def __create_sex_histograms(self, data):
sex_histogram_geometric = wn.dp_histogram(
wn.to_bool(data['sex'], true_label="0"),
upper=self.__nsize,
privacy_usage={'epsilon': .5, 'delta': 0.00001}
)
sex_prep = wn.histogram(wn.to_bool(
data['sex'], true_label="0"), null_value=True)
sex_histogram_laplace = wn.laplace_mechanism(
sex_prep, privacy_usage={"epsilon": 0.4, "delta": .000001})
return sex_histogram_geometric, sex_histogram_laplace
def __create_state_histograms(self, data):
states = self.get_states()
state_histogram_geometric = wn.dp_histogram(
data['state'],
categories=states,
null_value=states[0],
privacy_usage={'epsilon': 0.2}
)
state_prep = wn.histogram(data['state'], categories=states,
null_value=states[0])
state_histogram_laplace = wn.laplace_mechanism(state_prep,
privacy_usage={"epsilon": 0.5, "delta": .000001})
return state_histogram_geometric, state_histogram_laplace
def __create_age_histograms(self, data):
age_edges = list(range(20, 80, 10))
age_histogram_geometric = wn.dp_histogram(
wn.to_int(data['age'], lower=20, upper=80),
edges=age_edges,
upper=self.__nsize,
null_value=20,
privacy_usage={'epsilon': 0.5}
)
age_prep = wn.histogram(wn.to_int(data['age'], lower=20, upper=80),
edges=age_edges, null_value=20)
age_histogram_laplace = wn.laplace_mechanism(
age_prep, privacy_usage={"epsilon": 0.5, "delta": .000001})
return age_histogram_geometric, age_histogram_laplace
def test_insertion_simple():
"""
Conduct a differentially private analysis with values inserted from other systems
:return:
"""
with wn.Analysis() as analysis:
# construct a fake dataset that describes your actual data (will never be run)
data = wn.Dataset(path="", column_names=["A", "B", "C", "D"])
# pull a column out
col_a = wn.to_float(data['A'])
# describe the preprocessing you actually perform on the data
col_a_clamped = wn.impute(wn.clamp(col_a, lower=0., upper=10.))
col_a_resized = wn.resize(col_a_clamped, n=1000000)
# run a fake aggregation
actual_mean = wn.mean(col_a_resized)
# insert aggregated data from an external system
actual_mean.set(10)
# describe the differentially private operation
gaussian_mean = wn.gaussian_mechanism(actual_mean,
privacy_usage={
"epsilon": .4,
"delta": 1e-6
})
# check if the analysis is permissible
analysis.validate()
# compute the missing releasable nodes- in this case, only the gaussian mean
analysis.release()
# retrieve the noised mean
print("gaussian mean", gaussian_mean.value)
# release a couple other statistics using other mechanisms in the same batch
actual_sum = wn.sum(col_a_clamped)
actual_sum.set(123456)
laplace_sum = wn.laplace_mechanism(actual_sum,
privacy_usage={"epsilon": .1})
actual_count = wn.count(col_a)
actual_count.set(9876)
geo_count = wn.simple_geometric_mechanism(
actual_count, 0, 10000, privacy_usage={"epsilon": .1})
analysis.release()
print("laplace sum", laplace_sum.value)
print("geometric count", geo_count.value)
actual_histogram_b = wn.histogram(
wn.clamp(data['B'], categories=['X', 'Y', 'Z'], null_value="W"))
actual_histogram_b.set([12, 1280, 2345, 12])
geo_histogram_b = wn.simple_geometric_mechanism(
actual_histogram_b, 0, 10000, privacy_usage={"epsilon": .1})
col_c = wn.to_bool(data['C'], true_label="T")
actual_histogram_c = wn.histogram(col_c)
actual_histogram_c.set([5000, 5000])
lap_histogram_c = wn.laplace_mechanism(actual_histogram_c,
privacy_usage={"epsilon": .1})
analysis.release()
print("noised histogram b", geo_histogram_b.value)
print("noised histogram c", lap_histogram_c.value)
print("C dimensionality", col_c.dimensionality)
print("C categories", col_c.categories)
# multicolumnar insertion
# pull a column out
col_rest = wn.to_float(data[['C', 'D']])
# describe the preprocessing you actually perform on the data
col_rest_resized = wn.resize(wn.impute(
wn.clamp(col_rest, lower=[0., 5.], upper=1000.)),
n=10000)
# run a fake aggregation
actual_mean = wn.mean(col_rest_resized)
# insert aggregated data from an external system
actual_mean.set([[10., 12.]])
