def test_list_fitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type='BEM')
rs = model.fit([data1, data2])
assert(len(rs) == 2)
for r in rs:
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
fcm1 = FCMdata('test_fcm1', data1, ['fsc', 'ssc'], [0, 1])
fcm2 = FCMdata('test_fcm2', data2, ['fsc', 'ssc'], [0, 1])
c = FCMCollection('fcms', [fcm1, fcm2])
rs = model.fit(c)
assert(len(rs) == 2)
for r in rs:
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
def testListFitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type="BEM")
rs = model.fit([data1, data2])
assert len(rs) == 2
for r in rs:
print "mu ", r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 2
fcm1 = FCMdata("test_fcm1", data1, ["fsc", "ssc"], [0, 1])
fcm2 = FCMdata("test_fcm2", data2, ["fsc", "ssc"], [0, 1])
c = FCMcollection("fcms", [fcm1, fcm2])
rs = model.fit(c)
assert len(rs) == 2
for r in rs:
print "mu ", r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 4
def testListFitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type='BEM')
rs = model.fit([data1, data2])
assert(len(rs) == 2)
for r in rs:
print 'mu ', r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert(np.vdot(diffs[i], diffs[i]) < 2)
fcm1 = FCMdata('test_fcm1', data1, ['fsc', 'ssc'], [0, 1])
fcm2 = FCMdata('test_fcm2', data2, ['fsc', 'ssc'], [0, 1])
c = FCMcollection('fcms', [fcm1, fcm2])
rs = model.fit(c)
assert(len(rs) == 2)
for r in rs:
print 'mu ', r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert(np.vdot(diffs[i], diffs[i]) < 2)
def fit_one(args):
x, name = args
print "fitting", name, "of size", x.shape
m = DPMixtureModel(nclusts=8, iter=100, burnin=0, last=1)
r = m.fit(x, verbose=10)
print "done fitting", name
return r
def fit_one(args):
x, name = args
print "fitting", name, "of size", x.shape
m = DPMixtureModel(nclusts=8, iter=100, burnin=0, last=1)
r = m.fit(x, verbose=10)
print 'done fitting', name
return r
def test_reference(self):
true, data = self.generate_data()
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
model.load_ref(array(true))
r = model.fit(data, verbose=True)
diffs = {}
for i in gen_mean:
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
assert(np.vdot(diffs[i], diffs[i]) < 1)
model.load_ref(r)
r = model.fit(data, verbose=True)
diffs = {}
for i in gen_mean:
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
assert(np.vdot(diffs[i], diffs[i]) < 1)
def test_mcmc_fitting(self):
true, data = self.generate_data()
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
r = model.fit(data, verbose=10)
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
def testRefernce(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
model.load_ref(array(true))
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
# diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i] - gen_mean[i])
# print i, gen_mean[i],r.mus[i], diffs[i],
# np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
# print diffs
print "MCMC fitting took %0.3f" % (end)
model.load_ref(r)
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
# diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i] - gen_mean[i])
# print i, gen_mean[i],r.mus[i], diffs[i],
# np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
def testRefernce(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,100,100,1)
model.seed = 1
model.load_ref(array(true))
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
#diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
#print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
#print diffs
print 'MCMC fitting took %0.3f' % (end)
model.load_ref(r)
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
#diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
#print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
def testBEMFitting(self):
print "starting BEM"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 2000, 100, 1, type="BEM")
model.seed = 1
start = time()
r = model.fit(data, verbose=False)
end = time() - start
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
print "BEM fitting took %0.3f" % (end)
