def test_fail_groupby():
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
educ_inc = sn.impute(
sn.clamp(sn.to_float(data[['educ', 'income']]),
lower=[0., 0.],
upper=[15., 200_000.]))
partitioned = sn.partition(educ_inc, by=is_male)
bounds = {
"data_lower": [0., 0.],
"data_upper": [15., 200_000.],
"data_rows": 500
}
union = sn.union({
True:
sn.mean(partitioned[True],
privacy_usage={"epsilon": 0.1},
**bounds),
False:
sn.mean(partitioned[False], **bounds),
})
sn.laplace_mechanism(union, privacy_usage={"epsilon": 1.0})
print(analysis.privacy_usage)
def analytic_gaussian_similarity():
analytic_gauss_estimates = []
gauss_estimates = []
with sn.Analysis(strict_parameter_checks=False):
PUMS = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
age = sn.impute(sn.to_float(PUMS['age']),
data_lower=0.,
data_upper=100.,
data_rows=1000)
for i in range(100):
an_gauss_component = sn.dp_mean(age,
mechanism="AnalyticGaussian",
privacy_usage={
"epsilon": 1.0,
"delta": 1E-6
})
gauss_component = sn.dp_mean(age,
mechanism="Gaussian",
privacy_usage={
"epsilon": 1.0,
"delta": 1E-6
})
# this triggers an analysis.release (which also computes gauss_component)
analytic_gauss_estimates.append(an_gauss_component.value)
gauss_estimates.append(gauss_component.value)
print(sum(analytic_gauss_estimates) / len(analytic_gauss_estimates))
print(sum(gauss_estimates) / len(gauss_estimates))
def test_groupby_3():
# now union the released output
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
educ_inc = sn.impute(
sn.clamp(sn.to_float(data[['educ', 'income']]),
lower=[0., 0.],
upper=[15., 200_000.]))
partitioned = sn.partition(educ_inc, by=is_male)
means = {}
for cat in is_male.categories:
part = partitioned[cat]
part = sn.resize(part, number_rows=500)
part = sn.dp_mean(part, privacy_usage={"epsilon": 1.0})
# print("mean: ", part.properties)
means[cat] = part
union = sn.union(means)
# analysis.plot()
analysis.release()
print(analysis.privacy_usage)
print(union.value)
def test_groupby_c_stab():
# use the same partition multiple times in union
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
educ_inc = sn.impute(
sn.clamp(sn.to_float(data[['educ', 'income']]),
lower=[0., 0.],
upper=[15., 200_000.]))
partitioned = sn.partition(educ_inc, by=is_male)
def analyze(data):
return sn.mean(sn.resize(data, number_rows=500))
means = {
True: analyze(partitioned[True]),
False: analyze(partitioned[False]),
"duplicate_that_inflates_c_stab": analyze(partitioned[True]),
}
union = sn.union(means)
noised = sn.laplace_mechanism(union, privacy_usage={"epsilon": 1.0})
# analysis.plot()
analysis.release()
print(analysis.privacy_usage)
print(noised.value)
def test_groupby_4():
# now union private data, and apply mechanism after
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
educ_inc = sn.impute(
sn.clamp(sn.to_float(data[['educ', 'income']]),
lower=[0., 0.],
upper=[15., 200_000.]))
