svclassifier.fit(x_train_t, y_train_t)
y_test_tp = y_test_t.to_numpy()
y_pred = svclassifier.predict(x_test_t)
acc = calc_acc(y_test_tp, y_pred)
if m < acc:
m = acc
x_train, x_test, y_train, y_test = x_train_t, x_test_t, y_train_t, y_test_t
if n > acc:
n = acc
print(m)
print(n)
# orig=np.arange(len(x_train.iloc[0]))
selected_features, fitness, precision, sensitivity, F1, AUC = da.DA(
x_train, y_train, x_test, y_test, 100, m, orig)
#selected_features = np.random.randint(288, size=)
x_train_selected_features = pd.DataFrame()
x_test_selected_features = pd.DataFrame()
reduced_dataset = pd.DataFrame()
for i in range(len(selected_features)):
x_train_selected_features[str(
selected_features[i])] = x_train.iloc[:, int(
selected_features[i])] # X_Train from selected features
x_test_selected_features[str(
selected_features[i])] = x_test.iloc[:, int(
selected_features[i])] # # X_Test from selected features
reduced_dataset['attr ' + str(int(
