def generate_dataset_in_correlated_attribute_mode(self,
n,
description_file,
seed=0):
set_random_seed(seed)
self.n = n
self.description = read_json_file(description_file)
all_attributes = self.description['meta']['all_attributes']
candidate_keys = set(self.description['meta']['candidate_keys'])
self.encoded_dataset = DataGenerator.generate_encoded_dataset(
self.n, self.description)
self.synthetic_dataset = DataFrame(columns=all_attributes)
for attr in all_attributes:
attr_info = self.description['attribute_description'][attr]
column = parse_json(attr_info)
if attr in self.encoded_dataset:
self.synthetic_dataset[
attr] = column.sample_values_from_binning_indices(
self.encoded_dataset[attr])
elif attr in candidate_keys:
self.synthetic_dataset[
attr] = column.generate_values_as_candidate_key(n)
else:
# for attributes not in BN or candidate keys, use independent attribute mode.
binning_indices = column.sample_binning_indices_in_independent_attribute_mode(
n)
self.synthetic_dataset[
attr] = column.sample_values_from_binning_indices(
binning_indices)
def generate_dataset_in_random_mode(self,
n,
description_file,
seed=0,
minimum=0,
maximum=100):
set_random_seed(seed)
description = read_json_file(description_file)
self.synthetic_dataset = DataFrame()
for attr in description['attribute_description'].keys():
attr_info = description['attribute_description'][attr]
datatype = attr_info['data_type']
is_categorical = attr_info['is_categorical']
is_candidate_key = attr_info['is_candidate_key']
if is_candidate_key:
self.synthetic_dataset[attr] = parse_json(
attr_info).generate_values_as_candidate_key(n)
elif is_categorical:
self.synthetic_dataset[attr] = random.choice(
attr_info['distribution_bins'], n)
elif datatype == 'String':
length = random.randint(attr_info['min'], attr_info['max'] + 1)
self.synthetic_dataset[attr] = length
self.synthetic_dataset[attr] = self.synthetic_dataset[
attr].map(lambda x: generate_random_string(x))
else:
if datatype == 'Integer':
self.synthetic_dataset[attr] = random.randint(
minimum, maximum + 1, n)
else:
self.synthetic_dataset[attr] = random.uniform(
minimum, maximum, n)
def generate_dataset_in_independent_mode(self, n, description_file, seed=0):
set_random_seed(seed)
self.description = read_json_file(description_file)
all_attributes = self.description['meta']['all_attributes']
candidate_keys = set(self.description['meta']['candidate_keys'])
self.synthetic_dataset = DataFrame(columns=all_attributes)
for attr in all_attributes:
attr_info = self.description['attribute_description'][attr]
column = parse_json(attr_info)
if attr in candidate_keys:
self.synthetic_dataset[attr] = column.generate_values_as_candidate_key(n)
else:
binning_indices = column.sample_binning_indices_in_independent_attribute_mode(n)
self.synthetic_dataset[attr] = column.sample_values_from_binning_indices(binning_indices)
