def test_ratio(self): ''' Compare several competing methods changing the ratio of the positive class in the dataset. We use binary class dataset for the easy of interpretation. ''' dataset = rcv1_binary_reader.toNumpy() set_size = 100 X_train_full, y_train_full, X_test, y_test = dataset X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], set_size) assert(len(y_train) == set_size) train_set = (X_train, y_train) test_set_original = (X_test, y_test) clf = LogisticRegression() clf.fit(X_train, y_train) p = Prior(clf) for r in np.arange(0.05, 1.0, 0.05): # Generate a new test set with desired positive proportions. X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1) test_set = [X_test_new, y_test_new] true_pos = DE.arrayToDist(y_test_new)[1] p.fit(X_train, y_train, {-1:1-true_pos, 1:true_pos}) y_pred = p.predict(X_test_new) cm = confusion_matrix(y_test_new, y_pred) acc = self.accuracy(cm) print r, acc