def testBEMFitting(self):
print 'starting BEM'
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,2000,100,1, type='BEM')
model.seed = 1
start = time()
r = model.fit(data, verbose=False)
end = time() - start
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
print 'BEM fitting took %0.3f' % (end)
def testMCMCFitting(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,100,100,1)
model.seed = 1
start = time()
r = model.fit(data, verbose=10)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
#print diffs
print r.classify(data)
print 'MCMC fitting took %0.3f' % (end)
def testMCMCFitting(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
start = time()
r = model.fit(data, verbose=10)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
# print diffs
print r.classify(data)
print "MCMC fitting took %0.3f" % (end)
class DPMixtureModel_TestCase(unittest.TestCase):
def generate_data(self, n=1e4, k=2, ncomps=3, seed=1):
npr.seed(seed)
data_concat = []
labels_concat = []
for j in xrange(ncomps):
mean = gen_mean[j]
sd = gen_sd[j]
corr = gen_corr[j]
cov = np.empty((k, k))
cov.fill(corr)
cov[np.diag_indices(k)] = 1
cov *= np.outer(sd, sd)
num = int(n * group_weights[j])
rvs = multivariate_normal(mean, cov, size=num)
data_concat.append(rvs)
labels_concat.append(np.repeat(j, num))
return (np.concatenate(labels_concat), np.concatenate(data_concat, axis=0))
def testListFitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type="BEM")
rs = model.fit([data1, data2])
assert len(rs) == 2
for r in rs:
print "mu ", r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 2
fcm1 = FCMdata("test_fcm1", data1, ["fsc", "ssc"], [0, 1])
fcm2 = FCMdata("test_fcm2", data2, ["fsc", "ssc"], [0, 1])
c = FCMcollection("fcms", [fcm1, fcm2])
rs = model.fit(c)
assert len(rs) == 2
for r in rs:
print "mu ", r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 4
def testBEMFitting(self):
print "starting BEM"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 2000, 100, 1, type="BEM")
model.seed = 1
start = time()
r = model.fit(data, verbose=False)
end = time() - start
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
print "BEM fitting took %0.3f" % (end)
#
def testMCMCFitting(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
start = time()
r = model.fit(data, verbose=10)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus - gen_mean[i]), 0)
# print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
# print diffs
print r.classify(data)
print "MCMC fitting took %0.3f" % (end)
def testRefernce(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
model.load_ref(array(true))
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
# diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i] - gen_mean[i])
# print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
# print diffs
print "MCMC fitting took %0.3f" % (end)
model.load_ref(r)
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
# print 'r.mus:', r.mus
for i in gen_mean:
# diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i] - gen_mean[i])
# print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert np.vdot(diffs[i], diffs[i]) < 1
# print diffs
def setUp(self):
self.mu = array([0, 0])
self.sig = eye(2)
self.pnts = multivariate_normal(self.mu, self.sig, 1000)
self.k = 16
self.niter = 10
self.model = DPMixtureModel(self.k, self.niter, 0, 1)
def testModel(self):
r = self.model.fit(self.pnts, verbose=False)
assert isinstance(r, DPMixture)
mus = r.mus
assert mus.shape == (16, 2)
def testModel_prior(self):
self.model.load_mu(self.mu.reshape(1, 2))
self.model.load_sigma(self.sig.reshape(1, 2, 2))
r = self.model.fit(self.pnts, verbose=False)
assert isinstance(r, DPMixture)
mus = r.mus
assert mus.shape == (16, 2)
def testModel_datatypes(self):
r = self.model.fit(self.pnts.astype("int"))
self.assertIsInstance(r, DPMixture, "failed to fit integer data")
r = self.model.fit(self.pnts.astype("float"))
self.assertIsInstance(r, DPMixture, "failed to fit float data")
r = self.model.fit(self.pnts.astype("double"))
