def example_private_table():
adult_data = pd.read_csv(os.path.join("dataset", "adult_data.txt"),
names=[
"Age", "Workclass", "fnlwgt", "Education",
"Education-Num", "Martial Status",
"Occupation", "Relationship", "Race", "Sex",
"Capital Gain", "Capital Loss",
"Hours per week", "Country", "Target"
])
data = {
'Age': adult_data["Age"].tolist(),
'Education': adult_data["Education"].tolist()
}
df = pd.DataFrame(data)
domains = {
'Age':
RealDataDomain(17., 90.),
'Education':
CategoricalDataDomain([
' Bachelors', ' HS-grad', ' 11th', ' Masters', ' 9th',
' Some-college', ' Assoc-acdm', ' Assoc-voc', ' 7th-8th',
' Doctorate', ' Prof-school', ' 5th-6th', ' 10th', ' 1st-4th',
' Preschool', ' 12th'
])
}
return PrivateTable(df, domains, PrivacyBudget(100000.0, 1.))
def test_column_names(example_table: DataFrame):
domains = {
'Name':
CategoricalDataDomain(
['Tom', 'Jack', 'Steve', 'Eve', 'Adam', 'Lucifer']),
'Age':
RealDataDomain(0., 130.)
}
t = PrivateTable(example_table, domains, PrivacyBudget(1.0, 0.))
assert 'Age' in t._columns
assert 'Name' in t._columns
def example_private_table():
data = {'Name': ['Tom', 'Jack', 'Steve', 'Jack'], 'Age': [28, 34, 29, 42]}
df = pd.DataFrame(data)
domains = {
'Name':
CategoricalDataDomain(
['Tom', 'Jack', 'Steve', 'Eve', 'Adam', 'Lucifer']),
'Age':
RealDataDomain(0., 130.)
}
return PrivateTable(df, domains, PrivacyBudget(100000.0, 1000.))
def test_column_names(example_table: DataFrame):
"""check to ensure column names correspond to the domains"""
domains = {'Sepal Length': RealDataDomain(0., 10.),
'Sepal Width': RealDataDomain(0., 10.),
'Petal Length': RealDataDomain(0., 10.),
'Petal Width': RealDataDomain(0., 10.),
'Class': CategoricalDataDomain(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])}
t = PrivateTable(example_table, domains, PrivacyBudget(1.0, 0.))
assert 'Sepal Length' in t._columns
assert 'Sepal Width' in t._columns
assert 'Petal Length' in t._columns
assert 'Petal Width' in t._columns
assert 'Class' in t._columns
def test_column_names(example_table: DataFrame):
"""check to ensure column names correspond to the domains"""
domains = {
'Age':
RealDataDomain(0., 130.),
'Education':
CategoricalDataDomain([
' Bachelors', ' HS-grad', ' 11th', ' Masters', ' 9th',
' Some-college', ' Assoc-acdm', ' Assoc-voc', ' 7th-8th',
' Doctorate', ' Prof-school', ' 5th-6th', ' 10th', ' 1st-4th',
' Preschool', ' 12th'
])
}
t = PrivateTable(example_table, domains, PrivacyBudget(1.0, 0.))
assert 'Age' in t._columns
assert 'Education' in t._columns
def example_private_table():
iris_data = pd.read_csv(os.path.join("dataset", "iris_data.txt"),
names=["Sepal Length", "Sepal Width", "Petal Length",
"Petal Width", "Class"])
data = {'Sepal Length': iris_data["Sepal Length"].tolist(),
'Sepal Width': iris_data["Sepal Width"].tolist(),
'Petal Length': iris_data["Petal Length"].tolist(),
'Petal Width': iris_data["Petal Width"].tolist(),
'Class': iris_data["Class"].tolist()}
df = pd.DataFrame(data)
domains = {'Sepal Length': RealDataDomain(0., 10.),
'Sepal Width': RealDataDomain(0., 10.),
'Petal Length': RealDataDomain(0., 10.),
'Petal Width': RealDataDomain(0., 10.),
'Class': CategoricalDataDomain(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])}
return PrivateTable(df, domains, PrivacyBudget(100000.0, 1.))