partitioned = sn.partition(educ_inc, by=is_male)
means = {}
for cat in is_male.categories:
part = partitioned[cat]
part = sn.resize(part, number_rows=500)
part = sn.mean(part)
means[cat] = part
union = sn.union(means)
noised = sn.laplace_mechanism(union, privacy_usage={"epsilon": 1.0})
# analysis.plot()
analysis.release()
print(analysis.privacy_usage)
print(noised.value)
def snapping_similarity():
snapping_estimates = []
laplace_estimates = []
with sn.Analysis(strict_parameter_checks=False):
PUMS = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
age = sn.impute(sn.to_float(PUMS['age']),
data_lower=0.,
data_upper=100.,
data_rows=1000)
for i in range(100):
snapping_component = sn.dp_mean(age,
mechanism="snapping",
privacy_usage={
"epsilon": 1.0,
"delta": 1E-6
})
laplace_component = sn.dp_mean(age,
mechanism="laplace",
privacy_usage={
"epsilon": 1.0,
"delta": 1E-6
})
snapping_estimates.append(snapping_component.value)
laplace_estimates.append(laplace_component.value)
print(sum(snapping_estimates) / len(snapping_estimates))
print(sum(laplace_estimates) / len(laplace_estimates))
def test_dataframe_partitioning_2():
# dataframe partition with multi-index grouping
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
grouper = sn.clamp(data[['sex', 'educ']],
categories=[['0', '1'],
[str(i) for i in range(14)]],
null_value='-1')
partitioned = sn.partition(data, by=grouper)
sn.union(
{
key: sn.dp_count(partitioned[key],
privacy_usage={"epsilon": 0.5})
for key in partitioned.partition_keys
},
flatten=False)
print(
sn.union({
key: sn.dp_mean(
sn.to_float(partitioned[key]['income']),
implementation="plug-in",
# data_rows=100,
data_lower=0.,
data_upper=200_000.,
privacy_usage={"epsilon": 0.5})
for key in partitioned.partition_keys
}))
def test_multilayer_partition_1():
# multilayer partition with mechanisms applied inside partitions
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
educ_inc = sn.impute(
sn.clamp(sn.to_float(data[['educ', 'income']]),
lower=[0., 0.],
upper=[15., 200_000.]))
partitioned = sn.partition(educ_inc, by=is_male)
def analyze(data):
educ = sn.clamp(sn.to_int(sn.index(data, indices=0),
lower=0,
upper=15),
categories=list(range(15)),
null_value=-1)
income = sn.index(data, indices=1)
repartitioned = sn.partition(income, by=educ)
inner_count = {}
inner_means = {}
for key in [5, 8, 12]:
educ_level_part = repartitioned[key]
inner_count[key] = sn.dp_count(educ_level_part,
privacy_usage={"epsilon": 0.4})
inner_means[key] = sn.dp_mean(educ_level_part,
privacy_usage={"epsilon": 0.6},
data_rows=sn.row_max(
1, inner_count[key]))
return sn.union(inner_means,
flatten=False), sn.union(inner_count,
flatten=False)
means = {}
counts = {}
for key in partitioned.partition_keys:
part_means, part_counts = analyze(partitioned[key])
means[key] = part_means
counts[key] = part_counts
means = sn.union(means, flatten=False)
counts = sn.union(counts, flatten=False)
# analysis.plot()
print("releasing")
print(len(analysis.components.items()))
analysis.release()
print(analysis.privacy_usage)
print("Counts:")
print(counts.value)
print("Means:")
print(means.value)
def test_dp_covariance():
# establish data information
var_names = ["age", "sex", "educ", "race", "income", "married"]
with sn.Analysis() as analysis:
wn_data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
# # get scalar covariance
age_income_cov_scalar = sn.dp_covariance(
left=sn.to_float(wn_data['age']),
right=sn.to_float(wn_data['income']),
privacy_usage={'epsilon': 5000},
left_lower=0.,
left_upper=100.,
left_rows=1000,
right_lower=0.,
right_upper=500_000.,
right_rows=1000)
data = sn.to_float(wn_data['age', 'income'])
# get full covariance matrix
age_income_cov_matrix = sn.dp_covariance(
data=data,
privacy_usage={'epsilon': 5000},
data_lower=[0., 0.],
data_upper=[100., 500_000.],
data_rows=1000)