self.assertIsInstance(r, DPMixture, "failed to fit double data")
class DPMixtureModel_TestCase(unittest.TestCase):
def generate_data(self,n=1e4, k=2, ncomps=3, seed=1):
npr.seed(seed)
data_concat = []
labels_concat = []
for j in xrange(ncomps):
mean = gen_mean[j]
sd = gen_sd[j]
corr = gen_corr[j]
cov = np.empty((k, k))
cov.fill(corr)
cov[np.diag_indices(k)] = 1
cov *= np.outer(sd, sd)
num = int(n * group_weights[j])
rvs = multivariate_normal(mean, cov, size=num)
data_concat.append(rvs)
labels_concat.append(np.repeat(j, num))
return (np.concatenate(labels_concat),
np.concatenate(data_concat, axis=0))
def testListFitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3,2000,100,1, type='BEM')
rs = model.fit([data1,data2])
assert(len(rs) == 2)
for r in rs:
print 'mu ',r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
fcm1 = FCMdata('test_fcm1', data1, ['fsc','ssc'], [0,1])
fcm2 = FCMdata('test_fcm2', data2, ['fsc','ssc'], [0,1])
c = FCMcollection('fcms', [fcm1, fcm2])
rs = model.fit(c)
assert(len(rs) == 2)
for r in rs:
print 'mu ',r.mus
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
def testBEMFitting(self):
print 'starting BEM'
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,2000,100,1, type='BEM')
model.seed = 1
start = time()
r = model.fit(data, verbose=False)
end = time() - start
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
print 'BEM fitting took %0.3f' % (end)
#
def testMCMCFitting(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,100,100,1)
model.seed = 1
start = time()
r = model.fit(data, verbose=10)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
#print i, gen_mean[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
#print diffs
print r.classify(data)
print 'MCMC fitting took %0.3f' % (end)
def testRefernce(self):
print "starting mcmc"
true, data = self.generate_data()
m = data.mean(0)
s = data.std(0)
# true_mean = {}
# for i in gen_mean:
# true_mean[i] = (gen_mean[i]-m)/s
model = DPMixtureModel(3,100,100,1)
model.seed = 1
model.load_ref(array(true))
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
#diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
#print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
#print diffs
print 'MCMC fitting took %0.3f' % (end)
model.load_ref(r)
start = time()
r = model.fit(data, verbose=True)
end = time() - start
diffs = {}
#print 'r.mus:', r.mus
for i in gen_mean:
#diffs[i] = np.min(np.abs(r.mus-gen_mean[i]),0)
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
#print i, gen_mean[i],r.mus[i], diffs[i], np.vdot(diffs[i],diffs[i])
assert( np.vdot(diffs[i],diffs[i]) < 1)
#print diffs
def setUp(self):
self.mu = array([0,0])
self.sig = eye(2)
self.pnts = multivariate_normal(self.mu, self.sig, 1000)
self.k = 16
self.niter = 10
self.model = DPMixtureModel(self.k,self.niter,0,1)
def testModel(self):
r = self.model.fit(self.pnts, verbose=False)
assert(isinstance(r, DPMixture))
mus = r.mus
assert(mus.shape == (16,2))
def testModel_prior(self):
self.model.load_mu(self.mu.reshape(1,2))
self.model.load_sigma(self.sig.reshape(1,2,2))
r = self.model.fit(self.pnts, verbose=False)
assert(isinstance(r, DPMixture))
mus = r.mus
assert(mus.shape == (16,2))
def fit_one(args):
x, name = args
m = DPMixtureModel(nclusts=8, niter=100, burnin=0, last=1)
r = m.fit(x, verbose=10)
return r
xs[400:500, :] = numpy.random.multivariate_normal(mus[4, :], sigma, 100)
xs[500:600, :] = numpy.random.multivariate_normal(mus[5, :], sigma, 100)
true_z = numpy.zeros((600,))
true_z[0:100] = 0
true_z[100:200] = 1
true_z[200:300] = 2
true_z[300:400] = 3
true_z[400:500] = 4
true_z[500:600] = 5
pylab.subplot(1, 3, 1)
pylab.scatter(xs[:, 0], xs[:, 1], c=true_z)
pylab.title("True")
# pylab.show()
model = DPMixtureModel(xs, 6, 5000, 100, 1)
model.gamma = 1.0
model.fit(verbose=True)
pylab.subplot(1, 3, 2)
model_z = model.get_class()
results = model.get_results()
model_class = results.classify(xs)
pylab.scatter(xs[:, 0], xs[:, 1], c=model_class)
pylab.scatter(results.mus()[:, 0], results.mus()[:, 1], c='red')
pylab.title("component")
modal = results.make_modal()
