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 testLymphData():
k = 5
d = 11
aux = [0]*d
models = []
for i in range(k):
aux1 = [0]*d
aux2 = [0]*d
aux3 = [0]*d
models.append(mixture.ProductDistribution([mixture.DependenceTreeDistribution(d,aux1,aux2,aux3)]))
pi = [1.0]*k
pi = np.array(pi)/k
train = mixture.MixtureModel(k,pi,models)
data = mixture.DataSet()
data.fromFiles(['data/ltree2_2fold.txt'],)
train.modelInitialization(data)
train.EM(data,100,0.01,silent=1)
def getBayesModel(G, p, mixPrior=None):
"""
Constructs a PWM CSI BayesMixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: BayesMixtureModel object
"""
if not mixPrior:
piPrior = mixture.DirichletPrior(G, [1.0] * G)
compPrior = []
for i in range(p):
compPrior.append(
mixture.DirichletPrior(4, [1.02, 1.02, 1.02, 1.02]))
# arbitrary values of struct and comp parameters. Values should be
# reset by user using the structPriorHeuristic method.
mixPrior = mixture.MixtureModelPrior(0.05, 0.05, piPrior, compPrior)
DNA = mixture.Alphabet(['A', 'C', 'G', 'T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append(mixture.DiscreteDistribution(4, phi, DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.BayesMixtureModel(G, pi, comps, mixPrior, struct=1)
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 getModel(G, p):
"""
Constructs a PWM MixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: MixtureModel object
"""
DNA = mixture.Alphabet(['A', 'C', 'G', 'T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append(mixture.DiscreteDistribution(4, phi, DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.MixtureModel(G, pi, comps)
return m
def testdtree():
tree = {}
tree[0] = -1
tree[1] = 0
tree[2] = 1
n1 = mixture.ProductDistribution([mixture.ConditionalGaussDistribution(3,[0, 1, 0],
[0, -0.1, 0.1],
[0.5,0.5,0.5],tree)])
tree2 = {}
tree2[0] = -1
tree2[1] = 0
tree2[2] = 0
n2 = mixture.ProductDistribution([mixture.ConditionalGaussDistribution(3,[-1, 0, 1],
[0, 0.1, -0.1],
[0.5,0.5,0.5],tree2)])
pi = [0.4, 0.6]
gen = mixture.MixtureModel(2,pi,[n1,n2])
random.seed(1)
data = gen.sampleDataSet(1000)
print data
n1 = mixture.ProductDistribution([mixture.DependenceTreeDistribution(3,[0.1, 1.1, 0.1],
[0, 0, 0],
[1.0,1.0,1.0])])
n2 = mixture.ProductDistribution([mixture.DependenceTreeDistribution(3,[-1, 0, -0.1],
[0, 0, 0],
[1.0,1.0,1.0])])
n1 = mixture.ProductDistribution([mixture.ConditionalGaussDistribution(3,[0, 1, 0],
[0.0, 0.1, 0.1],
[0.1,0.1,0.1],tree)])
n2 = mixture.ProductDistribution([mixture.ConditionalGaussDistribution(3,[-1, 0, 1],
[0.0, 0.1, 0.1],
[0.1,0.1,0.1],tree2)])
train = mixture.MixtureModel(2,pi,[n1,n2])
train.modelInitialization(data)
train.EM(data,100,0.01,silent=1)
def getBackgroundModel(p, dist=None):
"""
Construct background model
@param p: number of positions of the binding site
@param dist: background nucleotide frequencies, uniform is default
@return: MixtureModel representing the background
"""
DNA = mixture.Alphabet(['A', 'C', 'G', 'T'])
dlist = []
if dist == None:
phi = [0.25] * 4
else:
phi = dist
for j in range(p):
dlist.append(mixture.DiscreteDistribution(4, phi, DNA))
comps = [mixture.ProductDistribution(dlist)]
m = mixture.MixtureModel(1, [1.0], comps)
return m
[dist_spelling, missing_spelling],
compFix=[0, 2])
# diagnoses for cormobidit disorders
#"ODD" "CONDUCT" "SOC PHO" "SEP ANX" "SPEC PHO" "ENUR NOC" "ENUR DIU" "ENCOPRES" "TOURET" "TIC CRON" "TIC TRAN"
comor = []
for j in range(COMOR):
p_comor = [0.0] + mixture.random_vector(3)
comor_missing = mixture.MultinomialDistribution(
1, 4, [1.0, 0.0, 0.0, 0.0], DIAG)
comor_mult = mixture.MultinomialDistribution(1, 4, p_comor, DIAG)
comor_mix = mixture.MixtureModel(2, [0.999, 0.001],
[comor_mult, comor_missing],
compFix=[0, 2])
comor.append(comor_mix)
pd_comor = mixture.ProductDistribution(comor)
# the drd4 VNTR are represented as a discrete distribution over the observed lengths,
# the specific repeat sequence tpyes are not considered at this time
p_drd4_vntr_len = [0.0] + mixture.random_vector(10)
dist_drd4_vntr_len = mixture.MultinomialDistribution(
1, 11, p_drd4_vntr_len, VNTR)
vntr_missing = mixture.MultinomialDistribution(1, 11, [1.0] + [0.0] * 10,
VNTR)
mix_drd4_vntr_len = mixture.MixtureModel(
2, [0.999, 0.001], [dist_drd4_vntr_len, vntr_missing], compFix=[0, 2])
components.append(
mixture.ProductDistribution([
mix_bd, mix_voc, mix_read, mix_math, mix_spelling, pd_comor,
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)
#k = 2
#xd = pm.NormalDistribution(datamu[0], k*datasigma[0])