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

switched signature to put more common options in the front

Browse Source
This commit is contained in:
Andy Eschbacher 2016-06-01 12:09:43 -04:00
parent 434cfcd1e9
commit 2b8adb744d
3 changed files with 55 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
src/pg/sql/10_moran.sql
View File

@ -3,17 +3,17 @@ CREATE OR REPLACE FUNCTION
CDB_AreasOfInterestGlobal(
subquery TEXT,
attr_name TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, significance NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran(subquery, attr, num_ngbrs, permutations, geom_col, id_col, w_type)
return moran(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
$$ LANGUAGE plpythonu;
-- Moran's I Local (internal function)
@ -21,17 +21,17 @@ CREATE OR REPLACE FUNCTION
_CDB_AreasOfInterestLocal(
subquery TEXT,
attr TEXT,
w_type TEXT,
num_ngbrs INT,
permutations INT,
geom_col TEXT,
id_col TEXT,
w_type TEXT,
num_ngbrs INT)
id_col TEXT)
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran_local(subquery, attr, permutations, geom_col, id_col, w_type, num_ngbrs)
return moran_local(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
$$ LANGUAGE plpythonu;
-- Moran's I Local (public-facing function)
@ -39,16 +39,16 @@ CREATE OR REPLACE FUNCTION
CDB_AreasOfInterestLocal(
subquery TEXT,
attr TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, permutations, geom_col, id_col, w_type, num_ngbrs);
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col);
$$ LANGUAGE SQL;
@ -57,16 +57,16 @@ CREATE OR REPLACE FUNCTION
CDB_GetSpatialHotspots(
subquery TEXT,
attr TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('HH', 'HL');
$$ LANGUAGE SQL;
@ -76,16 +76,16 @@ CREATE OR REPLACE FUNCTION
CDB_GetSpatialColdspots(
subquery TEXT,
attr TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('LL', 'LH');
$$ LANGUAGE SQL;
@ -95,16 +95,16 @@ CREATE OR REPLACE FUNCTION
CDB_GetSpatialOutliers(
subquery TEXT,
attr TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('HL', 'LH');
$$ LANGUAGE SQL;
@ -115,17 +115,17 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS TABLE (moran FLOAT, significance FLOAT)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local
# TODO: use named parameters or a dictionary
return moran_rate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs)
return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
$$ LANGUAGE plpythonu;
@ -135,18 +135,18 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT,
num_ngbrs INT,
permutations INT,
geom_col TEXT,
id_col TEXT,
w_type TEXT,
num_ngbrs INT)
id_col TEXT)
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
from crankshaft.clustering import moran_local_rate
# TODO: use named parameters or a dictionary
return moran_local_rate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs)
return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
$$ LANGUAGE plpythonu;
-- Moran's I Local Rate (public-facing function)
@ -155,17 +155,17 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs);
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
$$ LANGUAGE SQL;
@ -175,17 +175,17 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('HH', 'HL');
$$ LANGUAGE SQL;
@ -196,17 +196,17 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('LL', 'LH');
$$ LANGUAGE SQL;
@ -217,17 +217,17 @@ CREATE OR REPLACE FUNCTION
subquery TEXT,
numerator TEXT,
denominator TEXT,
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5,
permutations INT DEFAULT 99,
geom_col TEXT DEFAULT 'the_geom',
id_col TEXT DEFAULT 'cartodb_id',
w_type TEXT DEFAULT 'knn',
num_ngbrs INT DEFAULT 5)
id_col TEXT DEFAULT 'cartodb_id')
RETURNS
TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, ids INT, y NUMERIC)
AS $$
SELECT moran, quads, significance, ids, y
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, permutations, geom_col, id_col, w_type, num_ngbrs)
FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
WHERE quads IN ('HL', 'LH');
$$ LANGUAGE SQL;

8
src/py/crankshaft/crankshaft/clustering/moran.py
View File

@ -14,7 +14,7 @@ import crankshaft.pysal_utils as pu
# High level interface ---------------------------------------
def moran(subquery, attr_name,
permutations, geom_col, id_col, w_type, num_ngbrs):
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I (global)
Implementation building neighbors with a PostGIS database and Moran's I
@ -56,7 +56,7 @@ def moran(subquery, attr_name,
return zip([moran_global.I], [moran_global.EI])
def moran_local(subquery, attr,
permutations, geom_col, id_col, w_type, num_ngbrs):
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I implementation for PL/Python
Andy Eschbacher
@ -96,7 +96,7 @@ def moran_local(subquery, attr,
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def moran_rate(subquery, numerator, denominator,
permutations, geom_col, id_col, w_type, num_ngbrs):
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Rate (global)
Andy Eschbacher
@ -137,7 +137,7 @@ def moran_rate(subquery, numerator, denominator,
return zip([lisa_rate.I], [lisa_rate.EI])
def moran_local_rate(subquery, numerator, denominator,
permutations, geom_col, id_col, w_type, num_ngbrs):
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Local Rate
Andy Eschbacher

6
src/py/crankshaft/test/test_clustering_moran.py
View File

@ -52,7 +52,7 @@ class MoranTest(unittest.TestCase):
data = [ { 'id': d['id'], 'attr1': d['value'], 'neighbors': d['neighbors'] } for d in self.neighbors_data]
plpy._define_result('select', data)
random_seeds.set_random_seeds(1234)
result = cc.moran_local('subquery', 'value', 99, 'the_geom', 'cartodb_id', 'knn', 5)
result = cc.moran_local('subquery', 'value', 'knn', 5, 99, 'the_geom', 'cartodb_id')
result = [(row[0], row[1]) for row in result]
expected = self.moran_data
for ([res_val, res_quad], [exp_val, exp_quad]) in zip(result, expected):
@ -64,7 +64,7 @@ class MoranTest(unittest.TestCase):
data = [ { 'id': d['id'], 'attr1': d['value'], 'attr2': 1, 'neighbors': d['neighbors'] } for d in self.neighbors_data]
plpy._define_result('select', data)
random_seeds.set_random_seeds(1234)
result = cc.moran_local_rate('subquery', 'numerator', 'denominator', 99, 'the_geom', 'cartodb_id', 'knn', 5)
result = cc.moran_local_rate('subquery', 'numerator', 'denominator', 'knn', 5, 99, 'the_geom', 'cartodb_id')
print 'result == None? ', result == None
result = [(row[0], row[1]) for row in result]
expected = self.moran_data
@ -76,7 +76,7 @@ class MoranTest(unittest.TestCase):
data = [{ 'id': d['id'], 'attr1': d['value'], 'neighbors': d['neighbors'] } for d in self.neighbors_data]
plpy._define_result('select', data)
random_seeds.set_random_seeds(1235)
result = cc.moran('table', 'value', 99, 'the_geom', 'cartodb_id', 'knn', 5)
result = cc.moran('table', 'value', 'knn', 5, 99, 'the_geom', 'cartodb_id')
print 'result == None?', result == None
result_moran = result[0][0]
expected_moran = np.array([row[0] for row in self.moran_data]).mean()