from load_data import load_heart_uci
from measures import equalized_odds_measure_TP, equalized_odds_measure_FP, \
statistical_parity_measure, disparate_impact_measure
from sklearn import svm
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.decomposition import PCA
from sklearn.preprocessing import MinMaxScaler
set_of_exps = 2
if set_of_exps == 1:
dataset = load_heart_uci()
scaler = MinMaxScaler(feature_range=(-1, 1))
dataset.data = scaler.fit(dataset.data).transform(dataset.data)
# print(heart.data[1, :], heart.data[2, :], heart.data[3, :])
# % for train
ntrain = 5 * len(
dataset.target
) // 10 # from 30% to 50% the accuracy is the same BUT more fairness!
# Train an SVM using the training set
clf = svm.SVC(C=1.0)
clf.fit(dataset.data[:ntrain, :], dataset.target[:ntrain])
# The dataset becomes the test set
dataset.data = dataset.data[ntrain:, :]
dataset.target = dataset.target[ntrain:]
self.model.fit(self.dataset.data, self.dataset.target)
#if hasattr(self.model, 'best_estimator_'):
# self.model = self.model.best_estimator_
#self.coef_ = self.model.coef_
#self.intercept_ = self.model.intercept_
if __name__ == "__main__":
experiment_number = 0
if experiment_number == 0:
dataset_train = load_binary_diabetes_uci()
dataset_test = load_binary_diabetes_uci()
sensible_feature = 1 # sex
elif experiment_number == 1:
dataset_train = load_heart_uci()
dataset_test = load_heart_uci()
sensible_feature = 1 # sex
elif experiment_number == 2:
dataset_train, dataset_test = load_adult(smaller=False)
sensible_feature = 9 # sex
print('Different values of the sensible feature', sensible_feature,
':', set(dataset_train.data[:, sensible_feature]))
elif experiment_number == 3:
dataset_train, dataset_test = load_adult_race(smaller=False)
sensible_feature = 8 # race
print('Different values of the sensible feature', sensible_feature,
':', set(dataset_train.data[:, sensible_feature]))
if experiment_number in [0, 1]:
# % for train