def test_synthetic_data():
""" Generate the synthetic data """
X, y, x_control = generate_synthetic_data(plot_data=False)
ut.compute_p_rule(x_control["s1"], y) # compute the p-rule in the original data
""" Classify the data without any constraints """
apply_fairness_constraints = 0
apply_accuracy_constraint = 0
sep_constraint = 0
loss_function = lf._logistic_loss
X = ut.add_intercept(X) # add intercept to X before applying the linear classifier
test_acc_arr, train_acc_arr, correlation_dict_test_arr, correlation_dict_train_arr, cov_dict_test_arr, cov_dict_train_arr = ut.compute_cross_validation_error(X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints, apply_accuracy_constraint, sep_constraint, ['s1'], [{} for i in range(0,NUM_FOLDS)])
print
print "== Unconstrained (original) classifier =="
ut.print_classifier_fairness_stats(test_acc_arr, correlation_dict_test_arr, cov_dict_test_arr, "s1")
""" Now classify such that we achieve perfect fairness """
apply_fairness_constraints = 1
cov_factor = 0
test_acc_arr, train_acc_arr, correlation_dict_test_arr, correlation_dict_train_arr, cov_dict_test_arr, cov_dict_train_arr = ut.compute_cross_validation_error(X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints, apply_accuracy_constraint, sep_constraint, ['s1'], [{'s1':cov_factor} for i in range(0,NUM_FOLDS)])
print
print "== Constrained (fair) classifier =="
ut.print_classifier_fairness_stats(test_acc_arr, correlation_dict_test_arr, cov_dict_test_arr, "s1")
""" Now plot a tradeoff between the fairness and accuracy """
ut.plot_cov_thresh_vs_acc_pos_ratio(X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints, apply_accuracy_constraint, sep_constraint, ['s1'])
def test_synthetic_data():
""" Generate the synthetic data """
print(sys.path)
X, y, x_control = generate_synthetic_data(plot_data=False)
ut.compute_p_rule(x_control["s1"], y) # compute the p-rule in the original data
""" Classify the data without any constraints """
apply_fairness_constraints = 0
apply_accuracy_constraint = 0
sep_constraint = 0
loss_function = lf._logistic_loss
X = ut.add_intercept(X) # add intercept to X before applying the linear classifier
test_acc_arr, train_acc_arr, correlation_dict_test_arr, correlation_dict_train_arr, cov_dict_test_arr, cov_dict_train_arr = ut.compute_cross_validation_error(
X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints, apply_accuracy_constraint,
sep_constraint, ['s1'], [{} for i in range(0, NUM_FOLDS)])
print
print "== Unconstrained (original) classifier =="
ut.print_classifier_fairness_stats(test_acc_arr, correlation_dict_test_arr, cov_dict_test_arr, "s1")
""" Now classify such that we achieve perfect fairness """
apply_fairness_constraints = 1
cov_factor = 0
test_acc_arr, train_acc_arr, correlation_dict_test_arr, correlation_dict_train_arr, cov_dict_test_arr, cov_dict_train_arr = ut.compute_cross_validation_error(
X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints, apply_accuracy_constraint,
sep_constraint, ['s1'], [{'s1': cov_factor} for i in range(0, NUM_FOLDS)])
print
print "== Constrained (fair) classifier =="
ut.print_classifier_fairness_stats(test_acc_arr, correlation_dict_test_arr, cov_dict_test_arr, "s1")
""" Now plot a tradeoff between the fairness and accuracy """
ut.plot_cov_thresh_vs_acc_pos_ratio(X, y, x_control, NUM_FOLDS, loss_function, apply_fairness_constraints,
apply_accuracy_constraint, sep_constraint, ['s1'])
def train_test_classifier():
w = ut.train_model(x_train, y_train, x_control_train, loss_function,
apply_fairness_constraints,
apply_accuracy_constraint, sep_constraint,
sensitive_attrs, sensitive_attrs_to_cov_thresh,
