def run(data_amount):
print "Starting chain on %s data points" % data_amount
data = makeVariableLexiconData(eval(options.word), options.word, the_context, n=data_amount, s=options.s,
alpha=options.alpha, verbose=True)
h0 = KinshipLexicon(words=[options.word], alpha=options.alpha)
h0.set_word(options.word, LOTHypothesis(grammar, value=None, args=['recurse_', 'C', 'X']))
hyps = TopN(N=options.top_count)
mhs = MHSampler(h0, data, options.steps, likelihood_temperature=options.llt,
prior_temperature=options.prior_temp)
for samples_yielded, h in break_ctrlc(enumerate(mhs)):
#if samples_yielded % 100 == 0:
# print h.prior, h.likelihood, h
hyps.add(h)
return hyps
for dp in hypothesized_word_data:
if dp in true_word_data:
correct_count += 1
# Figure out if it was characteristic or defining
hyptype = hypothesis.value[w].value.args[0].returntype
# Add it to the results: So Ideally we would have a line like this for every different context and all the contexts together
findings.append([hyptype, hypothesis.prior, hypothesis.point_ll[0], hypothesis.point_ll[1],
hypothesis.point_ll[2], w, correct_count, len(hypothesized_word_data), len(true_word_data), hypothesis.value])
return findings
#############################################################################################
# MAIN CODE
#############################################################################################
print "Making data sets of size %s . . ." % options.data_size
huge_data_0 = makeVariableLexiconData(eval(options.word), options.word, the_context, n=options.data_size,
s=0, alpha=options.alpha)
huge_data_1 = makeVariableLexiconData(eval(options.word), options.word, the_context, n=options.data_size,
s=1, alpha=options.alpha)
huge_data_2 = makeVariableLexiconData(eval(options.word), options.word, the_context, n=options.data_size,
s=2, alpha=options.alpha)
print "Loading hypothesis space . . ."
hypothesis_space = set()
for i in os.listdir(options.input_loc):
with open(options.input_loc + i, 'r') as f:
hypothesis_space.update(pickle.load(f))
print "Assessing hypotheses . . ."
results = []
result_strings = []
for s, h in enumerate(hypothesis_space):
hyptype, hypothesis.prior, hypothesis.point_ll[0],
hypothesis.point_ll[1], hypothesis.point_ll[2], w, correct_count,
len(hypothesized_word_data),
len(true_word_data), hypothesis.value
])
return findings
#############################################################################################
# MAIN CODE
#############################################################################################
print "Making data sets of size %s . . ." % options.data_size
huge_data_0 = makeVariableLexiconData(eval(options.word),
options.word,
the_context,
n=options.data_size,
s=0,
alpha=options.alpha)
huge_data_1 = makeVariableLexiconData(eval(options.word),
options.word,
the_context,
n=options.data_size,
s=1,
alpha=options.alpha)
huge_data_2 = makeVariableLexiconData(eval(options.word),
options.word,
the_context,
n=options.data_size,
s=2,
alpha=options.alpha)