def __init__(self):
dataset = Dataset('config_compas.json')
x, y = dataset.get_data(readable=True)
# r = "Af_vs_all"
r = "Af_vs_Caucasian"
# r = "all"
x, y = get_dataframe(x, y, requested=r)
self.finder = RelationshipsFinder(pd.concat([x, y], axis=1))
def main():
dataset = Dataset('config_compas.json')
x, y = dataset.get_data(readable=True)
# r = "Af_vs_all"
r = "Af_vs_Caucasian"
# r = "all"
x, y = get_dataframe(x, y, requested=r)
x_encoded, y_encoded = dataset.encode_data(x_df=x, y_df=y)
# experimental setup
# sex _|_ race | priors count
# modify this to our experiment cases
conditional_variables = ['race']
sensitive_attributes = ['sex']
combos, train_dfs = get_conditional_distribution(
pd.concat((x_encoded, y_encoded), axis=1), conditional_variables)
m = Metrics()
if not combos:
y_train = train_dfs['is_recid'].copy()
x_train = train_dfs.drop('is_recid', axis=1).copy()
x_test, y_test, pred = classify(x_train, y_train)
print(x_test, y_test)
df = pd.concat((x_test, y_test), axis=1).dropna().reset_index()
y_hat = pd.DataFrame(pred).rename({0: 'y_hat'}, axis=1)
dp = m.demographic_parity(x=df,
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
print(dp)
pp = m.predictive_parity(x=x_test.reset_index(drop=True),
y=y_test.reset_index(drop=True),
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
eo = m.equalized_odds(x=x_test.reset_index(drop=True),
y=y_test.reset_index(drop=True),
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
print(pp)
print(eo)
for combo, strat_df in list(zip(combos, train_dfs)):
combo, strat = list(zip(combos, train_dfs))[-1]
print("Conditional Attributes : " + str(conditional_variables))
# print("Sensitive attributes : "+str(sensitive_attributes))
print(" Combination: " + str(vars) + " " + str(combo))
y_train = strat_df['is_recid'].copy()
x_train = strat_df.drop('is_recid', axis=1).copy()
x_test, y_test, pred = classify(x_train, y_train)
df = pd.concat((x_test, y_test), axis=1).dropna().reset_index()
y_hat = pd.DataFrame(pred).rename({0: 'y_hat'}, axis=1)
y_test.name = 'y'
dp = m.demographic_parity(x=df,
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
pp = m.predictive_parity(x=x_test.reset_index(drop=True),
y=y_test.reset_index(drop=True),
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
eo = m.equalized_odds(x=x_test.reset_index(drop=True),
y=y_test.reset_index(drop=True),
y_hat=y_hat,
sensitive_attributes=sensitive_attributes)
print(" Demographic Pariy: ")
print(dp)
