from pymix.distributions.normal import NormalDistribution
from pymix.distributions.product import ProductDistribution
from pymix.models.mixture import MixtureModel
from pymix.util.dataset import DataSet
pr1 = ProductDistribution([
NormalDistribution(-6.0, 0.5),
NormalDistribution(-4.0, 0.5),
NormalDistribution(-3.0, 0.5)
])
pr2 = ProductDistribution([
NormalDistribution(-5.0, 0.5),
NormalDistribution(-3.3, 0.5),
NormalDistribution(-2.3, 0.5)
])
m = MixtureModel(2, [0.7, 0.3], [pr1, pr2])
seq = m.sampleSet(5)
#print seq
z = 0
m.printTraceback(DataSet().fromList(seq), z)
import random
#d = DataSet(["test.txt","drd1.txt","pheno.txt"])
from pymix.distributions.multinomial import MultinomialDistribution
from pymix.distributions.normal import NormalDistribution
from pymix.distributions.product import ProductDistribution
from pymix.models.mixture import MixtureModel
from pymix.util.dataset import DataSet
from test_mixture import SNP
d = DataSet(["test.txt", "drd1.txt", "pheno.txt"])
print d
p1 = []
p2 = []
p3 = []
p4 = []
for i in range(25):
p1.append(random.random())
p2.append(random.random())
p3.append(random.random())
p4.append(random.random())
g1 = lambda x: x / sum(p1)
p1 = map(g1, p1)
g2 = lambda x: x / sum(p2)
p2 = map(g2, p2)
g3 = lambda x: x / sum(p3)
p3 = map(g3, p3)
from pymix import mixture
import random
from pymix.parse import readMixture
from pymix.util.alphabet import Alphabet
from pymix.util.dataset import DataSet
VNTR = Alphabet(['.', '2/4', '2/7', '3/4', '3/7', '4/4', '4/6', '4/7', '4/8', '4/9', '7/7'])
DIAG = Alphabet(['.', '0', '8', '1'])
data = DataSet()
# iq.txt = iq and achievement test fields from pheno.txt
# drd4_len.txt = drd4 vntr types, only number of repeats
data.fromFiles(["filt_WISC_WIAT_DISC_134.txt"]) # ,"DRD4_134_len.txt"
m = readMixture('pheno_best.py')
print "Without deterministic anealing:"
m.randMaxEM(data, 100, 30, 0.1, tilt=0, silent=0)
print "\nWith deterministic annealing:"
m.randMaxEM(data, 100, 30, 0.1, tilt=1, silent=0)
#e2.EM(seq2,60,5)
# ----------------------------- Example 3 -----------------------------
m3 = MixtureModel(2, [0.3, 0.7],
[NormalDistribution(0.0, 0.5),
NormalDistribution(1.3, 0.5)])
(true, seq3) = m3.sampleSetLabels(380)
m4 = MixtureModel(
2, [0.5, 0.5],
[NormalDistribution(-1.5, 1.5),
NormalDistribution(1.5, 1.5)])
dat = DataSet()
dat.fromArray(seq3)
print "vorher ------\n", m4
pred = m4.cluster(dat,
nr_runs=5,
nr_init=9,
max_iter=30,
delta=0.1,
labels=None,
entropy_cutoff=None)
classes = m4.classify(dat)
m4.shortInitEM(dat, 5, 5, 5, 0.1)
m4.EM(seq3, 20, 0.1)
"""
items = [c.distList[0] for c in mixx.components]
items.reverse()
new_pi = np.array(mixx.pi.tolist() + [0.01])[::-1]
new_pi = new_pi / np.sum(new_pi)
#items = items + [MultiNormalDistribution(4, means, sigma)]
items = items + [MultivariateTDistribution(DIMS, means, sigma, 5)]
# Fix parameters of all components but the new one:
#comp_fix = [1] * (len(new_pi) - 1) + [0]
return MixtureModel(len(new_pi), new_pi, items)
#import ipdb; ipdb.set_trace()
st = MultivariateTDistribution(DIMS, xy.mean(axis=1)*1.1, np.diag(xy.var(axis=1)), 3)
da = xy.T #[:500]
ds = DataSet()
ds.fromArray(da)
m = MixtureModel(1, [1], [st])
print m
m.EM(ds, 60, 0.1)
print m
#import ipdb; ipdb.set_trace()
#m2 = mix.MixtureModel(2, [0.8, 0.2], [m.components[0].distList[0], d2], compFix=[0, 0])
for _ in xrange(6):
m = mixturate(m, xy.mean(axis=1)-10., np.diag(xy.var(axis=1)))
m.randMaxEM(ds, 3, 30, 0.1)
print m
import joblib
joblib.dump(m, 'test2.mix', compress=3)
pl.plotData(da[:, :2])
seq2 = e1.sample(500) e2 = MixtureModel(2, [0.5, 0.5], [NormalDistribution(2.0, 0.4), ExponentialDistribution(0.1)]) # e2.EM(seq2,60,5) # ----------------------------- Example 3 ----------------------------- m3 = MixtureModel(2, [0.3, 0.7], [NormalDistribution(0.0, 0.5), NormalDistribution(1.3, 0.5)]) (true, seq3) = m3.sampleSetLabels(380) m4 = MixtureModel(2, [0.5, 0.5], [NormalDistribution(-1.5, 1.5), NormalDistribution(1.5, 1.5)]) dat = DataSet() dat.fromArray(seq3) print "vorher ------\n", m4 pred = m4.cluster(dat, nr_runs=5, nr_init=9, max_iter=30, delta=0.1, labels=None, entropy_cutoff=None) classes = m4.classify(dat) m4.shortInitEM(dat, 5, 5, 5, 0.1) m4.EM(seq3, 20, 0.1) print "####Finish\n", m4 dat.printClustering(2, pred) evaluate(pred, true)
