.0}"
);
src/pg/test/expected/01_install_test.out
-1
View File
@@ -1,6 +1,5 @@
-- Install dependencies
CREATE EXTENSION plpythonu;
CREATE EXTENSION postgis;
CREATE EXTENSION cartodb;
-- Install the extension
CREATE EXTENSION crankshaft VERSION 'dev';
src/pg/test/expected/05_kmeans_test.out
+10
View File
@@ -0,0 +1,10 @@
\pset format unaligned
\set ECHO all
SELECT count(DISTINCT cluster_no) as clusters from cdb_crankshaft.cdb_kmeans('select * from ppoints', 2);
clusters
2
(1 row)
SELECT count(*) clusters from (select cdb_crankshaft.CDB_WeightedMean(the_geom, value::NUMERIC), code from ppoints group by code) p;
clusters
52
(1 row)
src/pg/test/expected/08_interpolation_test.out
+5
View File
@@ -0,0 +1,5 @@
SET client_min_messages TO WARNING;
\set ECHO none
cdb_spatialinterpolation
t
(1 row)
src/pg/test/sql/01_install_test.sql
-1
View File
@@ -1,7 +1,6 @@
-- Install dependencies
CREATE EXTENSION plpythonu;
CREATE EXTENSION postgis;
CREATE EXTENSION cartodb;
-- Install the extension
CREATE EXTENSION crankshaft VERSION 'dev';
src/pg/test/sql/05_kmeans_test.sql
+6
View File
@@ -0,0 +1,6 @@
\pset format unaligned
\set ECHO all
SELECT count(DISTINCT cluster_no) as clusters from cdb_crankshaft.cdb_kmeans('select * from ppoints', 2);
SELECT count(*) clusters from (select cdb_crankshaft.CDB_WeightedMean(the_geom, value::NUMERIC), code from ppoints group by code) p;
src/pg/test/sql/08_interpolation_test.sql
+10
View File
@@ -0,0 +1,10 @@
SET client_min_messages TO WARNING;
\set ECHO none
\pset format unaligned
WITH a AS (
SELECT
ARRAY[800, 700, 600, 500, 400, 300, 200, 100] AS vals,
ARRAY[ST_GeomFromText('POINT(2.1744 41.403)'),ST_GeomFromText('POINT(2.1228 41.380)'),ST_GeomFromText('POINT(2.1511 41.374)'),ST_GeomFromText('POINT(2.1528 41.413)'),ST_GeomFromText('POINT(2.165 41.391)'),ST_GeomFromText('POINT(2.1498 41.371)'),ST_GeomFromText('POINT(2.1533 41.368)'),ST_GeomFromText('POINT(2.131386 41.41399)')] AS g
)
SELECT (cdb_crankshaft.CDB_SpatialInterpolation(g, vals, ST_GeomFromText('POINT(2.154 41.37)'), 1) - 780.79470198683925288365) / 780.79470198683925288365 < 0.001 As cdb_spatialinterpolation FROM a;
src/pg/test/sql/90_permissions.sql
+1 -1
View File
@@ -4,7 +4,7 @@ SELECT cdb_crankshaft._cdb_random_seeds(1234);
SET ROLE test_regular_user;
-- Add to the search path the schema
SET search_path TO public,cartodb,cdb_crankshaft;
SET search_path TO public,cdb_crankshaft;
-- Exercise public functions
SELECT ppoints.code, m.quads