def test_cumaltive_to_point1():
""" can we determine cumulative 1-d pdf at a set of points"""
#generate a fake df, flat across the 500 bins
pdf = np.ones(500, dtype=float)
pdf = pdf / np.sum(pdf)
#calcalate cumulative df of this, up to 0, 1, 2, 3,.. ngals etc
for i in np.arange(40) + 1:
res = pval.cumaltive_to_point(pdf, np.arange(500) + 0.5, i)
print i, np.sum(pdf[0:i]) / 500.0, res
np.testing.assert_almost_equal(res, np.sum(pdf[0:i]) / 500.0, 3)
def test_cumaltive_to_point2():
""" can we determine cumulative n-d pdf at a set of points"""
#generate a fake df, flat across the 500 bins
ngals = 56
pdfs = np.zeros((ngals, 500))
binCenters = np.arange(500) + 0.5
for i in np.arange(ngals):
pdfs[i, :] = i + 1
#npfds = pval.normalisepdfs(pdfs, binCenters)
#calcalate cumulative df of this, up to 0, 1, 2, 3,.. ngals etc
res = pval.cumaltive_to_point(npfds, binCenters, np.arange(ngals) + 0.5)
for i in np.arange(ngals - 1) + 1:
print i, res[i], np.sum(npfds[i, 0:i + 1])
np.testing.assert_almost_equal(res[i], np.sum(npfds[i, 0:i + 1]), 1)
def test_cumaltive_to_point0():
"""check we can we draw a set of z_mc from a pdf, that are flat in histogram heights <h>
e.g. Bordoloi test"""
from scipy.stats import entropy
ngals = 20
sigs = np.random.uniform(size=ngals) * 0.5 + 0.1
x = np.arange(0.01, 3.01, 0.01)
dx = (x[1] - x[0]) / 2.0
print 'sigs', sigs
for i in range(ngals):
pdf = mlab.normpdf(x, sigs[i], 0.02)
z_mc = pval.get_mc(pdf, x, N=100000)
c = pval.cumaltive_to_point(pdf, x, z_mc)
h = np.histogram(c, bins=np.arange(0, 1.05, 0.05))
print h
print len(h), 'len(h)'
h = h[0]
res = entropy(h, [np.mean(h)] * len(h))
print 'res', res
np.testing.assert_array_less(res, 0.005)
def test_cumaltive_to_point01():
"""check we can we draw a set of z_mc from a pdf, that are flat in histogram heights <h>
e.g. Bordoloi test for sets of pdfs with 2 bins values """
from scipy.stats import entropy
x = np.arange(0.01, 3.01, 0.01)
dx = (x[1] - x[0]) / 2.0
for i in range(len(x) - 2):
pdf = np.zeros_like(x)
pdf[i:i + 2] = [0.1, 0.2]
z_mc = pval.get_mc(pdf, x, N=100000)
c = pval.cumaltive_to_point(pdf, x, z_mc)
h = np.histogram(c, bins=np.arange(0, 1.05, 0.05))
print h
print len(h), 'len(h)'
h = h[0]
res = entropy(h, [np.mean(h)] * len(h))
print 'res', res
np.testing.assert_array_less(res, 0.005)