def pos_seq(rec, infos):
"""
1. evaluate posterior probability on different data sizes
run: serial
"""
seq = []
seen = set()
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print e, 'done'
fff()
print '=' * 50
return seq
def pos_seq(rec, infos):
"""
1. evaluate posterior probability on different data sizes
run: serial
"""
seq = []
seen = set()
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen: prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print e, 'done'; fff()
print '='*50
return seq
def test_sto():
"""
objective: test if our posterior distribution is stable for each time of estimation
run: mpiexec -n 12
"""
rec = load_hypo('out/simulations/staged/', ['staged', 'normal0', 'normal1'])
# rec = load_hypo('out/simulations/staged/', ['staged'])
seen = set()
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
print rank, 'hypo len: ', len(seen); fff()
seq = []
inner_kl_seq = []
infos = [[i, 4*((i-1)/48+1)] for i in xrange(12, 145, 2)]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
if len(seq) > 1: inner_kl_seq.append(compute_kl(seq[-2], seq[-1]))
print 'rank: ', rank, e, 'done'; fff()
dump(seq, open('seq_'+str(rank)+suffix,'w'))
dump(inner_kl_seq, open('inner_kl_seq_'+str(rank)+suffix, 'w'))
if rank != 0:
comm.send(seq, dest=0)
print rank, 'send'; fff()
sys.exit(0)
else:
seq_set = [seq]
for i_s in xrange(size - 1):
seq_set.append(comm.recv(source=i_s+1))
print rank, 'recv:', i_s; fff()
cross_kl_seq = []
for i_s in xrange(len(seq_set[0])):
tmp = []
for i_ss in xrange(len(seq_set)-1):
current_dict = seq_set[i_ss][i_s]
next_dict = seq[i_ss+1][i_s]
tmp.append(compute_kl(current_dict, next_dict))
print 'row %i column %i done' % (i_ss, i_s); fff()
cross_kl_seq.append(tmp)
dump(cross_kl_seq, open('cross_kl_seq_'+str(rank)+suffix, 'w'))
for e in cross_kl_seq:
print e; fff()
def test_sto():
"""
objective: test if our posterior distribution is stable for each time of estimation
run: mpiexec -n 12
"""
rec = load_hypo('out/simulations/staged/',
['staged', 'normal0', 'normal1'])
# rec = load_hypo('out/simulations/staged/', ['staged'])
seen = set()
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
print rank, 'hypo len: ', len(seen)
fff()
seq = []
inner_kl_seq = []
infos = [[i, 4 * ((i - 1) / 48 + 1)] for i in xrange(12, 145, 2)]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
if len(seq) > 1: inner_kl_seq.append(compute_kl(seq[-2], seq[-1]))
print 'rank: ', rank, e, 'done'
fff()
dump(seq, open('seq_' + str(rank) + suffix, 'w'))
dump(inner_kl_seq, open('inner_kl_seq_' + str(rank) + suffix, 'w'))
if rank != 0:
comm.send(seq, dest=0)
print rank, 'send'
fff()
sys.exit(0)
else:
seq_set = [seq]
for i_s in xrange(size - 1):
seq_set.append(comm.recv(source=i_s + 1))
print rank, 'recv:', i_s
fff()
cross_kl_seq = []
for i_s in xrange(len(seq_set[0])):
tmp = []
for i_ss in xrange(len(seq_set) - 1):
current_dict = seq_set[i_ss][i_s]
next_dict = seq[i_ss + 1][i_s]
tmp.append(compute_kl(current_dict, next_dict))
print 'row %i column %i done' % (i_ss, i_s)
fff()
cross_kl_seq.append(tmp)
dump(cross_kl_seq, open('cross_kl_seq_' + str(rank) + suffix, 'w'))
for e in cross_kl_seq:
print e
fff()
def make_staged_seq2(jump, temp):
"""
run: mpiexec -n 12
"""
rec = load_hypo('out/simulations/staged/',
['staged', 'normal0', 'normal1'])
seen = set()
work_list = slice_list(range(size), 3)
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
if rank in work_list[0]:
seq = []
infos = [[i, min(4 * ((int(i) - 1) / 48 + 1), 12)]
for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1] + (e[1] % 2 != 0))
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'
fff()
elif rank in work_list[1]:
seq = []
infos = [[i, 12] for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'
fff()
else:
seq = []
infos = [[i, 12] for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
eval_data = uniform_data(e[0], e[1])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'
fff()
# TODO no need ?
from copy import deepcopy
dict_0 = deepcopy(seq[0])
for h in dict_0:
dict_0[h] = h.compute_posterior(
[FunctionData(input=[], output=Counter())])
seq.insert(0, dict_0)
dump(seq, open('seq' + str(rank) + suffix, 'w'))
def make_staged_seq2(jump, temp):
"""
run: mpiexec -n 12
"""
rec = load_hypo('out/simulations/staged/', ['staged', 'normal0', 'normal1'])
seen = set()
work_list = slice_list(range(size), 3)
for e in rec:
for h in e[1]:
if h in seen: continue
seen.add(h)
if rank in work_list[0]:
seq = []
infos = [[i, min(4*((int(i)-1)/48+1), 12)] for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1]+(e[1]%2!=0))
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'; fff()
elif rank in work_list[1]:
seq = []
infos = [[i, 12] for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
language = AnBn(max_length=e[1])
eval_data = language.sample_data_as_FuncData(e[0])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'; fff()
else:
seq = []
infos = [[i, 12] for i in [10**e for e in np.arange(0, 2.2, 0.1)]]
for e in infos:
prob_dict = {}
eval_data = uniform_data(e[0], e[1])
for h in seen:
h.likelihood_temperature = temp
prob_dict[h] = h.compute_posterior(eval_data)
seq.append(prob_dict)
print 'rank: ', rank, e, 'done'; fff()
# TODO no need ?
from copy import deepcopy
dict_0 = deepcopy(seq[0])
for h in dict_0:
dict_0[h] = h.compute_posterior([FunctionData(input=[], output=Counter())])
seq.insert(0, dict_0)
dump(seq, open('seq'+str(rank)+suffix, 'w'))
In this case, we investigate the effect of different observed data distributions on training convergence.
"""
if __name__ == '__main__':
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
# ========================================================================================================
# Process command line arguments
# ========================================================================================================
(options, args) = parser.parse_args()
suffix = time.strftime('_' + options.NAME + '_%m%d_%H%M%S', time.localtime())
prefix = '../out/simulations/skewed/'
# ========================================================================================================
# Running
# ========================================================================================================
language = AnBn()
show_info('running skewed input case..')
rec = probe_MHsampler(make_hypothesis('AnBn'), language, options, prefix + 'skewed_out_' + str(rank) + suffix)
show_info('running normal input case..')
CASE += 1
cnt = Counter()
num = 64.0 * 2 / options.FINITE
for i in xrange(1, options.FINITE/2+1):
cnt['a'*i+'b'*i] = num
rec1 = probe_MHsampler(make_hypothesis('AnBn'), language, options, prefix + 'normal_out' + str(rank) + suffix, data=[FunctionData(input=[], output=cnt)])
