def method3(acc_matrix):
df_train = pd.read_csv ('temp/adult_binary_train_prediction0.csv')
# df_train = pd.concat ([df_train] * 10, ignore_index=True)
train = DataSet (df_train)
df_test = pd.read_csv ('temp/adult_binary_test_prediction0.csv')
df_test = pd.concat ([df_test] * 3, ignore_index=True)
test = DataSet (df_test)
acc = []
for name in ['LR', 'SVM']:
probabilistic_cbn = load_xml_to_cbn (os.path.join (src_path, '../data/adult/adult.xml'))
def find_condition_prob(e, t):
return probabilistic_cbn.find_prob (e, t)
def get_loc(e):
return probabilistic_cbn.get_loc (e)
A1 = probabilistic_cbn.v['age']
A2 = probabilistic_cbn.v['education']
S = probabilistic_cbn.v['sex']
M1 = probabilistic_cbn.v['workclass']
M2 = probabilistic_cbn.v['marital-status']
N = probabilistic_cbn.v['hours']
Y = probabilistic_cbn.v['income']
YH = Variable (name=name, index=Y.index + 1, domains=Y.domains)
probabilistic_cbn.v[(YH.index, YH.name)] = YH
YT = Variable (name=name + "M", index=Y.index + 2, domains=Y.domains)
probabilistic_cbn.v[(YT.index, YT.name)] = YT
# build linear loss function
C_vector = np.zeros ((2 ** 8 + 2 ** 8 // 4, 1))
for a1, a2, n, m1, m2, s in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), M1.domains.get_all (), M2.domains.get_all (),
S.domains.get_all ()):
p_x_s = train.get_marginal_prob (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
p_yh_1_y = p_x_s * train.count (Event ({Y: 0, YH: 0}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}), 'notequal')
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: 0, YT: 0}))
C_vector[loc] = p_yh_1_y * train.get_conditional_prob (Event ({YH: 0}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: 1, YT: 1}))
C_vector[loc] = p_yh_1_y * train.get_conditional_prob (Event ({YH: 1}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
p_yh__y = p_x_s * train.count (Event ({Y: 0, YH: 0}), Event ({A1: a1, A2: a2, M1: m1, M2: m2, N: n, S: s}), 'equal')
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: 0, YT: 1}))
C_vector[loc] = p_yh__y * train.get_conditional_prob (Event ({YH: 0}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: 1, YT: 0}))
C_vector[loc] = p_yh__y * train.get_conditional_prob (Event ({YH: 1}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
# the inequality of max and min
G_matrix_1 = np.zeros ((2 ** 8, 2 ** 8 + 2 ** 8 // 4))
h_1 = np.zeros (2 ** 8)
# max
i = 0
for a1, a2, n, s, yt in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), S.domains.get_all (), YT.domains.get_all ()):
for m1, m2 in product (M1.domains.get_all (), M2.domains.get_all ()):
for yh in YH.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))
G_matrix_1[i, loc] = train.get_conditional_prob (Event ({YH: yh}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
loc = get_loc (Event ({A1: a1, A2: a2, N: n, S: s, YT: yt}))
G_matrix_1[i, 2 ** 8 + loc] = -1
i += 1
# min
assert i == 2 ** 8 // 2
for a1, a2, n, s, yt in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), S.domains.get_all (), YT.domains.get_all ()):
for m1, m2 in product (M1.domains.get_all (), M2.domains.get_all ()):
for yh in YH.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))
G_matrix_1[i, loc] = -train.get_conditional_prob (Event ({YH: yh}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}))
loc = get_loc (Event ({A1: a1, A2: a2, N: n, S: s, YT: yt}))
G_matrix_1[i, 2 ** 8 + 2 ** 8 // 8 + loc] = 1
i += 1
# build counterfactual fairness constraints
G_matrix_2 = np.zeros ((2 ** 4 * 2, 2 ** 8 + 2 ** 8 // 4))
h_2 = np.ones (2 ** 4 * 2) * tau
i = 0
for a1, a2, m1, m2 in product (A1.domains.get_all (), A2.domains.get_all (), M1.domains.get_all (), M2.domains.get_all ()):