# get cross-covariance matrix
cross_covar = sn.dp_covariance(left=data,
right=data,
privacy_usage={'epsilon': 5000},
left_lower=[0., 0.],
left_upper=[100., 500_000.],
left_rows=1_000,
right_lower=[0., 0.],
right_upper=[100., 500_000.],
right_rows=1000)
analysis.release()
print('scalar covariance:\n{0}\n'.format(age_income_cov_scalar.value))
print('covariance matrix:\n{0}\n'.format(age_income_cov_matrix.value))
print('cross-covariance matrix:\n{0}'.format(cross_covar.value))
def test_private_clamped_sum_helpers():
# Compute the CI with smartnoise
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_DATA_PATH, column_names=TEST_DATA_COLUMNS)
D = sn.to_float(data["age"])
D_tilde = sn.resize(sn.clamp(data=D, lower=0.0, upper=100.0), number_rows=1000,)
release = sn.dp_sum(data=sn.impute(D_tilde), privacy_usage={"epsilon": 1.0})
smartnoise_ci = release.get_accuracy(0.05)
op = PrivateClampedSum(lower_bound=0, upper_bound=100)
eeprivacy_ci = op.confidence_interval(epsilon=1, confidence=0.95)
assert pytest.approx(smartnoise_ci, abs=0.001) == eeprivacy_ci
def test_reports():
with sn.Analysis() as analysis:
# load data
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
# get mean of age
age_mean = sn.dp_mean(data=sn.to_float(data['age']),
privacy_usage={'epsilon': .65},
data_lower=0.,
data_upper=100.,
data_rows=1000)
print("Pre-Release\n")
print("DP mean of age: {0}".format(age_mean.value))
print("Privacy usage: {0}\n\n".format(analysis.privacy_usage))
def try_sn():
# establish data information
#data_path = 'https://raw.githubusercontent.com/opendp/smartnoise-samples/86-requirements-fix/analysis/data/PUMS_california_demographics_1000/data.csv'
data_path = os.path.join('.', 'data', 'PUMS_california_demographics_1000',
'data.csv')
data_path = os.path.abspath(data_path)
print('data_path', data_path)
var_names = ["age", "sex", "educ", "race", "income", "married", "pid"]
D = pd.read_csv(data_path)['age']
D_mean_age = np.mean(D)
print('D_mean_age', D_mean_age)
# establish extra information for this simulation
age_lower_bound = 0.
age_upper_bound = 100.
D_tilde = np.clip(D, age_lower_bound, age_upper_bound)
D_tilde_mean_age = np.mean(D_tilde)
data_size = 1000
df = pd.read_csv(data_path)
df_as_array = [list(row) for row in df.itertuples()]
#df.values.tolist()
print('D.values', df_as_array)
n_sims = 2
releases = []
with sn.Analysis(dynamic=True) as analysis:
data = sn.Dataset(path=data_path, column_names=var_names)
#data = sn.Dataset(value=df_as_array, column_names=var_names)
D = sn.to_float(data['age'])
# preprocess data (resize is a no-op because we have the correct data size)
D_tilde = sn.resize(sn.clamp(data=D, lower=0., upper=100.),
number_rows=data_size)
for index in range(n_sims):
# get DP mean of age
releases.append(
sn.dp_mean(data=sn.impute(D_tilde),
privacy_usage={'epsilon': 1}))
accuracy = releases[0].get_accuracy(0.05)
analysis.release()
dp_values = [release.value for release in releases]
print(
'Accuracy interval (with accuracy value {0}) contains the true mean on D_tilde with probability {1}'
.format(
round(accuracy, 4),
np.mean([(D_tilde_mean_age >= val - accuracy) &
(D_tilde_mean_age <= val + accuracy)
for val in dp_values])))
def test_raw_dataset(run=True):
with sn.Analysis() as analysis:
data = sn.to_float(sn.Dataset(value=[1., 2., 3., 4., 5.]))
sn.dp_mean(data=data,
privacy_usage={'epsilon': 1},
data_lower=0.,
data_upper=10.,
data_rows=10,
data_columns=1)
if run:
analysis.release()
return analysis
def test_map_3():
# chain multiple maps over an array partition with implicit preprocessing
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
partitioned = sn.partition(sn.to_float(data['age']),
by=sn.to_bool(data['sex'], true_label="1"))
means = sn.dp_mean(partitioned,
privacy_usage={'epsilon': 0.1},
data_rows=500,
data_lower=0.,
data_upper=15.)
