def example1():
""" Optimize AllRange workload using PIdentity template and report the expected error """
print('Example 1')
W = workload.AllRange(256)
pid = templates.PIdentity(16, 256)
res = pid.optimize(W)
err = error.rootmse(W, pid.strategy())
err2 = error.rootmse(W, workload.Identity(256))
print(err, err2)
def example3():
""" Optimize Union-of-Kronecker product workload using kronecker parameterization
and marginals parameterization """
print('Example 3')
sub_workloads1 = [workload.Prefix(64) for _ in range(4)]
sub_workloads2 = [workload.AllRange(64) for _ in range(4)]
W1 = workload.Kronecker(sub_workloads1)
W2 = workload.Kronecker(sub_workloads2)
W = workload.VStack([W1, W2])
K = templates.KronPIdentity([4]*4, [64]*4)
K.optimize(W)
print(error.expected_error(W, K.strategy()))
M = templates.Marginals([64]*4)
M.optimize(W)
print(error.expected_error(W, M.strategy()))
identity = workload.Kronecker([workload.Identity(64) for _ in range(4)])
print(error.expected_error(W, identity))
def setUp(self):
self.prng = np.random.RandomState(0)
self.domain = (2,3,4)
I = lambda n: workload.Identity(n)
T = lambda n: workload.Total(n)
P = lambda n: workload.Prefix(n)
R = lambda n: matrix.EkteloMatrix(self.prng.rand(n,n))
W1 = workload.Kronecker([I(2), T(3), P(4)])
W2 = workload.Kronecker([T(2), T(3), I(4)])
W3 = workload.Kronecker([I(2), I(3), T(4)])
self.W = workload.VStack([W1, W2, W3])
# three representations of Identity matrix
self.A1 = I(2*3*4)
self.A2 = workload.Kronecker([I(2),I(3),I(4)])
self.A3 = workload.Marginals.fromtuples(self.domain, {(0,1,2) : 1.0 })
self.A4 = workload.Marginals(self.domain, self.prng.rand(8))
self.A5 = workload.Kronecker([R(2), R(3), R(4)])
def adult_benchmark():
data = Dataset.load('../data/adult.csv', '../data/adult-domain.json')
projections = [('occupation', 'race', 'capital-loss'),
('occupation', 'sex', 'native-country'),
('marital-status', 'relationship', 'income>50K'),
('age', 'education-num', 'sex'),
('workclass', 'education-num', 'occupation'),
('marital-status', 'occupation', 'income>50K'),
('race', 'native-country', 'income>50K'),
('occupation', 'capital-gain', 'income>50K'),
('marital-status', 'hours-per-week', 'income>50K'),
('workclass', 'race', 'capital-gain'),
('marital-status', 'relationship', 'capital-gain'),
('workclass', 'education-num', 'capital-gain'),
('education-num', 'relationship', 'race'),
('fnlwgt', 'hours-per-week', 'income>50K'),
('workclass', 'sex', 'native-country')]
lookup = {}
for attr in data.domain:
n = data.domain.size(attr)
lookup[attr] = workload.Identity(n)
lookup['age'] = workload.Prefix(85)
lookup['fnlwgt'] = workload.Prefix(100)
lookup['capital-gain'] = workload.Prefix(100)
lookup['capital-loss'] = workload.Prefix(100)
lookup['hours-per-week'] = workload.Prefix(99)
workloads = []
for proj in projections:
W = workload.Kronecker([lookup[a] for a in proj])
workloads.append((proj, W))
return data, workloads
def Identity(n):
""" Builds a template strategy that is always Identity """
return Static(workload.Identity(n))