for n in N.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, S: spos, YT: yt_pos}))
G_matrix_2[i, 2 ** 8 + loc] = find_condition_prob (Event ({N: n}), Event ({A1: a1, A2: a2, M1: m1, M2: m2, S: spos}))
for yh in YH.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: sneg, YH: yh, YT: yt_pos}))
G_matrix_2[i, loc] = -find_condition_prob (Event ({N: n}), Event ({A1: a1, A2: a2, M1: m1, M2: m2, S: sneg})) \
* train.get_conditional_prob (Event ({YH: yh}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: sneg}))
i += 1
assert i == 2 ** 4
for a1, a2, m1, m2 in product (A1.domains.get_all (), A2.domains.get_all (), M1.domains.get_all (), M2.domains.get_all ()):
for n in N.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, S: spos, YT: yt_pos}))
G_matrix_2[i, 2 ** 8 + 2 ** 8 // 8 + loc] = -find_condition_prob (Event ({N: n}), Event ({A1: a1, A2: a2, M1: m1, M2: m2, S: spos}))
for yh in YH.domains.get_all ():
loc = get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: sneg, YH: yh, YT: yt_pos}))
G_matrix_2[i, loc] = find_condition_prob (Event ({N: n}), Event ({A1: a1, A2: a2, M1: m1, M2: m2, S: sneg})) \
* train.get_conditional_prob (Event ({YH: yh}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: sneg}))
i += 1
###########
# mapping in [0, 1]
G_matrix_3 = np.zeros ((2 * (2 ** 8 + 2 ** 8 // 4), 2 ** 8 + 2 ** 8 // 4))
h_3 = np.zeros (2 * (2 ** 8 + 2 ** 8 // 4))
for i in range (2 ** 8 + 2 ** 8 // 4):
G_matrix_3[i, i] = 1
h_3[i] = 1
G_matrix_3[2 ** 8 + 2 ** 8 // 4 + i, i] = -1
h_3[2 ** 8 + 2 ** 8 // 4 + i] = 0
# sum = 1
A_matrix = np.zeros ((2 ** 8 // 2, 2 ** 8 + 2 ** 8 // 4))
b = np.ones (2 ** 8 // 2)
i = 0
for a1, a2, n, m1, m2, s, yh in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), M1.domains.get_all (), M2.domains.get_all (),
S.domains.get_all (),
YH.domains.get_all ()):
for yt in YT.domains.get_all ():
A_matrix[i, get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))] = 1
i += 1
assert i == 2 ** 8 // 2
# combine the inequality constraints
G_matrix = np.vstack ([G_matrix_1, G_matrix_2, G_matrix_3])
h = np.hstack ([h_1, h_2, h_3])
# Test
# print (np.linalg.matrix_rank (A_matrix), A_matrix.shape[0])
# print (np.linalg.matrix_rank (np.vstack ([A_matrix, G_matrix])), A_matrix.shape[1])
# def check():
# sol = np.zeros (2 ** 8 + 2 ** 8 // 4)
# for a1, a2, n, m1, m2, s, yh, yt in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), M1.domains.get_all (), M2.domains.get_all (),
# S.domains.get_all (), YH.domains.get_all (), YT.domains.get_all ()):
# if yh.name == yt.name:
# sol[get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))] = 1.0
# else:
# sol[get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))] = 0.0
#
# for a1, a2, n, s, yt in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), S.domains.get_all (), YT.domains.get_all ()):
# p_min = 1
# p_max = 0
# for m1, m2 in product (M1.domains.get_all (), M2.domains.get_all ()):
# p = 0.0
# for yh in YH.domains.get_all ():
# p = train.get_conditional_prob (Event ({YH: yh}), Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s})) \
# * sol[get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt}))]
# if p < p_min:
# p_min = p
# if p > p_max:
# p_max = p
# loc = get_loc (Event ({A1: a1, A2: a2, N: n, S: s, YT: yt}))
# sol[2 ** 8 + loc] = p_max
# sol[2 ** 8 + 2 ** 8 // 8 + loc] = p_min
#
# np.dot (G_matrix_2, sol)
# check ()
# solver
solvers.options['show_progress'] = False
sol = solvers.lp (c=matrix (C_vector),
G=matrix (G_matrix),
h=matrix (h),
A=matrix (A_matrix),
b=matrix (b),
solver=solvers
)
mapping = np.array (sol['x'])
# build the post-processing result in training and testing
train.df.loc[:, name + 'M'] = train.df[name]
test.df[name + 'M'] = test.df[name]