print(means.value)
print(analysis.privacy_usage)
def test_covariance():
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
data = np.genfromtxt(TEST_PUMS_PATH, delimiter=',', names=True)
with sn.Analysis() as analysis:
wn_data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
# get full covariance matrix
cov = sn.dp_covariance(data=sn.to_float(wn_data['age', 'sex', 'educ',
'income', 'married']),
privacy_usage={'epsilon': 10},
data_lower=[0., 0., 1., 0., 0.],
data_upper=[100., 1., 16., 500_000., 1.],
data_rows=1000)
analysis.release()
# store DP covariance and correlation matrix
dp_cov = cov.value
print(dp_cov)
dp_corr = dp_cov / np.outer(np.sqrt(np.diag(dp_cov)),
np.sqrt(np.diag(dp_cov)))
# get non-DP covariance/correlation matrices
age = list(data[:]['age'])
sex = list(data[:]['sex'])
educ = list(data[:]['educ'])
income = list(data[:]['income'])
married = list(data[:]['married'])
non_dp_cov = np.cov([age, sex, educ, income, married])
non_dp_corr = non_dp_cov / np.outer(np.sqrt(np.diag(non_dp_cov)),
np.sqrt(np.diag(non_dp_cov)))
print('Non-DP Covariance Matrix:\n{0}\n\n'.format(
pd.DataFrame(non_dp_cov)))
print('Non-DP Correlation Matrix:\n{0}\n\n'.format(
pd.DataFrame(non_dp_corr)))
print('DP Correlation Matrix:\n{0}'.format(pd.DataFrame(dp_corr)))
# skip plot step
if IS_CI_BUILD:
return
plt.imshow(non_dp_corr - dp_corr, interpolation='nearest')
plt.colorbar()
plt.show()
def test_median_education():
# import pandas as pd
# print(pd.read_csv(data_path)['value'].median())
with sn.Analysis(filter_level="all") as analysis:
data = sn.Dataset(path=TEST_EDUC_PATH, column_names=TEST_EDUC_NAMES)
candidates = list(map(float, range(1, 200, 2)))
median_scores = sn.median(sn.impute(sn.to_float(data['value']), 100.,
200.),
candidates=candidates)
# print(list(zip(candidates, median_scores.value[0])))
dp_median = sn.exponential_mechanism(median_scores,
candidates=candidates,
privacy_usage={"epsilon": 100.})
print(dp_median.value)
analysis.release()
def test_dp_median_raw():
with sn.Analysis() as analysis:
# create a literal data vector, and tag it as private
data = sn.Component.of([float(i) for i in range(20)], public=False)
dp_median = sn.dp_median(
sn.to_float(data),
privacy_usage={
"epsilon": 1.
},
candidates=[-10., -2., 2., 3., 4., 7., 10., 12.],
data_lower=0.,
data_upper=10.,
data_columns=1).value
print(dp_median)
# analysis.plot()
assert dp_median is not None
def test_dataframe_partitioning_1():
# dataframe partition
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
partitioned = sn.partition(data, by=is_male)
print(
sn.union({
key: sn.dp_mean(sn.impute(
sn.clamp(sn.to_float(partitioned[key]['income']), 0.,
200_000.)),
implementation="plug-in",
privacy_usage={"epsilon": 0.5})
for key in partitioned.partition_keys
}).value)
print(analysis.privacy_usage)
def test_dp_linear_regression():
with sn.Analysis():
wn_data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
wn_data = sn.resize(sn.to_float(wn_data[["age", "income"]]),
number_rows=1000,
lower=[0., 0.],
upper=[100., 500_000.])
dp_linear_regression = sn.dp_linear_regression(
data_x=sn.index(wn_data, indices=0),
data_y=sn.index(wn_data, indices=1),
privacy_usage={'epsilon': 10.},
lower_slope=0.,
upper_slope=1000.,
lower_intercept=0.,
upper_intercept=1000.)
print(dp_linear_regression.value)
def test_snapping():
with sn.Analysis():
PUMS = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
statistic = sn.mean(sn.to_float(PUMS['age']),
data_lower=0.,
data_upper=100.,
data_rows=1000)
privatized = sn.snapping_mechanism(statistic,
lower=30.,
upper=70.,
binding_probability=0.4,
privacy_usage={"epsilon": 0.1})
print(privatized.value)
print(privatized.get_accuracy(0.5))
necessary_usage = privatized.from_accuracy(4., 0.5)
print("usage: ", necessary_usage)
print("accuracy: ", privatized.get_accuracy(0.5, necessary_usage))
def test_map_4():
# chain multiple mapped releases over a partition with implicit preprocessing
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
partitioned = sn.partition(sn.to_float(data['age']),
by=sn.to_bool(data['sex'], true_label="1"))
counts = sn.row_max(
1, sn.dp_count(partitioned, privacy_usage={'epsilon': 0.5}))
means = sn.dp_mean(partitioned,
privacy_usage={'epsilon': 0.7},
data_rows=counts,
data_lower=0.,
data_upper=15.)
