def sampleRow(self, amount):
category = ST.drawCategory(self.mixture)
dirichlet = self.dirichlets[category]
multinomial = ST.drawFromDirichlet(dirichlet)
retVal = [0]*self.K
for i in range(0, amount):
k = ST.drawCategory(multinomial)
retVal[k] += 1
return retVal
def sampleRow(self, amount):
category = ST.drawCategory(self.mixture)
dirichlet = self.dirichlets[category]
multinomial = ST.drawFromDirichlet(dirichlet)
retVal = [0] * self.K
for i in range(0, amount):
k = ST.drawCategory(multinomial)
retVal[k] += 1
return retVal
def initMixtureModel(data, hyperParams):
# Initialize parameter data structs
C = hyperParams.C
K = hyperParams.K
mixture = [1.0 / C] * C
multinomials = []
for c in range(0, C):
randomMultinomial = ST.drawFromDirichlet(hyperParams.componentDirich)
multinomials.append(randomMultinomial)
return MME.MultinomialMixtureModel(C, K, multinomials, mixture)
def initMixtureModel(data, hyperParams):
# Initialize parameter data structs
C = hyperParams.C
K = hyperParams.K
mixture = [1.0 / C] * C
multinomials = []
for c in range(0, C):
randomMultinomial = ST.drawFromDirichlet(hyperParams.componentDirich)
multinomials.append(randomMultinomial)
return MME.MultinomialMixtureModel(C, K, multinomials, mixture)
#
#
import sys
import csv
import math
import random
import samplingTools as Sample
from optparse import OptionParser
parser = OptionParser()
parser.add_option('-N', '--numMulinomials', dest='N', type="int", default=100, help='Number of distinct multinomials to generate')
parser.add_option('-M', '--numSamplesPerRow', dest='M', type="int", default=100, help='The number of samples for each multinomial')
parser.add_option('-A', '--alpha', dest='A', default='1,1', help='Comma-separated dirichlet parameters')
parser.add_option('-O', '--outputType', dest='O', default='countMatrix', help='The type of output: countMatrix (default), or UMatrix')
(options, args) = parser.parse_args()
alphas = map(float, options.A.split(","))
K = len(alphas)
outputType = "countMatrix"
if (options.O == "UMatrix"): outputType = options.O
if (outputType == "UMatrix"):
data = Sample.generateRandomDataset(options.M, options.N, alphas)
print "\t".join(map(str, data))
else:
for i in range(0, options.N):
multinomial = Sample.drawFromDirichlet(alphas)
buckets = Sample.sampleFromMultinomial(multinomial, options.M)
print "\t".join(map(str, buckets))
'--numMulinomials',
dest='N',
type="int",
default=100,
help='Number of distinct multinomials to generate')
parser.add_option('-A',
'--alpha',
dest='A',
default='1,1',
help='Comma-separated dirichlet parameters')
parser.add_option(
'-O',
'--outputType',
dest='O',
default='multnomials',
help=
'The type of output: multnomials (default), or ss (sufficient statistic) which is the average of the sum of the logs for each category'
)
(options, args) = parser.parse_args()
alphas = map(float, options.A.split(","))
K = len(alphas)
if (options.O == "ss"):
for i in range(0, options.N):
multinomial = Sample.drawFromDirichlet(alphas)
print "\t".join(map(str, multinomial))
else:
for i in range(0, options.N):
multinomial = Sample.drawFromDirichlet(alphas)
print "\t".join(map(str, multinomial))
