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_map_1():
# map a count over all dataframe partitions
with sn.Analysis() as analysis:
data = sn.Dataset(path=TEST_PUMS_PATH, column_names=TEST_PUMS_NAMES)
partitioned = sn.partition(data,
by=sn.to_bool(data['sex'], true_label="1"))
counts = sn.dp_count(partitioned, privacy_usage={"epsilon": 0.5})
print(counts.value)
print(analysis.privacy_usage)
def test_dp_count(run=True):
with sn.Analysis() as analysis:
dataset_pums = sn.Dataset(path=TEST_PUMS_PATH,
column_names=TEST_PUMS_NAMES)
count = sn.dp_count(dataset_pums['sex'] == '1',
privacy_usage={'epsilon': 0.5})
if run:
analysis.release()
print(count.value)
return analysis
def test_map_2():
# map a count over a large number of tuple partitions of dataframes
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)
counts = sn.dp_count(partitioned, privacy_usage={"epsilon": 0.5})
print(counts.value)
print(analysis.privacy_usage)
def test_groupby_1():
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[['educ', 'income']], by=is_male)
counts = {
cat: sn.dp_count(partitioned[cat], privacy_usage={'epsilon': 0.1})
for cat in is_male.categories
}
# analysis.plot()
analysis.release()
print(analysis.privacy_usage)
print({cat: counts[cat].value for cat in counts})
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 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.mean(
sn.resize(educ_level_part,
number_rows=sn.row_min(1, inner_count[key] * 4 //
5)))
return sn.union(inner_means), sn.union(inner_count)
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 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