def __init__(self, vtree_filename, sdd_filename):
# Load the Sdd, convert to psdd
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename, manager)
pmanager = PSddManager(vtree)
# Storing psdd
self.beta = pmanager.copy_and_normalize_sdd(alpha, vtree)
def run_test(vtree_filename,sdd_filename,seed=0,enum_models=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
# CONVERT TO PSDD
with Timer("converting to psdd"):
pmanager = PSddManager(vtree)
beta = pmanager.copy_and_normalize_sdd(alpha,vtree)
prior = UniformSmoothing(2.0)
#prior.initialize_psdd(beta)
Prior.random_parameters(beta,seed=seed)
# PRINT SOME STATS
print "================================"
print " sdd model count: %s" % fmt(alpha.model_count(vtree))
print " sdd count: %s" % fmt(alpha.count())
print " sdd size: %s" % fmt(alpha.size())
print "================================"
print "psdd model count: %s" % fmt(beta.model_count())
print " psdd count: %s" % fmt(beta.count())
print " psdd size: %s" % fmt(beta.size())
print "================================"
print " theta count: %s" % fmt(beta.theta_count())
print " zero count: %s" % fmt(beta.zero_count())
print " true count: %s" % fmt(beta.true_count())
if beta.vtree.var_count <= 10:
print beta.as_table()
mpe_val,mpe_inst = beta.mpe()
mpe_val = mpe_val if beta.is_false_sdd else mpe_val/beta.theta_sum
print "mpe: %s %.8f" % (mpe_inst,mpe_val)
if enum_models:
models = []
with Timer("enumerating %d models" % enum_models):
for model in beta.enumerate_mpe(pmanager):
models.append(model)
if len(models) >= enum_models: break
for model in models[:10]:
print model
print "%d models (%d max)" % (len(models),10)
"""
with Timer("evaluating %d models" % enum_models):
for model in models:
if not alpha.is_model(model):
print "error: non-model", model
if not alpha._is_bits_and_data_clear(): # random check
print "error: bits or data not clear"
"""
return beta,pmanager
def run_test(vtree_filename,sdd_filename,\
print_models=10,count_models=100,enum_models=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
with Timer("counting %d models" % count_models):
for i in range(count_models):
alpha.model_count(vtree)
# PRINT SOME STATS
print("================================")
print(" sdd model count: %s" % fmt(alpha.model_count(vtree)))
print(" sdd count: %s" % fmt(alpha.count()))
print(" sdd size: %s" % fmt(alpha.size()))
if print_models:
models = []
with Timer("enumerating models"):
for model in alpha.models(vtree,lexical=True):
st = "".join( str(val) for var,val in model )
models.append(st)
if len(models) >= print_models: break
for model in models:
print(model)
print("%d models (%d max)" % (len(models),print_models))
if enum_models:
models = []
with Timer("enumerating %d models" % enum_models):
for model in alpha.models(vtree):
models.append(model)
if len(models) >= enum_models: break
with Timer("evaluating %d models" % enum_models):
for model in models:
if not alpha.is_model(model):
print("error: non-model", model)
if not alpha._is_bits_and_data_clear(): # random check
print("error: bits or data not clear")
return alpha,manager
def run_test(vtree_filename,sdd_filename,\
print_models=10,count_models=100,enum_models=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
with Timer("counting %d models" % count_models):
for i in xrange(count_models):
alpha.model_count(vtree)
# PRINT SOME STATS
print "================================"
print " sdd model count: %s" % fmt(alpha.model_count(vtree))
print " sdd count: %s" % fmt(alpha.count())
print " sdd size: %s" % fmt(alpha.size())
if print_models:
models = []
with Timer("enumerating models"):
for model in alpha.models(vtree,lexical=True):
st = "".join( str(val) for var,val in model )
models.append(st)
if len(models) >= print_models: break
for model in models:
print model
print "%d models (%d max)" % (len(models),print_models)
if enum_models:
models = []
