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'))
def make_staged_posterior_seq(_dir, temperature, lang_name, dtype):
"""
script: python parse_hypothesis.py --mode=make_staged_posterior_seq --file=file --temp=1 --language=AnBn --dtype=staged/uniform
1. read raw file
2. compute fixed Counter
3. compute posterior for different amounts
dumped posterior format: [topn, [z,amount,finite,[s1,s2,....]], [], [], ....]
NOTE: if _dir is previously dumped posterior seq, then we use it
"""
if not (os.path.isfile(_dir) and 'posterior_seq' in _dir):
topn = set()
for filename in os.listdir(_dir):
if ('staged' in filename
or 'normal' in filename) and 'seq' not in filename:
print 'load', filename
_set = load(open(_dir + filename))
topn.update([h for h in _set])
topn = list(topn)
# fix the llcnts to save time and make curve smooth
print 'get llcnts...'
for h in topn:
llcnts = Counter([h() for _ in xrange(2048)])
h.fixed_ll_counts = llcnts
seq = []
seq.append(topn)
for amount, finite in mk_staged_wlist(0, 200, 2, [48, 96]):
print 'posterior on', amount, finite
if dtype == 'staged':
language = instance(lang_name, finite)
eval_data = language.sample_data_as_FuncData(amount)
elif dtype == 'uniform':
eval_data = uniform_data(amount, 12)
for h in topn:
h.likelihood_temperature = temperature
h.compute_posterior(eval_data)
Z = logsumexp([h.posterior_score for h in topn])
seq.append([Z, amount, finite, [h.posterior_score for h in topn]])
dump(seq, open(dtype + '_posterior_seq' + suffix, 'w'))
else:
seq = load(open(_dir))
# ====================== compute KL based on seq =======================
print 'compute kl seq...'
kl_seq = []
topn = seq.pop(0)
for i in xrange(len(seq) - 1):
kl_seq.append([seq[i][1], compute_kl2(seq[i], seq[i + 1])])
dump(kl_seq, open(dtype + '_kl_seq' + suffix, 'w'))
def make_staged_posterior_seq(_dir, temperature, lang_name, dtype):
"""
script: python parse_hypothesis.py --mode=make_staged_posterior_seq --file=file --temp=1 --language=AnBn --dtype=staged/uniform
1. read raw file
2. compute fixed Counter
3. compute posterior for different amounts
dumped posterior format: [topn, [z,amount,finite,[s1,s2,....]], [], [], ....]
NOTE: if _dir is previously dumped posterior seq, then we use it
"""
if not (os.path.isfile(_dir) and 'posterior_seq' in _dir):
topn = set()
for filename in os.listdir(_dir):
if ('staged' in filename or 'normal' in filename) and 'seq' not in filename:
print 'load', filename
_set = load(open(_dir+filename))
topn.update([h for h in _set])
topn = list(topn)
# fix the llcnts to save time and make curve smooth
print 'get llcnts...'
for h in topn:
llcnts = Counter([h() for _ in xrange(2048)])
h.fixed_ll_counts = llcnts
seq = []
seq.append(topn)
for amount, finite in mk_staged_wlist(0,200,2,[48,96]):
print 'posterior on', amount, finite
if dtype == 'staged':
language = instance(lang_name, finite)
eval_data = language.sample_data_as_FuncData(amount)
elif dtype == 'uniform':
eval_data = uniform_data(amount, 12)
for h in topn:
h.likelihood_temperature = temperature
h.compute_posterior(eval_data)
Z = logsumexp([h.posterior_score for h in topn])
seq.append([Z, amount, finite, [h.posterior_score for h in topn]])
dump(seq,open(dtype + '_posterior_seq' + suffix, 'w'))
else:
seq = load(open(_dir))
# ====================== compute KL based on seq =======================
print 'compute kl seq...'
kl_seq = []
topn = seq.pop(0)
for i in xrange(len(seq)-1):
kl_seq.append([seq[i][1],compute_kl2(seq[i],seq[i+1])])
dump(kl_seq,open(dtype + '_kl_seq' + suffix,'w'))