print("counts:", counts.value)
print("means:", means.value)
print(analysis.privacy_usage)
def test_dp_mean():
with sn.Analysis():
data = generate_synthetic(float, variants=['Random'])
mean = sn.dp_mean(data['F_Random'],
privacy_usage={'epsilon': 0.1},
data_lower=0.,
data_upper=10.,
data_rows=10)
print("accuracy", mean.get_accuracy(0.05))
print(mean.from_accuracy(2.3, .05))
with sn.Analysis():
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
print(
sn.dp_mean(sn.to_float(data['income']),
implementation="plug-in",
data_lower=0.,
data_upper=200_000.,
privacy_usage={
"epsilon": 0.5
}).value)
def test_mechanism(args, constructor):
with sn.Analysis() as analysis:
PUMS = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
categorical = sn.resize(sn.clamp(PUMS['sex'],
categories=["0", "1"],
null_value="0"),
number_rows=1000)
numeric = sn.impute(sn.to_float(PUMS['age']),
data_lower=0.,
data_upper=100.,
data_rows=1000)
all = constructor(numeric, categorical, args)
analysis.release()
all_values = {stat: all[stat].value for stat in all}
print()
pprint(all_values)
for value in all_values.values():
assert value is not None
def test_private_clamped_mean_helpers():
# Compute the CI with smartnoise
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_DATA_PATH, column_names=TEST_DATA_COLUMNS)
D = sn.to_float(data["age"])
D_tilde = sn.resize(sn.clamp(data=D, lower=0.0, upper=100.0), number_rows=1000,)
release = sn.dp_mean(data=sn.impute(D_tilde), privacy_usage={"epsilon": 1.0})
smartnoise_ci = release.get_accuracy(0.05)
# Compute the CI with eeprivacy
op = PrivateClampedMean(lower_bound=0, upper_bound=100)
eeprivacy_ci = op.confidence_interval(epsilon=1, N=1000, confidence=0.95)
# Compare computed confidence intervals
assert pytest.approx(smartnoise_ci, abs=0.001) == eeprivacy_ci
smartnoise_epsilon = release.from_accuracy(value=1, alpha=0.05)[0]["epsilon"]
eeprivacy_epsilon = op.epsilon_for_confidence_interval(
target_ci=1, N=1000, confidence=0.95
)
# Compare computed epsilons for confidence interval
assert pytest.approx(smartnoise_epsilon, abs=0.001) == eeprivacy_epsilon
def test_groupby_2():
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
is_male = sn.to_bool(data['sex'], true_label="1")
partitioned = sn.partition(sn.to_float(data[['educ', 'income']]),
by=is_male)
counts = {
True:
sn.dp_count(partitioned[True], privacy_usage={'epsilon': 0.1}),
False:
sn.dp_mean(partitioned[False],
privacy_usage={'epsilon': 0.1},
data_rows=500,
data_lower=[0., 0.],
data_upper=[15., 200_000.])
}
# analysis.plot()
analysis.release()
print(analysis.privacy_usage)
print({cat: counts[cat].value for cat in counts})
def test_histogram():
# generate raw data
import numpy as np
import pandas as pd
import tempfile
import os
n = 1000
data = np.random.normal(loc=10, scale=25, size=n)
mean = np.mean(data)
sd = np.std(data)
data = pd.DataFrame([(elem - mean) / sd for elem in data])
with sn.Analysis(), tempfile.TemporaryDirectory() as temp_dir:
data_path = os.path.join(temp_dir, 'temp_data.csv')
data.to_csv(data_path)
print(
sn.dp_histogram(sn.to_float(
sn.Dataset(path=data_path, column_names=['d'])['d']),
edges=np.linspace(-3., 3., 1000),
privacy_usage={
'epsilon': 0.1
}).value)
def test_multilayer_analysis(run=True):
with sn.Analysis() as analysis:
PUMS = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
age = sn.to_float(PUMS['age'])
sex = sn.to_bool(PUMS['sex'], true_label="TRUE")
age_clamped = sn.clamp(age, lower=0., upper=150.)