with Timer("enumerating %d models" % enum_models):
for model in alpha.models(vtree):
models.append(model)
if len(models) >= enum_models: break
with Timer("evaluating %d models" % enum_models):
for model in models:
if not alpha.is_model(model):
print "error: non-model", model
if not alpha._is_bits_and_data_clear(): # random check
print "error: bits or data not clear"
return alpha,manager
def run_test(vtree_filename,sdd_filename,seed=0,enum_models=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
# CONVERT TO PSDD
with Timer("converting to two psdds"):
pmanager1 = PSddManager(vtree)
pmanager2 = PSddManager(vtree)
beta = pmanager1.copy_and_normalize_sdd(alpha,vtree)
gamma = pmanager2.copy_and_normalize_sdd(alpha,vtree)
#prior = DirichletPrior(2.0)
prior = UniformSmoothing(1.0)
prior.initialize_psdd(beta)
Prior.random_parameters(gamma,seed=(seed+1))
# PRINT SOME STATS
print("================================")
print(" sdd model count: %s" % fmt(alpha.model_count(vtree)))
print(" sdd count: %s" % fmt(alpha.count()))
print(" sdd size: %s" % fmt(alpha.size()))
print("================================")
print("psdd model count: %s" % fmt(beta.model_count()))
print(" psdd count: %s" % fmt(beta.count()))
print(" psdd size: %s" % fmt(beta.size()))
print("================================")
print(" theta count: %s" % fmt(beta.theta_count()))
print(" zero count: %s" % fmt(beta.zero_count()))
print(" true count: %s" % fmt(beta.true_count()))
if beta.vtree.var_count <= PSddNode._brute_force_limit:
print("=== beta ===")
print(beta.as_table())
print("=== gamma ===")
print(gamma.as_table())
print("=== end ===")
print("brute force:")
print("kl(beta,gamma) = %.8g" % beta.kl_psdd_brute_force(gamma))
print("kl(gamma,beta) = %.8g" % gamma.kl_psdd_brute_force(beta))
print("kl(beta,beta) = %.8g" % beta.kl_psdd_brute_force(beta))
print("kl(gamma,gamma) = %.8g" % gamma.kl_psdd_brute_force(gamma))
print("compute:")
print("kl(beta,gamma) = %.8g" % beta.kl_psdd(gamma))
print("kl(gamma,beta) = %.8g" % gamma.kl_psdd(beta))
print("kl(beta,beta) = %.8g" % beta.kl_psdd(beta))
print("kl(gamma,gamma) = %.8g" % gamma.kl_psdd(gamma))
print("compute:")
print("kl(beta,gamma) = %.8g" % beta.kl_psdd_alt(gamma))
print("kl(gamma,beta) = %.8g" % gamma.kl_psdd_alt(beta))
print("kl(beta,beta) = %.8g" % beta.kl_psdd_alt(beta))
print("kl(gamma,gamma) = %.8g" % gamma.kl_psdd_alt(gamma))
ess = 2.0
prior = UniformSmoothing(ess)
print("log prior (ess=%.8f,mc=%d):" % (ess,beta.model_count()))
if beta.vtree.var_count <= PSddNode._brute_force_limit:
print("method 1 = %.8g" % prior.log_prior_brute_force(beta))
print("method 2 = %.8g" % prior.log_prior(beta))
return beta,pmanager1
import glob from pylab import * from pypsdd import Vtree,SddManager,PSddManager,io from pypsdd import DataSet,Prior,DirichletPrior,UniformSmoothing k = 50 # number of training sets Ns = range(8,13) # dataset sizes vtree_filename = "pypsdd/tests/examples/example.vtree" sdd_filename = "pypsdd/tests/examples/example.sdd" print "reading vtree and sdd ..." vtree = Vtree.read(vtree_filename) manager = SddManager(vtree) alpha = io.sdd_read(sdd_filename,manager) print "converting to two psdds ..." pmanager1 = PSddManager(vtree) pmanager2 = PSddManager(vtree) beta = pmanager1.copy_and_normalize_sdd(alpha,vtree) gamma = pmanager2.copy_and_normalize_sdd(alpha,vtree) Prior.random_parameters(beta) # randomly parameterize beta print "simulating datasets from beta ..." # for each N, simulate a set of k datasets train_sets = [ [DataSet.simulate(beta,2**N) for i in xrange(k)] for N in Ns ] print "running learning experiments ..." results = [] prior = DirichletPrior(2.0)
def run_test(vtree_filename,
sdd_filename,
N=1024,
seed=0,
print_models=True,
test_learning=True):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename, manager)
# CONVERT TO PSDD
with Timer("converting to psdd"):
