def test_em_selection():
# test that the basic GMM-based model selection tool returns
# something sensible (i.e. the gmm used to represent the data has
# indeed one or two classes)
# generate some data
dim = 2
x = np.concatenate((nr.randn(100, dim), 3 + 2 * nr.randn(100, dim)))
krange = range(1, 10)
lgmm = gmm.best_fitting_GMM(x, krange, prec_type="full", niter=100, delta=1.0e-4, ninit=1, verbose=0)
assert_true(lgmm.k < 4)
The possible number of clusters is in the [1,10] range
The proposed algorithm correctly selects a solution with 2 or 3 classes
Author : Bertrand Thirion, 2008-2009
"""
print __doc__
import numpy as np
import nipy.neurospin.clustering.gmm as gmm
dim = 2
# 1. generate a 3-components mixture
x1 = np.random.randn(100,dim)
x2 = 3+ 2*np.random.randn(50,dim)
x3 = np.repeat(np.array([-2, 2], ndmin=2), 30, 0) \
+ 0.5*np.random.randn(30, dim)
x = np.concatenate((x1, x2, x3))
# 2. fit the mixture with a bunch of possible models
krange = range(1,5)
lgmm = gmm.best_fitting_GMM(x, krange,
prec_type='diag',
niter=100, delta=1.e-4,
ninit=1, verbose=0)
# 3, plot the result
z = lgmm.map_label(x)
gmm.plot2D(x, lgmm, z, show=1, verbose=0)