# describe the differentially private operation
gaussian_mean = wn.gaussian_mechanism(actual_mean,
privacy_usage={
"epsilon": .4,
"delta": 1e-6
})
# check if the analysis is permissible
analysis.validate()
# compute the missing releasable nodes- in this case, only the gaussian mean
analysis.release()
# retrieve the noised mean
print("rest gaussian mean", gaussian_mean.value)
def test_everything(run=True):
with wn.Analysis(dynamic=True) as analysis:
data = wn.Dataset(path=TEST_CSV_PATH, column_names=test_csv_names)
age_int = wn.to_int(data['age'], 0, 150)
sex = wn.to_bool(data['sex'], "1")
educ = wn.to_float(data['educ'])
race = data['race']
income = wn.to_float(data['income'])
married = wn.to_bool(data['married'], "1")
numerics = wn.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 = numerics[0]
income = numerics[[False, True]]
# boolean ops and broadcasting
mask = sex & married | (~married ^ False) | (age > 50.) | (age_int
== 25)
# numerical clamping
wn.clamp(numerics, 0., [150., 150_000.])
wn.clamp(data['educ'],
categories=[str(i) for i in range(8, 10)],
null_value="-1")
wn.count(mask)
wn.covariance(age, income)
wn.digitize(educ, edges=[1., 3., 10.], null_value=-1)
# checks for safety against division by zero
income / 2.
income / wn.clamp(educ, 5., 20.)
wn.dp_count(data, privacy_usage={"epsilon": 0.5})
wn.dp_count(mask, privacy_usage={"epsilon": 0.5})
wn.dp_histogram(mask, privacy_usage={"epsilon": 0.5})
age = wn.impute(wn.clamp(age, 0., 150.))
wn.dp_maximum(age, privacy_usage={"epsilon": 0.5})
wn.dp_minimum(age, privacy_usage={"epsilon": 0.5})
wn.dp_median(age, privacy_usage={"epsilon": 0.5})
age_n = wn.resize(age, n=800)
wn.dp_mean(age_n, privacy_usage={"epsilon": 0.5})
wn.dp_moment_raw(age_n, order=3, privacy_usage={"epsilon": 0.5})
wn.dp_sum(age, privacy_usage={"epsilon": 0.5})
wn.dp_variance(age_n, privacy_usage={"epsilon": 0.5})
wn.filter(income, mask)
race_histogram = wn.histogram(race,
categories=["1", "2", "3"],
null_value="3")
wn.histogram(income, edges=[0., 10000., 50000.], null_value=-1)
wn.dp_histogram(married, privacy_usage={"epsilon": 0.5})
wn.gaussian_mechanism(race_histogram,
privacy_usage={
"epsilon": 0.5,
"delta": .000001
})
wn.laplace_mechanism(race_histogram,
privacy_usage={
"epsilon": 0.5,
"delta": .000001
})
wn.kth_raw_sample_moment(educ, k=3)
wn.log(wn.clamp(educ, 0.001, 50.))
wn.maximum(educ)
wn.mean(educ)
wn.minimum(educ)
educ % 2.
educ**2.
wn.quantile(educ, .32)
wn.resize(educ, 1200, 0., 50.)
wn.resize(race, 1200, categories=["1", "2"], weights=[1, 2])
wn.resize(data[["age", "sex"]],
1200,
categories=[["1", "2"], ["a", "b"]],
weights=[1, 2])
wn.resize(data[["age", "sex"]],
1200,
categories=[["1", "2"], ["a", "b", "c"]],
weights=[[1, 2], [3, 7, 2]])
wn.sum(educ)
wn.variance(educ)
if run:
analysis.release()
return analysis