pmanager = PSddManager(vtree)
beta = pmanager.copy_and_normalize_sdd(alpha, vtree)
if test_learning:
# SIMULATE DATASETS
with Timer("simulating datasets"):
#prior = DirichletPrior(2.0)
prior = UniformSmoothing(1024.0)
prior.initialize_psdd(beta)
training = DataSet.simulate(beta, N, seed=seed)
testing = DataSet.simulate(beta, N, seed=(seed + 1))
# LEARN A PSDD
with Timer("learning complete data"):
beta.learn(training, prior)
with Timer("evaluate log likelihood"):
train_ll = beta.log_likelihood(training) / training.N
test_ll = beta.log_likelihood(testing) / testing.N
# PRINT SOME STATS
print "================================"
print " sdd model count: %s" % fmt(alpha.model_count(vtree))
print " sdd count: %s" % fmt(alpha.count())
print " sdd size: %s" % fmt(alpha.size())
print "================================"
print "psdd model count: %s" % fmt(beta.model_count())
print " psdd count: %s" % fmt(beta.count())
print " psdd size: %s" % fmt(beta.size())
print "================================"
print " theta count: %s" % fmt(beta.theta_count())
print " zero count: %s" % fmt(beta.zero_count())
print " true count: %s" % fmt(beta.true_count())
if test_learning:
print "================================"
print " training size: %d" % training.N
print " testing size: %d" % testing.N
print " unique training: %d" % len(training)
print " unique testing: %d" % len(testing)
print "================================"
print " training ll: %.8f" % train_ll
print " testing ll: %.8f" % test_ll
print "================================"
print training
value = beta.value()
print "================================"
print " p(T) value: %.8f" % beta.value()
e_inst = Inst.from_literal(1, pmanager.var_count)
pval = beta.value(evidence=e_inst)
e_inst = Inst.from_literal(-1, pmanager.var_count)
nval = beta.value(evidence=e_inst)
print "p(a)+p(~a) value: %.8f" % (pval + nval)
print " p(a) value: %.8f" % pval
print " p(~a) value: %.8f" % nval
if value:
print " probability: %.8f" % beta.probability(evidence=e_inst)
var_marginals = beta.marginals()
value = var_marginals[0]
check = True
for var in xrange(1, pmanager.var_count + 1):
e_inst = Inst.from_literal(1, pmanager.var_count)
pval = beta.value(evidence=e_inst)
e_inst = Inst.from_literal(-1, pmanager.var_count)
nval = beta.value(evidence=e_inst)
if abs(pval + nval - value) > 1e-8: check = False
assert check
print " marginals check: %s" % ("ok" if check else "NOT OK")
inst = InstMap()
inst[1] = 1
inst[pmanager.var_count] = 0
var_marginals = beta.marginals(evidence=inst)
value = var_marginals[0]
check = True
for var in xrange(2, pmanager.var_count):
inst[var] = 1
pval = beta.value(evidence=inst)
inst[var] = 0
nval = beta.value(evidence=inst)
del inst[var]
if abs(pval + nval - value) > 1e-8: check = False
assert check
print " marginals check: %s" % ("ok" if check else "NOT OK")
return beta, pmanager
import glob from pylab import * from pypsdd import Vtree, SddManager, PSddManager, io from pypsdd import DataSet, Prior, DirichletPrior, UniformSmoothing k = 50 # number of training sets Ns = range(8, 13) # dataset sizes vtree_filename = "pypsdd/tests/examples/example.vtree" sdd_filename = "pypsdd/tests/examples/example.sdd" print "reading vtree and sdd ..." vtree = Vtree.read(vtree_filename) manager = SddManager(vtree) alpha = io.sdd_read(sdd_filename, manager) print "converting to two psdds ..." pmanager1 = PSddManager(vtree) pmanager2 = PSddManager(vtree) beta = pmanager1.copy_and_normalize_sdd(alpha, vtree) gamma = pmanager2.copy_and_normalize_sdd(alpha, vtree) Prior.random_parameters(beta) # randomly parameterize beta print "simulating datasets from beta ..." # for each N, simulate a set of k datasets train_sets = [[DataSet.simulate(beta, 2**N) for i in xrange(k)] for N in Ns] print "running learning experiments ..." results = [] prior = DirichletPrior(2.0)