age_resized = sn.resize(age_clamped, number_rows=1000)
race = sn.to_float(PUMS['race'])
mean_age = sn.dp_mean(data=race,
privacy_usage={'epsilon': .65},
data_lower=0.,
data_upper=100.,
data_rows=500)
analysis.release()
sex_plus_22 = sn.add(sn.to_float(sex),
22.,
left_rows=1000,
left_lower=0.,
left_upper=1.)
sn.dp_mean(age_resized / 2. + sex_plus_22,
privacy_usage={'epsilon': .1},
data_lower=mean_age - 5.2,
data_upper=102.,
data_rows=500) + 5.
sn.dp_variance(data=sn.to_float(PUMS['educ']),
privacy_usage={'epsilon': .15},
data_rows=1000,
data_lower=0.,
data_upper=12.)
# sn.dp_raw_moment(
# sn.to_float(PUMS['married']),
# privacy_usage={'epsilon': .15},
# data_rows=1000000,
# data_lower=0.,
# data_upper=12.,
# order=3
# )
#
# sn.dp_covariance(
# left=sn.to_float(PUMS['age']),
# right=sn.to_float(PUMS['married']),
# privacy_usage={'epsilon': .15},
# left_rows=1000,
# right_rows=1000,
# left_lower=0.,
# left_upper=1.,
# right_lower=0.,
# right_upper=1.
# )
if run:
analysis.release()
return analysis
def create_dicts(data, non_income_data, plausible_variable_combinations):
count_dict = dict()
priv_count_dict = dict()
mean_income_dict = dict()
priv_mean_income_dict = dict()
median_income_dict = dict()
priv_median_income_dict = dict()
min_income_dict = dict()
priv_min_income_dict = dict()
max_income_dict = dict()
priv_max_income_dict = dict()
# get number of data elements with each set of variable values
for i, combination in enumerate(plausible_variable_combinations):
# print('run {0} of {1}'.format(i+1, len(plausible_variable_combinations)))
if len(combination) == 1:
dt = data[non_income_data[combination[0]] == 1]
elif len(combination) == 2:
dt = data[(non_income_data[combination[0]] == 1)
& (non_income_data[combination[1]] == 1)]
elif len(combination) == 3:
dt = data[(non_income_data[combination[0]] == 1)
& (non_income_data[combination[1]] == 1) &
(non_income_data[combination[2]] == 1)]
elif len(combination) == 4:
dt = data[(non_income_data[combination[0]] == 1)
& (non_income_data[combination[1]] == 1) &
(non_income_data[combination[2]] == 1) &
(non_income_data[combination[3]] == 1)]
elif len(combination) == 5:
dt = data[(non_income_data[combination[0]] == 1)
& (non_income_data[combination[1]] == 1) &
(non_income_data[combination[2]] == 1) &
(non_income_data[combination[3]] == 1) &
(non_income_data[combination[4]] == 1)]
count_dict['__'.join(combination)] = dt.shape[0]
mean_income_dict['__'.join(combination)] = np.mean(dt['income'])
median_income_dict['__'.join(combination)] = np.median(dt['income'])
min_income_dict['__'.join(combination)] = np.min(dt['income'])
max_income_dict['__'.join(combination)] = np.max(dt['income'])
with sn.Analysis() as analysis:
# load data
priv_data = sn.Dataset(value=dt['income'])
# estimate sample size
count = sn.dp_count(priv_data, privacy_usage={'epsilon': .05})
# preprocess data
priv_data = sn.resize(sn.to_float(priv_data),
number_columns=1,
number_rows=sn.row_max(1, count),
lower=0.,
upper=100_000.)
priv_data = sn.impute(sn.clamp(priv_data, lower=0.,
upper=100_000.))
