def main(args):
setup = experiment_setups.parse(args.setup)
dirname = fileutil.run_dir(args.dest_dir, setup.name, args.max_quantifier_length, args.model_size, args.name)
file_util = FileUtil(dirname)
languages = []
universe = generator.generate_simplified_models(args.model_size)
FakeEvaluatedExpression = namedtuple('FakeEvaluatedExpression', 'meaning')
expressions = [FakeEvaluatedExpression(tuple([random.choice([True, False]) for model in universe]))
for i in range(args.random_size)]
if args.sample is None:
print("generate_all() called.")
languages = generate_all(expressions, args.max_words, args.fixedwordcount)
else:
print("generate_sampled() called.")
languages = generate_sampled(expressions, args.max_words, args.sample)
complexity_measurer = WordCountComplexityMeasurer(args.max_words)
informativeness_measurer_exact = InformativenessMeasurer(len(universe))
informativeness_measurer_simmax = SimMaxInformativenessMeasurer(universe)
with ProcessPool(nodes=args.processes) as pool:
complexity = pool.map(complexity_measurer, languages)
informativeness_exact = pool.map(informativeness_measurer_exact, languages)
informativeness_simmax = pool.map(informativeness_measurer_simmax, languages)
file_util.dump_dill(complexity, 'complexity_wordcount.dill')
file_util.dump_dill(informativeness_exact, 'informativeness_exact.dill')
file_util.dump_dill(informativeness_simmax, 'informativeness_simmax.dill')
print("coinflip_languages.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
dirname = fileutil.run_dir(args.dest_dir, setup.name,
args.max_quantifier_length, args.model_size,
args.name)
file_util = FileUtil(dirname)
languages = language_loader.load_languages(file_util)
if args.comp_strat == 'wordcount':
complexity_measurer = WordCountComplexityMeasurer(args.max_words)
elif args.comp_strat == 'wordcomplexity':
complexity_measurer = SumComplexityMeasurer(args.max_words, 1)
elif args.comp_strat == 'special':
complexity_measurer = SpecialComplexityMeasurer(args.max_words)
else:
raise ValueError('{0} is not a valid complexity strategy.'.format(
args.comp_strat))
with ProcessPool(nodes=args.processes) as pool:
complexity = pool.map(complexity_measurer, languages)
file_util.dump_dill(complexity,
'complexity_{0}.dill'.format(args.comp_strat))
print("measure_complexity.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
dirname = fileutil.run_dir(args.dest_dir, setup.name,
args.max_quantifier_length, args.model_size,
args.name)
file_util = FileUtil(dirname)
languages = language_loader.load_languages(file_util)
universe = generator.generate_simplified_models(args.model_size)
if args.inf_strat == 'exact':
informativeness_measurer = InformativenessMeasurer(len(universe))
elif args.inf_strat == 'simmax':
informativeness_measurer = SimMaxInformativenessMeasurer(universe)
else:
raise ValueError('{0} is not a valid informativeness strategy.'.format(
args.inf_strat))
with ProcessPool(nodes=args.processes) as pool:
informativeness = pool.map(informativeness_measurer, languages)
file_util.dump_dill(informativeness,
'informativeness_{0}.dill'.format(args.inf_strat))
print("measure_informativeness.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
file_util_out = FileUtil(
fileutil.run_dir(setup.dest_dir, setup.name,
setup.max_quantifier_length, setup.model_size,
setup.random_name))
file_util_in = FileUtil(
fileutil.base_dir(setup.dest_dir, setup.name,
setup.max_quantifier_length, setup.model_size))
unevaluated_expressions = file_util_in.load_dill('expressions.dill')
if args.indices is not None:
index_sets = []
for indices_name in args.indices:
index_sets.append(
set(
file_util_in.load_dill(
'{0}_expression_indices.dill'.format(indices_name))))
indices = set.intersection(*index_sets)
else:
indices = range(len(unevaluated_expressions))
if args.sample is None:
languages = generate_all(indices, args.max_words, args.fixedwordcount)
else:
languages = generate_sampled(indices, setup.max_words, args.sample)
file_util_out.dump_dill(languages, 'language_indices.dill')
file_util_out.save_stringlist([list(map(str, lang)) for lang in languages],
'languages.txt')
print("languages.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
file_util = FileUtil(