gamma)
train_score, test_score, correct_answers_train, correct_answers_test = ut.check_accuracy(
w, x_train, y_train, x_test, y_test, None, None)
distances_boundary_test = (np.dot(x_test, w)).tolist()
all_class_labels_assigned_test = np.sign(distances_boundary_test)
correlation_dict_test = ut.get_correlations(
None, None, all_class_labels_assigned_test, x_control_test,
sensitive_attrs)
cov_dict_test = ut.print_covariance_sensitive_attrs(
None, x_test, distances_boundary_test, x_control_test,
sensitive_attrs)
p_rule = ut.print_classifier_fairness_stats([test_score],
[correlation_dict_test],
[cov_dict_test],
sensitive_attrs[0])
eq_op_acc, chance_bin_zero, chance_bin_one = ut.get_eq_op_acc(
w, x_train, y_train, x_control_train, None)
eq_odds_acc = ut.get_eq_odds_acc(w, x_train, y_train, x_control_train,
None)
pred_rate_par_acc = ut.get_pred_rate_par_acc(w, x_train, y_train,
x_control_train, None)
demo_par_acc_f_cons = ut.get_dem_par_acc(w, x_train, y_train,
x_control_train, None)
return w, p_rule, test_score, eq_op_acc, eq_odds_acc, pred_rate_par_acc, demo_par_acc_f_cons
def test_classifier(w, x, y, control, sensitive_attrs):
distances_boundary_test = (np.dot(x, w)).tolist()
all_class_labels_assigned_test = np.sign(distances_boundary_test)
test_score, _ = check_accuracy(w, x, y)
correlation_dict_test = ut.get_correlations(None, None, all_class_labels_assigned_test, control, sensitive_attrs)
cov_dict_test = ut.print_covariance_sensitive_attrs(None, x, distances_boundary_test, control, sensitive_attrs)
p_rule = ut.print_classifier_fairness_stats([test_score], [correlation_dict_test], [cov_dict_test], sensitive_attrs[0])
return p_rule, test_score
def train_test_classifier(): w = ut.train_model(x_train, y_train, x_control_train, loss_function, apply_fairness_constraints, apply_accuracy_constraint, sep_constraint, sensitive_attrs, sensitive_attrs_to_cov_thresh, gamma) train_score, test_score, correct_answers_train, correct_answers_test = ut.check_accuracy(w, x_train, y_train, x_test, y_test, None, None) distances_boundary_test = (np.dot(x_test, w)).tolist() all_class_labels_assigned_test = np.sign(distances_boundary_test) correlation_dict_test = ut.get_correlations(None, None, all_class_labels_assigned_test, x_control_test, sensitive_attrs) cov_dict_test = ut.print_covariance_sensitive_attrs(None, x_test, distances_boundary_test, x_control_test, sensitive_attrs) p_rule = ut.print_classifier_fairness_stats([test_score], [correlation_dict_test], [cov_dict_test], sensitive_attrs[0]) return w, p_rule, test_score
def train_test_classifier():
w = ut.train_model(x_train, y_train, x_control_train, loss_function, apply_fairness_constraints, apply_accuracy_constraint, sep_constraint, sensitive_attrs, sensitive_attrs_to_cov_thresh, gamma)
train_score, test_score, correct_answers_train, correct_answers_test = ut.check_accuracy(w, x_train, y_train, x_test, y_test, None, None)
distances_boundary_test = np.dot(x_test, w)
distances_boundary_train = np.dot(x_train, w)
prob_test = [sigmoid(x) for x in distances_boundary_test]
prob_train = [sigmoid(x) for x in distances_boundary_train]
all_class_labels_assigned_test = np.sign(distances_boundary_test)
correlation_dict_test = ut.get_correlations(None, None, all_class_labels_assigned_test, x_control_test, sensitive_attrs)
cov_dict_test = ut.print_covariance_sensitive_attrs(None, x_test, distances_boundary_test, x_control_test, sensitive_attrs)
p_rule = ut.print_classifier_fairness_stats([test_score], [correlation_dict_test], [cov_dict_test], sensitive_attrs[0])
# return w, p_rule, test_score
return prob_train, prob_test