z = modal.classify(xs)
print z.min(), z.max()
pylab.subplot(1, 3, 3)
pylab.scatter(xs[:, 0], xs[:, 1], c=z)
pylab.title("modal")
pylab.show()
ctot = 0
xs[400:500, :] = numpy.random.multivariate_normal(mus[4, :], sigma, 100)
xs[500:600, :] = numpy.random.multivariate_normal(mus[5, :], sigma, 100)
true_z = numpy.zeros((600, ))
true_z[0:100] = 0
true_z[100:200] = 1
true_z[200:300] = 2
true_z[300:400] = 3
true_z[400:500] = 4
true_z[500:600] = 5
pylab.subplot(1, 3, 1)
pylab.scatter(xs[:, 0], xs[:, 1], c=true_z)
pylab.title("True")
#pylab.show()
model = DPMixtureModel(xs, 6, 5000, 100, 1)
model.gamma = 1.0
model.fit(verbose=True)
pylab.subplot(1, 3, 2)
model_z = model.get_class()
results = model.get_results()
model_class = results.classify(xs)
pylab.scatter(xs[:, 0], xs[:, 1], c=model_class)
pylab.scatter(results.mus()[:, 0], results.mus()[:, 1], c='red')
pylab.title("component")
modal = results.make_modal()
z = modal.classify(xs)
print z.min(), z.max()
pylab.subplot(1, 3, 3)
pylab.scatter(xs[:, 0], xs[:, 1], c=z)
pylab.title("modal")
pylab.show()
ctot = 0
class DPMixtureModelTestCase(unittest.TestCase):
def generate_data(self, n=1e4, k=2, ncomps=3, seed=1):
np.random.seed(seed)
data_concat = []
labels_concat = []
for j in xrange(ncomps):
mean = gen_mean[j]
sd = gen_sd[j]
corr = gen_corr[j]
cov = np.empty((k, k))
cov.fill(corr)
cov[np.diag_indices(k)] = 1
cov *= np.outer(sd, sd)
num = int(n * group_weights[j])
rvs = multivariate_normal(mean, cov, size=(num,))
data_concat.append(rvs)
labels_concat.append(np.repeat(j, num))
return (np.concatenate(labels_concat),
np.concatenate(data_concat, axis=0))
def test_list_fitting(self):
true1, data1 = self.generate_data()
true2, data2 = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type='BEM')
rs = model.fit([data1, data2])
assert(len(rs) == 2)
for r in rs:
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
fcm1 = FCMdata('test_fcm1', data1, ['fsc', 'ssc'], [0, 1])
fcm2 = FCMdata('test_fcm2', data2, ['fsc', 'ssc'], [0, 1])
c = FCMCollection('fcms', [fcm1, fcm2])
rs = model.fit(c)
assert(len(rs) == 2)
for r in rs:
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
def test_bem_fitting(self):
true, data = self.generate_data()
model = DPMixtureModel(3, 2000, 100, 1, type='BEM')
model.seed = 1
r = model.fit(data, verbose=False)
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
def test_mcmc_fitting(self):
true, data = self.generate_data()
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
r = model.fit(data, verbose=10)
diffs = {}
for i in gen_mean:
diffs[i] = np.min(np.abs(r.mus-gen_mean[i]), 0)
assert(np.vdot(diffs[i], diffs[i]) < 1)
def test_reference(self):
true, data = self.generate_data()
model = DPMixtureModel(3, 100, 100, 1)
model.seed = 1
model.load_ref(array(true))
r = model.fit(data, verbose=True)
diffs = {}
for i in gen_mean:
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
assert(np.vdot(diffs[i], diffs[i]) < 1)
model.load_ref(r)
r = model.fit(data, verbose=True)
diffs = {}
for i in gen_mean:
diffs[i] = np.abs(r.mus[i]-gen_mean[i])
assert(np.vdot(diffs[i], diffs[i]) < 1)
def setUp(self):
self.mu = array([0, 0])
self.sig = eye(2)
self.pnts = multivariate_normal(self.mu, self.sig, size=(1000,))
self.k = 16
self.niter = 10
self.model = DPMixtureModel(self.k, self.niter, 0, 1)
def test_model(self):
r = self.model.fit(self.pnts, verbose=False)
assert(isinstance(r, DPMixture))
mus = r.mus
assert(mus.shape == (16, 2))
def test_model_prior(self):
self.model.load_mu(self.mu.reshape(1, 2))
self.model.load_sigma(self.sig.reshape(1, 2, 2))
r = self.model.fit(self.pnts, verbose=False)
assert(isinstance(r, DPMixture))
mus = r.mus
assert(mus.shape == (16, 2))
def test_model_datatypes(self):
r = self.model.fit(self.pnts.astype('int'))
self.assertIsInstance(r, DPMixture, 'failed to fit integer data')
r = self.model.fit(self.pnts.astype('float'))
self.assertIsInstance(r, DPMixture, 'failed to fit float data')
r = self.model.fit(self.pnts.astype('double'))
self.assertIsInstance(r, DPMixture, 'failed to fit double data')