fileutil.run_dir(args.dest_dir, setup.name, args.max_quantifier_length,
args.model_size, args.name))
universe = generator.generate_simplified_models(args.model_size)
monotonicity_measure = MonotonicityMeasurer(universe, args.model_size, 'A')
conservativity_measurer = ConservativityMeasurer(universe, args.model_size,
'A')
#special_complexity_measurer = SpecialComplexityMeasurer(args.max_words)
special_complexity_measurer = SpecialComplexityMeasurer(
setup.operators, args.model_size)
if args.inf_strat == 'exact':
informativeness_measurer = InformativenessMeasurer(len(universe))
elif args.inf_strat == 'simmax':
informativeness_measurer = SimMaxInformativenessMeasurer(universe)
else:
raise ValueError('{0} is not a valid informativeness strategy.'.format(
args.inf_strat))
if args.comp_strat == 'wordcount':
complexity_measurer = WordCountComplexityMeasurer(args.max_words)
elif args.comp_strat == 'wordcomplexity':
complexity_measurer = SumComplexityMeasurer(args.max_words, 1)
else:
raise ValueError('{0} is not a valid complexity strategy.'.format(
args.comp_strat))
languages_dir = setup.natural_languages_dirname
languages = []
language_names = []
for filename in os.listdir(languages_dir):
if filename.endswith('.json'):
language_file = os.path.join(languages_dir, filename)
language = parse_language(language_file, setup, universe, \
monotonicity_measure, \
conservativity_measurer, \
special_complexity_measurer)
languages.append(language)
language_names.append(filename[:-5]) # Name without extension
informativeness = zip(language_names,
map(informativeness_measurer, languages))
complexity = zip(language_names, map(complexity_measurer, languages))
file_util.dump_dill(
informativeness,
'informativeness_{0}_{1}.dill'.format(setup.name, args.inf_strat))
file_util.dump_dill(
complexity, 'complexity_{0}_{1}.dill'.format(setup.name,
args.comp_strat))
print("measure_lexicalized.py finished")
def main(args):
setup = experiment_setups.parse(args.setup)
dirname = fileutil.run_dir(setup.dest_dir, setup.name, setup.max_quantifier_length, setup.model_size, args.name)
file_util = FileUtil(dirname)
languages = language_loader.load_languages(file_util)
with ProcessPool(nodes=setup.processes) as process_pool:
monotonicities = process_pool.map(measure_monotonicity, languages)
file_util.dump_dill(monotonicities, 'monotonicity.dill')
print("measure_monotonicity.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
# use_base_dir = False
dirname = fileutil.run_dir(setup.dest_dir, setup.name,
setup.max_quantifier_length, setup.model_size,
setup.pareto_name)
file_util = FileUtil(dirname)
expressions = language_loader.load_all_evaluated_expressions(file_util)
languages_0 = language_generator.generate_sampled(
expressions, args.lang_size, int(args.sample_size / args.lang_size))
universe = generator.generate_simplified_models(setup.model_size)
measure_complexity = SumComplexityMeasurer(args.lang_size, 1)
measure_informativeness = SimMaxInformativenessMeasurer(universe)
pool = ProcessPool(nodes=setup.processes)
languages = languages_0 #lanuages will be iteratively updated in subsequent loop
for gen in range(args.generations):
print('GENERATION {0}'.format(gen))
print('measuring')
complexity = pool.map(measure_complexity, languages)
informativeness = pool.map(measure_informativeness, languages)
measurements = [(1 - inf, comp)
for inf, comp in zip(informativeness, complexity)]
print('calculating dominating')
dominating_indices = pygmo.non_dominated_front_2d(measurements)
dominating_languages = [languages[i] for i in dominating_indices]
print('mutating')
languages = sample_mutated(dominating_languages, args.sample_size,
expressions)
language_indices = [[e.index for e in lang]
for lang in dominating_languages]
dominating_complexity = [complexity[i] for i in dominating_indices]
dominating_informativeness = [
informativeness[i] for i in dominating_indices
]
file_util.dump_dill(dominating_complexity,
'complexity_wordcomplexity.dill')
file_util.dump_dill(dominating_informativeness,
'informativeness_simmax.dill')
file_util.dump_dill(language_indices, 'language_indices.dill')
file_util.save_stringlist([list(map(str, lang)) for lang in languages],
'languages.txt')
print("generate_evolutionary.py finished.")