# get mean
mean = sn.dp_mean(priv_data, privacy_usage={'epsilon': 0.1})
# get median
median = sn.dp_median(priv_data, privacy_usage={'epsilon': 0.1})
# get min
_min = sn.dp_minimum(priv_data, privacy_usage={'epsilon': 0.1})
# get max
_max = sn.dp_maximum(priv_data, privacy_usage={'epsilon': 0.1})
analysis.release()
priv_count_dict['__'.join(combination)] = max(0, count.value)
priv_mean_income_dict['__'.join(combination)] = min(
max(0, mean.value), 100_000)
priv_median_income_dict['__'.join(combination)] = min(
max(0, median.value), 100_000)
priv_min_income_dict['__'.join(combination)] = min(
max(0, _min.value), 100_000)
priv_max_income_dict['__'.join(combination)] = min(
max(0, _max.value), 100_000)
return (count_dict, priv_count_dict, mean_income_dict,
priv_mean_income_dict, median_income_dict, priv_median_income_dict,
min_income_dict, priv_min_income_dict, max_income_dict,
priv_max_income_dict)
def test_dp_linear_stats(run=True):
with sn.Analysis() as analysis:
dataset_pums = sn.Dataset(path=TEST_PUMS_PATH,
column_names=TEST_PUMS_NAMES)
age = dataset_pums['age']
analysis.release()
num_records = sn.dp_count(age,
privacy_usage={'epsilon': .5},
lower=0,
upper=10000)
analysis.release()
print("number of records:", num_records.value)
vars = sn.to_float(dataset_pums[["age", "income"]])
covariance = sn.dp_covariance(data=vars,
privacy_usage={'epsilon': .5},
data_lower=[0., 0.],
data_upper=[150., 150000.],
data_rows=num_records)
print("covariance released")
num_means = sn.dp_mean(data=vars,
privacy_usage={'epsilon': .5},
data_lower=[0., 0.],
data_upper=[150., 150000.],
data_rows=num_records)
analysis.release()
print("covariance:\n", covariance.value)
print("means:\n", num_means.value)
age = sn.to_float(age)
age_variance = sn.dp_variance(age,
privacy_usage={'epsilon': .5},
data_lower=0.,
data_upper=150.,
data_rows=num_records)
analysis.release()
print("age variance:", age_variance.value)
# If I clamp, impute, resize, then I can reuse their properties for multiple statistics
clamped_age = sn.clamp(age, lower=0., upper=100.)
imputed_age = sn.impute(clamped_age)
preprocessed_age = sn.resize(imputed_age, number_rows=num_records)
# properties necessary for mean are statically known
mean = sn.dp_mean(preprocessed_age, privacy_usage={'epsilon': .5})
# properties necessary for variance are statically known
variance = sn.dp_variance(preprocessed_age,
privacy_usage={'epsilon': .5})
# sum doesn't need n, so I pass the data in before resizing
age_sum = sn.dp_sum(imputed_age, privacy_usage={'epsilon': .5})
# mean with lower, upper properties propagated up from prior bounds
transformed_mean = sn.dp_mean(-(preprocessed_age + 2.),
privacy_usage={'epsilon': .5})
analysis.release()
print("age transformed mean:", transformed_mean.value)
# releases may be pieced together from combinations of smaller components
custom_mean = sn.laplace_mechanism(sn.mean(preprocessed_age),
privacy_usage={'epsilon': .5})
custom_maximum = sn.laplace_mechanism(sn.maximum(preprocessed_age),
privacy_usage={'epsilon': .5})
custom_maximum = sn.laplace_mechanism(sn.maximum(preprocessed_age),
privacy_usage={'epsilon': .5})
custom_quantile = sn.laplace_mechanism(sn.quantile(preprocessed_age,
alpha=.5),
privacy_usage={'epsilon': 500})
income = sn.to_float(dataset_pums['income'])
income_max = sn.laplace_mechanism(sn.maximum(income,
data_lower=0.,
data_upper=1000000.),
privacy_usage={'epsilon': 10})
# releases may also be postprocessed and reused as arguments to more components
age_sum + custom_maximum * 23.
