except NameError:
# relasfile doesn't exist
relas = map(str, range(R))
vocab = {'words': words, 'relas': relas}
# --- actually get the training data --- #
if ONLINE:
train_data = dstream
else:
train_data = dstream.acquire_all()
# --- initialise parameters --- #
pp = bf2f.params((C, G, V),
vocab,
fix_words=fix_words,
fix_relas=fix_relas,
trans_rela=trans_rela)
# --- ll before --- #
if CALC_LL:
print 'pre ll:', bf2f.log_likelihood(pp, train_data)
# --- start the logfile --- #
if DIAGNOSTICS:
logf = open(fname + '_logfile.txt', 'w')
logf.write(
'n\ttime\tll\tdata_energy\tmodel_energy\tvaliset_energy\trandom_energy\tperm_energy\tC_lens\tG_lens\tV_lens\n'
)
logf.close()
else:
rela = line.split()[1]
relas[index] = rela
except NameError:
# relasfile doesn't exist
relas = map(str, range(R))
vocab = {'words':words, 'relas': relas}
# --- actually get the training data --- #
if ONLINE:
train_data = dstream
else:
train_data = dstream.acquire_all()
# --- initialise parameters --- #
pp = bf2f.params((C, G, V), vocab, fix_words=fix_words, fix_relas=fix_relas, trans_rela=trans_rela)
# --- ll before --- #
if CALC_LL:
print 'pre ll:', bf2f.log_likelihood(pp, train_data)
# --- start the logfile --- #
if DIAGNOSTICS:
logf = open(fname+'_logfile.txt','w')
logf.write('n\ttime\tll\tdata_energy\tmodel_energy\tvaliset_energy\trandom_energy\tperm_energy\tC_lens\tG_lens\tV_lens\n')
logf.close()
else:
print 'WARNING: no diagnostics.'
# ---- TRAIN! --- #
for epoch in xrange(n_epochs):
C[:,-1] = 1
V[:,-1] = 1
# G
G = bf2f.np.random.normal(scale=0.01, size=(R, d+1, d+1))
G[0, :, :] = bf2f.np.eye(d+1)
G[:, -1, :] = 0
G[:, -1, -1] = 1
initial_params = (C, G, V)
if options['diagnostics_rate'] > 0:
DIAGNOSTICS = True
else:
DIAGNOSTICS = False
# --- initialise parameters --- #
pp = bf2f.params(initial_params, options, vocab)
# --- ll before --- #
if options['calc_ll']:
pre_ll = bf2f.log_likelihood(pp, train_data)
print 'pre ll:', pre_ll
# --- start the logfile --- #
if DIAGNOSTICS:
logf = open(output_root+'_logfile.txt','w')
logf.write('n\ttime\tll\tdata_energy\tmodel_energy\tvaliset_energy\trandom_energy\tperm_energy\tC_lens\tG_lens\tV_lens\n')
logf.close()
# ---- TRAIN! --- #
for epoch in xrange(options['n_epochs']):
print 'epoch:', epoch
except IndexError:
sys.exit('ERROR: requires cfg file.')
try:
epoch = sys.argv[2]
except IndexError:
sys.exit('ERROR: requires epoch')
# --- unroll options --- #
output_root = options['output_root']
wordlist = options['wordlist']
relalist = options['relalist']
# --- load parameters --- #
params_path = output_root+'_epoch'+epoch+'_XXX.txt'
pp = bf2f.params(params_path, options, (wordlist, relalist))
print 'loaded params from', params_path
# --- save results? --- #
if save:
# note: appending
socher_auc_test_path = output_root+'_auc_test.txt'
socher_auc_test_file = open(socher_auc_test_path, 'a')
socher_acc_test_path = output_root+'_acc_test.txt'
socher_acc_test_file = open(socher_acc_test_path, 'a')
# --- load the evaluation data --- #
if simple_socher:
droot = '/cbio/grlab/home/hyland/data/nips13-dataset/Wordnet/simplified_vocab/'
dev_path = droot + 'dev_triples_simple.txt'
dev = bf2f.np.array(map(lambda x: map(int, x.strip('\n').split(' ')), open(dev_path,'r').readlines()))