def main():
parser = argparse.ArgumentParser(
description='Evaluate the utility of synthesized dataset compared with '
'the source dataset.',
formatter_class=CustomFormatter,
add_help=False)
# positional arguments
parser.add_argument('source',
help='set file path of source (raw) dataset to be '
'compared with synthesized dataset, only support '
'CSV files')
parser.add_argument(
'target',
help='set file path of target (synthesized) dataset to '
'evaluate')
# optional arguments
group = parser.add_argument_group('general arguments')
group.add_argument("-h",
"--help",
action="help",
help="show this help message and exit")
group.add_argument('--na-values',
metavar='LIST',
help='set additional values to recognize as NA/NaN; ('
'default null values are from pandas.read_csv)')
group.add_argument('-o',
'--output',
metavar='FILE',
default='report.html',
help='set output path for evaluation report; (default '
'is "report.html" under current work directory)')
group = parser.add_argument_group('advanced arguments')
group.add_argument('--category',
metavar='LIST',
help='set categorical columns separated by a comma.')
group.add_argument(
'-t',
'--test',
help='set test dataset for classification or regression '
'task; (default take 20%% from source dataset)')
group.add_argument(
'--class-label',
metavar='LIST',
help='set column name as class label for classification '
'or regression task; supports one or multiple '
'columns (separated by comma)')
args = parser.parse_args()
start = time.time()
na_values = str_to_list(args.na_values)
class_labels = str_to_list(args.class_label)
categories = str_to_list(args.category)
# check kinds of parameters
args.output = os.path.join(os.getcwd(), args.output)
# if output folder not exists, then create it.
if not os.path.exists(os.path.dirname(args.output)):
os.makedirs(os.path.dirname(args.output))
def complement(attrs, full):
return set(attrs or []) - set(full)
# Initialization task:
source = read_data_from_csv(args.source,
na_values=na_values,
header='infer')
target = read_data_from_csv(args.target,
na_values=na_values,
header='infer')
test = read_data_from_csv(args.test) if args.test is not None else None
comp = complement(class_labels, source.columns)
if comp:
parser.exit(
message=f'--class-label(s): {comp} are not in source file.')
comp = complement(class_labels, target.columns)
if comp:
parser.exit(
message=f'--class-label(s): {comp} are not in target file.')
frame = BiFrame(source, target, categories=categories)
frame.to_html(buffer=args.output,
title='Data Utility Evaluation Report',
labels=class_labels,
test=test)
duration = time.time() - start
print(f'Evaluate dataset {args.source} and {args.target} and generate '
f'report at {args.output} in {round(duration, 2)} seconds.')
def test_read_data_from_csv():
from pandas import DataFrame
from .testdata import adult_with_head, adult_with_head_res
import io
data = read_data_from_csv(io.StringIO(adult_with_head))
assert data.equals(DataFrame(adult_with_head_res)) is True
def main():
parser = argparse.ArgumentParser(
description='Synthesize one dataset by differential privacy',
formatter_class=CustomFormatter,
add_help=False)
parser.add_argument('file', help='set path of a csv file to be synthesized '
'or path of a pattern file to be generated')
# optional arguments
group = parser.add_argument_group('general arguments')
group.add_argument("-h", "--help", action="help",
help="show this help message and exit")
group.add_argument('--pseudonym', metavar='LIST',
help='set candidate columns separated by a comma, which '
'will be replaced with a pseudonym. It only works '
'on the string column.')
group.add_argument('--delete', metavar='LIST',
help='set columns separated by a comma, which will be '
'deleted when synthesis.')