for a1, a2, n, m1, m2, s, yh, yt in product (A1.domains.get_all (), A2.domains.get_all (), N.domains.get_all (), M1.domains.get_all (), M2.domains.get_all (),
S.domains.get_all (), YH.domains.get_all (), YT.domains.get_all ()):
if yh.name != yt.name:
p = mapping[get_loc (Event ({A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s, YH: yh, YT: yt})), 0]
train.random_assign (Event ({YH: yh, A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}), Event ({YT: yt}), p)
test.random_assign (Event ({YH: yh, A1: a1, A2: a2, N: n, M1: m1, M2: m2, S: s}), Event ({YT: yt}), p)
train.df[name] = train.df[name + 'M']
train.df.drop ([name + 'M'], axis=1)
test.df[name] = test.df[name + 'M']
test.df.drop ([name + 'M'], axis=1)
acc.append (accuracy_score (train.df[name], train.df[Y.name]))
acc.append (accuracy_score (test.df[name], test.df[Y.name]))
acc_matrix.iloc[:, 3] = acc
train.df.to_csv ('temp/adult_binary_train_prediction3.csv', index=False)
test.df.to_csv ('temp/adult_binary_test_prediction3.csv', index=False)
def method3(acc_matrix):
df_train = pd.read_csv('temp/synthetic_train_prediction0.csv')
train = DataSet(df_train)
df_test = pd.read_csv('temp/synthetic_test_prediction0.csv')
test = DataSet(df_test)
acc = []
for name in ['LR', 'SVM']:
probabilistic_cbn = load_xml_to_cbn(
os.path.join(src_path,
'../data/synthetic/ProbabilisticBayesianModel.xml'))
def find_condition_prob(e, t):
return probabilistic_cbn.find_prob(e, t)
def get_loc(e):
return probabilistic_cbn.get_loc(e)
A = probabilistic_cbn.v['A']
S = probabilistic_cbn.v['S']
N = probabilistic_cbn.v['N']
M = probabilistic_cbn.v['M']
Y = probabilistic_cbn.v['Y']
YH = Variable(name='YH', index=Y.index + 1, domains=Y.domains)
probabilistic_cbn.v[(YH.index, YH.name)] = YH
YT = Variable(name='YT', index=Y.index + 2, domains=Y.domains)
probabilistic_cbn.v[(YT.index, YT.name)] = YT
# build linear loss function
C_vector = np.zeros((2**6 + 2**6 // 2, 1))
for a, n, m, s in product(A.domains.get_all(), N.domains.get_all(),
M.domains.get_all(), S.domains.get_all()):
p_x_s = train.get_marginal_prob(
Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
p_yh_1_y = p_x_s * train.count(
Event({
'Y': 0,
name: 0
}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}), 'notequal')
loc = get_loc(Event({A: a, M: m, N: n, S: s, YH: 0, YT: 0}))
C_vector[loc] = p_yh_1_y * train.get_conditional_prob(
Event({name: 0}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
loc = get_loc(Event({A: a, M: m, N: n, S: s, YH: 1, YT: 1}))
C_vector[loc] = p_yh_1_y * train.get_conditional_prob(
Event({name: 1}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
p_yh__y = p_x_s * train.count(
Event({
'Y': 0,
name: 0
}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}), 'equal')
loc = get_loc(Event({A: a, M: m, N: n, S: s, YH: 0, YT: 1}))
C_vector[loc] = p_yh__y * train.get_conditional_prob(
Event({name: 0}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
loc = get_loc(Event({A: a, M: m, N: n, S: s, YH: 1, YT: 0}))
C_vector[loc] = p_yh__y * train.get_conditional_prob(
Event({name: 1}), Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
# the inequality of max and min
G_matrix_1 = np.zeros((2**6, 2**6 + 2**6 // 2))
h_1 = np.zeros(2**6)
# max
i = 0
for a, n, s, yt in product(A.domains.get_all(), N.domains.get_all(),
S.domains.get_all(), YT.domains.get_all()):
for m in M.domains.get_all():
for yh in YH.domains.get_all():
loc = get_loc(
Event({
A: a,
M: m,
N: n,
S: s,
YH: yh,
YT: yt
}))
G_matrix_1[i, loc] = train.get_conditional_prob(
Event({name: yh}),
Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
loc = get_loc(Event({A: a, N: n, S: s, YT: yt}))
G_matrix_1[i, 2**6 + loc] = -1
i += 1
