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

Merge branch 'adds-getis-analysis' of https://github.com/cartodb/crankshaft into adds-getis-analysis

Browse Source
This commit is contained in:
Andy Eschbacher 2016-09-19 19:24:43 +00:00
commit 5127845100
2 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/py/crankshaft/crankshaft/clustering/getis.py
View File

@ -11,12 +11,13 @@ import crankshaft.pysal_utils as pu
# High level interface --------------------------------------- # High level interface ---------------------------------------
def getis_ord(subquery, attr, def getis_ord(subquery, attr,
w_type, num_ngbrs, permutations, geom_col, id_col): w_type, num_ngbrs, permutations, geom_col, id_col):
""" """
Getis-Ord's G* Getis-Ord's G*
Implementation building neighbors with a PostGIS database and PySAL's Getis-Ord's G* Implementation building neighbors with a PostGIS database and PySAL's
hotspot/coldspot module. Getis-Ord's G* hotspot/coldspot module.
Andy Eschbacher Andy Eschbacher
""" """
@ -41,11 +42,11 @@ def getis_ord(subquery, attr,
attr_vals = pu.get_attributes(result) attr_vals = pu.get_attributes(result)
## build PySAL weight object # build PySAL weight object
weight = pu.get_weight(result, w_type, num_ngbrs) weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate Getis-Ord's G* z- and p-values # calculate Getis-Ord's G* z- and p-values
getis = ps.esda.getisord.G_Local(attr_vals, weight, getis = ps.esda.getisord.G_Local(attr_vals, weight,
star=True, permutations=permutations) star=True, permutations=permutations)
return zip(getis.z_sim, getis.p_sim, getis.p_z_sim, weight.id_order) return zip(getis.z_sim, getis.p_sim, getis.p_z_sim, weight.id_order)

16
src/py/crankshaft/test/test_clustering_getis.py
View File

@ -14,29 +14,31 @@ import crankshaft.pysal_utils as pu
from crankshaft import random_seeds from crankshaft import random_seeds
import json import json
class GetisTest(unittest.TestCase): class GetisTest(unittest.TestCase):
"""Testing class for Getis-Ord's G funtion """Testing class for Getis-Ord's G funtion
This test replicates the work done in PySAL documentation: This test replicates the work done in PySAL documentation:
https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/autocorrelation.html#local-g-and-g https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/autocorrelation.html#local-g-and-g
""" """
def setUp(self): def setUp(self):
plpy._reset() plpy._reset()
self.neighbors_data = json.loads(open(fixture_file('neighbors_getis.json')).read()) self.neighbors_data = json.loads(
open(fixture_file('neighbors_getis.json')).read())
self.getis_data = json.loads(open(fixture_file('getis.json')).read()) self.getis_data = json.loads(open(fixture_file('getis.json')).read())
def test_getis_ord(self): def test_getis_ord(self):
"""Test Getis-Ord's G*""" """Test Getis-Ord's G*"""
data = [ { 'id': d['id'], data = [{'id': d['id'],
'attr1': d['value'], 'attr1': d['value'],
'neighbors': d['neighbors'] } for d in self.neighbors_data] 'neighbors': d['neighbors']} for d in self.neighbors_data]
plpy._define_result('select', data) plpy._define_result('select', data)
random_seeds.set_random_seeds(1234) random_seeds.set_random_seeds(1234)
result = cc.getis_ord('subquery', 'value', 'knn', 5, 999, 'the_geom', 'cartodb_id') result = cc.getis_ord('subquery', 'value',
'knn', 5, 999, 'the_geom', 'cartodb_id')
result = [(row[0], row[1]) for row in result] result = [(row[0], row[1]) for row in result]
expected = np.array(self.getis_data)[:, 0:2] expected = np.array(self.getis_data)[:, 0:2]
for ([res_z, res_p], [exp_z, exp_p]) in zip(result, expected): for ([res_z, res_p], [exp_z, exp_p]) in zip(result, expected):
self.assertAlmostEqual(res_z, exp_z, delta=1e-2) self.assertAlmostEqual(res_z, exp_z, delta=1e-2)
if exp_p <= 0.05: if exp_p <= 0.05:
self.assertTrue(res_p < 0.05) self.assertTrue(res_p < 0.05)