def run_test(vtree_filename,sdd_filename,seed=0,enum_models=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
# CONVERT TO PSDD
with Timer("converting to two psdds"):
pmanager1 = PSddManager(vtree)
pmanager2 = PSddManager(vtree)
beta = pmanager1.copy_and_normalize_sdd(alpha,vtree)
gamma = pmanager2.copy_and_normalize_sdd(alpha,vtree)
#prior = DirichletPrior(2.0)
prior = UniformSmoothing(1.0)
prior.initialize_psdd(beta)
Prior.random_parameters(gamma,seed=(seed+1))
# PRINT SOME STATS
print "================================"
print " sdd model count: %s" % fmt(alpha.model_count(vtree))
print " sdd count: %s" % fmt(alpha.count())
print " sdd size: %s" % fmt(alpha.size())
print "================================"
print "psdd model count: %s" % fmt(beta.model_count())
print " psdd count: %s" % fmt(beta.count())
print " psdd size: %s" % fmt(beta.size())
print "================================"
print " theta count: %s" % fmt(beta.theta_count())
print " zero count: %s" % fmt(beta.zero_count())
print " true count: %s" % fmt(beta.true_count())
if beta.vtree.var_count <= PSddNode._brute_force_limit:
print "=== beta ==="
print beta.as_table()
print "=== gamma ==="
print gamma.as_table()
print "=== end ==="
print "brute force:"
print "kl(beta,gamma) = %.8g" % beta.kl_psdd_brute_force(gamma)
print "kl(gamma,beta) = %.8g" % gamma.kl_psdd_brute_force(beta)
print "kl(beta,beta) = %.8g" % beta.kl_psdd_brute_force(beta)
print "kl(gamma,gamma) = %.8g" % gamma.kl_psdd_brute_force(gamma)
print "compute:"
print "kl(beta,gamma) = %.8g" % beta.kl_psdd(gamma)
print "kl(gamma,beta) = %.8g" % gamma.kl_psdd(beta)
print "kl(beta,beta) = %.8g" % beta.kl_psdd(beta)
print "kl(gamma,gamma) = %.8g" % gamma.kl_psdd(gamma)
print "compute:"
print "kl(beta,gamma) = %.8g" % beta.kl_psdd_alt(gamma)
print "kl(gamma,beta) = %.8g" % gamma.kl_psdd_alt(beta)
print "kl(beta,beta) = %.8g" % beta.kl_psdd_alt(beta)
print "kl(gamma,gamma) = %.8g" % gamma.kl_psdd_alt(gamma)
ess = 2.0
prior = UniformSmoothing(ess)
print "log prior (ess=%.8f,mc=%d):" % (ess,beta.model_count())
if beta.vtree.var_count <= PSddNode._brute_force_limit:
print "method 1 = %.8g" % prior.log_prior_brute_force(beta)
print "method 2 = %.8g" % prior.log_prior(beta)
return beta,pmanager1
def run_test(vtree_filename, sdd_filename, N=1024, seed=0):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename, manager)
# CONVERT TO PSDD
with Timer("converting to psdd"):
pmanager = PSddManager(vtree)
beta = pmanager.copy_and_normalize_sdd(alpha, vtree)
#prior = DirichletPrior(2.0)
prior = UniformSmoothing(1024.0)
prior.initialize_psdd(beta)
# SIMULATE DATASETS
with Timer("drawing samples"):
random.seed(seed)
training, testing = [], []
for i in range(N):
training.append(beta.simulate())
for i in range(N):
testing.append(beta.simulate())
# SIMULATE DATASETS
with Timer("drawing samples (into dict)"):
random.seed(seed)
training, testing = defaultdict(lambda: 1), defaultdict(lambda: 1)
for i in range(N):
training[tuple(beta.simulate())] += 1
for i in range(N):
testing[tuple(beta.simulate())] += 1
# SIMULATE DATASETS
with Timer("drawing samples new (list)"):
random.seed(seed)
training, testing = [], []
for i in range(N):
inst = [None] * (manager.var_count + 1)
training.append(beta.simulate(inst=inst))
for i in range(N):
inst = [None] * (manager.var_count + 1)
testing.append(beta.simulate(inst=inst))
# SIMULATE DATASETS
"""
with Timer("drawing samples new (map)"):
random.seed(seed)
training,testing = [],[]
for i in xrange(N):
training.append(beta.simulate())
for i in xrange(N):
testing.append(beta.simulate())
"""
# SIMULATE DATASETS
with Timer("simulating datasets"):
training = DataSet.simulate(beta, N, seed=seed)
testing = DataSet.simulate(beta, N, seed=(seed + 1))
# PRINT SOME STATS
print("================================")
print(" sdd model count: %s" % fmt(alpha.model_count(vtree)))
print(" sdd count: %s" % fmt(alpha.count()))