# min
assert i == 2**6 // 2
for a, n, s, yt in product(A.domains.get_all(), N.domains.get_all(),
S.domains.get_all(), YT.domains.get_all()):
for m in M.domains.get_all():
for yh in YH.domains.get_all():
loc = get_loc(
Event({
A: a,
M: m,
N: n,
S: s,
YH: yh,
YT: yt
}))
G_matrix_1[i, loc] = -train.get_conditional_prob(
Event({name: yh}),
Event({
'A': a,
'M': m,
'N': n,
'S': s
}))
loc = get_loc(Event({A: a, N: n, S: s, YT: yt}))
G_matrix_1[i, 2**6 + 2**6 // 4 + loc] = 1
i += 1
# build counterfactual fairness constraints
G_matrix_2 = np.zeros((2**2 * 2, 2**6 + 2**6 // 2))
h_2 = np.ones(2**2 * 2) * tau
i = 0
for a, m in product(A.domains.get_all(), M.domains.get_all()):
for n in N.domains.get_all():
loc = get_loc(Event({A: a, N: n, S: spos, YT: yt_pos}))
G_matrix_2[i, 2**6 + loc] = find_condition_prob(
Event({N: n}), Event({
A: a,
S: spos
}))
for yh in YH.domains.get_all():
loc = get_loc(
Event({
A: a,
M: m,
N: n,
S: sneg,
YH: yh,
YT: yt_pos
}))
G_matrix_2[i, loc] = -find_condition_prob (Event ({N: n}), Event ({A: a, S: sneg})) \
* train.get_conditional_prob (Event ({name: yh}), Event ({'A': a, 'M': m, 'N': n, 'S': sneg}))
i += 1
assert i == 2**2
for a, m in product(A.domains.get_all(), M.domains.get_all()):
for n in N.domains.get_all():
loc = get_loc(Event({A: a, N: n, S: spos, YT: yt_pos}))
G_matrix_2[i, 2**6 + 2**6 // 4 + loc] = -find_condition_prob(
Event({N: n}), Event({
A: a,
S: spos
}))
for yh in YH.domains.get_all():
loc = get_loc(
Event({
A: a,
M: m,
N: n,
S: sneg,
YH: yh,
YT: yt_pos
}))
G_matrix_2[i, loc] = find_condition_prob (Event ({N: n}), Event ({A: a, S: sneg})) \
* train.get_conditional_prob (Event ({name: yh}), Event ({'A': a, 'M': m, 'N': n, 'S': sneg}))
i += 1
###########
# mapping in [0, 1]
G_matrix_3 = np.zeros(((2**6 + 2**6 // 2) * 2, 2**6 + 2**6 // 2))
h_3 = np.zeros((2**6 + 2**6 // 2) * 2)
for i in range(2**6 + 2**6 // 2):
G_matrix_3[i, i] = 1
h_3[i] = 1
G_matrix_3[2**6 + 2**6 // 2 + i, i] = -1
h_3[2**6 + 2**6 // 2 + i] = 0
# sum = 1
A_matrix = np.zeros((2**6 // 2, 2**6 + 2**6 // 2))
b = np.ones(2**6 // 2)
i = 0
for a, n, m, s, yh in product(A.domains.get_all(), N.domains.get_all(),
M.domains.get_all(), S.domains.get_all(),
YH.domains.get_all()):
for yt in YT.domains.get_all():
A_matrix[
i,
get_loc(Event({
A: a,
M: m,
N: n,
S: s,
YH: yh,
YT: yt
}))] = 1
i += 1
assert i == 2**6 // 2
# combine the inequality constraints
G_matrix = np.vstack([G_matrix_1, G_matrix_2, G_matrix_3])
h = np.hstack([h_1, h_2, h_3])
# solver
solvers.options['show_progress'] = False
sol = solvers.lp(c=matrix(C_vector),
G=matrix(G_matrix),
h=matrix(h),
A=matrix(A_matrix),
b=matrix(b),
solver=solvers)
mapping = np.array(sol['x'])
# build the post-processing result in training and testing
train.df[name + '1'] = train.df[name]
test.df[name + '1'] = test.df[name]
for a, n, m, s, yh, yt in product(A.domains.get_all(),
N.domains.get_all(),
M.domains.get_all(),
S.domains.get_all(),
YH.domains.get_all(),
YT.domains.get_all()):
if yh.name != yt.name:
p = mapping[
get_loc(Event({
A: a,
M: m,
N: n,
S: s,
YH: yh,
YT: yt
})), 0]
train.random_assign(
Event({
name: yh,
'A': a,
'M': m,
'N': n,
'S': s
}), Event({name + '1': yt}), p)
test.random_assign(
Event({
name: yh,
'A': a,
'M': m,
'N': n,
'S': s
}), Event({name + '1': yt}), p)
train.df[name] = train.df[name + '1']
train.df.drop([name + '1'], axis=1)
test.df[name] = test.df[name + '1']
test.df.drop([name + '1'], axis=1)
acc.append(accuracy_score(train.df['Y'], train.df[name]))
acc.append(accuracy_score(test.df['Y'], test.df[name]))
acc_matrix.iloc[:, 3] = acc
train.df.to_csv('temp/synthetic_train_prediction3.csv', index=False)
test.df.to_csv('temp/synthetic_test_prediction3.csv', index=False)