group.add_argument('--na-values', metavar='LIST',
help='set additional values to recognize as NA/NaN; '
'(default null values are from pandas.read_csv)')
group.add_argument('-o', '--output', metavar='FILE',
help="set the file name of output synthesized dataset ("
"default is input file name with suffix '-a.csv')")
group.add_argument('--no-header', action='store_true',
help='indicate there is no header in a CSV file, and '
'will take [#0, #1, #2, ...] as header. (default: '
'the tool will try to detect and take actions)')
group.add_argument('--records', metavar='INT', type=int,
help='specify the records you want to generate; default '
'is the same records with the original dataset')
group.add_argument('--sep', metavar='STRING', default=',',
help='specify the delimiter of the input file')
group = parser.add_argument_group('advanced arguments')
group.add_argument('-e', '--epsilon', metavar='FLOAT', type=float,
help='set epsilon for differential privacy (default 0.1)',
default=0.1)
group.add_argument('--category', metavar='LIST',
help='set categorical columns separated by a comma.')
group.add_argument('--retain', metavar='LIST',
help='set columns to retain the values')
args = parser.parse_args()
start = time.time()
pseudonyms = str_to_list(args.pseudonym)
deletes = str_to_list(args.delete)
categories = str_to_list(args.category)
na_values = str_to_list(args.na_values)
retains = str_to_list(args.retain)
header = None if args.no_header else 'infer'
# check the file type from its extension
is_pattern = ends_with_json(args.file)
if is_pattern:
if retains is not None and len(retains) != 0:
parser.exit(message='Do not support --retain option when '
'synthesize from pattern file.')
# construct DataSet from pattern file
dataset = DataSet.from_pattern(args.file)
else:
data = read_data_from_csv(args.file, na_values=na_values, header=header,
sep=args.sep)
def complement(attrs, full):
return set(attrs or []) - set(full)
# check parameters: pseudonyms, deletes, categories
comp = complement(pseudonyms, data.columns)
if comp:
parser.exit(
message=f'--pseudonym columns: {comp} are not in csv file.')
comp = complement(deletes, data.columns)
if comp:
parser.exit(
message=f'--delete columns: {comp} are not in csv file.')
comp = complement(categories, data.columns)
if comp:
parser.exit(
message=f'--category columns: {comp} are not in csv file.')
dataset = DataSet(data, categories=categories)
synthesized = dataset.synthesize(epsilon=args.epsilon,
pseudonyms=pseudonyms, deletes=deletes,
retains=retains, records=args.records)
if args.output is None:
name = file_name(args.file)
args.output = f'{name}-a.csv'
synthesized.to_csv(args.output, index=False, sep=args.sep)
duration = time.time() - start
print(f'Synthesize from {args.file} to file {args.output} in '
f'{round(duration, 2)} seconds.')
def main():
parser = argparse.ArgumentParser(
description='Serialize patterns of a dataset anonymously',
formatter_class=CustomFormatter,
add_help=False)
parser.add_argument('file', help='set path of a csv file to be patterned '
'anonymously')
# optional arguments
group = parser.add_argument_group('general arguments')
group.add_argument("-h", "--help", action="help",
help="show this help message and exit")
group.add_argument('--pseudonym', metavar='LIST',
help='set candidate columns separated by a comma, which '
'will be replaced with a pseudonym. It only works '
'on the string column.')
group.add_argument('--delete', metavar='LIST',
help='set columns separated by a comma, which will be '
'deleted when synthesis.')
group.add_argument('--na-values', metavar='LIST',
help='set additional values to recognize as NA/NaN; '
'(default null values are from pandas.read_csv)')
group.add_argument('-o', '--output', metavar='FILE',
help="set the file name of anonymous patterns (default "
"is input file name with a suffix '-pattern.json')")
group.add_argument('--no-header', action='store_true',
help='indicate there is no header in a CSV file, and '
'will take [#0, #1, #2, ...] as header. (default: '
'the tool will try to detect and take actions)')
group.add_argument('--sep', metavar='STRING',
help='specify the delimiter of the input file')
group = parser.add_argument_group('advanced arguments')
group.add_argument('-e', '--epsilon', metavar='FLOAT', type=float,
help='set epsilon for differential privacy (default 0.1)',
default=0.1)
group.add_argument('--category', metavar='LIST',
help='set categorical columns separated by a comma.')
