1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
|
# NOTE: contains only one test, _est_cont_fit, that is renamed so that
# nose doesn't run it
# I put this here for the record and for the case when someone wants to
# verify the quality of fit
# with current parameters: relatively small sample size, default starting values
# Ran 84 tests in 401.797s
# FAILED (failures=15)
import numpy.testing as npt
import numpy as np
from scipy import stats
from test_continuous_basic import distcont
# this is not a proper statistical test for convergence, but only
# verifies that the estimate and true values don't differ by too much
n_repl1 = 1000 # sample size for first run
n_repl2 = 5000 # sample size for second run, if first run fails
thresh_percent = 0.25 # percent of true parameters for fail cut-off
thresh_min = 0.75 # minimum difference estimate - true to fail test
#distcont = [['genextreme', (3.3184017469423535,)]]
def _est_cont_fit():
# this tests the closeness of the estimated parameters to the true
# parameters with fit method of continuous distributions
# Note: is slow, some distributions don't converge with sample size <= 10000
for distname, arg in distcont:
yield check_cont_fit, distname,arg
def check_cont_fit(distname,arg):
distfn = getattr(stats, distname)
rvs = distfn.rvs(size=n_repl1,*arg)
est = distfn.fit(rvs) #,*arg) # start with default values
truearg = np.hstack([arg,[0.0,1.0]])
diff = est-truearg
txt = ''
diffthreshold = np.max(np.vstack([truearg*thresh_percent,
np.ones(distfn.numargs+2)*thresh_min]),0)
# threshold for location
diffthreshold[-2] = np.max([np.abs(rvs.mean())*thresh_percent,thresh_min])
if np.any(np.isnan(est)):
raise AssertionError('nan returned in fit')
else:
if np.any((np.abs(diff) - diffthreshold) > 0.0):
## txt = 'WARNING - diff too large with small sample'
## print 'parameter diff =', diff - diffthreshold, txt
rvs = np.concatenate([rvs,distfn.rvs(size=n_repl2-n_repl1,*arg)])
est = distfn.fit(rvs) #,*arg)
truearg = np.hstack([arg,[0.0,1.0]])
diff = est-truearg
if np.any((np.abs(diff) - diffthreshold) > 0.0):
txt = 'parameter: %s\n' % str(truearg)
txt += 'estimated: %s\n' % str(est)
txt += 'diff : %s\n' % str(diff)
raise AssertionError('fit not very good in %s\n' % distfn.name + txt)
if __name__ == "__main__":
import nose
#nose.run(argv=['', __file__])
nose.runmodule(argv=[__file__,'-s'], exit=False)
|