def init(use_base_dir=False):
parser = argparse.ArgumentParser(description="Analyze")
parser.add_argument('--setup',
help='Path to the setup json file.',
required=True)
args = parser.parse_args()
setup = experiment_setups.parse(args.setup)
dirname = fileutil.base_dir(setup.dest_dir, setup.name, setup.max_quantifier_length, setup.model_size) if use_base_dir \
else fileutil.run_dir(setup.dest_dir, setup.name, setup.max_quantifier_length, setup.model_size, setup.name)
file_util = FileUtil(dirname)
return args, setup, file_util
def __init__(self, props):
self._props = props # private
# common setups
self.name = props['name']
self.pareto_name = props['pareto_name']
self.natural_name = props['natural_name']
self.random_name = props['random_name']
self.lexical_quantifiers_filename = \
path.join(path.dirname(props['setup_filename']), props['lexical_quantifiers_filename'])
self.generate_models = locate(props['model_generator'])
self.generate_primitives = locate(props['primitive_generator'])
self.parse_primitive = locate(props['primitive_parser'])
self.measure_expression_complexity = locate(
props['expression_complexity_measurer'])
self.measure_quantifier_complexity = locate(
props['quantifier_complexity_measurer'])
self.operators = {
name: op.operators[name]
for name in props['operators']
}
self.natural_languages_dirname = \
path.join(path.dirname(props['setup_filename']), 'Languages/{0}'.format(props['name']))
self.possible_input_types = []
for (name, operator) in self.operators.items():
self.possible_input_types.append(operator.inputTypes)
#set up of quantifiers, sizes, etc
self.max_quantifier_length = int(props['max_quantifier_length'])
self.model_size = int(props['model_size'])
self.processes = int(props['processes'])
# self.run_name = props['run_name']
self.comp_strat = props['comp_strat']
self.inf_strat = props['inf_strat']
self.max_words = props['max_words']
#set up of files
self.dest_dir = props['dest_dir']
self.use_base_dir = True if props['use_base_dir'].lower(
) == "true" else False
self.dirname = fileutil.base_dir(self.dest_dir, self.name, self.max_quantifier_length, self.model_size) \
if self.use_base_dir else \
fileutil.run_dir(self.dest_dir, self.name, self.max_quantifier_length, self.model_size, self.run_name)
self.file_util = FileUtil(self.dirname)
def main(args):
setup = experiment_setups.parse(args.setup)
file_util = FileUtil(
fileutil.run_dir(setup.dest_dir, setup.name,
setup.max_quantifier_length, setup.model_size,
args.name))
languages = language_loader.load_languages(file_util)
universe = generator.generate_simplified_models(setup.model_size)
pool = ProcessPool(nodes=setup.processes)
if setup.inf_strat == 'exact':
informativeness_measurer = InformativenessMeasurer(len(universe))
elif setup.inf_strat == 'simmax':
informativeness_measurer = SimMaxInformativenessMeasurer(universe)
else:
raise ValueError('{0} is not a valid informativeness strategy.'.format(
setup.inf_strat))
if setup.comp_strat == 'wordcount':
complexity_measurer = WordCountComplexityMeasurer(setup.max_words)
elif setup.comp_strat == 'wordcomplexity':
complexity_measurer = SumComplexityMeasurer(setup.max_words, 1)
else:
raise ValueError('{0} is not a valid complexity strategy.'.format(
setup.comp_strat))
informativeness = pool.map(informativeness_measurer, languages)
complexity = pool.map(complexity_measurer, languages)
file_util.dump_dill(informativeness,
'informativeness_{0}.dill'.format(setup.inf_strat))
file_util.dump_dill(complexity,
'complexity_{0}.dill'.format(setup.comp_strat))
print("measure.py finished.")
def main(args):
setup = experiment_setups.parse(args.setup)
dirname = fileutil.run_dir(setup.dest_dir, setup.name,
setup.max_quantifier_length, setup.model_size,
setup.natural_name)
file_util_out = FileUtil(dirname)
file_util_in = file_util_out.get_base_file_util()
natural_indices = set(
file_util_in.load_dill('{0}_expression_indices.dill'.format(
args.indices)))
expressions = file_util_in.load_dill('expressions.dill')
non_natural_indices = set(range(len(expressions))) - natural_indices
language_indices = []
naturalness = []
sizes = []
for lang_size in range(1, setup.max_words + 1):
for i in range(args.sample):
len_natural = random.randint(0, lang_size)
len_random = lang_size - len_natural
lang_random = next(
random_combinations(non_natural_indices, len_random, 1))
lang_natural = next(
random_combinations(natural_indices, len_natural, 1))
naturalness.append(len_natural / lang_size)
language_indices.append(lang_random + lang_natural)
file_util_out.dump_dill(language_indices, 'language_indices.dill')
file_util_out.dump_dill(naturalness, 'naturalness.dill')
file_util_out.save_stringlist([
list(map(lambda i: str(expressions[i]), lang))
for lang in language_indices
], 'languages.txt')
print("sample_indexset_degrees.py finished.")