def setup2():
# Setting up a two component mixture over four features.
# Two features are Normal distributions, two discrete.
# initializing atomar distributions for first component
n1 = mixture.NormalDistribution(1.0,1.5)
n2 = mixture.NormalDistribution(2.0,0.5)
d1 = mixture.DiscreteDistribution(4,[0.1,0.4,0.4,0.1])
c1 = mixture.ProductDistribution([n1,n2])
c2 = mixture.ProductDistribution([n1,d1])
# intializing mixture
pi = [0.4,0.6]
m = mixture.MixtureModel(2,pi,[c1,c2])
return m
def setup():
# Setting up a two component mixture over four features.
# Two features are Normal distributions, two discrete.
# initializing atomar distributions for first component
n11 = mixture.NormalDistribution(1.0,1.5)
n12 = mixture.NormalDistribution(2.0,0.5)
d13 = mixture.DiscreteDistribution(4,[0.1,0.4,0.4,0.1])
d14 = mixture.DiscreteDistribution(4,[0.25,0.25,0.25,0.25])
# initializing atomar distributions for second component
n21 = mixture.NormalDistribution(4.0,0.5)
n22 = mixture.NormalDistribution(-6.0,0.5)
d23 = mixture.DiscreteDistribution(4,[0.7,0.1,0.1,0.1])
d24 = mixture.DiscreteDistribution(4,[0.1,0.1,0.2,0.6])
# creating component distributions
c1 = mixture.ProductDistribution([n11,n12,d13,d14])
c2 = mixture.ProductDistribution([n21,n22,d23,d24])
# intializing mixture
pi = [0.4,0.6]
m = mixture.MixtureModel(2,pi,[c1,c2])
return m
def sample(self,returnType='tuple'):
assert returnType in ['tuple','object']
grand = random.gammavariate(self.shape, self.scale )
#return grand
sigma = 1.0 / grand
#print sigma
mu = random.normalvariate(self.mu, math.sqrt(self.tau*sigma) )
#mu = random.normalvariate(self.mu, self.tau*sigma )
if returnType == 'tuple':
return (mu,sigma)
elif returnType == 'object':
return mixture.NormalDistribution(mu,math.sqrt(sigma))
def mixture_model(allele_freq,
max_components,
p_mean=np.nan,
p_std=np.nan,
quiet=False):
data = mixture.DataSet()
data.fromList(allele_freq)
distributions = []
for i in xrange(max_components):
if np.isnan(p_mean):
mean = random()
else:
mean = p_mean
if np.isnan(p_std):
std = random()
else:
std = p_std
distributions.append(mixture.NormalDistribution(mean, std))
total_models = []
for i in xrange(max_components):
weights = list(np.repeat(1.0 / (i + 1), i + 1))
components = distributions[0:i + 1]
model = mixture.MixtureModel(i + 1, weights, components)
model.EM(data, 1000, 0.001, silent=quiet)
if not quiet:
print
print model
print '------------------------------'
total_models.append(model)
model_selections = mixture.modelSelection(data, total_models, silent=quiet)
best_model = total_models[model_selections[1].index(
min(model_selections[1]))]
best_model_bic = min(model_selections[1])
labels = best_model.classify(data, silent=1)
return best_model, labels, best_model_bic
data = mixture.DataSet()
# iq.txt = iq and achievement test fields from pheno.txt
# drd4_len.txt = drd4 vntr types, only number of repeats
data.fromFiles(["iq.txt", "phys.txt", "drd4_len.txt"])
COMOR = 11
G = 8
components = []
for i in range(G):
# intelligence and achivement tests as univariate normal distributions. (TEST)
bd_mu = float(random.randint(3, 16))
bd_sigma = random.uniform(1.0, 8.0)
missing_bd = mixture.NormalDistribution(-9999.9, 0.00001)
dist_bd = mixture.NormalDistribution(bd_mu, bd_sigma)
mix_bd = mixture.MixtureModel(2, [0.999, 0.001], [dist_bd, missing_bd],
compFix=[0, 2])
voc_mu = float(random.randint(3, 16))
voc_sigma = random.uniform(1.0, 8.0)
missing_voc = mixture.NormalDistribution(-9999.9, 0.00001)
dist_voc = mixture.NormalDistribution(voc_mu, voc_sigma)
mix_voc = mixture.MixtureModel(2, [0.999, 0.001], [dist_voc, missing_voc],
compFix=[0, 2])
read_mu = float(random.randint(80, 120))
read_sigma = random.uniform(1.0, 28.0)
missing_read = mixture.NormalDistribution(-9999.9, 0.00001)
dist_read = mixture.NormalDistribution(read_mu, read_sigma)
pos = np.asarray([[-27, 1305], [33, 1299], [-36, 1256], [-34,
1237], [27, 1250],
[-35, 1213], [-36, 1176], [-38, 1151], [-38, 1044],
[12, 1036], [-19, 995], [-37, 962], [-23, 925], [55, 950],
[23, 931], [-20, 873], [20, 855], [23, 800], [-7, 781],
[-28, 741], [30, 548], [-16, 482], [9, 289], [-31, 272],
[-35, 167], [-19, 155], [30, 151], [62, 149], [-35, 110],
[-24, 100], [38, 102], [-30, 73], [-24, 49]])
ndistribs = 50
distribs = []
for mu in pos:
#mu = np.random.random(nd)
#mu = mins + mu * ranges
xd = pm.NormalDistribution(mu[0], 30)
yd = pm.NormalDistribution(mu[1], 30)
distrib = pm.ProductDistribution([xd, yd])
distribs.append(distrib)
# add some extra random ones
for i in range(len(pos), ndistribs):
mu = np.random.random(nd)
mu = mins + mu * ranges
xd = pm.NormalDistribution(mu[0], 30)
yd = pm.NormalDistribution(mu[1], 30)
distrib = pm.ProductDistribution([xd, yd])
distribs.append(distrib)
'''
# add background noise distrib, see 2006 Bar-Hillel
#datamu = data.mean(axis=0)
#datasigma = data.std(axis=0)