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

finishes python tests for regression

Browse Source
This commit is contained in:
Andy Eschbacher
2017-01-09 10:00:44 -05:00
parent 87890926ad
commit 0007082efe
2 changed files with 18 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/py/crankshaft/test/fixtures/gwr_packed_data.json vendored
View File

File diff suppressed because one or more lines are too long

50
src/py/crankshaft/test/test_regression_gwr.py
View File

@@ -25,7 +25,7 @@ class GWRTest(unittest.TestCase):
fixture packed from canonical GWR georgia dataset using the
following query:
SELECT array_agg(x) As x,
array_agg(x) As y,
array_agg(y) As y,
array_agg(pctbach) As dep_var,
array_agg(pctrural) As attr1,
array_agg(pctpov) As attr2,
@@ -33,8 +33,8 @@ class GWRTest(unittest.TestCase):
array_agg(areakey) As rowid
FROM g_utm
WHERE pctbach is not NULL AND
pctpov IS NOT NULL AND
pctrural IS NOT NULL AND
pctpov IS NOT NULL AND
pctblack IS NOT NULL
"""
self.data = json.loads(
@@ -46,12 +46,13 @@ class GWRTest(unittest.TestCase):
'dep_var': 'pctbach',
'ind_vars': ['pctrural', 'pctpov', 'pctblack'],
'bw': 90.000,
'fixed': False}
'fixed': False,
'geom_col': 'the_geom',
'id_col': 'areakey'}
def test_gwr(self):
"""
"""
gwr = GWR(FakeDataProvider(self.data))
gwr_resp = gwr.gwr(self.params['subquery'], self.params['dep_var'],
self.params['ind_vars'], bw=self.params['bw'],
@@ -62,11 +63,8 @@ class GWRTest(unittest.TestCase):
# known_coeffs = self.knowns['coeffs']
# data packed from https://github.com/TaylorOshan/pysal/blob/a44c5541e2e0d10a99ff05edc1b7f81b70f5a82f/pysal/examples/georgia/georgia_BS_NN_listwise.csv
coeff_known_inter = self.knowns['est_intercept']
coeff_known_pctpov = self.knowns['est_pctpov']
coeff_known_pctrural = self.knowns['est_pctrural']
coeff_known_pctblack = self.knowns['est_pctblack']
# coeff_known_pcteld = self.knowns['est_pcteld']
tval_known_pctblack = self.knowns['t_pctrural']
pctpov_se = self.knowns['se_pctpov']
ids = self.knowns['area_key']
resp_idx = None
@@ -78,30 +76,16 @@ class GWRTest(unittest.TestCase):
with open('gwr_test_data.json', 'w') as f:
print("writing to file")
f.write(str(zip(rowids, coeffs)))
# test pctpov coefficient estimates
for idx, val in enumerate(coeff_known_pctpov):
# print idx, val, ids[idx], rowids[rowids.index(ids[idx])]
resp_idx = rowids.index(ids[idx])
if resp_idx is None:
print('missed lookup on {0}'.format(ids[idx]))
print('comparison: %d: %f, %f' % (
rowids[resp_idx],
val,
json.loads(coeffs[resp_idx])['pctpov']))
# print('comparison: %f, %f, %f, %f, | Intercepts: (%f, %f)' % (
# val,
# json.loads(coeffs[resp_idx])['pctpov'],
# json.loads(coeffs[resp_idx])['pctrural'],
# json.loads(coeffs[resp_idx])['pctblack'],
# coeff_known_inter[idx],
# json.loads(coeffs[resp_idx])['intercept']))
# self.assertAlmostEquals(val, coeffs[resp_idx])
assert False
# labels = [a[1] for a in clusters]
# c1 = [a for a in clusters if a[1] == 0]
# c2 = [a for a in clusters if a[1] == 1]
#
# self.assertEqual(len(np.unique(labels)), 2)
# self.assertEqual(len(c1), 20)
# self.assertEqual(len(c2), 20)
self.assertAlmostEquals(val,
json.loads(coeffs[resp_idx])['pctpov'],
places=4)
# test pctrural tvals
for idx, val in enumerate(tval_known_pctblack):
resp_idx = rowids.index(ids[idx])
self.assertAlmostEquals(val,
json.loads(t_vals[resp_idx])['pctrural'],
places=4)