def runAdult():
from data import adult
from decisionstump import buildDecisionStump
train, test = adult.load()
weakLearner = buildDecisionStump
rounds = 20
h = boosting.boost(train, weakLearner, rounds)
print("Training error: %G" % error(h, train))
print("Test error: %G" % error(h, test))
def runAdult():
from data import adult
from decisionstump import buildDecisionStump
train, test = adult.load()
weakLearner = buildDecisionStump
rounds = 20
h = boosting.boost(train, weakLearner, rounds)
print("Training error: %G" % error(h, train))
print("Test error: %G" % error(h, test))
nonfavored_data = [(feats, label) for feats, label in trainingData
if not feats[protectedIndex] == favored_trait]
NF, NFn = (len(nonfavored_data),
len([1 for x, label in nonfavored_data if h(x) == -1]))
p = NF * abs(bias) / NFn
def relabeledClassifier(point):
origClass = h(point)
if point[protectedIndex] != favored_trait and origClass == -1:
if random() < p:
return -origClass
else:
return origClass
else:
return origClass
return relabeledClassifier
if __name__ == '__main__':
from data import adult
from boosting import boost
trainingData, testData = adult.load()
protectedIndex = adult.protectedIndex
protectedValue = adult.protectedValue
h = boost(trainingData, 5)
rr = randomOneSideRelabelData(h, trainingData, protectedIndex,
protectedValue)
# to get rated 1
def randomOneSideRelabelData(h, trainingData, protectedIndex, protectedValue):
bias = signedStatisticalParity(trainingData, protectedIndex, protectedValue, h)
favored_trait = zeroOneSign(bias)
nonfavored_data = [(feats,label) for feats,label in trainingData if not feats[protectedIndex]==favored_trait]
NF, NFn = len(nonfavored_data), len([1 for x,label in nonfavored_data if h(x)==-1])
p = NF*abs(bias)/NFn
def relabeledClassifier(point):
origClass = h(point)
if point[protectedIndex] != favored_trait and origClass == -1:
if random() < p:
return -origClass
else:
return origClass
else:
return origClass
return relabeledClassifier
if __name__ == '__main__':
from data import adult
from boosting import boost
trainingData, testData = adult.load()
protectedIndex = adult.protectedIndex
protectedValue = adult.protectedValue
h = boost(trainingData, 5)
rr = randomOneSideRelabelData(h, trainingData, protectedIndex, protectedValue)
protectedProb = sum(1 for (x,l) in protectedClass if l == 1) / len(protectedClass)
elseProb = sum(1 for (x,l) in elseClass if l == 1) / len(elseClass)
return elseProb - protectedProb
# signedBias: [[float]], int, obj, h -> float
# compute the signed bias of a hypothesis on a given dataset
def signedBias(data, h, protectedIndex, protectedValue):
return labelBias(data, [h(x) for x in data], protectedIndex, protectedValue)
if __name__ == "__main__":
from data import adult
train, test = adult.load(separatePointsAndLabels=True)
tests = [('female', (1,0)),
('private employment', (2,1)),
('asian race', (33,1)),
('divorced', (12, 1))]
for (name, (index, value)) in tests:
print("anti-'%s' bias in training data: %.4f" %
(name, labelBias(train[0], train[1], index, value)))
indian = lambda x: x[47] == 1
print(len([x for x in train[0] if indian(x)]) / len(train[0]))
print(signedBias(train[0], indian, 1, 0))
raise Exception("Nobody in the unprotected class")
else:
protectedProb = sum(
1 for (x, l) in protectedClass if l == 1) / len(protectedClass)
elseProb = sum(1 for (x, l) in elseClass if l == 1) / len(elseClass)
return elseProb - protectedProb
# signedBias: [[float]], int, obj, h -> float
# compute the signed bias of a hypothesis on a given dataset
def signedBias(data, h, protectedIndex, protectedValue):
return labelBias(data, [h(x) for x in data], protectedIndex,
protectedValue)
if __name__ == "__main__":
from data import adult
train, test = adult.load(separatePointsAndLabels=True)
tests = [('female', (1, 0)), ('private employment', (2, 1)),
('asian race', (33, 1)), ('divorced', (12, 1))]
for (name, (index, value)) in tests:
print("anti-'%s' bias in training data: %.4f" %
(name, labelBias(train[0], train[1], index, value)))
indian = lambda x: x[47] == 1
print(len([x for x in train[0] if indian(x)]) / len(train[0]))
print(signedBias(train[0], indian, 1, 0))