print(" sdd size: %s" % fmt(alpha.size()))
print("================================")
print("psdd model count: %s" % fmt(beta.model_count()))
print(" psdd count: %s" % fmt(beta.count()))
print(" psdd size: %s" % fmt(beta.size()))
print("================================")
print(" theta count: %s" % fmt(beta.theta_count()))
print(" zero count: %s" % fmt(beta.zero_count()))
print(" true count: %s" % fmt(beta.true_count()))
print("================================")
print(" training size: %d" % training.N)
print(" testing size: %d" % testing.N)
print(" unique training: %d" % len(training))
print(" unique testing: %d" % len(testing))
if manager.var_count <= PSddNode._brute_force_limit:
pass
return beta, manager
def run_test(vtree_filename,sdd_filename,N=1024,seed=0,
print_models=True,test_learning=True):
# READ SDD
with Timer("reading vtree and sdd"):
vtree = Vtree.read(vtree_filename)
manager = SddManager(vtree)
alpha = io.sdd_read(sdd_filename,manager)
# CONVERT TO PSDD
with Timer("converting to psdd"):
pmanager = PSddManager(vtree)
beta = pmanager.copy_and_normalize_sdd(alpha,vtree)
if test_learning:
# SIMULATE DATASETS
with Timer("simulating datasets"):
#prior = DirichletPrior(2.0)
prior = UniformSmoothing(1024.0)
prior.initialize_psdd(beta)
training = DataSet.simulate(beta,N,seed=seed)
testing = DataSet.simulate(beta,N,seed=(seed+1))
# LEARN A PSDD
with Timer("learning complete data"):
beta.learn(training,prior)
with Timer("evaluate log likelihood"):
train_ll = beta.log_likelihood(training)/training.N
test_ll = beta.log_likelihood(testing)/testing.N
# PRINT SOME STATS
print "================================"
print " sdd model count: %s" % fmt(alpha.model_count(vtree))
print " sdd count: %s" % fmt(alpha.count())
print " sdd size: %s" % fmt(alpha.size())
print "================================"
print "psdd model count: %s" % fmt(beta.model_count())
print " psdd count: %s" % fmt(beta.count())
print " psdd size: %s" % fmt(beta.size())
print "================================"
print " theta count: %s" % fmt(beta.theta_count())
print " zero count: %s" % fmt(beta.zero_count())
print " true count: %s" % fmt(beta.true_count())
if test_learning:
print "================================"
print " training size: %d" % training.N
print " testing size: %d" % testing.N
print " unique training: %d" % len(training)
print " unique testing: %d" % len(testing)
print "================================"
print " training ll: %.8f" % train_ll
print " testing ll: %.8f" % test_ll
print "================================"
print training
value = beta.value()
print "================================"
print " p(T) value: %.8f" % beta.value()
e_inst = Inst.from_literal(1,pmanager.var_count)
pval = beta.value(evidence=e_inst)
e_inst = Inst.from_literal(-1,pmanager.var_count)
nval = beta.value(evidence=e_inst)
print "p(a)+p(~a) value: %.8f" % (pval+nval)
print " p(a) value: %.8f" % pval
print " p(~a) value: %.8f" % nval
if value:
print " probability: %.8f" % beta.probability(evidence=e_inst)
var_marginals = beta.marginals()
value = var_marginals[0]
check = True
for var in xrange(1,pmanager.var_count+1):
e_inst = Inst.from_literal(1,pmanager.var_count)
pval = beta.value(evidence=e_inst)
e_inst = Inst.from_literal(-1,pmanager.var_count)
nval = beta.value(evidence=e_inst)
if abs(pval+nval - value) > 1e-8: check = False
assert check
print " marginals check: %s" % ("ok" if check else "NOT OK")
inst = InstMap()
inst[1] = 1
inst[pmanager.var_count] = 0
var_marginals = beta.marginals(evidence=inst)
value = var_marginals[0]
check = True
for var in xrange(2,pmanager.var_count):
inst[var] = 1
pval = beta.value(evidence=inst)
inst[var] = 0
nval = beta.value(evidence=inst)
del inst[var]
if abs(pval+nval - value) > 1e-8: check = False
assert check
print " marginals check: %s" % ("ok" if check else "NOT OK")
return beta,pmanager
