def reset(self, params, rep):
logging.info("Resetting experiment, parameters: %s", str(params))
datadir = params['datadir']
dataset_path = os.path.join(datadir, params['dataset'] + '.json')
random.seed(abs(hash(str(params))))
with open(dataset_path) as dataset_file:
dataset = json.load(dataset_file)
vectors_path = os.path.join(datadir, params['vectors'])
print "DB path: ", vectors_path
vectors = TermDB(vectors_path)
terms = set(x[0] for x in dataset) | set(x[1] for x in dataset)
vectors.nouns.load(terms)
maker = ClassifierMaker(vectors, params)
classifier = maker.make(params['classifier'])
num_folds = params['repetitions']
self.experiment = EntailmentExperiment(dataset, classifier, num_folds)
class EntailmentSuite(PyExperimentSuite):
def __init__(self, **options):
self.additional_options = options
logging.info("Additional options: %s", str(options))
super(EntailmentSuite, self).__init__()
def reset(self, params, rep):
logging.info("Resetting experiment, parameters: %s", str(params))
datadir = params['datadir']
dataset_path = os.path.join(datadir, params['dataset'] + '.json')
random.seed(abs(hash(str(params))))
with open(dataset_path) as dataset_file:
dataset = json.load(dataset_file)
vectors_path = os.path.join(datadir, params['vectors'])
print "DB path: ", vectors_path
vectors = TermDB(vectors_path)
terms = set(x[0] for x in dataset) | set(x[1] for x in dataset)
vectors.nouns.load(terms)
maker = ClassifierMaker(vectors, params)
classifier = maker.make(params['classifier'])
num_folds = params['repetitions']
self.experiment = EntailmentExperiment(dataset, classifier, num_folds)
def iterate(self, params, rep, n):
logging.info("Beginning iteration %d, repetition %d", n, rep)
assert n == 0
confusion, time, info, classparams, predictions, target = self.experiment.runFold(
rep)
return {
'rep': rep,
'iter': n,
'confusion': confusion,
'time': time.total_seconds(),
'classifier': params['classifier'],
'info': info,
'params': classparams,
'predictions': predictions,
'target': target
}
def parse_opt(self):
""" parses the command line options for different settings. """
options, args = super(EntailmentSuite, self).parse_opt()
self.options.__dict__.update(self.additional_options)
def reset(self, params, rep):
logging.info("Resetting experiment, parameters: %s", str(params))
datadir = params['datadir']
dataset_path = os.path.join(datadir, params['dataset'] + '.json')
random.seed(abs(hash(str(params))))
with open(dataset_path) as dataset_file:
dataset = json.load(dataset_file)
vectors_path = os.path.join(datadir, params['vectors'])
print "DB path: ", vectors_path
vectors = TermDB(vectors_path)
maker = ClassifierMaker(vectors, params)
classifier = maker.make(params['classifier'])
num_folds = params['repetitions']
self.experiment = EntailmentExperiment(dataset, classifier, num_folds)
class EntailmentSuite(PyExperimentSuite):
def __init__(self, **options):
self.additional_options = options
logging.info("Additional options: %s", str(options))
super(EntailmentSuite, self).__init__()
def reset(self, params, rep):
logging.info("Resetting experiment, parameters: %s", str(params))
datadir = params['datadir']
dataset_path = os.path.join(datadir, params['dataset'] + '.json')
random.seed(abs(hash(str(params))))
with open(dataset_path) as dataset_file:
dataset = json.load(dataset_file)
vectors_path = os.path.join(datadir, params['vectors'])
print "DB path: ", vectors_path
vectors = TermDB(vectors_path)
terms = set(x[0] for x in dataset) | set(x[1] for x in dataset)
vectors.nouns.load(terms)
maker = ClassifierMaker(vectors, params)
classifier = maker.make(params['classifier'])
num_folds = params['repetitions']
self.experiment = EntailmentExperiment(dataset, classifier, num_folds)
def iterate(self, params, rep, n):
logging.info("Beginning iteration %d, repetition %d", n, rep)
assert n == 0
confusion, time, info, classparams, predictions, target = self.experiment.runFold(rep)
return {'rep':rep,
'iter':n,
'confusion':confusion,
'time':time.total_seconds(),
'classifier':params['classifier'],
'info': info,
'params': classparams,
'predictions': predictions,
'target': target}
def parse_opt(self):
""" parses the command line options for different settings. """
options, args = super(EntailmentSuite, self).parse_opt()
self.options.__dict__.update(self.additional_options)