args = parser.parse_args()
start = time.time()
pseudonyms = str_to_list(args.pseudonym)
deletes = str_to_list(args.delete)
categories = str_to_list(args.category)
na_values = str_to_list(args.na_values)
header = None if args.no_header else 'infer'
sep = ',' if args.sep is None else args.sep
data = read_data_from_csv(args.file, na_values=na_values, header=header,
sep=sep)
def complement(attrs, full):
return set(attrs or []) - set(full)
# check parameters: pseudonyms, deletes, categories
comp = complement(pseudonyms, data.columns)
if comp:
parser.exit(message=f'--pseudonym columns: {comp} are not in csv file.')
comp = complement(deletes, data.columns)
if comp:
parser.exit(message=f'--delete columns: {comp} are not in csv file.')
comp = complement(categories, data.columns)
if comp:
parser.exit(message=f'--category columns: {comp} are not in csv file.')
dataset = DataSet(data, categories=categories)
if args.output is None:
name = file_name(args.file)
args.output = f'{name}-pattern.json'
dataset.to_pattern(path=args.output, epsilon=args.epsilon, deletes=deletes,
pseudonyms=pseudonyms, retains=[])
duration = time.time() - start
print(f'Analyze and serialize the patterns of {args.file} at {args.output} '
f'in {round(duration, 2)} seconds.')
def main():
parser = argparse.ArgumentParser(
description='Synthesize one dataset by Differential Privacy',
formatter_class=CustomFormatter,
add_help=False)
parser.add_argument('file', help='set path of the CSV to be synthesized')
# optional arguments
group = parser.add_argument_group('general arguments')
group.add_argument("-h",
"--help",
action="help",
help="show this help message and exit")
group.add_argument(
'--pseudonym',
metavar='LIST',
help='set candidate columns separated by a comma, which will be '
'replaced with a pseudonym. '
'It only works on the string column.')
group.add_argument('--delete',
metavar='LIST',
help='set columns separated by a comma, which will be '
'deleted when synthesis.')
group.add_argument('--na-values',
metavar='LIST',
help='set additional values to recognize as NA/NaN; '
'(default null values are from pandas.read_csv)')
group.add_argument('-o',
'--output',
metavar='FILE',
help="set the file name of output synthesized dataset ("
"default is input file name with suffix '_a')")
group.add_argument('--no-header',
action='store_true',
help='indicate there is no header in a CSV file, and '
'will take [#0, #1, #2, ...] as header. (default: '
'the tool will try to detect and take actions)')
group = parser.add_argument_group('advanced arguments')
group.add_argument(
'-e',
'--epsilon',
metavar='FLOAT',
type=float,
help='set epsilon for differential privacy (default 0.1)',
default=0.1)
group.add_argument('--category',
metavar='LIST',
help='set categorical columns separated by a comma.')
group.add_argument('--retain',
metavar='LIST',
help='set columns to retain the values')
args = parser.parse_args()
start = time.time()
pseudonyms = str_to_list(args.pseudonym)
deletes = str_to_list(args.delete)
categories = str_to_list(args.category)
na_values = str_to_list(args.na_values)
retains = str_to_list(args.retain)
header = None if args.no_header else 'infer'
data = read_data_from_csv(args.file, na_values=na_values, header=header)
def complement(attrs, full):
return set(attrs or []) - set(full)
# check parameters: pseudonyms, deletes, categories
comp = complement(pseudonyms, data.columns)
if comp:
parser.exit(
message=f'--pseudonym columns: {comp} are not in csv file.')
comp = complement(deletes, data.columns)
if comp:
parser.exit(message=f'--delete columns: {comp} are not in csv file.')
comp = complement(categories, data.columns)
if comp:
parser.exit(message=f'--category columns: {comp} are not in csv file.')
dataset = DataSet(data, categories=categories)
synthesized = dataset.synthesize(epsilon=args.epsilon,
pseudonyms=pseudonyms,
deletes=deletes,
retains=retains)
if args.output is None:
name = file_name(args.file)
args.output = f'{name}_a.csv'
synthesized.to_csv(args.output, index=False)
duration = time.time() - start
print(f'Synthesized data {args.output} in {round(duration, 2)} seconds.')