analysis.release()
print("laplace quantile:", custom_quantile.value)
age_histogram = sn.dp_histogram(sn.to_int(age, lower=0, upper=100),
edges=list(range(0, 100, 25)),
null_value=150,
privacy_usage={'epsilon': 2.})
sex_histogram = sn.dp_histogram(sn.to_bool(dataset_pums['sex'],
true_label="1"),
privacy_usage={'epsilon': 2.})
education_histogram = sn.dp_histogram(dataset_pums['educ'],
categories=["5", "7", "10"],
null_value="-1",
privacy_usage={'epsilon': 2.})
analysis.release()
print("age histogram: ", age_histogram.value)
print("sex histogram: ", sex_histogram.value)
print("education histogram: ", education_histogram.value)
if run:
analysis.release()
# get the mean computed when release() was called
print(mean.value)
print(variance.value)
return analysis
def test_everything(run=True):
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
age_int = sn.to_int(data['age'], 0, 150)
sex = sn.to_bool(data['sex'], "1")
educ = sn.to_float(data['educ'])
race = data['race']
income = sn.to_float(data['income'])
married = sn.to_bool(data['married'], "1")
numerics = sn.to_float(data[['age', 'income']])
# intentionally busted component
# print("invalid component id ", (sex + "a").component_id)
# broadcast scalar over 2d, broadcast scalar over 1d, columnar broadcasting, left and right mul
numerics * 2. + 2. * educ
# add different values for each column
numerics + [[1., 2.]]
# index into first column
age = sn.index(numerics, indices=0)
income = sn.index(numerics, mask=[False, True])
# boolean ops and broadcasting
mask = sex & married | (~married ^ False) | (age > 50.) | (age_int
== 25)
# numerical clamping
sn.clamp(numerics, 0., [150., 150_000.])
sn.clamp(data['educ'],
categories=[str(i) for i in range(8, 10)],
null_value="-1")
sn.count(mask)
sn.covariance(age, income)
sn.digitize(educ, edges=[1., 3., 10.], null_value=-1)
# checks for safety against division by zero
income / 2.
income / sn.clamp(educ, 5., 20.)
sn.dp_count(data, privacy_usage={"epsilon": 0.5})
sn.dp_count(mask, privacy_usage={"epsilon": 0.5})
sn.dp_histogram(mask, privacy_usage={"epsilon": 0.5})
age = sn.impute(sn.clamp(age, 0., 150.))
sn.dp_maximum(age, privacy_usage={"epsilon": 0.5})
sn.dp_minimum(age, privacy_usage={"epsilon": 0.5})
sn.dp_median(age, privacy_usage={"epsilon": 0.5})
age_n = sn.resize(age, number_rows=800)
sn.dp_mean(age_n, privacy_usage={"epsilon": 0.5})
sn.dp_raw_moment(age_n, order=3, privacy_usage={"epsilon": 0.5})
sn.dp_sum(age, privacy_usage={"epsilon": 0.5})
sn.dp_variance(age_n, privacy_usage={"epsilon": 0.5})
sn.filter(income, mask)
race_histogram = sn.histogram(race,
categories=["1", "2", "3"],
null_value="3")
sn.histogram(income, edges=[0., 10000., 50000.], null_value=-1)
sn.dp_histogram(married, privacy_usage={"epsilon": 0.5})
sn.gaussian_mechanism(race_histogram,
privacy_usage={
"epsilon": 0.5,
"delta": .000001
})
sn.laplace_mechanism(race_histogram,
privacy_usage={
"epsilon": 0.5,
"delta": .000001
})
sn.raw_moment(educ, order=3)
sn.log(sn.clamp(educ, 0.001, 50.))
sn.maximum(educ)
sn.mean(educ)
sn.minimum(educ)
educ % 2.
educ**2.
sn.quantile(educ, .32)
sn.resize(educ, number_rows=1200, lower=0., upper=50.)
sn.resize(race,
number_rows=1200,
categories=["1", "2"],
weights=[1, 2])
sn.resize(data[["age", "sex"]],
1200,
categories=[["1", "2"], ["a", "b"]],
weights=[1, 2])
sn.resize(data[["age", "sex"]],
1200,
categories=[["1", "2"], ["a", "b", "c"]],
weights=[[1, 2], [3, 7, 2]])
sn.sum(educ)
sn.variance(educ)
if run:
analysis.release()
return analysis
